WO2023074079A1 - Diagnostic system and diagnostic method - Google Patents

Diagnostic system and diagnostic method Download PDF

Info

Publication number
WO2023074079A1
WO2023074079A1 PCT/JP2022/029991 JP2022029991W WO2023074079A1 WO 2023074079 A1 WO2023074079 A1 WO 2023074079A1 JP 2022029991 W JP2022029991 W JP 2022029991W WO 2023074079 A1 WO2023074079 A1 WO 2023074079A1
Authority
WO
WIPO (PCT)
Prior art keywords
deterioration
information
unit
maintenance
component
Prior art date
Application number
PCT/JP2022/029991
Other languages
French (fr)
Japanese (ja)
Inventor
翔吾 多田
充 田原
巌 兼高
潤一 横田
アレックス ヴァルディヴィエルソ
Original Assignee
パナソニックＩｐマネジメント株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by パナソニックＩｐマネジメント株式会社 filed Critical パナソニックＩｐマネジメント株式会社
Publication of WO2023074079A1 publication Critical patent/WO2023074079A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • H—ELECTRICITY
    • H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
    • H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
    • H05K13/00—Apparatus or processes specially adapted for manufacturing or adjusting assemblages of electric components
    • H05K13/08—Monitoring manufacture of assemblages
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Definitions

  • the present disclosure relates to, for example, a system for diagnosing production equipment such as a component mounting device.
  • a component mounting apparatus is a production facility for producing a mounted board in which a board is mounted or mounted on a component, and is also called a component mounting apparatus.
  • the switching valve is a component provided in the component mounting apparatus, and selectively connects the vacuum pump and the air supply source to the suction nozzle.
  • a suction nozzle is a nozzle that sucks and holds a component in order to mount the component on the board.
  • a vacuum pump is connected to the suction nozzle by a switching valve, and when the vacuum pump is driven, the suction nozzle sucks ambient air.
  • an air supply source is connected to the suction nozzle by a switching valve, and when the air supply source is driven, the suction nozzle blows out air to the surroundings. It can be said that such a component mounting apparatus is provided with a diagnostic system for determining whether or not the constituent member, which is the switching valve, is normal.
  • the present disclosure provides a diagnostic system and the like that can more appropriately support maintenance of production equipment by workers.
  • a diagnostic system includes: (i) production plan information indicating a production plan for producing a mounting board, which is a board on which components are mounted, using production equipment; and (ii) using the production equipment an acquisition unit that acquires production performance information indicating the production performance of the mounting board by means of an acquisition unit; deterioration information that indicates the past or present deterioration state of a constituent member included in the production equipment; and deterioration information acquired by the acquisition unit a prediction unit for predicting a time when the future deterioration state of the component member reaches a prescribed deterioration state, which is a predetermined deterioration state, based on the production plan information and the actual production information; and an output unit that outputs arrival time information indicating the arrival time.
  • these comprehensive or specific aspects may be realized by a system, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM (Compact Disc Read-Only Memory). , methods, integrated circuits, computer programs and recording media. Also, the recording medium may be a non-temporary recording medium.
  • a computer-readable CD-ROM Compact Disc Read-Only Memory
  • the recording medium may be a non-temporary recording medium.
  • the diagnostic system of the present disclosure can more appropriately support maintenance of production equipment by workers.
  • FIG. 1 is a plan view of the component mounting device according to the embodiment.
  • FIG. 2 is a perspective view of a transfer head used in the component mounting device according to the embodiment.
  • FIG. 3 is a diagram showing an example of the configuration of an air control mechanism according to the embodiment.
  • FIG. 4 is a block diagram showing an example of the functional configuration of the component mounting device according to the embodiment.
  • FIG. 5 is a block diagram showing an example of the functional configuration of the diagnostic system according to the embodiment.
  • FIG. 6 is a diagram for explaining a learning unit and a diagnostic model according to the embodiment;
  • FIG. 7 is a diagram for explaining a deterioration identifying unit and a diagnostic model according to the embodiment;
  • FIG. 8 is a diagram showing a specific example of deterioration information in the embodiment.
  • FIG. 9 is a diagram for explaining inputs and outputs of an abnormality processing unit, a classification processing unit, and a deterioration degree processing unit according to the embodiment;
  • FIG. 10 is a diagram for explaining processing of a prediction unit in the embodiment;
  • FIG. 11 is a flow chart showing an example of processing operations related to identification of a deterioration state by the diagnosis system in the embodiment.
  • FIG. 12 is a flowchart showing an example of a processing operation regarding a maintenance instruction by the diagnosis system according to the embodiment.
  • FIG. 13 is a flowchart showing an example of processing operations related to maintenance timing prediction by the diagnostic system in the embodiment.
  • the diagnostic system includes: (i) production plan information indicating a production plan for producing a mounting board, which is a board on which components are mounted, using production equipment; an acquisition unit for acquiring production performance information indicating the production performance of the mounting substrate using equipment; a prediction unit that predicts a time when the future deterioration state of the component member reaches a specified deterioration state, which is a predetermined deterioration state, based on the obtained production plan information and the obtained production performance information; and an output unit that outputs arrival time information indicating the predicted arrival time.
  • the specified deterioration state requires maintenance of the constituent members or a second specified deterioration state that requires preparation for performing the maintenance.
  • the predicting unit indicates a future deterioration state of the constituent member, which indicates a larger value as the degree of deterioration of the constituent member increases. is estimated, and the arrival time when the future deterioration degree reaches the first threshold value corresponding to the first specified deterioration state, or the arrival time when the second threshold value corresponding to the second specified deterioration state is reached, A prediction may be made based on the production plan information.
  • the time when maintenance of the deteriorated component member is required or the time when preparation for the maintenance is required is predicted as the arrival time, and the arrival time information indicating the arrival time is output. be done. Therefore, the worker who works using the production equipment can grasp the arrival time, that is, the maintenance execution time or the maintenance preparation time. As a result, the worker can perform work in anticipation of those times, and can improve work efficiency. Also, efficiency of maintenance can be improved. In this way, maintenance of production equipment by workers can be more appropriately supported.
  • the deterioration information may indicate the deterioration state of the constituent member at each of a plurality of past points of time.
  • the production facility is a component mounting device that picks up a component with a transfer head and mounts it on a substrate
  • the diagnostic system includes: Further, a deterioration specifying unit that specifies a deterioration state of the constituent members included in the transfer head based on flow rate information about a flow rate of air flowing through the transfer head, wherein the prediction unit causes the deterioration specifying unit to Information indicating the identified deterioration state may be acquired as the deterioration information.
  • the deterioration state of the constituent members included in the transfer head is identified based on the flow rate information, and the identified deterioration state is used to predict the arrival time. Therefore, the deterioration state can be appropriately specified, and the prediction accuracy of arrival time can be improved.
  • the deterioration specifying unit specifies the deterioration state of the constituent member by estimating the degree of deterioration indicating the degree of deterioration of the constituent member. good too.
  • the deterioration state can be estimated in more detail as the degree of deterioration, so it is possible to further improve the prediction accuracy of the arrival time.
  • the deterioration specifying unit determines whether or not there is an abnormality in the constituent member, and if it is determined that there is an abnormality, the deterioration of the constituent member The degree of deterioration may be estimated.
  • the arrival time is predicted for the component that is assumed to have signs of deterioration, and it is assumed that there is no sign of deterioration. It is possible to omit the prediction of arrival times for the constituent members. As a result, it is possible to reduce the processing load of predicting the arrival time.
  • the production performance information includes the number of times the component has been attached to the substrate by the transfer head.
  • the prediction unit may estimate a future deterioration state of the constituent member based on the mounting number information and the deterioration information.
  • each figure is a schematic diagram and is not necessarily strictly illustrated. Moreover, in each figure, the same code
  • FIG. 1 is a plan view of a component mounting apparatus according to this embodiment. That is, FIG. 1 shows the internal configuration of the component mounting apparatus as viewed from above.
  • the vertical direction is referred to as the Z-axis direction or the vertical direction
  • one direction in a plane perpendicular to the vertical direction is referred to as the Y-axis direction or the depth direction
  • the vertical direction is referred to as the Y-axis direction.
  • the direction is referred to as the X-axis direction, left-right direction, or lateral direction.
  • the positive side of the Z-axis direction is upward or upward
  • the negative side of the Z-axis direction is downward or downward.
  • the positive side in the Y-axis direction is the back side or back
  • the negative side in the Y-axis direction is the front side or front side
  • the positive side in the X-axis direction is the right side or right side
  • the negative side in the X-axis direction is the left side or left side.
  • the component mounting apparatus 1 is a production facility that produces mounting boards by picking up components with the transfer head 8 and mounting them on the board 3 .
  • a component mounting apparatus 1 includes a base 1a, a substrate transport mechanism 2, two component supply units 4, a Y-axis beam 6, two X-axis beams 7, two transfer heads 8, Two board recognition cameras 12 and two component recognition cameras 11 are provided.
  • the base 1a is a table on which the substrate transport mechanism 2, the Y-axis beam 6, the two X-axis beams 7, and the two component recognition cameras 11 are arranged.
  • the substrate transport mechanism 2 has two rails along the X-axis direction, and is arranged in the center of the base 1a in the Y-axis direction.
  • the board transport mechanism 2 transports the board 3 carried in from the upstream side (for example, the negative side in the X-axis direction) and positions and holds the board 3 on the mounting stage, which is the position for performing the component mounting work.
  • the two component supply units 4 are arranged so as to sandwich the substrate transport mechanism 2 in the Y-axis direction.
  • a plurality of tape feeders 5 are arranged along the X-axis direction in the component supply section 4 .
  • the tape feeder 5, also simply called a feeder, supplies components. Specifically, the tape feeder 5 feeds the component by pitch-feeding the carrier tape containing the component in the tape feeding direction.
  • the component is an electronic component such as an IC (Integrated Circuit) chip.
  • the Y-axis beam 6 is arranged along the Y-axis direction on the upper surface of the base 1a on the positive side in the X-axis direction (the right end in the example shown in FIG. 1).
  • the two X-axis beams 7 are arranged on the Y-axis beam 6 so as to be movable in the Y-axis direction while each extending in the X-axis direction.
  • each of the two X-axis beams 7 is horizontally moved in the Y-axis direction by being driven by the driving mechanism of the Y-axis beam 6 .
  • Each of the two transfer heads 8 is attached to the X-axis beam 7 via a coupling plate 8a so as to be freely movable in the X-axis direction. Therefore, the transfer head 8 is moved in the X-axis direction and the Y-axis direction by the Y-axis beam 6 and the X-axis beam 7 .
  • the transfer head 8 is detachably mounted with a plurality of nozzle units 9 capable of picking up and holding components and moving up and down. By moving in the X-axis direction and the Y-axis direction, the transfer head 8 picks up the component supplied from the component supply unit 4 by means of the nozzle unit 9, and moves the mounting point of the substrate 3 positioned by the substrate transport mechanism 2. mount or attach the part to
  • Each of the two substrate recognition cameras 12 is located on the lower surface side of the X-axis beam 7 and arranged on the coupling plate 8a so as to move integrally with the transfer head 8 .
  • the substrate recognition camera 12 is arranged on the coupling plate 8a in a posture in which the imaging direction faces downward.
  • the substrate recognition camera 12 moves together with the transfer head 8 onto the substrate 3 positioned by the substrate transport mechanism 2 and takes an image of the substrate 3 in order to recognize the position and type of the substrate 3 .
  • the two component recognition cameras 11 are arranged on the base 1a so as to sandwich the substrate transport mechanism 2 in the Y-axis direction. Each of the two component recognition cameras 11 moves the component from the negative side in the Z-axis direction when the transfer head 8 corresponding to the component recognition camera 11 moves over the component recognition camera 11 with the component picked up. Take an image. By performing recognition processing on the image obtained by this imaging, the position, angle, type, etc. of the component sucked and held by the transfer head 8 are identified.
  • FIG. 2 is a perspective view of the transfer head 8 used in the component mounting device 1.
  • FIG. 2 is a perspective view of the transfer head 8 used in the component mounting device 1.
  • the transfer head 8 is attached to the X-axis beam 7 via the coupling plate 8a as described above.
  • a plurality of nozzle units 9 are arranged side by side on the transfer head 8 .
  • Each nozzle unit 9 has a nozzle driving portion 9 a , a nozzle shaft 13 , a nozzle mounting portion 14 and a suction nozzle 15 .
  • the nozzle drive unit 9a has a nozzle lifting mechanism that lifts and lowers the lifting shaft by a linear motor.
  • the nozzle shaft 13 is connected to the elevation shaft of the nozzle driving portion 9a so as to extend downward from the nozzle driving portion 9a.
  • the nozzle mounting part 14 is coupled to the lower end of the nozzle shaft 13 .
  • the suction nozzle 15 is detachably attached to the lower side of the nozzle mounting portion 14, and sucks and holds a component by vacuum suction. In such a transfer head 8, the suction nozzles 15 attached to the nozzle attachment portions 14 are individually moved up and down by driving the linear motors of the nozzle drive portions 9a in each of the plurality of nozzle units 9.
  • Each nozzle mounting portion 14 is mounted with a suction nozzle 15 of a type corresponding to the size and shape of a component to be suctioned.
  • the component mounting apparatus 1 also includes an air control mechanism for sucking air in the suction nozzle 15 and blowing out air from the suction nozzle 15 .
  • FIG. 3 is a diagram showing an example of the configuration of the air control mechanism according to this embodiment.
  • the air control mechanism of the component mounting apparatus 1 includes a vacuum pump 19, an air supply source 21, an atmosphere supply source 22, the plurality of nozzle units 9 described above, and a nozzle control section 23.
  • the vacuum pump 19 generates negative pressure (also called vacuum).
  • the vacuum pump 19 is connected to the input port P1 of the switching valve 18 of the nozzle unit 9 via an air flow path.
  • the air supply source 21 is connected to the input port P3 of the blow valve 20 of the nozzle unit 9 via an air flow path, and supplies positive pressure air to the blow valve 20 .
  • the air supply source 22 is connected to the input port P4 of the blow valve 20 via an air flow path, and supplies atmospheric pressure air to the blow valve 20, for example.
  • the air supply source 22 can also be realized by opening the input port P4 of the blow valve 20 .
  • the nozzle control unit 23 controls the switching valve 18 and the blow valve 20 of the nozzle unit 9.
  • the nozzle unit 9 includes a switching valve 18, a blow valve 20, a flow sensor 16, a nozzle shaft 13, a nozzle mounting portion 14, a suction nozzle 15, an air tube 40, and a filter 41.
  • the air tube 40 is connected to the nozzle shaft 13.
  • the cavities formed inside the air tube 40, the nozzle shaft 13, the nozzle mounting portion 14, and the suction nozzle 15 communicate with each other. Therefore, air can flow from the upper end of the air tube 40 to the lower end of the suction nozzle 15 , and conversely, air can flow from the lower end of the suction nozzle 15 to the upper end of the air tube 40 . .
  • the filter 41 is arranged inside the nozzle mounting portion 14 and purifies the air passing through the inside thereof.
  • the blow valve 20 is composed of an electromagnetic valve or the like having two input ports P3 and P4 and an output port A2.
  • the output port A2 of the blow valve 20 is connected to the input port P2 of the switching valve 18 via an air flow path.
  • Such a blow valve 20 switches the flow path of air by opening and closing an electromagnetic valve according to control by the nozzle control section 23 . That is, the blow valve 20 switches the air flow path between the first flow path and the second flow path.
  • the first flow path is a flow path through which air flows between the air supply source 21 and the switching valve 18 via the blow valve 20 .
  • positive pressure air is supplied from the air supply source 21 along the first flow path to the switching valve 18 .
  • the second flow path is a flow path through which air flows between the atmosphere supply source 22 and the switching valve 18 via the blow valve 20 .
  • air at atmospheric pressure is supplied from the atmospheric supply source 22 along the second flow path to the switching valve 18 .
  • the switching valve 18 is composed of an electromagnetic valve or the like having two input ports P1 and P2 and an output port A1.
  • the output port A ⁇ b>1 of the switching valve 18 is connected to the suction nozzle 15 via the output path 17 , which is an air flow path, the air tube 40 , the nozzle shaft 13 and the nozzle mounting portion 14 .
  • Such a switching valve 18 switches the flow path of air by opening and closing a solenoid valve according to control by the nozzle control section 23 . That is, the switching valve 18 switches the air flow path between the third flow path and the fourth flow path.
  • the third flow path is a flow path through which air flows between the suction nozzle 15 and the vacuum pump 19 via the nozzle mounting portion 14, the air tube 40, the output path 17, and the switching valve 18.
  • the vacuum pump 19 is driven and air flows along the third flow path, the air flows in the direction indicated by the arrow b in FIG.
  • Surrounding air is sucked into the suction holes formed in the suction holding surface 15 a at the lower end of the suction nozzle 15 .
  • the component D is sucked and held by the suction holding surface 15a.
  • a fourth flow path is a flow path through which air flows between the suction nozzle 15 and the blow valve 20 via the switching valve 18 , the output path 17 , the air tube 40 , the nozzle shaft 13 and the nozzle mounting portion 14 .
  • the air flow path is switched to the first flow path by the blow valve 20 and the air flow path is switched to the fourth flow path by the switching valve 18, the air flows in the direction indicated by the arrow a in FIG. , air is blown out from the suction holes of the suction nozzle 15 . That is, by driving the air supply source 21, positive pressure air flows from the air supply source 21 to the suction nozzle 15 via the blow valve 20, the switching valve 18, etc., and is formed on the suction holding surface 15a of the suction nozzle 15.
  • the flow rate sensor 16 measures the flow rate of air flowing through the output path 17 and outputs flow rate information d1 indicating the measurement result.
  • flow rate information d1 indicates, for example, a temporal change in flow rate as a waveform.
  • Such flow rate information d ⁇ b>1 is output from each flow rate sensor 16 of each of the plurality of nozzle units 9 included in the transfer head 8 .
  • the suction nozzle 15 When the suction nozzle 15 sucks air while the component D is in contact with the suction holding surface 15a, the component D is vacuum-sucked by the suction nozzle 15. At this time, the flow rate of air measured by the flow rate sensor 16 is almost zero. When the suction nozzle 15 is sucking the surrounding air while the component D is not in contact with the suction holding surface 15a, the air flow rate measured by the flow rate sensor 16 is a negative flow rate. Further, when air is blowing out from the suction nozzle 15, the air flow rate measured by the flow rate sensor 16 is a positive flow rate.
  • the flow rate sensor 16 When the air pressure inside each of the air supply source 22, the blow valve 20, the switching valve 18, the air tube 40, the nozzle shaft 13, the nozzle mounting portion 14, and the suction nozzle 15 is the atmospheric pressure, the flow rate sensor 16 The air flow rate measured by is almost zero.
  • FIG. 4 is a block diagram showing an example of the functional configuration of the component mounting apparatus 1 according to this embodiment.
  • the component mounting apparatus 1 includes the substrate transport mechanism 2, the component supply unit 4, the head moving mechanism 10, the component recognition camera 11, the substrate recognition camera 12, the vacuum pump 19, the air supply source 21, the atmosphere supply source 22, and a transfer head 8 .
  • the component mounting apparatus 1 further includes a device control section 30 , a device storage section 31 , an input section 32 , a presentation section 33 and a diagnostic system 100 .
  • the head moving mechanism 10 is a mechanism including the Y-axis beam 6 and the X-axis beam 7 described above.
  • the device control unit 30 controls each component of the component mounting device 1 .
  • the device control unit 30 is configured by a CPU (Central Processing Unit) or a processor.
  • the device storage unit 31 is a recording medium storing various data for mounting the component D on the substrate 3 by the component mounting device 1 .
  • the device storage unit 31 is a hard disk drive, RAM (Random Access Memory), ROM (Read Only Memory), semiconductor memory, or the like. Note that such a device storage unit 31 may be volatile or nonvolatile.
  • the device storage section 31 may store a computer program that is read and executed by the device control section 30 . In this case, the device control section 30 controls each component of the component mounting device 1 by reading and executing the computer program.
  • the input unit 32 is configured as, for example, a keyboard, touch sensor, touch pad, mouse, or the like. Such an input section 32 accepts input operations by an operator who manufactures mounting boards using the component mounting apparatus 1, and outputs signals corresponding to the input operations to the device control section 30, the diagnostic system 100, or the like.
  • the presentation unit 33 receives a presentation signal from the device control unit 30 or the diagnostic system 100, and outputs at least one of an image and a sound according to the presentation signal.
  • the presentation unit 33 is a display such as a liquid crystal display or an organic EL (Electro-Luminescence) display. In this case, the presentation unit 33 displays an image according to the presentation signal.
  • the presentation unit 33 may be a speaker or the like. In this case, the presentation unit 33 outputs a sound corresponding to the presentation signal.
  • the presentation unit 33 may include a display and a speaker.
  • the diagnosis system 100 diagnoses the state of deterioration of each component included in each nozzle unit 9 of each of the plurality of nozzle units 9 of the transfer head 8 . In other words, the diagnosis system 100 estimates the current degree of deterioration of each of the components, and further estimates the degree of deterioration in the future. The diagnostic system 100 also predicts maintenance timings for those components.
  • Each component included in the nozzle unit 9 is a member through which air passes. Specifically, each component is an air tube 40, a filter 41, a valve, a shaft, or the like.
  • the valve is at least one of switching valve 18 and blow valve 20 .
  • the shaft is for example the nozzle shaft 13 .
  • FIG. 5 is a block diagram showing an example of the functional configuration of diagnostic system 100 according to the present embodiment.
  • the diagnostic system 100 diagnoses the state of deterioration of each component included in each of the plurality of nozzle units 9 using the flow rate information d1, the production plan information d2, and the production performance information d3, and presents a presentation signal indicating the diagnosis result. is output to the presentation unit 33 .
  • the diagnosis result is presented by the presenting unit 33 in the form of an image, sound, or the like.
  • Such a diagnostic system 100 includes an acquisition unit 101, a maintenance processing unit 102, a prediction unit 103, an output unit 104, a learning unit 110, a model storage unit 120, and a deterioration identification unit 130.
  • the acquisition unit 101 acquires flow rate information d1, production plan information d2, and production performance information d3.
  • the flow rate information d1 is information about the flow rate of the air flowing through the transfer head 8 in the component mounting apparatus 1 that picks up the component D by the transfer head 8 and mounts it on the substrate 3 .
  • the production plan information d2 is information indicating a plan for producing mounted substrates using the component mounting apparatus 1.
  • FIG. In other words, the production plan information d2 is information indicating a production plan for producing the mounted board, which is the board 3 on which the component D is mounted, using production equipment.
  • the production planning information d2 indicates the number of times the component D is picked up by the nozzle unit 9 and mounted on the substrate 3 (hereinafter referred to as the number of times of mounting) for each of the plurality of nozzle units 9 of the component mounting apparatus 1. shown as a plan. More specifically, the production plan information d2 indicates the number of mounting times at each of a plurality of points in the future.
  • the production performance information d3 is information indicating the performance of the operation of the component mounting apparatus 1 for producing the mounted substrates according to the production plan information d2. In other words, the actual production information d3 is information indicating the actual production of mounted substrates using production equipment.
  • the actual production information d3 indicates the past number of times the nozzle unit 9 picked up the component D and mounted it on the substrate 3 up to the present time for each of the plurality of nozzle units 9 of the component mounting apparatus 1. Shown as a result. More specifically, the actual production information d3 indicates the number of mounting times at each of a plurality of points in the past.
  • the acquisition unit 101 outputs the flow rate information d1 to the learning unit 110 and the deterioration identification unit 130. Furthermore, the acquisition unit 101 outputs the production plan information d2 and the actual production information d3 to the prediction unit 103.
  • FIG. 1 A block diagram illustrating an exemplary computing environment in accordance with the present disclosure.
  • the learning unit 110 acquires the flow rate information d1 from the acquisition unit 101 as training data, generates a diagnostic model by machine learning using the flow rate information d1, and stores the diagnostic model in the model storage unit 120.
  • the diagnostic model is a machine learning model used for diagnosing the state of deterioration of each component included in the nozzle unit 9 .
  • the diagnostic model is a neural network.
  • Such a diagnostic model is such that the learning unit 110 outputs information indicating the deterioration state of each component included in the nozzle unit 9 corresponding to the flow rate information d1 in response to the input of the flow rate information d1. is generated by performing machine learning. That is, it can be said that the diagnostic model indicates the relationship between the flow rate information d1 and the deterioration state of each component included in the nozzle unit 9 .
  • the model storage unit 120 is a recording medium for storing diagnostic models.
  • a model storage unit 120 may be a hard disk drive, RAM, ROM, semiconductor memory, or the like.
  • the deterioration identification unit 130 identifies the deterioration state of each of the plurality of constituent members included in the nozzle unit 9 corresponding to the flow rate information d1 of the transfer head 8 based on the flow rate information d1. Specifically, the deterioration identification unit 130 acquires the flow rate information d1 from the acquisition unit 101 and acquires the diagnostic model from the model storage unit 120 . Then, the deterioration specifying unit 130 inputs the flow rate information d1 to the diagnostic model and acquires the deterioration information output from the diagnostic model. This deterioration information indicates the deterioration state of each component included in the nozzle unit 9 .
  • the deterioration identifying unit 130 identifies the deterioration state of each component by acquiring such deterioration information. That is, the deterioration identifying unit 130 identifies the deterioration state by using the diagnostic model. Deterioration identifying section 130 outputs deterioration information indicating the identified deterioration state to output section 104 , maintenance processing section 102 and prediction section 103 .
  • the deterioration information is information indicating the past or present deterioration state of each constituent member included in the production facility that is the component mounting apparatus 1 . Further, the deterioration information may indicate the deterioration state of each component at each of a plurality of past points of time.
  • the maintenance processing unit 102 acquires deterioration information from the deterioration identification unit 130 and generates maintenance information regarding maintenance of constituent members included in the nozzle unit 9 based on the deterioration information. The maintenance processing unit 102 then outputs the maintenance information to the output unit 104 .
  • the prediction unit 103 estimates the future deterioration state of each component included in the nozzle unit 9 of the transfer head 8 . Furthermore, the prediction unit 103 predicts the arrival time when the deterioration state reaches the prescribed deterioration state as the maintenance timing. That is, the prediction unit 103 acquires information indicating the deterioration state identified by the deterioration identification unit 130 as deterioration information. Based on the deterioration information and the production plan information d2 and the actual production information d3 acquired by the acquisition unit 101, the prediction unit 103 predicts the future deterioration state of each constituent member in a predetermined deterioration state. Predict the arrival time to reach a specified deterioration state. The prediction unit 103 outputs arrival time information indicating the predicted arrival time to the output unit 104 .
  • the output unit 104 outputs deterioration information indicating the specified deterioration state.
  • the output unit 104 when acquiring the deterioration information from the deterioration specifying unit 130, the output unit 104 outputs the deterioration information to the presentation unit 33 as a presentation signal.
  • the presentation unit 33 presents the content of the deterioration information (that is, the deterioration state).
  • the output unit 104 also outputs arrival time information indicating the predicted arrival time. That is, when the arrival time information is acquired from the prediction unit 103, the output unit 104 outputs the arrival time information to the presentation unit 33 as a presentation signal.
  • the presentation unit 33 presents the content of the arrival time information (that is, the arrival time).
  • the output unit 104 outputs maintenance information. That is, when the maintenance information is acquired from the maintenance processing unit 102, the output unit 104 outputs the maintenance information to the presentation unit 33 as a presentation signal. As a result, the presentation unit 33 presents the content of the maintenance information (that is, the content regarding maintenance).
  • FIG. 6 is a diagram for explaining the learning unit 110 and the diagnostic model.
  • the learning unit 110 includes a feature extraction unit 111 and a learning processing unit 112 .
  • the feature amount extraction unit 111 acquires the flow rate information d1, which is training data, from the acquisition unit 101, extracts a plurality of types of feature amounts related to the air flow rate from the flow rate information d1, and extracts a training data indicating the plurality of types of feature amounts. is output to the learning processing unit 112 .
  • the flow rate information d1 is, for example, a flow rate waveform that indicates the change over time of the air flow rate measured by the flow rate sensor 16 .
  • This flow rate waveform is obtained, for example, by causing the nozzle unit 9 to intermittently and repeatedly suck or blow air under the control of the nozzle control section 23 when the component mounting apparatus 1 is not producing mounted substrates. It may be a waveform. Also, the flow waveform may be a waveform obtained when the suction nozzle 15 is not attached to the nozzle attachment portion 14 .
  • the feature quantity extraction unit 111 extracts, for example, a characteristic time or flow rate indicated by the flow waveform as a feature quantity.
  • the feature amount is a numerical value such as a positive peak flow rate, a negative peak flow rate, a steady flow rate, a response time, or a steady time.
  • the feature amount may be a value calculated by calculation using two or more of these numerical values, or may be a vector composed of these numerical values.
  • the response time is, for example, the time from when the air flow path is switched by the switching valve 18 and the blow valve 20 until the flow rate of air stabilizes. Steady time is the time during which the stable flow rate continues. A steady flow is that flow that is steady.
  • the learning processing unit 112 acquires the feature amount data da1 for training from the feature amount extraction unit 111, performs machine learning using the feature amount data da1, generates the diagnostic model 121, and uses the diagnostic model 121 as Stored in the model storage unit 120 .
  • Machine learning is learning using, for example, a neural network or a deep neural network.
  • Machine learning may be supervised learning or unsupervised learning.
  • Machine learning may also be random forest, SVM (Support Vector Machine), Gaussian process regression, SVR (Support Vector Regression), or random forest regression.
  • Machine learning may be learning that generates an exponential model, a power model, a logarithmic model, a Gompertz model, or a Lloyd-Lipow model as the diagnostic model 121 .
  • Such a learning processing unit 112 includes an anomaly learning unit 112a, a classification learning unit 112b, and a deterioration degree learning unit 112c.
  • the abnormality learning unit 112a generates the abnormality determination model 121a by machine learning using the feature amount data da1 for training.
  • This abnormality determination model 121a is, for example, a model that outputs abnormality determination result information indicating whether or not the nozzle unit 9 corresponding to the feature amount data da1 is abnormal in response to input of the feature amount data da1.
  • the abnormal learning unit 112a performs learning using feature data da1 for training and teacher data corresponding to at least one feature indicated by the feature data da1.
  • the teacher data indicates whether or not the nozzle unit 9 is abnormal.
  • the abnormality determination model 121a indicates, for example, a region in which the nozzle unit 9 is abnormal and a region in which the nozzle unit 9 is normal in a two-dimensional space whose coordinate axes are each of the two types of feature amounts.
  • the classification learning unit 112b generates an anomaly classification model 121b by machine learning using the training feature data da1.
  • This abnormality classification model 121b is a model that outputs abnormality classification information indicating which component of the nozzle unit 9 corresponding to the feature amount data da1 is abnormal at least in response to the input of the feature amount data da1. is.
  • the classification learning unit 112b performs learning using feature amount data da1 for training and teacher data corresponding to at least one feature amount indicated by the feature amount data da1.
  • the teacher data indicates which component of the nozzle unit 9 is abnormal.
  • the deterioration degree learning unit 112c generates the deterioration degree estimation model 121c by machine learning using the training feature data da1.
  • This deterioration degree estimation model 121c is a model that outputs deterioration degree information indicating the degree of deterioration of the constituent member of the nozzle unit 9 corresponding to at least the feature amount data da1 in response to the input of the feature amount data da1.
  • the deterioration degree learning unit 112c performs learning using feature data da1 for training and teacher data corresponding to at least one feature represented by the feature data da1.
  • the teacher data indicates the degree of deterioration of the constituent members of the nozzle unit 9 .
  • FIG. 7 is a diagram for explaining the deterioration identifying unit 130 and the diagnostic model.
  • the deterioration identification unit 130 includes a feature quantity extraction unit 131 and a identification processing unit 132 .
  • the feature amount extraction section 131 After acquiring the flow rate information d1 from the acquisition section 101, the feature amount extraction section 131 extracts a plurality of types of feature amounts relating to the air flow rate from the flow rate information d1, and specifies feature amount data da1 indicating the plurality of types of feature amounts. Output to the processing unit 132 . That is, the feature amount extraction unit 131 of the deterioration identification unit 130 has the same configuration and functions as the feature amount extraction unit 111 of the learning unit 110 .
  • the specific processing unit 132 acquires the feature amount data da1 from the feature amount extraction unit 131 and acquires the diagnostic model 121 from the model storage unit 120 . Then, the specific processing unit 132 acquires the deterioration information db output from the diagnostic model 121 by inputting the characteristic amount data da1 to the diagnostic model 121 . As a result, the deteriorated state of each component included in the nozzle unit 9 corresponding to the feature amount data da1 is identified.
  • the identification processing unit 132 includes an abnormality processing unit 132a, a classification processing unit 132b, and a deterioration degree processing unit 132c.
  • the abnormality processing unit 132a acquires the abnormality determination model 121a of the diagnostic model 121 from the model storage unit 120, and inputs the feature amount data da1 to the abnormality determination model 121a. As a result, the abnormality processing unit 132a acquires the abnormality determination result information db1 output from the abnormality determination model 121a. This abnormality determination result information db1 indicates whether or not the nozzle unit 9 corresponding to the feature amount data da1 is abnormal. In other words, the abnormality processing section 132a determines whether or not the nozzle unit 9 corresponding to the feature amount data da1 is abnormal.
  • the classification processing unit 132b acquires the abnormality classification model 121b of the diagnostic model 121 from the model storage unit 120, and inputs the feature data da1 to the abnormality classification model 121b. As a result, the classification processing unit 132b acquires the abnormality classification information db2 output from the abnormality classification model 121b. This abnormality classification information db2 indicates which constituent member of the nozzle unit 9 corresponding to the feature amount data da1 is abnormal. That is, the classification processing unit 132b classifies the state of each of the plurality of constituent members included in the nozzle unit 9 corresponding to the feature amount data da1 into either normal or abnormal.
  • the deterioration degree processing unit 132c acquires the deterioration degree estimation model 121c of the diagnostic model 121 from the model storage unit 120, and inputs the characteristic amount data da1 to the deterioration degree estimation model 121c. Thereby, the deterioration degree processing unit 132c acquires the deterioration degree information db3 output from the deterioration degree estimation model 121c. This deterioration degree information db3 indicates the deterioration degree of the constituent members of the nozzle unit 9 . That is, the deterioration degree processing unit 132c estimates the deterioration degree of the constituent members of the nozzle unit 9 using the deterioration degree estimation model 121c.
  • the deterioration identifying unit 130 identifies the deterioration state by estimating the degree of deterioration indicating the degree of deterioration of each of at least one component included in the nozzle unit 9 . Further, the degree of deterioration indicates a larger value as the degree of deterioration increases.
  • FIG. 8 is a diagram showing a specific example of the deterioration information db.
  • the deterioration specifying unit 130 generates and outputs deterioration information db for each of the nozzle units 9 included in the transfer head 8 .
  • the deterioration information db includes, as shown in FIG. 8, abnormality determination result information db1, abnormality classification information db2, and deterioration degree information db3.
  • the abnormality determination result information db1 indicates that the nozzle unit 9 corresponding to the abnormality determination result information db1 is abnormal.
  • the abnormality classification information db2 indicates whether each component included in the nozzle unit 9 is normal or abnormal.
  • the abnormality classification information db2 indicates that the filter 41 is normal, the valves such as the switching valve 18 are normal, the air tube 40 is abnormal, and the shaft that is the nozzle shaft 13 is normal.
  • the deterioration degree information db3 indicates the deterioration degree of each component included in the nozzle unit 9 by an integer value of 0-10. The closer the deterioration degree is to 10, the higher the deterioration degree, and the closer the deterioration degree is to 0, the smaller the deterioration degree.
  • the deterioration degree information db3 indicates the deterioration degree "1" of the filter 41, the deterioration degree "5" of the valve, the deterioration degree “9” of the air tube 40, and the deterioration degree "6" of the shaft.
  • the presentation unit 33 presents the content of such deterioration information db. Therefore, an operator who performs work using the component mounting apparatus 1 can grasp the deterioration state of each of at least one component included in the transfer head 8 from the output deterioration information db. As a result, the detailed state of the transfer head 8 can be diagnosed rather than a simple state such as whether or not the constituent members are normal. Since the state of deterioration of each of the plurality of constituent members is diagnosed, the operator can easily determine whether maintenance of those constituent members is necessary or whether preparation for such maintenance is necessary. Therefore, the operator can avoid wasting maintenance on components that do not require maintenance. Alternatively, the operator can avoid wasting maintenance or preparations for components that do not require maintenance preparations. As a result, it is possible to improve efficiency of maintenance, shorten maintenance time, and reduce maintenance costs. In this way, it is possible to more appropriately support the maintenance of the component mounting apparatus 1, which is production equipment, by the operator.
  • the maintenance processing unit 102 Based on such deterioration information db, the maintenance processing unit 102 generates maintenance information regarding maintenance of the constituent members included in the nozzle unit 9 corresponding to the deterioration information db. Specifically, the maintenance processing unit 102 determines whether or not the degree of deterioration estimated for each of the plurality of constituent members included in the nozzle unit 9 exceeds a threshold, and determines the threshold. Maintenance information is generated regarding maintenance of the component having the degree of deterioration determined to be exceeded. The maintenance information is, for example, maintenance warning information prompting maintenance of the constituent members, or maintenance forecast information prompting preparation for maintenance of the constituent members. The maintenance alert information can also be said to be an alert or warning for notifying the operator that maintenance is now required.
  • the maintenance forecast information can also be said to be a forecast or advance notice for informing the worker in advance that the timing for maintenance is imminent.
  • the maintenance processing unit 102 After generating maintenance information such as maintenance warning information and maintenance forecast information, the maintenance processing unit 102 outputs the maintenance information to the output unit 104 .
  • the output unit 104 When acquiring the maintenance information from the maintenance processing unit 102, the output unit 104 outputs the maintenance information to the presentation unit 33 as a presentation signal. As a result, the content of the maintenance information is presented to the presentation unit 33 by means of images, sounds, or the like.
  • the deterioration identifying unit 130 determines whether or not there is an abnormality in each of one or more constituent members included in the nozzle unit 9 of the transfer head 8, and determines whether or not there is an abnormality among the one or more constituent members. A degree of deterioration of each of the at least one component determined to be present may be estimated. In other words, the deterioration identifying unit 130 may determine whether or not there is an abnormality in the constituent member, and estimate the degree of deterioration of the constituent member when it is determined that there is an abnormality.
  • FIG. 9 is a diagram for explaining inputs and outputs of the abnormality processing unit 132a, the classification processing unit 132b, and the deterioration degree processing unit 132c.
  • Each of the abnormality processing unit 132a, the classification processing unit 132b, and the deterioration degree processing unit 132c may add new information to the input data and output the input data. That is, the abnormality processing unit 132a acquires the feature amount data da1 output from the feature amount extraction unit 131 as input data, adds abnormality determination result information db1, which is new information, to the input data, and outputs the result.
  • the classification processing unit 132b acquires the feature amount data da1 and the abnormality determination result information db1 output from the abnormality processing unit 132a as input data, adds abnormality classification information db2 as new information to the input data, and outputs the result. .
  • the deterioration degree processing unit 132c acquires the feature amount data da1, the abnormality determination result information db1, and the abnormality classification information db2 output from the classification processing unit 132b as input data, and adds deterioration degree information as new information to the input data. Add db3 and output.
  • the deterioration degree information db3 output at this time may indicate the deterioration degree of the constituent members (also called abnormal members) classified as abnormal in the abnormality classification information db2.
  • the deterioration degree processing unit 132c may acquire the feature amount data da1 output from the feature amount extraction unit 131 as input data.
  • the deterioration degree processing unit 132c outputs deterioration degree information db3 indicating the degree of deterioration of the constituent members (also called normal members) classified as normal in the abnormality classification information db2 based on the feature amount data da1.
  • FIG. 10 is a diagram for explaining the processing of the prediction unit 103.
  • FIG. 10 is a diagram for explaining the processing of the prediction unit 103.
  • the prediction unit 103 acquires the actual production information d3 from the acquisition unit 101 and acquires the deterioration information db from the deterioration identification unit 130 .
  • the actual production information d3 includes placement number information indicating the number of placements of the component D on the board 3 by each of the nozzle units 9 of the transfer head 8 . Then, the prediction unit 103 estimates the future deterioration state of each component included in each of the nozzle units 9 for each of the plurality of nozzle units 9 based on the number-of-mounting information and the deterioration information db.
  • the graph in FIG. 10 shows the relationship between the degree of deterioration of one component included in one nozzle unit 9 and the number of times component D is mounted on substrate 3 by that nozzle unit 9 .
  • the horizontal axis of the graph indicates the number of wearing times, and the vertical axis indicates the degree of deterioration.
  • the prediction unit 103 identifies a deterioration point (marked with a black circle in FIG. 10) indicating the current or past number of times of mounting and the degree of deterioration in the number of times of mounting from the actual production information d3 and the deterioration information db. Specifically, the prediction unit 103 predicts the number of times of mounting indicated by the number of times of mounting in the actual production information d3 and the degree of deterioration indicated in the deterioration information db obtained at that time, for each current or past point in time. By associating with , the point of deterioration at the present or at each point in the past is specified.
  • the prediction unit 103 calculates approximate curves for those deterioration points as deterioration approximate curves.
  • the deterioration approximation curve may be calculated by, for example, the least squares method. That is, the prediction unit 103 estimates the future deterioration state by calculating the deterioration approximation curve. Specifically, the prediction unit 103 estimates that the deterioration approximation curve indicates the relationship between the number of mounting times, which is greater than the current number of mounting times m0, and the degree of deterioration of the component. Therefore, the prediction unit 103 determines that the predicted deterioration point (square mark in FIG.
  • the prediction unit 103 estimates the future deterioration degree of the constituent member after the present time, which indicates a larger value as the degree of deterioration of the constituent member increases.
  • the prediction unit 103 predicts the time when the future deterioration state of the constituent member will reach a specified deterioration state, which is a predetermined deterioration state.
  • the prescribed deteriorated state is a first prescribed deteriorated state that requires maintenance of the component, or a second prescribed deteriorated state that requires preparation for the maintenance. That is, the first specified deterioration state is the deterioration state of the component when the maintenance warning information is generated for the component and the content of the maintenance warning information is presented from the presentation unit 33 .
  • the second prescribed deterioration state is the deterioration state of the component when the maintenance forecast information described above is generated for the component and the content of the maintenance forecast information is presented from the presentation unit 33 .
  • the prediction unit 103 predicts the arrival time when the future deterioration degree reaches the first threshold value corresponding to the first specified deterioration state, or the arrival time when the future deterioration degree reaches the second threshold value corresponding to the second specified deterioration state.
  • the timing is predicted based on the production plan information d2.
  • the prediction unit 103 specifies the number m1 of wearing times when the degree of deterioration is the first threshold on the deterioration approximation curve.
  • the prediction unit 103 refers to the production plan information d2, and specifies the period T1 from the current mounting number m0 to the mounting number m1 from the production planning information d2.
  • the production plan information d2 shows the relationship between the elapsed time and the number of mounting times for each nozzle unit 9 .
  • the prediction unit 103 predicts the timing after the elapse of the specified period T1 from the current time as the arrival time when the future deterioration state of the constituent member reaches the first specified deterioration state. This arrival time is also called maintenance implementation time.
  • the prediction unit 103 specifies the number of wearing times m2 when the degree of deterioration is the second threshold on the deterioration approximation curve. Note that the second threshold is a value smaller than the first threshold. Then, the prediction unit 103 refers to the production plan information d2, and specifies a period T2 from the current mounting number m0 to the mounting number m2 from the production planning information d2. The prediction unit 103 predicts the timing after the elapse of the specified period T2 from the current time as the arrival time when the future deterioration state of the constituent member reaches the second specified deterioration state. This arrival time is also called a maintenance preparation time. Note that the above-described maintenance implementation timing and maintenance preparation timing are collectively referred to as maintenance timing. Also, the arrival time information indicates the maintenance time.
  • the timing at which maintenance of the deteriorated component member is required or the timing at which preparation for the maintenance is required is predicted as the arrival time, and the arrival time is indicated. Arrival time information is output. Therefore, a worker who performs work using the component mounting apparatus 1, which is a production facility, can grasp the arrival time, that is, the maintenance execution time or the maintenance preparation time. As a result, the worker can perform work in anticipation of those times, and can improve work efficiency. Also, efficiency of maintenance can be improved. In this way, maintenance of production equipment by workers can be more appropriately supported.
  • FIG. 11 is a flowchart showing an example of a processing operation regarding identification of a deterioration state by the diagnostic system 100. As shown in FIG.
  • the acquisition unit 101 of the diagnostic system 100 acquires the flow rate information d1 (step S1).
  • the feature amount extraction unit 131 of the deterioration identification unit 130 generates feature amount data da1 by extracting the feature amount from the flow rate information d1 (step S2).
  • the identification processing unit 132 of the deterioration identification unit 130 executes the processing of steps S3, S4 and S5. That is, the abnormality processing section 132a of the specific processing section 132 determines whether or not there is an abnormality in the nozzle unit 9 (step S3).
  • the classification processing unit 132b of the specific processing unit 132 classifies the state of each component included in the nozzle unit 9 into abnormal and normal (step S4).
  • the deterioration degree processing unit 132c of the specific processing unit 132 estimates the deterioration degree of each component included in the nozzle unit 9 (step S5).
  • the output unit 104 outputs the deterioration information db indicating the results of the processing of steps S3, S4 and S5 performed by the identification processing unit 132 of the deterioration identification unit 130 to the presentation unit 33 as a diagnosis result (step S6).
  • the presentation unit 33 presents the content of the deterioration information db.
  • FIG. 12 is a flowchart showing an example of a processing operation regarding a maintenance instruction by the diagnostic system 100.
  • step S10 the diagnostic system 100 executes diagnostic processing (step S10).
  • This diagnosis process is the process of steps S1 to S5 included in the flowchart of FIG.
  • the maintenance processing unit 102 of the diagnostic system 100 determines whether or not the degree of deterioration of each component obtained in the diagnostic process of step S10 is greater than the first threshold (step S11).
  • the maintenance processing unit 102 determines that the degree of deterioration of the component is greater than the first threshold value (Yes in step S11)
  • the maintenance processing unit 102 instructs the operator to perform maintenance via the output unit 104 and the presentation unit 33. (Step S12). That is, the maintenance processing unit 102 determines whether or not the degree of deterioration estimated for each of the plurality of constituent members included in the nozzle unit 9 exceeds the first threshold.
  • the maintenance processing unit 102 generates maintenance warning information that prompts maintenance of the component having the degree of deterioration determined to exceed the first threshold. After that, the maintenance processing unit 102 outputs the maintenance warning information to the output unit 104 , and the output unit 104 outputs the maintenance warning information to the presentation unit 33 . As a result, the content of the maintenance warning information is presented from the presentation unit 33 .
  • maintenance warning information is generated and output to prompt maintenance of the structural member.
  • maintenance warning information is notified to the worker, and the worker can quickly and appropriately perform maintenance on the component.
  • step S11 when the maintenance processing unit 102 determines that the degree of deterioration of the component is equal to or less than the first threshold (No in step S11), it further determines whether the degree of deterioration is greater than the second threshold. Determine (step S13).
  • the maintenance processing unit 102 determines that the degree of deterioration of the component is greater than the second threshold value (Yes in step S13)
  • the maintenance processing unit 102 instructs the operator to prepare for maintenance via the output unit 104 and the presentation unit 33.
  • This second threshold is a numerical value less than the first threshold.
  • the maintenance processing unit 102 determines that the degree of deterioration estimated for each of the plurality of constituent members included in the nozzle unit 9 is equal to or lower than the first threshold, and the degree of deterioration is equal to or lower than the first threshold. It is determined whether or not a second threshold smaller than is exceeded. Then, the maintenance processing unit 102 generates maintenance forecast information that prompts preparation for performing maintenance on the constituent member having the degree of deterioration determined to be equal to or less than the first threshold value and to exceed the second threshold value. After that, the maintenance processing unit 102 outputs the maintenance forecast information to the output unit 104 , and the output unit 104 outputs the maintenance forecast information to the presentation unit 33 . As a result, the content of the maintenance forecast information is presented from the presentation unit 33 .
  • Maintenance forecast information is generated and output. As a result, the maintenance forecast information is notified to the worker, and the worker can appropriately prepare for the maintenance of the constituent member well in advance.
  • the output unit 104 outputs the deterioration information db indicating the result of the diagnosis processing in step S10 to the presentation unit 33 as a diagnosis result (step S6).
  • the presentation unit 33 presents the content of the deterioration information db.
  • FIG. 13 is a flow chart showing an example of processing operations related to maintenance timing prediction by the diagnosis system 100.
  • FIG. 13 is a flow chart showing an example of processing operations related to maintenance timing prediction by the diagnosis system 100.
  • step S10 the diagnostic system 100 executes diagnostic processing (step S10).
  • This diagnosis process is the process of steps S1 to S5 included in the flowchart of FIG.
  • the acquisition unit 101 of the diagnostic system 100 acquires the production plan information d2 (step S21) and acquires the actual production information d3 (step S22).
  • the prediction unit 103 estimates the future degree of deterioration of each component included in the nozzle unit 9 based on the acquired production performance information d3 (step S23). This future degree of deterioration is estimated with respect to the number of mounting times that the nozzle unit 9 will be used to mount the component D in the future. Then, the prediction unit 103 predicts the maintenance timing of each component of the nozzle unit 9 based on the future deterioration degree and the production plan information d2 acquired in step S21 (step S24).
  • This maintenance timing is the maintenance execution timing when the future deterioration degree reaches a first threshold value corresponding to the first specified deterioration state, or the maintenance execution timing when the future deterioration degree reaches the second threshold value corresponding to the second specified deterioration state. It's time to prepare.
  • the output unit 104 outputs arrival time information indicating the maintenance time predicted in step S24 to the presentation unit 33 (step S25).
  • the presentation unit 33 presents the content of the arrival time information (that is, the maintenance time).
  • the deterioration state of each of at least one component included in the transfer head 8 is specified, and the deterioration information db indicating the deterioration state is output.
  • the deterioration information db indicating the deterioration state is output.
  • the deterioration identifying unit 130 identifies the deterioration state of the constituent member by estimating the degree of deterioration indicating the degree of deterioration of the constituent member. This allows the operator to grasp the deterioration state in more detail.
  • the deterioration identifying unit 130 determines whether or not there is an abnormality in each of one or more constituent members included in the transfer head 8, and determines that one or more constituent members have an abnormality.
  • a degree of deterioration of each of the at least one component may be estimated.
  • the degree of deterioration is estimated for the component determined to be abnormal. It is possible to omit the estimation of the degree of deterioration for components assumed to be less likely to be damaged. As a result, the processing load for estimating the degree of deterioration can be reduced.
  • the degree of deterioration is estimated for the component determined to be abnormal, the operator can determine what kind of maintenance is required or whether maintenance is unnecessary for the component determined to be abnormal. can be easily grasped. For example, it is possible to easily grasp the form of required maintenance such as follow-up observation of the constituent members, cleaning of the constituent members, repair of the constituent members, replacement of parts included in the constituent members, and replacement of the constituent members themselves.
  • the maintenance processing unit 102 determines whether or not the degree of deterioration estimated for each of the at least one constituent members exceeds a threshold, and determines whether the degree of deterioration is determined to exceed the threshold. Generate maintenance information about component maintenance. Then, the output unit 104 outputs the maintenance information. As a result, for example, for a degraded component, maintenance information regarding maintenance of the component is generated and output. As a result, the maintenance information is notified to the operator, and the operator can quickly or appropriately perform maintenance on the component.
  • the deterioration identifying unit 130 also identifies the deterioration state by using the diagnostic model 121 that indicates the relationship between the flow rate information d1 and the deterioration state of each of at least one component. This makes it possible to appropriately identify the deterioration state.
  • the diagnostic model 121 is generated by performing machine learning so that information indicating the deterioration state of each of at least one component is output in response to the input of the flow rate information d1. Accordingly, by appropriately performing machine learning, it is possible to improve the accuracy of identifying the deterioration state.
  • the timing at which maintenance of the deteriorated component member is required or the timing at which preparation for the maintenance is required is predicted as the arrival time. is output. Therefore, it is possible to more appropriately support maintenance of production equipment by workers.
  • the deterioration information db indicates the deterioration state of the constituent member at each of a plurality of past points in time.
  • the deterioration state of the constituent members included in the transfer head 8 is specified based on the flow rate information d1, and the identified deterioration state is used to predict the arrival time. Therefore, the deterioration state can be appropriately specified, and the prediction accuracy of arrival time can be improved.
  • the deterioration state is estimated in more detail as the degree of deterioration, so it is possible to further improve the prediction accuracy of the arrival time.
  • the diagnostic system 100 when the degree of deterioration is estimated for a component determined to be abnormal, the arrival time of a component assumed to have signs of deterioration is predicted, and the signs of deterioration are predicted. It is possible to omit the prediction of arrival times for components assumed to be absent. As a result, it is possible to reduce the processing load of predicting the arrival time.
  • the actual production information d3 includes placement number information indicating the number of placement times that the component D has been placed on the substrate 3 by the transfer head 8, and the prediction unit 103 predicts the number of component parts based on the placement number information and the deterioration information db.
  • Estimate the future state of deterioration of This makes it possible to appropriately estimate the degree of deterioration with respect to the number of times of wearing in the future based on the degree of deterioration with respect to the number of times of wearing in the past.
  • diagnosis system 100 is provided inside the component mounting apparatus 1 in the above embodiment, it may be provided outside the component mounting apparatus 1, for example, a personal computer connected to the component mounting apparatus 1. It may be configured as a computer.
  • the transfer head 8 is provided with a plurality of nozzle units 9, but the number of nozzle units 9 provided in the transfer head 8 may be one.
  • the deterioration state is specified for each of the plurality of constituent members such as the air tube 40, the filter 41, and the valve included in the nozzle unit 9, and the maintenance time is predicted. Deterioration degree identification, maintenance timing prediction, and the like may be performed for each. In other words, each process such as identification and prediction may be performed on at least one component included in the transfer head 8 .
  • the learning unit 110 includes the feature amount extraction unit 111 and the deterioration identification unit 130 includes the feature amount extraction unit 131, but the feature amount extraction units 111 and 131 may not be provided.
  • various feature amounts are extracted from the flow rate information d1, and the feature amount data da1 representing these feature amounts are used by the learning processing section 112 and the specific processing section 132.
  • the flow rate information d1 may be directly used by the learning processing unit 112 and the specific processing unit 132.
  • FIG. That is, the flow rate waveform indicated by the flow rate information d1 may be directly used for machine learning, or may be directly used for identifying the deterioration state.
  • the deterioration identifying unit 130 includes the abnormality processing unit 132a and the classification processing unit 132b, but these components may not be included.
  • the abnormality determined by the abnormality processing unit 132a and the abnormality classified by the classification processing unit 132b may be an abnormality caused by deterioration of the constituent members, or may be an abnormality based on a factor other than deterioration. .
  • the component mounting device 1 is an example of production equipment, but the production equipment may be a device different from the component mounting device 1.
  • a production facility may also be referred to as a work facility.
  • various information is presented to a worker who performs production using the production equipment, and the worker performs maintenance of the production equipment. Such information may be presented and maintenance may be performed by a person other than the operator.
  • the diagnosis system 100 includes the maintenance processing unit 102 and the prediction unit 103, but may include only one of them. Further, even if the first threshold and the second threshold used in the maintenance processing unit 102 shown in FIG. 12 and the first threshold and the second threshold used in the prediction unit 103 shown in FIG. can be different.
  • the diagnostic model 121 is a machine learning model, but it may be a table that associates various feature amounts with the state of the nozzle unit 9 .
  • the state of the nozzle unit 9 may be the normality or abnormality of the nozzle unit 9, the normality or abnormality of each component included in the nozzle unit 9, or the degree of deterioration of each component. good.
  • each component may be configured by dedicated hardware or implemented by executing a software program suitable for each component.
  • Each component may be implemented by a program execution unit such as a CPU (Central Processing Unit) or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory.
  • the software that implements the diagnostic system 100 and the like of the above embodiment is a program that causes a computer to execute each step included in the flowcharts shown in FIGS. 11 to 13.
  • Each of the above devices is specifically a computer system composed of a microprocessor, ROM, RAM, hard disk unit, display unit, keyboard, mouse, and the like.
  • a computer program is stored in the RAM or hard disk unit.
  • Each device achieves its function by the microprocessor operating according to the computer program.
  • the computer program is constructed by combining a plurality of instruction codes indicating instructions to the computer in order to achieve a predetermined function.
  • a part or all of the components constituting each of the devices described above may be configured from one system LSI (Large Scale Integration).
  • a system LSI is an ultra-multifunctional LSI manufactured by integrating multiple components on a single chip. Specifically, it is a computer system that includes a microprocessor, ROM, RAM, etc. . A computer program is stored in the RAM. The system LSI achieves its functions by the microprocessor operating according to the computer program.
  • the IC card or module is a computer system composed of a microprocessor, ROM, RAM and the like.
  • the IC card or the module may include the super multifunctional LSI.
  • the IC card or the module achieves its function by the microprocessor operating according to the computer program. This IC card or this module may be tamper resistant.
  • the present disclosure may be the method shown above. Moreover, it may be a computer program for realizing these methods by a computer, or it may be a digital signal composed of the computer program.
  • the present disclosure includes a computer-readable recording medium for the computer program or the digital signal, such as a flexible disk, hard disk, CD-ROM, MO, DVD, DVD-ROM, DVD-RAM, BD (Blu-ray ( (Registered Trademark) Disc), semiconductor memory, or the like. Moreover, it may be the digital signal recorded on these recording media.
  • a computer-readable recording medium for the computer program or the digital signal such as a flexible disk, hard disk, CD-ROM, MO, DVD, DVD-ROM, DVD-RAM, BD (Blu-ray ( (Registered Trademark) Disc), semiconductor memory, or the like.
  • BD Blu-ray (Registered Trademark) Disc
  • semiconductor memory or the like.
  • it may be the digital signal recorded on these recording media.
  • the computer program or the digital signal may be transmitted via an electric communication line, a wireless or wired communication line, a network represented by the Internet, data broadcasting, or the like.
  • the present disclosure may also be a computer system comprising a microprocessor and memory, the memory storing the computer program, and the microprocessor operating according to the computer program.
  • the present disclosure can be used, for example, for systems that manage production equipment.

Landscapes

  • Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Operations Research (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Supply And Installment Of Electrical Components (AREA)

Abstract

A diagnostic system (100) is provided with: an acquisition unit (101) that acquires (i) production plan information (d2) indicating a production plan for producing, using production equipment, a mounted substrate which is a substrate (3) on which a component (D) is mounted, and (ii) production history information (d3) indicating the history of using the production equipment to produce mounted substrates; a prediction unit (103) that predicts an arrival time when the future state of degradation of a constituent member included in the production equipment reaches a prescribed degradation state, which is a predetermined degradation state, such prediction being on the basis of degradation information (db) indicating the past or current degradation state of the constituent member, and the production plan information (d2) and the production history information (d3) acquired by the acquisition unit (101); and an output unit (104) that outputs the arrival time information indicating the predicted arrival time.

Description

診断システムおよび診断方法Diagnostic system and diagnostic method
　本開示は、例えば部品装着装置などの生産設備を診断するシステムなどに関する。 The present disclosure relates to, for example, a system for diagnosing production equipment such as a component mounting device.
　従来、切換バルブが正常か否かを判定する部品実装装置が提案されている（例えば、特許文献１参照）。なお、部品実装装置は、部品に基板が実装または装着された装着基板を生産する生産設備であって、部品装着装置とも呼ばれる。切換バルブは、部品実装装置に備えられている構成部材であり、真空ポンプとエア供給源とを選択的に吸着ノズルに接続させる。吸着ノズルは、部品を基板に装着するためにその部品を吸着して保持するノズルである。切換バルブによって真空ポンプが吸着ノズルに接続され、その真空ポンプが駆動すれば、吸着ノズルは周囲の空気を吸引する。一方、切換バルブによってエア供給源が吸着ノズルに接続され、そのエア供給源が駆動すれば、吸着ノズルは周囲に空気を吹き出す。このような部品実装装置は、切換バルブである構成部材が正常か否かを判定する診断システムを備えていると言える。 Conventionally, there has been proposed a component mounting apparatus that determines whether or not a switching valve is normal (see Patent Document 1, for example). A component mounting apparatus is a production facility for producing a mounted board in which a board is mounted or mounted on a component, and is also called a component mounting apparatus. The switching valve is a component provided in the component mounting apparatus, and selectively connects the vacuum pump and the air supply source to the suction nozzle. A suction nozzle is a nozzle that sucks and holds a component in order to mount the component on the board. A vacuum pump is connected to the suction nozzle by a switching valve, and when the vacuum pump is driven, the suction nozzle sucks ambient air. On the other hand, an air supply source is connected to the suction nozzle by a switching valve, and when the air supply source is driven, the suction nozzle blows out air to the surroundings. It can be said that such a component mounting apparatus is provided with a diagnostic system for determining whether or not the constituent member, which is the switching valve, is normal.
特開２０２０－１９４９８６号公報JP 2020-194986 A
　しかしながら、上記特許文献１の診断システムでは、作業者による生産設備のメンテナンスを十分に支援することが難しいという課題がある。 However, the diagnostic system of Patent Document 1 above has the problem that it is difficult to sufficiently support maintenance of production equipment by workers.
　そこで、本開示は、作業者による生産設備のメンテナンスをより適切に支援することができる診断システムなどを提供する。 Therefore, the present disclosure provides a diagnostic system and the like that can more appropriately support maintenance of production equipment by workers.
　本開示の一態様に係る診断システムは、（ｉ）部品が装着された基板である装着基板を、生産設備を用いて生産する生産計画を示す生産計画情報と、（ｉｉ）前記生産設備を用いて前記装着基板が生産された実績を示す生産実績情報とを取得する取得部と、前記生産設備に含まれる構成部材の過去または現在の劣化状態を示す劣化情報と、前記取得部によって取得された前記生産計画情報および前記生産実績情報とに基づいて、前記構成部材の将来の劣化状態が、予め定められた劣化状態である規定劣化状態に到達する到達時期を予測する予測部と、予測された前記到達時期を示す到達時期情報を出力する出力部と、を備える。 A diagnostic system according to an aspect of the present disclosure includes: (i) production plan information indicating a production plan for producing a mounting board, which is a board on which components are mounted, using production equipment; and (ii) using the production equipment an acquisition unit that acquires production performance information indicating the production performance of the mounting board by means of an acquisition unit; deterioration information that indicates the past or present deterioration state of a constituent member included in the production equipment; and deterioration information acquired by the acquisition unit a prediction unit for predicting a time when the future deterioration state of the component member reaches a prescribed deterioration state, which is a predetermined deterioration state, based on the production plan information and the actual production information; and an output unit that outputs arrival time information indicating the arrival time.
　なお、これらの包括的または具体的な態様は、システム、方法、集積回路、コンピュータプログラムまたはコンピュータ読み取り可能なＣＤ－ＲＯＭ（Compact Disc Read-Only Memory）などの記録媒体で実現されてもよく、システム、方法、集積回路、コンピュータプログラムおよび記録媒体の任意な組み合わせで実現されてもよい。また、記録媒体は、非一時的な記録媒体であってもよい。 In addition, these comprehensive or specific aspects may be realized by a system, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM (Compact Disc Read-Only Memory). , methods, integrated circuits, computer programs and recording media. Also, the recording medium may be a non-temporary recording medium.
　本開示の診断システムは、作業者による生産設備のメンテナンスをより適切に支援することができる。 The diagnostic system of the present disclosure can more appropriately support maintenance of production equipment by workers.
　なお、本開示の一態様における更なる利点および効果は、明細書および図面から明らかにされる。かかる利点および／または効果は、いくつかの実施の形態並びに明細書および図面に記載された特徴によってそれぞれ提供されるが、１つまたはそれ以上の同一の特徴を得るために必ずしも全てが提供される必要はない。 Further advantages and effects in one aspect of the present disclosure will be made clear from the specification and drawings. Such advantages and/or advantages are provided by the several embodiments and features described in the specification and drawings, respectively, but not necessarily all to obtain one or more of the same features. No need.
図１は、実施の形態における部品装着装置の平面図である。FIG. 1 is a plan view of the component mounting device according to the embodiment. 図２は、実施の形態における部品装着装置に用いられる移載ヘッドの斜視図である。FIG. 2 is a perspective view of a transfer head used in the component mounting device according to the embodiment. 図３は、実施の形態におけるエア制御機構の構成の一例を示す図である。FIG. 3 is a diagram showing an example of the configuration of an air control mechanism according to the embodiment. 図４は、実施の形態における部品装着装置の機能構成の一例を示すブロック図である。FIG. 4 is a block diagram showing an example of the functional configuration of the component mounting device according to the embodiment. 図５は、実施の形態における診断システムの機能構成の一例を示すブロック図である。FIG. 5 is a block diagram showing an example of the functional configuration of the diagnostic system according to the embodiment. 図６は、実施の形態における学習部および診断モデルを説明するための図である。FIG. 6 is a diagram for explaining a learning unit and a diagnostic model according to the embodiment; 図７は、実施の形態における劣化特定部および診断モデルを説明するための図である。FIG. 7 is a diagram for explaining a deterioration identifying unit and a diagnostic model according to the embodiment; 図８は、実施の形態における劣化情報の具体的な一例を示す図である。FIG. 8 is a diagram showing a specific example of deterioration information in the embodiment. 図９は、実施の形態における異常処理部、分類処理部、および劣化度処理部の入出力を説明するための図である。FIG. 9 is a diagram for explaining inputs and outputs of an abnormality processing unit, a classification processing unit, and a deterioration degree processing unit according to the embodiment; 図１０は、実施の形態における予測部の処理を説明するための図である。FIG. 10 is a diagram for explaining processing of a prediction unit in the embodiment; 図１１は、実施の形態における診断システムによる劣化状態の特定に関する処理動作の一例を示すフローチャートである。FIG. 11 is a flow chart showing an example of processing operations related to identification of a deterioration state by the diagnosis system in the embodiment. 図１２は、実施の形態における診断システムによるメンテナンス指示に関する処理動作の一例を示すフローチャートである。FIG. 12 is a flowchart showing an example of a processing operation regarding a maintenance instruction by the diagnosis system according to the embodiment. 図１３は、実施の形態における診断システムによるメンテナンス時期予測に関する処理動作の一例を示すフローチャートである。FIG. 13 is a flowchart showing an example of processing operations related to maintenance timing prediction by the diagnostic system in the embodiment.
　また、本開示の第１態様に係る診断システムは、（ｉ）部品が装着された基板である装着基板を、生産設備を用いて生産する生産計画を示す生産計画情報と、（ｉｉ）前記生産設備を用いて前記装着基板が生産された実績を示す生産実績情報とを取得する取得部と、前記生産設備に含まれる構成部材の過去または現在の劣化状態を示す劣化情報と、前記取得部によって取得された前記生産計画情報および前記生産実績情報とに基づいて、前記構成部材の将来の劣化状態が、予め定められた劣化状態である規定劣化状態に到達する到達時期を予測する予測部と、予測された前記到達時期を示す到達時期情報を出力する出力部と、を備える。例えば、第１態様および後述の第２態様～第６態様のうちの何れか１つの態様に従属する第７態様に係る診断システムでは、前記規定劣化状態は、前記構成部材のメンテナンスの実施が必要な第１規定劣化状態、または、前記メンテナンスの実施のための準備が必要な第２規定劣化状態であってもよい。さらに、第７態様に従属する第８態様に係る診断システムでは、前記予測部は、前記構成部材の将来の劣化状態として、前記構成部材の劣化の度合いが大きいほど大きい値を示す将来の劣化度を推定し、前記将来の劣化度が、前記第１規定劣化状態に対応する第１閾値に到達する到達時期、または、前記第２規定劣化状態に対応する第２閾値に到達する到達時期を、前記生産計画情報に基づいて予測してもよい。 Further, the diagnostic system according to the first aspect of the present disclosure includes: (i) production plan information indicating a production plan for producing a mounting board, which is a board on which components are mounted, using production equipment; an acquisition unit for acquiring production performance information indicating the production performance of the mounting substrate using equipment; a prediction unit that predicts a time when the future deterioration state of the component member reaches a specified deterioration state, which is a predetermined deterioration state, based on the obtained production plan information and the obtained production performance information; and an output unit that outputs arrival time information indicating the predicted arrival time. For example, in the diagnostic system according to the seventh aspect, which is dependent on the first aspect and any one aspect of the second to sixth aspects described later, the specified deterioration state requires maintenance of the constituent members or a second specified deterioration state that requires preparation for performing the maintenance. Further, in the diagnostic system according to an eighth aspect that is dependent on the seventh aspect, the predicting unit indicates a future deterioration state of the constituent member, which indicates a larger value as the degree of deterioration of the constituent member increases. is estimated, and the arrival time when the future deterioration degree reaches the first threshold value corresponding to the first specified deterioration state, or the arrival time when the second threshold value corresponding to the second specified deterioration state is reached, A prediction may be made based on the production plan information.
　これにより、例えば、劣化した構成部材のメンテナンスの実施が必要となる時期、またはそのメンテナンスの実施のための準備が必要となる時期が到達時期として予測され、その到達時期を示す到達時期情報が出力される。したがって、その生産設備を用いて作業を行う作業者は、その到達時期、すなわちメンテナンス実施時期またはメンテナンス準備時期を把握することができる。その結果、作業者は、それらの時期を見越して作業を行うことができ、作業効率を向上することができる。また、メンテナンスの効率化を図ることができる。このように、作業者による生産設備のメンテナンスをより適切に支援することができる。 As a result, for example, the time when maintenance of the deteriorated component member is required or the time when preparation for the maintenance is required is predicted as the arrival time, and the arrival time information indicating the arrival time is output. be done. Therefore, the worker who works using the production equipment can grasp the arrival time, that is, the maintenance execution time or the maintenance preparation time. As a result, the worker can perform work in anticipation of those times, and can improve work efficiency. Also, efficiency of maintenance can be improved. In this way, maintenance of production equipment by workers can be more appropriately supported.
　また、第１態様に従属する第２態様に係る診断システムでは、前記劣化情報は、複数の過去の時点のそれぞれにおける前記構成部材の劣化状態を示してもよい。 Further, in the diagnostic system according to the second aspect subordinate to the first aspect, the deterioration information may indicate the deterioration state of the constituent member at each of a plurality of past points of time.
　これにより、劣化状態の経時的な変化に基づいて将来の劣化状態を適切に推定することができ、その結果、到達時期の予測精度を向上することができる。 As a result, it is possible to appropriately estimate the future deterioration state based on the change in the deterioration state over time, and as a result, it is possible to improve the prediction accuracy of the arrival time.
　また、第１態様または第２態様に従属する第３態様に係る診断システムでは、前記生産設備は、移載ヘッドによって部品を吸着して基板に装着する部品装着装置であり、前記診断システムは、さらに、前記移載ヘッドに流れるエアの流量に関する流量情報に基づいて、前記移載ヘッドに含まれる前記構成部材の劣化状態を特定する劣化特定部を備え、前記予測部は、前記劣化特定部によって特定された劣化状態を示す情報を前記劣化情報として取得してもよい。 Further, in a diagnostic system according to a third aspect, which is subordinate to the first aspect or the second aspect, the production facility is a component mounting device that picks up a component with a transfer head and mounts it on a substrate, and the diagnostic system includes: Further, a deterioration specifying unit that specifies a deterioration state of the constituent members included in the transfer head based on flow rate information about a flow rate of air flowing through the transfer head, wherein the prediction unit causes the deterioration specifying unit to Information indicating the identified deterioration state may be acquired as the deterioration information.
　これにより、移載ヘッドに含まれる構成部材の劣化状態が流量情報に基づいて特定されて、その特定された劣化状態が到達時期の予測に用いられる。したがって、その劣化状態を適切に特定することができ、到達時期の予測精度を向上することができる。 As a result, the deterioration state of the constituent members included in the transfer head is identified based on the flow rate information, and the identified deterioration state is used to predict the arrival time. Therefore, the deterioration state can be appropriately specified, and the prediction accuracy of arrival time can be improved.
　また、第３態様に従属する第４態様に係る診断システムでは、前記劣化特定部は、前記構成部材の劣化の度合いを示す劣化度を推定することによって、前記構成部材の劣化状態を特定してもよい。 Further, in the diagnostic system according to the fourth aspect, which is dependent on the third aspect, the deterioration specifying unit specifies the deterioration state of the constituent member by estimating the degree of deterioration indicating the degree of deterioration of the constituent member. good too.
　これにより、劣化状態が劣化度としてより詳細に推定されるため、到達時期の予測精度をさらに向上することができる。 As a result, the deterioration state can be estimated in more detail as the degree of deterioration, so it is possible to further improve the prediction accuracy of the arrival time.
　また、第４態様に従属する第５態様に係る診断システムでは、前記劣化特定部は、前記構成部材に異常があるか否かを判定し、異常があると判定した場合に、前記構成部材の前記劣化度を推定してもよい。 Further, in the diagnostic system according to the fifth aspect, which is dependent on the fourth aspect, the deterioration specifying unit determines whether or not there is an abnormality in the constituent member, and if it is determined that there is an abnormality, the deterioration of the constituent member The degree of deterioration may be estimated.
　これにより、異常と判定された構成部材に対して劣化度が推定されるため、劣化の兆候があると想定される構成部材に対して到達時期を予測し、劣化の兆候がないと想定される構成部材に対する到達時期の予測を省くことができる。その結果、到達時期の予測の処理負担を軽減することができる。 As a result, since the degree of deterioration is estimated for the component determined to be abnormal, the arrival time is predicted for the component that is assumed to have signs of deterioration, and it is assumed that there is no sign of deterioration. It is possible to omit the prediction of arrival times for the constituent members. As a result, it is possible to reduce the processing load of predicting the arrival time.
　また、第３態様～第５態様のうちの何れか１つの態様に従属する第６態様に係る診断システムでは、前記生産実績情報は、前記移載ヘッドによって部品が基板に装着された装着回数を示す装着回数情報を含み、前記予測部は、前記装着回数情報と前記劣化情報とに基づいて前記構成部材の将来の劣化状態を推定してもよい。 Further, in the diagnostic system according to the sixth aspect, which is subordinate to any one of the third to fifth aspects, the production performance information includes the number of times the component has been attached to the substrate by the transfer head. The prediction unit may estimate a future deterioration state of the constituent member based on the mounting number information and the deterioration information.
　これにより、過去の装着回数に対する劣化度に基づいて、将来の装着回数に対する劣化度を適切に推定することができる。 As a result, it is possible to appropriately estimate the degree of deterioration for the number of times of wearing in the future based on the degree of deterioration for the number of times of wearing in the past.
　以下、実施の形態について、図面を参照しながら具体的に説明する。 Hereinafter, embodiments will be specifically described with reference to the drawings.
　なお、以下で説明する実施の形態は、いずれも包括的または具体的な例を示すものである。以下の実施の形態で示される数値、形状、材料、構成要素、構成要素の配置位置および接続形態、ステップ、ステップの順序などは、一例であり、本開示を限定する主旨ではない。また、以下の実施の形態における構成要素のうち、最上位概念を示す独立請求項に記載されていない構成要素については、任意の構成要素として説明される。 It should be noted that the embodiments described below are all comprehensive or specific examples. Numerical values, shapes, materials, components, arrangement positions and connection forms of components, steps, order of steps, and the like shown in the following embodiments are examples, and are not intended to limit the present disclosure. In addition, among the constituent elements in the following embodiments, constituent elements that are not described in independent claims representing the highest concept will be described as arbitrary constituent elements.
　また、各図は、模式図であり、必ずしも厳密に図示されたものではない。また、各図において、同じ構成部材については同じ符号を付している。 In addition, each figure is a schematic diagram and is not necessarily strictly illustrated. Moreover, in each figure, the same code|symbol is attached|subjected about the same component.
　（実施の形態）
　［部品装着装置の構成］
　図１は、本実施の形態における部品装着装置の平面図である。つまり、図１は、部品装着装置の内部構成を上方から見た状態を示す。なお、本開示において、鉛直方向をＺ軸方向または上下方向と称し、鉛直方向に対して垂直な面における一方向をＹ軸方向または奥行き方向と称し、その垂直な面においてＹ軸方向と垂直な方向をＸ軸方向、左右方向または横方向と称す。また、本開示において、Ｚ軸方向の正側は、上向きまたは上であり、Ｚ軸方向の負側は、下向きまたは下である。また、本開示において、Ｙ軸方向の正側は、奥側または奥であり、Ｙ軸方向の負側は、手前側または手前である。また、本開示において、Ｘ軸方向の正側は、右側または右であり、Ｘ軸方向の負側は左側または左である。 (Embodiment)
[Configuration of component mounting device]
FIG. 1 is a plan view of a component mounting apparatus according to this embodiment. That is, FIG. 1 shows the internal configuration of the component mounting apparatus as viewed from above. In the present disclosure, the vertical direction is referred to as the Z-axis direction or the vertical direction, one direction in a plane perpendicular to the vertical direction is referred to as the Y-axis direction or the depth direction, and the vertical direction is referred to as the Y-axis direction. The direction is referred to as the X-axis direction, left-right direction, or lateral direction. Also, in the present disclosure, the positive side of the Z-axis direction is upward or upward, and the negative side of the Z-axis direction is downward or downward. In addition, in the present disclosure, the positive side in the Y-axis direction is the back side or back, and the negative side in the Y-axis direction is the front side or front side. Also, in the present disclosure, the positive side in the X-axis direction is the right side or right side, and the negative side in the X-axis direction is the left side or left side.
　本実施の形態における部品装着装置１は、移載ヘッド８によって部品を吸着して基板３に装着することにより、装着基板を生産する生産設備である。このような部品装着装置１は、基台１ａと、基板搬送機構２と、２つの部品供給部４と、Ｙ軸ビーム６と、２つのＸ軸ビーム７と、２つの移載ヘッド８と、２つの基板認識カメラ１２と、２つの部品認識カメラ１１とを備える。 The component mounting apparatus 1 according to the present embodiment is a production facility that produces mounting boards by picking up components with the transfer head 8 and mounting them on the board 3 . Such a component mounting apparatus 1 includes a base 1a, a substrate transport mechanism 2, two component supply units 4, a Y-axis beam 6, two X-axis beams 7, two transfer heads 8, Two board recognition cameras 12 and two component recognition cameras 11 are provided.
　基台１ａは、基板搬送機構２と、Ｙ軸ビーム６と、２つのＸ軸ビーム７と、２つの部品認識カメラ１１とを配設するための台である。 The base 1a is a table on which the substrate transport mechanism 2, the Y-axis beam 6, the two X-axis beams 7, and the two component recognition cameras 11 are arranged.
　基板搬送機構２は、Ｘ軸方向に沿う２つのレールを備え、基台１ａのＹ軸方向中央に配設される。基板搬送機構２は、上流側（例えばＸ軸方向負側）から搬入された基板３を搬送し、部品実装作業を実行するための位置である実装ステージにその基板３を位置決めして保持する。 The substrate transport mechanism 2 has two rails along the X-axis direction, and is arranged in the center of the base 1a in the Y-axis direction. The board transport mechanism 2 transports the board 3 carried in from the upstream side (for example, the negative side in the X-axis direction) and positions and holds the board 3 on the mounting stage, which is the position for performing the component mounting work.
　２つの部品供給部４は、基板搬送機構２をＹ軸方向に挟むように配置されている。部品供給部４には、複数のテープフィーダ５がＸ軸方向に沿って配列されている。テープフィーダ５は、単にフィーダとも呼ばれ、部品を供給する。具体的には、テープフィーダ５は、部品を収納したキャリアテープをテープ送り方向にピッチ送りすることによってその部品を供給する。なお、部品は、例えばＩＣ（Integrated Circuit）チップなどの電子部品である。 The two component supply units 4 are arranged so as to sandwich the substrate transport mechanism 2 in the Y-axis direction. A plurality of tape feeders 5 are arranged along the X-axis direction in the component supply section 4 . The tape feeder 5, also simply called a feeder, supplies components. Specifically, the tape feeder 5 feeds the component by pitch-feeding the carrier tape containing the component in the tape feeding direction. The component is an electronic component such as an IC (Integrated Circuit) chip.
　Ｙ軸ビーム６は、基台１ａ上面におけるＸ軸方向の正側（図１に示す例では右端）に、Ｙ軸方向に沿うように配設されている。 The Y-axis beam 6 is arranged along the Y-axis direction on the upper surface of the base 1a on the positive side in the X-axis direction (the right end in the example shown in FIG. 1).
　２つのＸ軸ビーム７は、それぞれＸ軸方向に沿った状態で、Ｙ軸方向に移動自在にＹ軸ビーム６に配設されている。例えば、２つのＸ軸ビーム７のそれぞれは、Ｙ軸ビーム６の駆動機構による駆動によって、Ｙ軸方向に水平移動する。 The two X-axis beams 7 are arranged on the Y-axis beam 6 so as to be movable in the Y-axis direction while each extending in the X-axis direction. For example, each of the two X-axis beams 7 is horizontally moved in the Y-axis direction by being driven by the driving mechanism of the Y-axis beam 6 .
　２つの移載ヘッド８のそれぞれは、結合プレート８ａを介してＸ軸ビーム７に、Ｘ軸方向に移動自在に装着されている。したがって、移載ヘッド８は、Ｙ軸ビーム６とＸ軸ビーム７とによって、Ｘ軸方向およびＹ軸方向に移動する。移載ヘッド８には、部品を吸着して保持し昇降可能な複数のノズルユニット９が着脱自在に装着されている。移載ヘッド８は、Ｘ軸方向およびＹ軸方向に移動することによって、部品供給部４から供給される部品をノズルユニット９によって吸着し、基板搬送機構２によって位置決めされている基板３の実装点にその部品を実装または装着する。 Each of the two transfer heads 8 is attached to the X-axis beam 7 via a coupling plate 8a so as to be freely movable in the X-axis direction. Therefore, the transfer head 8 is moved in the X-axis direction and the Y-axis direction by the Y-axis beam 6 and the X-axis beam 7 . The transfer head 8 is detachably mounted with a plurality of nozzle units 9 capable of picking up and holding components and moving up and down. By moving in the X-axis direction and the Y-axis direction, the transfer head 8 picks up the component supplied from the component supply unit 4 by means of the nozzle unit 9, and moves the mounting point of the substrate 3 positioned by the substrate transport mechanism 2. mount or attach the part to
　２つの基板認識カメラ１２のそれぞれは、Ｘ軸ビーム７の下面側に位置し、移載ヘッド８と一体的に移動するように結合プレート８ａに配設されている。具体的には、基板認識カメラ１２は、撮像方向を下向きにした姿勢で結合プレート８ａに配設されている。基板認識カメラ１２は、基板搬送機構２によって位置決めされている基板３上に移載ヘッド８と共に移動し、その基板３の位置および種別などを認識するために、その基板３を撮像する。 Each of the two substrate recognition cameras 12 is located on the lower surface side of the X-axis beam 7 and arranged on the coupling plate 8a so as to move integrally with the transfer head 8 . Specifically, the substrate recognition camera 12 is arranged on the coupling plate 8a in a posture in which the imaging direction faces downward. The substrate recognition camera 12 moves together with the transfer head 8 onto the substrate 3 positioned by the substrate transport mechanism 2 and takes an image of the substrate 3 in order to recognize the position and type of the substrate 3 .
　２つの部品認識カメラ１１は、基板搬送機構２をＹ軸方向に挟むように基台１ａ上に配設されている。２つの部品認識カメラ１１のそれぞれは、その部品認識カメラ１１に対応する移載ヘッド８が部品を吸着した状態でその部品認識カメラ１１上を移動するときに、その部品をＺ軸方向負側から撮像する。この撮像によって得られた画像に対して認識処理が行われることによって、移載ヘッド８に吸着保持されている部品の位置、角度および種類などが識別される。 The two component recognition cameras 11 are arranged on the base 1a so as to sandwich the substrate transport mechanism 2 in the Y-axis direction. Each of the two component recognition cameras 11 moves the component from the negative side in the Z-axis direction when the transfer head 8 corresponding to the component recognition camera 11 moves over the component recognition camera 11 with the component picked up. Take an image. By performing recognition processing on the image obtained by this imaging, the position, angle, type, etc. of the component sucked and held by the transfer head 8 are identified.
　図２は、部品装着装置１に用いられる移載ヘッド８の斜視図である。 FIG. 2 is a perspective view of the transfer head 8 used in the component mounting device 1. FIG.
　移載ヘッド８は、上述のように、結合プレート８ａを介してＸ軸ビーム７に装着されている。移載ヘッド８には、複数のノズルユニット９が並設されている。それぞれのノズルユニット９は、ノズル駆動部９ａ、ノズル軸１３、ノズル装着部１４、および吸着ノズル１５を有する。 The transfer head 8 is attached to the X-axis beam 7 via the coupling plate 8a as described above. A plurality of nozzle units 9 are arranged side by side on the transfer head 8 . Each nozzle unit 9 has a nozzle driving portion 9 a , a nozzle shaft 13 , a nozzle mounting portion 14 and a suction nozzle 15 .
　ノズル駆動部９ａは、昇降軸をリニアモータにより昇降させるノズル昇降機構を有している。ノズル軸１３は、ノズル駆動部９ａから下方に延びるように、そのノズル駆動部９ａの昇降軸に結合されている。ノズル装着部１４は、そのノズル軸１３の下端部に結合される。吸着ノズル１５は、そのノズル装着部１４の下方側に着脱自在に装着され、真空吸引によって部品を吸着して保持する。このような移載ヘッド８では、複数のノズルユニット９のそれぞれで、ノズル駆動部９ａのリニアモータが駆動することにより、ノズル装着部１４に装着された吸着ノズル１５は個別に昇降する。なお、各ノズル装着部１４には、吸着される部品のサイズおよび形状に応じた種類の吸着ノズル１５が装着されている。 The nozzle drive unit 9a has a nozzle lifting mechanism that lifts and lowers the lifting shaft by a linear motor. The nozzle shaft 13 is connected to the elevation shaft of the nozzle driving portion 9a so as to extend downward from the nozzle driving portion 9a. The nozzle mounting part 14 is coupled to the lower end of the nozzle shaft 13 . The suction nozzle 15 is detachably attached to the lower side of the nozzle mounting portion 14, and sucks and holds a component by vacuum suction. In such a transfer head 8, the suction nozzles 15 attached to the nozzle attachment portions 14 are individually moved up and down by driving the linear motors of the nozzle drive portions 9a in each of the plurality of nozzle units 9. FIG. Each nozzle mounting portion 14 is mounted with a suction nozzle 15 of a type corresponding to the size and shape of a component to be suctioned.
　また、部品装着装置１は、吸着ノズル１５におけるエアの吸引と、その吸着ノズル１５からのエアの吹き出しとを行うためのエア制御機構を備える。 The component mounting apparatus 1 also includes an air control mechanism for sucking air in the suction nozzle 15 and blowing out air from the suction nozzle 15 .
　図３は、本実施の形態におけるエア制御機構の構成の一例を示す図である。 FIG. 3 is a diagram showing an example of the configuration of the air control mechanism according to this embodiment.
　部品装着装置１のエア制御機構は、真空ポンプ１９、エア供給源２１、大気供給源２２、上述の複数のノズルユニット９、およびノズル制御部２３を備える。 The air control mechanism of the component mounting apparatus 1 includes a vacuum pump 19, an air supply source 21, an atmosphere supply source 22, the plurality of nozzle units 9 described above, and a nozzle control section 23.
　真空ポンプ１９は、負の圧力（真空とも呼ばれる）を発生させる。この真空ポンプ１９は、エアの流路を介してノズルユニット９の切換バルブ１８の入力ポートＰ１に接続されている。エア供給源２１は、エアの流路を介してノズルユニット９のブローバルブ２０の入力ポートＰ３に接続され、正の圧力のエアをブローバルブ２０に供給する。大気供給源２２は、エアの流路を介してブローバルブ２０の入力ポートＰ４に接続され、例えば大気圧のエアをブローバルブ２０に供給する。なお、大気供給源２２は、ブローバルブ２０の入力ポートＰ４を開放状態にすることでも実現される。 The vacuum pump 19 generates negative pressure (also called vacuum). The vacuum pump 19 is connected to the input port P1 of the switching valve 18 of the nozzle unit 9 via an air flow path. The air supply source 21 is connected to the input port P3 of the blow valve 20 of the nozzle unit 9 via an air flow path, and supplies positive pressure air to the blow valve 20 . The air supply source 22 is connected to the input port P4 of the blow valve 20 via an air flow path, and supplies atmospheric pressure air to the blow valve 20, for example. The air supply source 22 can also be realized by opening the input port P4 of the blow valve 20 .
　ノズル制御部２３は、ノズルユニット９の切換バルブ１８およびブローバルブ２０を制御する。 The nozzle control unit 23 controls the switching valve 18 and the blow valve 20 of the nozzle unit 9.
　ノズルユニット９は、切換バルブ１８、ブローバルブ２０、流量センサ１６、ノズル軸１３、ノズル装着部１４、吸着ノズル１５、エアチューブ４０、およびフィルタ４１を備える。 The nozzle unit 9 includes a switching valve 18, a blow valve 20, a flow sensor 16, a nozzle shaft 13, a nozzle mounting portion 14, a suction nozzle 15, an air tube 40, and a filter 41.
　エアチューブ４０は、ノズル軸１３に接続されている。そして、エアチューブ４０、ノズル軸１３、ノズル装着部１４および吸着ノズル１５のそれぞれの内部に形成されている空洞は連通している。したがって、エアチューブ４０の上端側から吸着ノズル１５の下端へはエアが流れることが可能であり、逆に、吸着ノズル１５の下端からエアチューブ４０の上端側へもエアが流れることが可能である。 The air tube 40 is connected to the nozzle shaft 13. The cavities formed inside the air tube 40, the nozzle shaft 13, the nozzle mounting portion 14, and the suction nozzle 15 communicate with each other. Therefore, air can flow from the upper end of the air tube 40 to the lower end of the suction nozzle 15 , and conversely, air can flow from the lower end of the suction nozzle 15 to the upper end of the air tube 40 . .
　また、フィルタ４１は、ノズル装着部１４の内部に配設され、その内部を通過するエアを浄化する。 In addition, the filter 41 is arranged inside the nozzle mounting portion 14 and purifies the air passing through the inside thereof.
　ブローバルブ２０は、２つの入力ポートＰ３およびＰ４と出力ポートＡ２とを有する電磁弁などで構成される。ブローバルブ２０の出力ポートＡ２は、エアの流路を介して切換バルブ１８の入力ポートＰ２に接続されている。このようなブローバルブ２０は、ノズル制御部２３による制御に応じて、電磁弁を開閉することによって、エアの流路を切り換える。つまり、ブローバルブ２０は、エアの流路を第１流路と第２流路とに切り換える。 The blow valve 20 is composed of an electromagnetic valve or the like having two input ports P3 and P4 and an output port A2. The output port A2 of the blow valve 20 is connected to the input port P2 of the switching valve 18 via an air flow path. Such a blow valve 20 switches the flow path of air by opening and closing an electromagnetic valve according to control by the nozzle control section 23 . That is, the blow valve 20 switches the air flow path between the first flow path and the second flow path.
　第１流路は、ブローバルブ２０を介してエア供給源２１と切換バルブ１８との間でエアが流れる流路である。例えば、正の圧力のエアが、エア供給源２１から第１流路に沿って切換バルブ１８に供給される。第２流路は、ブローバルブ２０を介して大気供給源２２と切換バルブ１８との間でエアが流れる流路である。例えば、大気圧のエアが、大気供給源２２から第２流路に沿って切換バルブ１８に供給される。 The first flow path is a flow path through which air flows between the air supply source 21 and the switching valve 18 via the blow valve 20 . For example, positive pressure air is supplied from the air supply source 21 along the first flow path to the switching valve 18 . The second flow path is a flow path through which air flows between the atmosphere supply source 22 and the switching valve 18 via the blow valve 20 . For example, air at atmospheric pressure is supplied from the atmospheric supply source 22 along the second flow path to the switching valve 18 .
　切換バルブ１８は、２つの入力ポートＰ１およびＰ２と出力ポートＡ１とを有する電磁弁などで構成される。切換バルブ１８の出力ポートＡ１は、エアの流路である出力経路１７、エアチューブ４０、ノズル軸１３、およびノズル装着部１４を介して吸着ノズル１５に接続されている。このような切換バルブ１８は、ノズル制御部２３による制御に応じて、電磁弁を開閉することによって、エアの流路を切り換える。つまり、切換バルブ１８は、エアの流路を第３流路と第４流路とに切り換える。 The switching valve 18 is composed of an electromagnetic valve or the like having two input ports P1 and P2 and an output port A1. The output port A<b>1 of the switching valve 18 is connected to the suction nozzle 15 via the output path 17 , which is an air flow path, the air tube 40 , the nozzle shaft 13 and the nozzle mounting portion 14 . Such a switching valve 18 switches the flow path of air by opening and closing a solenoid valve according to control by the nozzle control section 23 . That is, the switching valve 18 switches the air flow path between the third flow path and the fourth flow path.
　第３流路は、ノズル装着部１４、エアチューブ４０、出力経路１７、および切換バルブ１８を介して、吸着ノズル１５と真空ポンプ１９との間でエアが流れる流路である。真空ポンプ１９の駆動によってこの第３流路に沿ってエアが流れるときには、図３の矢印ｂによって示される向きにエアが流れる。そして、吸着ノズル１５の下端にある吸着保持面１５ａに形成されている吸着孔に、周囲のエアが吸引される。これによって、部品Ｄが吸着保持面１５ａに吸着されて保持される。 The third flow path is a flow path through which air flows between the suction nozzle 15 and the vacuum pump 19 via the nozzle mounting portion 14, the air tube 40, the output path 17, and the switching valve 18. When the vacuum pump 19 is driven and air flows along the third flow path, the air flows in the direction indicated by the arrow b in FIG. Surrounding air is sucked into the suction holes formed in the suction holding surface 15 a at the lower end of the suction nozzle 15 . As a result, the component D is sucked and held by the suction holding surface 15a.
　第４流路は、切換バルブ１８、出力経路１７、エアチューブ４０、ノズル軸１３、およびノズル装着部１４を介して、吸着ノズル１５とブローバルブ２０との間でエアが流れる流路である。ブローバルブ２０によってエアの流路が第１流路に切り換えられ、かつ、切換バルブ１８によってエアの流路が第４流路に切り換えられる場合、図３の矢印ａによって示される向きにエアが流れ、吸着ノズル１５の吸着孔からエアが吹き出る。つまり、エア供給源２１の駆動によって、正の圧力のエアが、エア供給源２１からブローバルブ２０および切換バルブ１８などを介して吸着ノズル１５に流れて、吸着ノズル１５の吸着保持面１５ａに形成されている吸着孔から吹き出る。また、ブローバルブ２０によってエアの流路が第２流路に切り換えられ、かつ、切換バルブ１８によってエアの流路が第４流路に切り換えられる場合、第２流路および第４流路の気圧が大気圧になるようにエアが流れる。つまり、大気供給源２２、ブローバルブ２０、切換バルブ１８、エアチューブ４０、ノズル軸１３、ノズル装着部１４、および吸着ノズル１５のそれぞれの内部の気圧が大気圧になる。 A fourth flow path is a flow path through which air flows between the suction nozzle 15 and the blow valve 20 via the switching valve 18 , the output path 17 , the air tube 40 , the nozzle shaft 13 and the nozzle mounting portion 14 . When the air flow path is switched to the first flow path by the blow valve 20 and the air flow path is switched to the fourth flow path by the switching valve 18, the air flows in the direction indicated by the arrow a in FIG. , air is blown out from the suction holes of the suction nozzle 15 . That is, by driving the air supply source 21, positive pressure air flows from the air supply source 21 to the suction nozzle 15 via the blow valve 20, the switching valve 18, etc., and is formed on the suction holding surface 15a of the suction nozzle 15. It blows out from the adsorption hole that is attached. Further, when the air flow path is switched to the second flow path by the blow valve 20 and the air flow path is switched to the fourth flow path by the switching valve 18, the air pressure of the second flow path and the fourth flow path Air flows so that is at atmospheric pressure. That is, the air pressure inside each of the air supply source 22, the blow valve 20, the switching valve 18, the air tube 40, the nozzle shaft 13, the nozzle mounting portion 14, and the suction nozzle 15 becomes the atmospheric pressure.
　流量センサ１６は、出力経路１７に流れるエアの流量を計測し、その計測結果を示す流量情報ｄ１を出力する。例えば、図３の矢印ａによって示される向きに流れるエアの流量は、正の流量として計測され、図３の矢印ｂによって示される向きに流れるエアの流量は、負の流量として計測される。流量情報ｄ１は、例えば、流量の経時的な変化を波形として示す。このような流量情報ｄ１は、移載ヘッド８に含まれる複数のノズルユニット９のそれぞれの流量センサ１６から出力される。 The flow rate sensor 16 measures the flow rate of air flowing through the output path 17 and outputs flow rate information d1 indicating the measurement result. For example, the flow rate of air flowing in the direction indicated by arrow a in FIG. 3 is measured as a positive flow rate, and the flow rate of air flowing in the direction indicated by arrow b in FIG. 3 is measured as a negative flow rate. The flow rate information d1 indicates, for example, a temporal change in flow rate as a waveform. Such flow rate information d<b>1 is output from each flow rate sensor 16 of each of the plurality of nozzle units 9 included in the transfer head 8 .
　吸着保持面１５ａに部品Ｄが当接している状態で吸着ノズル１５がエアを吸引すると、吸着ノズル１５によって部品Ｄが真空吸着される。このとき、流量センサ１６によって計測されるエアの流量は、ほぼゼロである。吸着保持面１５ａに部品Ｄが当接していない状態で吸着ノズル１５が周囲のエアを吸引しているときには、流量センサ１６によって計測されるエアの流量は、負の流量となる。また、吸着ノズル１５からエアが吹き出ているときには、流量センサ１６によって計測されるエアの流量は、正の流量である。また、大気供給源２２、ブローバルブ２０、切換バルブ１８、エアチューブ４０、ノズル軸１３、ノズル装着部１４、および吸着ノズル１５のそれぞれの内部の気圧が大気圧である場合には、流量センサ１６によって計測されるエアの流量は、ほぼゼロである。 When the suction nozzle 15 sucks air while the component D is in contact with the suction holding surface 15a, the component D is vacuum-sucked by the suction nozzle 15. At this time, the flow rate of air measured by the flow rate sensor 16 is almost zero. When the suction nozzle 15 is sucking the surrounding air while the component D is not in contact with the suction holding surface 15a, the air flow rate measured by the flow rate sensor 16 is a negative flow rate. Further, when air is blowing out from the suction nozzle 15, the air flow rate measured by the flow rate sensor 16 is a positive flow rate. Further, when the air pressure inside each of the air supply source 22, the blow valve 20, the switching valve 18, the air tube 40, the nozzle shaft 13, the nozzle mounting portion 14, and the suction nozzle 15 is the atmospheric pressure, the flow rate sensor 16 The air flow rate measured by is almost zero.
　図４は、本実施の形態における部品装着装置１の機能構成の一例を示すブロック図である。 FIG. 4 is a block diagram showing an example of the functional configuration of the component mounting apparatus 1 according to this embodiment.
　部品装着装置１は、上述のように、基板搬送機構２、部品供給部４、ヘッド移動機構１０、部品認識カメラ１１、基板認識カメラ１２、真空ポンプ１９、エア供給源２１、大気供給源２２、および移載ヘッド８を備える。部品装着装置１は、さらに、装置制御部３０、装置記憶部３１、入力部３２、提示部３３、および診断システム１００を備える。 As described above, the component mounting apparatus 1 includes the substrate transport mechanism 2, the component supply unit 4, the head moving mechanism 10, the component recognition camera 11, the substrate recognition camera 12, the vacuum pump 19, the air supply source 21, the atmosphere supply source 22, and a transfer head 8 . The component mounting apparatus 1 further includes a device control section 30 , a device storage section 31 , an input section 32 , a presentation section 33 and a diagnostic system 100 .
　ヘッド移動機構１０は、上述のＹ軸ビーム６およびＸ軸ビーム７などを含む機構である。 The head moving mechanism 10 is a mechanism including the Y-axis beam 6 and the X-axis beam 7 described above.
　装置制御部３０は、部品装着装置１の各構成要素を制御する。例えば、装置制御部３０は、ＣＰＵ（Central Processing Unit）またはプロセッサなどによって構成されている。 The device control unit 30 controls each component of the component mounting device 1 . For example, the device control unit 30 is configured by a CPU (Central Processing Unit) or a processor.
　装置記憶部３１は、部品装着装置１が基板３に部品Ｄを実装するための各種データを格納している記録媒体である。例えば、装置記憶部３１は、ハードディスクドライブ、ＲＡＭ（Random Access Memory）、ＲＯＭ（Read Only Memory）、または半導体メモリなどである。なお、このような装置記憶部３１は、揮発性であっても不揮発性であってもよい。また、装置記憶部３１は、装置制御部３０によって読み出されて実行されるコンピュータプログラムを格納していてもよい。この場合、装置制御部３０は、そのコンピュータプログラムを読み出して実行することによって、部品装着装置１の各構成要素を制御する。 The device storage unit 31 is a recording medium storing various data for mounting the component D on the substrate 3 by the component mounting device 1 . For example, the device storage unit 31 is a hard disk drive, RAM (Random Access Memory), ROM (Read Only Memory), semiconductor memory, or the like. Note that such a device storage unit 31 may be volatile or nonvolatile. Further, the device storage section 31 may store a computer program that is read and executed by the device control section 30 . In this case, the device control section 30 controls each component of the component mounting device 1 by reading and executing the computer program.
　入力部３２は、例えばキーボード、タッチセンサ、タッチパッドまたはマウスなどとして構成されている。このような入力部３２は、部品装着装置１を用いて装着基板の生産を行う作業者による入力操作を受け付け、その入力操作に応じた信号を装置制御部３０または診断システム１００などに出力する。 The input unit 32 is configured as, for example, a keyboard, touch sensor, touch pad, mouse, or the like. Such an input section 32 accepts input operations by an operator who manufactures mounting boards using the component mounting apparatus 1, and outputs signals corresponding to the input operations to the device control section 30, the diagnostic system 100, or the like.
　提示部３３は、装置制御部３０または診断システム１００からの提示信号を受け付け、その提示信号に応じた画像および音声のうちの少なくとも一方を出力する。具体的には、提示部３３は、液晶ディスプレイ、有機ＥＬ（Electro-Luminescence）ディスプレイなどのディスプレイである。この場合、提示部３３は、提示信号に応じた画像を表示する。また、提示部３３は、スピーカーなどであってもよい。この場合、提示部３３は、提示信号に応じた音声を出力する。また、提示部３３は、ディスプレイおよびスピーカーを備えていてもよい。 The presentation unit 33 receives a presentation signal from the device control unit 30 or the diagnostic system 100, and outputs at least one of an image and a sound according to the presentation signal. Specifically, the presentation unit 33 is a display such as a liquid crystal display or an organic EL (Electro-Luminescence) display. In this case, the presentation unit 33 displays an image according to the presentation signal. Also, the presentation unit 33 may be a speaker or the like. In this case, the presentation unit 33 outputs a sound corresponding to the presentation signal. Also, the presentation unit 33 may include a display and a speaker.
　診断システム１００は、移載ヘッド８の複数のノズルユニット９のそれぞれについて、そのノズルユニット９に含まれる各構成部材の劣化状態を診断する。つまり、診断システム１００は、上記各構成部材の現在の劣化度を推定し、さらに、将来の劣化度を推定する。また、診断システム１００は、それらの構成部材のメンテナンス時期を予測する。そのノズルユニット９に含まれる各構成部材は、エアが通過する部材である。具体的には、各構成部材は、エアチューブ４０、フィルタ４１、バルブ、またはシャフトなどである。バルブは、切換バルブ１８およびブローバルブ２０のうちの少なくとも一方である。シャフトは、例えばノズル軸１３である。 The diagnosis system 100 diagnoses the state of deterioration of each component included in each nozzle unit 9 of each of the plurality of nozzle units 9 of the transfer head 8 . In other words, the diagnosis system 100 estimates the current degree of deterioration of each of the components, and further estimates the degree of deterioration in the future. The diagnostic system 100 also predicts maintenance timings for those components. Each component included in the nozzle unit 9 is a member through which air passes. Specifically, each component is an air tube 40, a filter 41, a valve, a shaft, or the like. The valve is at least one of switching valve 18 and blow valve 20 . The shaft is for example the nozzle shaft 13 .
　［診断システムの構成および動作］
　図５は、本実施の形態における診断システム１００の機能構成の一例を示すブロック図である。 [Configuration and Operation of Diagnosis System]
FIG. 5 is a block diagram showing an example of the functional configuration of diagnostic system 100 according to the present embodiment.
　診断システム１００は、流量情報ｄ１、生産計画情報ｄ２、および生産実績情報ｄ３を用いて、複数のノズルユニット９のそれぞれに含まれる各構成部材の劣化状態を診断し、その診断結果を示す提示信号を提示部３３に出力する。これにより、その診断結果が画像、音声などによって提示部３３から提示される。 The diagnostic system 100 diagnoses the state of deterioration of each component included in each of the plurality of nozzle units 9 using the flow rate information d1, the production plan information d2, and the production performance information d3, and presents a presentation signal indicating the diagnosis result. is output to the presentation unit 33 . As a result, the diagnosis result is presented by the presenting unit 33 in the form of an image, sound, or the like.
　このような診断システム１００は、取得部１０１、メンテナンス処理部１０２、予測部１０３、出力部１０４、学習部１１０、モデル格納部１２０、および劣化特定部１３０を備える。 Such a diagnostic system 100 includes an acquisition unit 101, a maintenance processing unit 102, a prediction unit 103, an output unit 104, a learning unit 110, a model storage unit 120, and a deterioration identification unit 130.
　取得部１０１は、流量情報ｄ１、生産計画情報ｄ２、および生産実績情報ｄ３を取得する。流量情報ｄ１は、移載ヘッド８によって部品Ｄを吸着して基板３に装着する部品装着装置１におけるその移載ヘッド８に流れるエアの流量に関する情報である。生産計画情報ｄ２は、部品装着装置１を用いて装着基板を生産する計画を示す情報である。つまり、生産計画情報ｄ２は、部品Ｄが装着された基板３である装着基板を、生産設備を用いて生産する生産計画を示す情報である。例えば、生産計画情報ｄ２は、部品装着装置１の複数のノズルユニット９のそれぞれについて、そのノズルユニット９によって部品Ｄが吸着されて基板３に装着される回数（以下、装着回数と呼ばれる）を上述の計画として示す。より具体的には、生産計画情報ｄ２は、将来の複数の時点のそれぞれにおける装着回数を示す。生産実績情報ｄ３は、生産計画情報ｄ２にしたがって装着基板を生産するために部品装着装置１が稼働した実績を示す情報である。つまり、生産実績情報ｄ３は、生産設備を用いて装着基板が生産された実績を示す情報である。例えば、生産実績情報ｄ３は、部品装着装置１の複数のノズルユニット９のそれぞれについて、現時点までに、そのノズルユニット９によって部品Ｄが吸着されて基板３に装着された過去の装着回数を上述の実績として示す。より具体的には、生産実績情報ｄ３は、過去の複数の時点のそれぞれにおける装着回数を示す。 The acquisition unit 101 acquires flow rate information d1, production plan information d2, and production performance information d3. The flow rate information d1 is information about the flow rate of the air flowing through the transfer head 8 in the component mounting apparatus 1 that picks up the component D by the transfer head 8 and mounts it on the substrate 3 . The production plan information d2 is information indicating a plan for producing mounted substrates using the component mounting apparatus 1. FIG. In other words, the production plan information d2 is information indicating a production plan for producing the mounted board, which is the board 3 on which the component D is mounted, using production equipment. For example, the production planning information d2 indicates the number of times the component D is picked up by the nozzle unit 9 and mounted on the substrate 3 (hereinafter referred to as the number of times of mounting) for each of the plurality of nozzle units 9 of the component mounting apparatus 1. shown as a plan. More specifically, the production plan information d2 indicates the number of mounting times at each of a plurality of points in the future. The production performance information d3 is information indicating the performance of the operation of the component mounting apparatus 1 for producing the mounted substrates according to the production plan information d2. In other words, the actual production information d3 is information indicating the actual production of mounted substrates using production equipment. For example, the actual production information d3 indicates the past number of times the nozzle unit 9 picked up the component D and mounted it on the substrate 3 up to the present time for each of the plurality of nozzle units 9 of the component mounting apparatus 1. Shown as a result. More specifically, the actual production information d3 indicates the number of mounting times at each of a plurality of points in the past.
　取得部１０１は、流量情報ｄ１を学習部１１０および劣化特定部１３０に出力する。さらに、取得部１０１は、生産計画情報ｄ２および生産実績情報ｄ３を予測部１０３に出力する。 The acquisition unit 101 outputs the flow rate information d1 to the learning unit 110 and the deterioration identification unit 130. Furthermore, the acquisition unit 101 outputs the production plan information d2 and the actual production information d3 to the prediction unit 103. FIG.
　学習部１１０は、取得部１０１から流量情報ｄ１を訓練データとして取得し、その流量情報ｄ１を用いた機械学習によって診断モデルを生成し、その診断モデルをモデル格納部１２０に格納する。診断モデルは、ノズルユニット９に含まれる各構成部材のそれぞれの劣化状態を診断するために用いられる機械学習モデルである。具体的な一例では、診断モデルは、ニューラルネットワークである。このような診断モデルは、流量情報ｄ１の入力に対して、その流量情報ｄ１に対応するノズルユニット９に含まれる各構成部材のそれぞれの劣化状態を示す情報が出力されるように、学習部１１０が機械学習を行うことによって生成されている。つまり、診断モデルは、流量情報ｄ１と、ノズルユニット９に含まれる各構成部材のそれぞれの劣化状態との関係を示していると言える。 The learning unit 110 acquires the flow rate information d1 from the acquisition unit 101 as training data, generates a diagnostic model by machine learning using the flow rate information d1, and stores the diagnostic model in the model storage unit 120. The diagnostic model is a machine learning model used for diagnosing the state of deterioration of each component included in the nozzle unit 9 . In one specific example, the diagnostic model is a neural network. Such a diagnostic model is such that the learning unit 110 outputs information indicating the deterioration state of each component included in the nozzle unit 9 corresponding to the flow rate information d1 in response to the input of the flow rate information d1. is generated by performing machine learning. That is, it can be said that the diagnostic model indicates the relationship between the flow rate information d1 and the deterioration state of each component included in the nozzle unit 9 .
　モデル格納部１２０は、診断モデルを格納するための記録媒体である。このようなモデル格納部１２０は、ハードディスクドライブ、ＲＡＭ、ＲＯＭ、または半導体メモリなどである。 The model storage unit 120 is a recording medium for storing diagnostic models. Such a model storage unit 120 may be a hard disk drive, RAM, ROM, semiconductor memory, or the like.
　劣化特定部１３０は、流量情報ｄ１に基づいて、移載ヘッド８のその流量情報ｄ１に対応するノズルユニット９に含まれる複数の構成部材のそれぞれの劣化状態を特定する。具体的には、劣化特定部１３０は、取得部１０１から流量情報ｄ１を取得し、モデル格納部１２０から診断モデルを取得する。そして、劣化特定部１３０は、その流量情報ｄ１を診断モデルに入力し、その診断モデルから出力される劣化情報を取得する。この劣化情報は、ノズルユニット９に含まれる各構成部材のそれぞれの劣化状態を示す。劣化特定部１３０は、このような劣化情報を取得することによって、その各構成部材の劣化状態を特定する。つまり、劣化特定部１３０は、診断モデルを用いることによって劣化状態を特定する。劣化特定部１３０は、その特定された劣化状態を示す劣化情報を出力部１０４、メンテナンス処理部１０２および予測部１０３に出力する。なお、劣化情報は、部品装着装置１である生産設備に含まれる各構成部材の過去または現在の劣化状態を示す情報である。また、劣化情報は、複数の過去の時点のそれぞれにおける各構成部材の劣化状態を示していてもよい。 The deterioration identification unit 130 identifies the deterioration state of each of the plurality of constituent members included in the nozzle unit 9 corresponding to the flow rate information d1 of the transfer head 8 based on the flow rate information d1. Specifically, the deterioration identification unit 130 acquires the flow rate information d1 from the acquisition unit 101 and acquires the diagnostic model from the model storage unit 120 . Then, the deterioration specifying unit 130 inputs the flow rate information d1 to the diagnostic model and acquires the deterioration information output from the diagnostic model. This deterioration information indicates the deterioration state of each component included in the nozzle unit 9 . The deterioration identifying unit 130 identifies the deterioration state of each component by acquiring such deterioration information. That is, the deterioration identifying unit 130 identifies the deterioration state by using the diagnostic model. Deterioration identifying section 130 outputs deterioration information indicating the identified deterioration state to output section 104 , maintenance processing section 102 and prediction section 103 . The deterioration information is information indicating the past or present deterioration state of each constituent member included in the production facility that is the component mounting apparatus 1 . Further, the deterioration information may indicate the deterioration state of each component at each of a plurality of past points of time.
　メンテナンス処理部１０２は、劣化特定部１３０から劣化情報を取得し、その劣化情報に基づいて、ノズルユニット９に含まれる構成部材のメンテナンスに関するメンテナンス情報を生成する。そして、メンテナンス処理部１０２は、そのメンテナンス情報を出力部１０４に出力する。 The maintenance processing unit 102 acquires deterioration information from the deterioration identification unit 130 and generates maintenance information regarding maintenance of constituent members included in the nozzle unit 9 based on the deterioration information. The maintenance processing unit 102 then outputs the maintenance information to the output unit 104 .
　予測部１０３は、移載ヘッド８のノズルユニット９に含まれる各構成部材の将来の劣化状態を推定する。さらに、予測部１０３は、その劣化状態が規定劣化状態に到達する到達時期をメンテナンス時期として予測する。つまり、予測部１０３は、劣化特定部１３０によって特定された劣化状態を示す情報を劣化情報として取得する。そして、予測部１０３は、その劣化情報と、取得部１０１によって取得された生産計画情報ｄ２および生産実績情報ｄ３とに基づいて、各構成部材の将来の劣化状態が、予め定められた劣化状態である規定劣化状態に到達する到達時期を予測する。予測部１０３は、その予測された到達時期を示す到達時期情報を出力部１０４に出力する。 The prediction unit 103 estimates the future deterioration state of each component included in the nozzle unit 9 of the transfer head 8 . Furthermore, the prediction unit 103 predicts the arrival time when the deterioration state reaches the prescribed deterioration state as the maintenance timing. That is, the prediction unit 103 acquires information indicating the deterioration state identified by the deterioration identification unit 130 as deterioration information. Based on the deterioration information and the production plan information d2 and the actual production information d3 acquired by the acquisition unit 101, the prediction unit 103 predicts the future deterioration state of each constituent member in a predetermined deterioration state. Predict the arrival time to reach a specified deterioration state. The prediction unit 103 outputs arrival time information indicating the predicted arrival time to the output unit 104 .
　出力部１０４は、特定された劣化状態を示す劣化情報を出力する。つまり、出力部１０４は、劣化特定部１３０から劣化情報を取得すると、その劣化情報を提示信号として提示部３３に出力する。これにより、提示部３３からは劣化情報の内容（すなわち劣化状態）が提示される。また、出力部１０４は、予測された到達時期を示す到達時期情報を出力する。つまり、出力部１０４は、予測部１０３から到達時期情報を取得すると、その到達時期情報を提示信号として提示部３３に出力する。これにより、提示部３３からはその到達時期情報の内容（すなわち到達時期）が提示される。さらに、出力部１０４は、メンテナンス情報を出力する。つまり、出力部１０４は、メンテナンス処理部１０２からメンテナンス情報を取得すると、そのメンテナンス情報を提示信号として提示部３３に出力する。これにより、提示部３３からはそのメンテナンス情報の内容（すなわちメンテナンスに関する内容）が提示される。 The output unit 104 outputs deterioration information indicating the specified deterioration state. In other words, when acquiring the deterioration information from the deterioration specifying unit 130, the output unit 104 outputs the deterioration information to the presentation unit 33 as a presentation signal. As a result, the presentation unit 33 presents the content of the deterioration information (that is, the deterioration state). The output unit 104 also outputs arrival time information indicating the predicted arrival time. That is, when the arrival time information is acquired from the prediction unit 103, the output unit 104 outputs the arrival time information to the presentation unit 33 as a presentation signal. As a result, the presentation unit 33 presents the content of the arrival time information (that is, the arrival time). Furthermore, the output unit 104 outputs maintenance information. That is, when the maintenance information is acquired from the maintenance processing unit 102, the output unit 104 outputs the maintenance information to the presentation unit 33 as a presentation signal. As a result, the presentation unit 33 presents the content of the maintenance information (that is, the content regarding maintenance).
　図６は、学習部１１０および診断モデルを説明するための図である。 FIG. 6 is a diagram for explaining the learning unit 110 and the diagnostic model.
　学習部１１０は、特徴量抽出部１１１と、学習処理部１１２とを備える。特徴量抽出部１１１は、訓練データである流量情報ｄ１を取得部１０１から取得すると、その流量情報ｄ１からエアの流量に関する複数種の特徴量を抽出し、その複数種の特徴量を示す訓練用の特徴量データｄａ１を学習処理部１１２に出力する。 The learning unit 110 includes a feature extraction unit 111 and a learning processing unit 112 . The feature amount extraction unit 111 acquires the flow rate information d1, which is training data, from the acquisition unit 101, extracts a plurality of types of feature amounts related to the air flow rate from the flow rate information d1, and extracts a training data indicating the plurality of types of feature amounts. is output to the learning processing unit 112 .
　流量情報ｄ１は、例えば、流量センサ１６によって計測されたエアの流量の経時変化を示す流量波形である。この流量波形は、例えば、部品装着装置１が装着基板の生産を行っていないときに、ノズル制御部２３による制御によってノズルユニット９にエアの吸引または吹き出しを断続的に繰り返し実行させることによって得られる波形であってもよい。また、その流量波形は、吸着ノズル１５がノズル装着部１４に装着されていないときに得られる波形であってもよい。特徴量抽出部１１１は、例えば、その流量波形によって示される特徴的な時間または流量を特徴量として抽出する。具体的には、特徴量は、正側のピーク流量、負側のピーク流量、定常流量、応答時間、または定常時間などの数値である。あるいは、特徴量は、それらの数値のうちの２つ以上の数値を用いた演算によって算出される値であってもよく、それらの数値からなるベクトルであってもよい。応答時間は、例えば、切換バルブ１８およびブローバルブ２０によってエアの流路が切り換えられたときから、エアの流量が安定するまでの時間である。定常時間は、その安定している流量が継続している時間である。定常流量は、その安定している流量である。 The flow rate information d1 is, for example, a flow rate waveform that indicates the change over time of the air flow rate measured by the flow rate sensor 16 . This flow rate waveform is obtained, for example, by causing the nozzle unit 9 to intermittently and repeatedly suck or blow air under the control of the nozzle control section 23 when the component mounting apparatus 1 is not producing mounted substrates. It may be a waveform. Also, the flow waveform may be a waveform obtained when the suction nozzle 15 is not attached to the nozzle attachment portion 14 . The feature quantity extraction unit 111 extracts, for example, a characteristic time or flow rate indicated by the flow waveform as a feature quantity. Specifically, the feature amount is a numerical value such as a positive peak flow rate, a negative peak flow rate, a steady flow rate, a response time, or a steady time. Alternatively, the feature amount may be a value calculated by calculation using two or more of these numerical values, or may be a vector composed of these numerical values. The response time is, for example, the time from when the air flow path is switched by the switching valve 18 and the blow valve 20 until the flow rate of air stabilizes. Steady time is the time during which the stable flow rate continues. A steady flow is that flow that is steady.
　学習処理部１１２は、訓練用の特徴量データｄａ１を特徴量抽出部１１１から取得し、その特徴量データｄａ１を用いた機械学習を行うことによって、診断モデル１２１を生成し、その診断モデル１２１をモデル格納部１２０に格納する。機械学習は、例えば、ニューラルネットワークまたはディープニューラルネットワークなどを用いた学習である。また、機械学習は、教師あり学習であってもよく、教師なし学習であってもよい。また、機械学習は、ランダムフォレスト、ＳＶＭ（Support Vector Machine）、ガウス過程回帰、ＳＶＲ（Support Vector Regression）、またはランダムフォレスト回帰であってもよい。機械学習は、指数モデル、パワーモデル、対数モデル、Ｇｏｍｐｅｒｔｚモデル、またはＬｌｏｙｄ－Ｌｉｐｏｗモデルを診断モデル１２１として生成する学習であってもよい。 The learning processing unit 112 acquires the feature amount data da1 for training from the feature amount extraction unit 111, performs machine learning using the feature amount data da1, generates the diagnostic model 121, and uses the diagnostic model 121 as Stored in the model storage unit 120 . Machine learning is learning using, for example, a neural network or a deep neural network. Machine learning may be supervised learning or unsupervised learning. Machine learning may also be random forest, SVM (Support Vector Machine), Gaussian process regression, SVR (Support Vector Regression), or random forest regression. Machine learning may be learning that generates an exponential model, a power model, a logarithmic model, a Gompertz model, or a Lloyd-Lipow model as the diagnostic model 121 .
　このような学習処理部１１２は、異常学習部１１２ａ、分類学習部１１２ｂ、および劣化度学習部１１２ｃを備えている。異常学習部１１２ａは、訓練用の特徴量データｄａ１を用いた機械学習によって異常判定モデル１２１ａを生成する。この異常判定モデル１２１ａは、例えば、特徴量データｄａ１の入力に対して、その特徴量データｄａ１に対応するノズルユニット９が異常であるか否かを示す異常判定結果情報を出力するモデルである。教師あり学習の場合、異常学習部１１２ａは、訓練用の特徴量データｄａ１と、その特徴量データｄａ１に示される少なくとも１つの特徴量に対応する教師データとを用いて学習を行う。教師データは、ノズルユニット９が異常であるか否かを示す。異常判定モデル１２１ａは、例えば、２種類の特徴量のそれぞれを座標軸とする二次元空間において、ノズルユニット９が異常である領域と、ノズルユニット９が正常である領域とを示す。 Such a learning processing unit 112 includes an anomaly learning unit 112a, a classification learning unit 112b, and a deterioration degree learning unit 112c. The abnormality learning unit 112a generates the abnormality determination model 121a by machine learning using the feature amount data da1 for training. This abnormality determination model 121a is, for example, a model that outputs abnormality determination result information indicating whether or not the nozzle unit 9 corresponding to the feature amount data da1 is abnormal in response to input of the feature amount data da1. In the case of supervised learning, the abnormal learning unit 112a performs learning using feature data da1 for training and teacher data corresponding to at least one feature indicated by the feature data da1. The teacher data indicates whether or not the nozzle unit 9 is abnormal. The abnormality determination model 121a indicates, for example, a region in which the nozzle unit 9 is abnormal and a region in which the nozzle unit 9 is normal in a two-dimensional space whose coordinate axes are each of the two types of feature amounts.
　分類学習部１１２ｂは、訓練用の特徴量データｄａ１を用いた機械学習によって異常分類モデル１２１ｂを生成する。この異常分類モデル１２１ｂは、少なくとも特徴量データｄａ１の入力に対して、その特徴量データｄａ１に対応するノズルユニット９のうちの何れの構成部材が異常であるかを示す異常分類情報を出力するモデルである。教師あり学習の場合、分類学習部１１２ｂは、訓練用の特徴量データｄａ１と、その特徴量データｄａ１に示される少なくとも１つの特徴量に対応する教師データとを用いて学習を行う。教師データは、ノズルユニット９のうちの何れの構成部材が異常であるかを示す。 The classification learning unit 112b generates an anomaly classification model 121b by machine learning using the training feature data da1. This abnormality classification model 121b is a model that outputs abnormality classification information indicating which component of the nozzle unit 9 corresponding to the feature amount data da1 is abnormal at least in response to the input of the feature amount data da1. is. In the case of supervised learning, the classification learning unit 112b performs learning using feature amount data da1 for training and teacher data corresponding to at least one feature amount indicated by the feature amount data da1. The teacher data indicates which component of the nozzle unit 9 is abnormal.
　劣化度学習部１１２ｃは、訓練用の特徴量データｄａ１を用いた機械学習によって劣化度推定モデル１２１ｃを生成する。この劣化度推定モデル１２１ｃは、少なくとも特徴量データｄａ１の入力に対して、その特徴量データｄａ１に対応するノズルユニット９の構成部材の劣化度を示す劣化度情報を出力するモデルである。教師あり学習の場合、劣化度学習部１１２ｃは、訓練用の特徴量データｄａ１と、その特徴量データｄａ１に示される少なくとも１つの特徴量に対応する教師データとを用いて学習を行う。教師データは、ノズルユニット９の構成部材の劣化度を示す。 The deterioration degree learning unit 112c generates the deterioration degree estimation model 121c by machine learning using the training feature data da1. This deterioration degree estimation model 121c is a model that outputs deterioration degree information indicating the degree of deterioration of the constituent member of the nozzle unit 9 corresponding to at least the feature amount data da1 in response to the input of the feature amount data da1. In the case of supervised learning, the deterioration degree learning unit 112c performs learning using feature data da1 for training and teacher data corresponding to at least one feature represented by the feature data da1. The teacher data indicates the degree of deterioration of the constituent members of the nozzle unit 9 .
　図７は、劣化特定部１３０および診断モデルを説明するための図である。 FIG. 7 is a diagram for explaining the deterioration identifying unit 130 and the diagnostic model.
　劣化特定部１３０は、特徴量抽出部１３１と、特定処理部１３２とを備える。特徴量抽出部１３１は、流量情報ｄ１を取得部１０１から取得すると、その流量情報ｄ１からエアの流量に関する複数種の特徴量を抽出し、その複数種の特徴量を示す特徴量データｄａ１を特定処理部１３２に出力する。つまり、劣化特定部１３０の特徴量抽出部１３１は、学習部１１０の特徴量抽出部１１１と同様の構成および機能を有する。 The deterioration identification unit 130 includes a feature quantity extraction unit 131 and a identification processing unit 132 . After acquiring the flow rate information d1 from the acquisition section 101, the feature amount extraction section 131 extracts a plurality of types of feature amounts relating to the air flow rate from the flow rate information d1, and specifies feature amount data da1 indicating the plurality of types of feature amounts. Output to the processing unit 132 . That is, the feature amount extraction unit 131 of the deterioration identification unit 130 has the same configuration and functions as the feature amount extraction unit 111 of the learning unit 110 .
　特定処理部１３２は、特徴量データｄａ１を特徴量抽出部１３１から取得し、診断モデル１２１をモデル格納部１２０から取得する。そして、特定処理部１３２は、その特徴量データｄａ１を診断モデル１２１に入力することによって、その診断モデル１２１から出力される劣化情報ｄｂを取得する。これにより、その特徴量データｄａ１に対応するノズルユニット９に含まれる各構成部材の劣化状態が特定される。具体的には、特定処理部１３２は、異常処理部１３２ａ、分類処理部１３２ｂ、および劣化度処理部１３２ｃを備える。 The specific processing unit 132 acquires the feature amount data da1 from the feature amount extraction unit 131 and acquires the diagnostic model 121 from the model storage unit 120 . Then, the specific processing unit 132 acquires the deterioration information db output from the diagnostic model 121 by inputting the characteristic amount data da1 to the diagnostic model 121 . As a result, the deteriorated state of each component included in the nozzle unit 9 corresponding to the feature amount data da1 is identified. Specifically, the identification processing unit 132 includes an abnormality processing unit 132a, a classification processing unit 132b, and a deterioration degree processing unit 132c.
　異常処理部１３２ａは、診断モデル１２１のうちの異常判定モデル１２１ａをモデル格納部１２０から取得し、特徴量データｄａ１をその異常判定モデル１２１ａに入力する。これにより、異常処理部１３２ａは、その異常判定モデル１２１ａから出力される異常判定結果情報ｄｂ１を取得する。この異常判定結果情報ｄｂ１は、その特徴量データｄａ１に対応するノズルユニット９が異常であるか否かを示す。つまり、異常処理部１３２ａは、特徴量データｄａ１に対応するノズルユニット９が異常であるか否かを判定する。 The abnormality processing unit 132a acquires the abnormality determination model 121a of the diagnostic model 121 from the model storage unit 120, and inputs the feature amount data da1 to the abnormality determination model 121a. As a result, the abnormality processing unit 132a acquires the abnormality determination result information db1 output from the abnormality determination model 121a. This abnormality determination result information db1 indicates whether or not the nozzle unit 9 corresponding to the feature amount data da1 is abnormal. In other words, the abnormality processing section 132a determines whether or not the nozzle unit 9 corresponding to the feature amount data da1 is abnormal.
　分類処理部１３２ｂは、診断モデル１２１のうちの異常分類モデル１２１ｂをモデル格納部１２０から取得し、特徴量データｄａ１をその異常分類モデル１２１ｂに入力する。これにより、分類処理部１３２ｂは、その異常分類モデル１２１ｂから出力される異常分類情報ｄｂ２を取得する。この異常分類情報ｄｂ２は、その特徴量データｄａ１に対応するノズルユニット９のうちの何れの構成部材が異常であるかを示す。つまり、分類処理部１３２ｂは、特徴量データｄａ１に対応するノズルユニット９に含まれる複数の構成部材のそれぞれについて、その構成部材の状態を正常および異常の何れかに分類する。 The classification processing unit 132b acquires the abnormality classification model 121b of the diagnostic model 121 from the model storage unit 120, and inputs the feature data da1 to the abnormality classification model 121b. As a result, the classification processing unit 132b acquires the abnormality classification information db2 output from the abnormality classification model 121b. This abnormality classification information db2 indicates which constituent member of the nozzle unit 9 corresponding to the feature amount data da1 is abnormal. That is, the classification processing unit 132b classifies the state of each of the plurality of constituent members included in the nozzle unit 9 corresponding to the feature amount data da1 into either normal or abnormal.
　劣化度処理部１３２ｃは、診断モデル１２１のうちの劣化度推定モデル１２１ｃをモデル格納部１２０から取得し、特徴量データｄａ１をその劣化度推定モデル１２１ｃに入力する。これにより、劣化度処理部１３２ｃは、その劣化度推定モデル１２１ｃから出力される劣化度情報ｄｂ３を取得する。この劣化度情報ｄｂ３は、ノズルユニット９の構成部材の劣化度を示す。つまり、劣化度処理部１３２ｃは、劣化度推定モデル１２１ｃを用いて、ノズルユニット９の構成部材の劣化度を推定する。このように、劣化特定部１３０は、ノズルユニット９に含まれる少なくとも１つの構成部材のそれぞれの劣化の度合いを示す劣化度を推定することによって、劣化状態を特定する。また、その劣化度は、劣化の度合いが大きいほど大きい値を示す。 The deterioration degree processing unit 132c acquires the deterioration degree estimation model 121c of the diagnostic model 121 from the model storage unit 120, and inputs the characteristic amount data da1 to the deterioration degree estimation model 121c. Thereby, the deterioration degree processing unit 132c acquires the deterioration degree information db3 output from the deterioration degree estimation model 121c. This deterioration degree information db3 indicates the deterioration degree of the constituent members of the nozzle unit 9 . That is, the deterioration degree processing unit 132c estimates the deterioration degree of the constituent members of the nozzle unit 9 using the deterioration degree estimation model 121c. In this way, the deterioration identifying unit 130 identifies the deterioration state by estimating the degree of deterioration indicating the degree of deterioration of each of at least one component included in the nozzle unit 9 . Further, the degree of deterioration indicates a larger value as the degree of deterioration increases.
　図８は、劣化情報ｄｂの具体的な一例を示す図である。 FIG. 8 is a diagram showing a specific example of the deterioration information db.
　劣化特定部１３０は、移載ヘッド８に含まれる複数のノズルユニット９のそれぞれについて、そのノズルユニット９の劣化情報ｄｂを生成して出力する。劣化情報ｄｂは、図８に示すように、異常判定結果情報ｄｂ１、異常分類情報ｄｂ２、および劣化度情報ｄｂ３を含む。具体的な例では、異常判定結果情報ｄｂ１は、その異常判定結果情報ｄｂ１に対応するノズルユニット９が異常であることを示す。そして、異常分類情報ｄｂ２は、そのノズルユニット９に含まれる各構成部材が正常であるか、異常であるかを示す。例えば、異常分類情報ｄｂ２は、フィルタ４１が正常であり、切換バルブ１８などのバルブが正常であり、エアチューブ４０が異常であり、ノズル軸１３であるシャフトが正常であることを示す。劣化度情報ｄｂ３は、そのノズルユニット９に含まれる各構成要素の劣化度を０～１０の整数値によって示す。劣化度が１０に近いほど、その劣化度は、劣化の度合いが大きいことを示し、劣化度が０に近いほど、その劣化度は、劣化の度合いが小さいことを示す。例えば、劣化度情報ｄｂ３は、フィルタ４１の劣化度「１」と、バルブの劣化度「５」と、エアチューブ４０の劣化度「９」と、シャフトの劣化度「６」とを示す。 The deterioration specifying unit 130 generates and outputs deterioration information db for each of the nozzle units 9 included in the transfer head 8 . The deterioration information db includes, as shown in FIG. 8, abnormality determination result information db1, abnormality classification information db2, and deterioration degree information db3. In a specific example, the abnormality determination result information db1 indicates that the nozzle unit 9 corresponding to the abnormality determination result information db1 is abnormal. The abnormality classification information db2 indicates whether each component included in the nozzle unit 9 is normal or abnormal. For example, the abnormality classification information db2 indicates that the filter 41 is normal, the valves such as the switching valve 18 are normal, the air tube 40 is abnormal, and the shaft that is the nozzle shaft 13 is normal. The deterioration degree information db3 indicates the deterioration degree of each component included in the nozzle unit 9 by an integer value of 0-10. The closer the deterioration degree is to 10, the higher the deterioration degree, and the closer the deterioration degree is to 0, the smaller the deterioration degree. For example, the deterioration degree information db3 indicates the deterioration degree "1" of the filter 41, the deterioration degree "5" of the valve, the deterioration degree "9" of the air tube 40, and the deterioration degree "6" of the shaft.
　本実施の形態では、このような劣化情報ｄｂの内容が提示部３３から提示される。したがって、部品装着装置１を用いて作業を行う作業者は、その出力された劣化情報ｄｂから、移載ヘッド８に含まれる少なくとも１つの構成部材のそれぞれの劣化状態を把握することができる。その結果、構成部材が正常か否かのような単純な状態よりも移載ヘッド８の詳細な状態を診断することができる。複数の構成部材のそれぞれの劣化状態が診断されるため、作業者は、それらの構成部材のメンテナンスが必要か、そのメンテナンスの準備をしておく必要があるのかを容易に判断することができる。したがって、作業者は、メンテナンスが必要でない構成部材に対して、メンテナンスを無駄に行ってしまうことを抑制することができる。あるいは、作業者は、メンテナンスの準備が必要でない構成部材に対して、メンテナンスまたはその準備を無駄に行ってしまうことを抑制することができる。その結果、メンテナンスの効率化、メンテナンス時間の短縮化、および、メンテナンスに係る費用の削減を図ることができる。このように、生産設備である部品装着装置１の作業者によるメンテナンスをより適切に支援することができる。 In the present embodiment, the presentation unit 33 presents the content of such deterioration information db. Therefore, an operator who performs work using the component mounting apparatus 1 can grasp the deterioration state of each of at least one component included in the transfer head 8 from the output deterioration information db. As a result, the detailed state of the transfer head 8 can be diagnosed rather than a simple state such as whether or not the constituent members are normal. Since the state of deterioration of each of the plurality of constituent members is diagnosed, the operator can easily determine whether maintenance of those constituent members is necessary or whether preparation for such maintenance is necessary. Therefore, the operator can avoid wasting maintenance on components that do not require maintenance. Alternatively, the operator can avoid wasting maintenance or preparations for components that do not require maintenance preparations. As a result, it is possible to improve efficiency of maintenance, shorten maintenance time, and reduce maintenance costs. In this way, it is possible to more appropriately support the maintenance of the component mounting apparatus 1, which is production equipment, by the operator.
　メンテナンス処理部１０２は、このような劣化情報ｄｂに基づいて、その劣化情報ｄｂに対応するノズルユニット９に含まれる構成部材のメンテナンスに関するメンテナンス情報を生成する。具体的には、メンテナンス処理部１０２は、ノズルユニット９に含まれる複数の構成部材のそれぞれについて、当該構成部材に対して推定された劣化度が閾値を超えるか否かを判定し、その閾値を超えると判定された劣化度を有する構成部材のメンテナンスに関するメンテナンス情報を生成する。そのメンテナンス情報は、例えば、構成部材のメンテナンスの実施を促す内容のメンテナンス警報情報、または、構成部材のメンテナンスの実施のための準備を促す内容のメンテナンス予報情報である。メンテナンス警報情報は、メンテナンスが今すぐに必要であることを作業者に知らせるための警報または警告であるとも言える。メンテナンス予報情報は、メンテナンスが必要なタイミングが迫っていることを作業者に事前に知らせるための予報または予告であるとも言える。メンテナンス処理部１０２は、メンテナンス警報情報、メンテナンス予報情報などのメンテナンス情報を生成すると、そのメンテナンス情報を出力部１０４に出力する。 Based on such deterioration information db, the maintenance processing unit 102 generates maintenance information regarding maintenance of the constituent members included in the nozzle unit 9 corresponding to the deterioration information db. Specifically, the maintenance processing unit 102 determines whether or not the degree of deterioration estimated for each of the plurality of constituent members included in the nozzle unit 9 exceeds a threshold, and determines the threshold. Maintenance information is generated regarding maintenance of the component having the degree of deterioration determined to be exceeded. The maintenance information is, for example, maintenance warning information prompting maintenance of the constituent members, or maintenance forecast information prompting preparation for maintenance of the constituent members. The maintenance alert information can also be said to be an alert or warning for notifying the operator that maintenance is now required. The maintenance forecast information can also be said to be a forecast or advance notice for informing the worker in advance that the timing for maintenance is imminent. After generating maintenance information such as maintenance warning information and maintenance forecast information, the maintenance processing unit 102 outputs the maintenance information to the output unit 104 .
　出力部１０４は、メンテナンス処理部１０２からメンテナンス情報を取得すると、そのメンテナンス情報を提示信号として提示部３３に出力する。これにより、メンテナンス情報の内容が画像または音声などによって提示部３３に提示される。 When acquiring the maintenance information from the maintenance processing unit 102, the output unit 104 outputs the maintenance information to the presentation unit 33 as a presentation signal. As a result, the content of the maintenance information is presented to the presentation unit 33 by means of images, sounds, or the like.
　また、劣化特定部１３０は、移載ヘッド８のノズルユニット９に含まれる１つ以上の構成部材のそれぞれに異常があるか否かを判定し、その１つ以上の構成部材のうち、異常があると判定された少なくとも１つの構成部材のそれぞれの劣化度を推定してもよい。言い換えれば、劣化特定部１３０は、構成部材に異常があるか否かを判定し、異常があると判定した場合に、その構成部材の劣化度を推定してもよい。 Further, the deterioration identifying unit 130 determines whether or not there is an abnormality in each of one or more constituent members included in the nozzle unit 9 of the transfer head 8, and determines whether or not there is an abnormality among the one or more constituent members. A degree of deterioration of each of the at least one component determined to be present may be estimated. In other words, the deterioration identifying unit 130 may determine whether or not there is an abnormality in the constituent member, and estimate the degree of deterioration of the constituent member when it is determined that there is an abnormality.
　図９は、異常処理部１３２ａ、分類処理部１３２ｂ、および劣化度処理部１３２ｃの入出力を説明するための図である。 FIG. 9 is a diagram for explaining inputs and outputs of the abnormality processing unit 132a, the classification processing unit 132b, and the deterioration degree processing unit 132c.
　異常処理部１３２ａ、分類処理部１３２ｂ、および劣化度処理部１３２ｃのそれぞれは、入力データに対して、新たな情報をその入力データに付加して出力してもよい。つまり、異常処理部１３２ａは、特徴量抽出部１３１から出力された特徴量データｄａ１を入力データとして取得し、その入力データに新たな情報である異常判定結果情報ｄｂ１を付加して出力する。 Each of the abnormality processing unit 132a, the classification processing unit 132b, and the deterioration degree processing unit 132c may add new information to the input data and output the input data. That is, the abnormality processing unit 132a acquires the feature amount data da1 output from the feature amount extraction unit 131 as input data, adds abnormality determination result information db1, which is new information, to the input data, and outputs the result.
　分類処理部１３２ｂは、異常処理部１３２ａから出力された特徴量データｄａ１および異常判定結果情報ｄｂ１を入力データとして取得し、その入力データに新たな情報である異常分類情報ｄｂ２を付加して出力する。 The classification processing unit 132b acquires the feature amount data da1 and the abnormality determination result information db1 output from the abnormality processing unit 132a as input data, adds abnormality classification information db2 as new information to the input data, and outputs the result. .
　劣化度処理部１３２ｃは、分類処理部１３２ｂから出力された特徴量データｄａ１、異常判定結果情報ｄｂ１、および異常分類情報ｄｂ２を入力データとして取得し、その入力データに新たな情報である劣化度情報ｄｂ３を付加して出力する。このとき出力される劣化度情報ｄｂ３は、異常分類情報ｄｂ２において異常に分類されている構成部材（異常部材とも呼ばれる）の劣化度を示していてもよい。さらに、劣化度処理部１３２ｃは、特徴量抽出部１３１から出力された特徴量データｄａ１を入力データとして取得してもよい。この場合、劣化度処理部１３２ｃは、その特徴量データｄａ１に基づいて、異常分類情報ｄｂ２において正常に分類されている構成部材（正常部材とも呼ばれる）の劣化度を示す劣化度情報ｄｂ３を出力してもよい。 The deterioration degree processing unit 132c acquires the feature amount data da1, the abnormality determination result information db1, and the abnormality classification information db2 output from the classification processing unit 132b as input data, and adds deterioration degree information as new information to the input data. Add db3 and output. The deterioration degree information db3 output at this time may indicate the deterioration degree of the constituent members (also called abnormal members) classified as abnormal in the abnormality classification information db2. Furthermore, the deterioration degree processing unit 132c may acquire the feature amount data da1 output from the feature amount extraction unit 131 as input data. In this case, the deterioration degree processing unit 132c outputs deterioration degree information db3 indicating the degree of deterioration of the constituent members (also called normal members) classified as normal in the abnormality classification information db2 based on the feature amount data da1. may
　図１０は、予測部１０３の処理を説明するための図である。 FIG. 10 is a diagram for explaining the processing of the prediction unit 103. FIG.
　予測部１０３は、取得部１０１から生産実績情報ｄ３を取得し、劣化特定部１３０から劣化情報ｄｂを取得する。生産実績情報ｄ３は、移載ヘッド８の複数のノズルユニット９のそれぞれについて、そのノズルユニット９によって部品Ｄが基板３に装着された装着回数を示す装着回数情報を含む。そして、予測部１０３は、その装着回数情報と劣化情報ｄｂとに基づいて、複数のノズルユニット９のそれぞれについて、そのノズルユニット９に含まれる各構成部材の将来の劣化状態を推定する。 The prediction unit 103 acquires the actual production information d3 from the acquisition unit 101 and acquires the deterioration information db from the deterioration identification unit 130 . The actual production information d3 includes placement number information indicating the number of placements of the component D on the board 3 by each of the nozzle units 9 of the transfer head 8 . Then, the prediction unit 103 estimates the future deterioration state of each component included in each of the nozzle units 9 for each of the plurality of nozzle units 9 based on the number-of-mounting information and the deterioration information db.
　例えば、図１０のグラフは、１つのノズルユニット９に含まれる１つの構成部材の劣化度と、そのノズルユニット９によって部品Ｄが基板３に装着される装着回数との関係を示す。そのグラフの横軸は装着回数を示し、縦軸は劣化度を示す。 For example, the graph in FIG. 10 shows the relationship between the degree of deterioration of one component included in one nozzle unit 9 and the number of times component D is mounted on substrate 3 by that nozzle unit 9 . The horizontal axis of the graph indicates the number of wearing times, and the vertical axis indicates the degree of deterioration.
　予測部１０３は、現在または過去の装着回数と、その装着回数における劣化度とを示す劣化点（図１０中の黒丸印）を、生産実績情報ｄ３および劣化情報ｄｂから特定する。具体的には、予測部１０３は、現在または過去の時点ごとに、生産実績情報ｄ３の装着回数情報に示されるその時点の装着回数と、その時点で得られた劣化情報ｄｂに示される劣化度とを関連付けることによって、現在または過去の各時点における劣化点を特定する。 The prediction unit 103 identifies a deterioration point (marked with a black circle in FIG. 10) indicating the current or past number of times of mounting and the degree of deterioration in the number of times of mounting from the actual production information d3 and the deterioration information db. Specifically, the prediction unit 103 predicts the number of times of mounting indicated by the number of times of mounting in the actual production information d3 and the degree of deterioration indicated in the deterioration information db obtained at that time, for each current or past point in time. By associating with , the point of deterioration at the present or at each point in the past is specified.
　予測部１０３は、１つ以上の劣化点を特定すると、それらの劣化点に対する近似曲線を劣化近似曲線として算出する。なお、その劣化近似曲線は、例えば最小二乗法によって算出されてもよい。つまり、予測部１０３は、その劣化近似曲線を算出することによって、将来の劣化状態を推定する。具体的には、予測部１０３は、現時点の装着回数ｍ０よりも多い装着回数と、構成部材の劣化度との関係がその劣化近似曲線によって示されると推定する。したがって、予測部１０３は、装着回数ｍよりも多い装着回数における劣化度を示す予測劣化点（図１０中の四角印）が、その劣化近似曲線上にあると判断する。このように、予測部１０３は、構成部材の現時点以降の将来の劣化状態として、その構成部材の劣化の度合いが大きいほど大きい値を示す将来の劣化度を推定する。 After identifying one or more deterioration points, the prediction unit 103 calculates approximate curves for those deterioration points as deterioration approximate curves. The deterioration approximation curve may be calculated by, for example, the least squares method. That is, the prediction unit 103 estimates the future deterioration state by calculating the deterioration approximation curve. Specifically, the prediction unit 103 estimates that the deterioration approximation curve indicates the relationship between the number of mounting times, which is greater than the current number of mounting times m0, and the degree of deterioration of the component. Therefore, the prediction unit 103 determines that the predicted deterioration point (square mark in FIG. 10) indicating the degree of deterioration at the number of times of wearing more than m is on the deterioration approximation curve. In this way, the prediction unit 103 estimates the future deterioration degree of the constituent member after the present time, which indicates a larger value as the degree of deterioration of the constituent member increases.
　次に、予測部１０３は、構成部材の将来の劣化状態が、予め定められた劣化状態である規定劣化状態に到達する到達時期を予測する。その規定劣化状態は、構成部材のメンテナンスの実施が必要な第１規定劣化状態、または、そのメンテナンスの実施のための準備が必要な第２規定劣化状態である。つまり、第１規定劣化状態は、構成部材に対して上述のメンテナンス警報情報が生成されて、そのメンテナンス警報情報の内容が提示部３３から提示されるときの、その構成部材の劣化状態である。また、第２規定劣化状態は、構成部材に対して上述のメンテナンス予報情報が生成されて、そのメンテナンス予報情報の内容が提示部３３から提示されるときの、その構成部材の劣化状態である。 Next, the prediction unit 103 predicts the time when the future deterioration state of the constituent member will reach a specified deterioration state, which is a predetermined deterioration state. The prescribed deteriorated state is a first prescribed deteriorated state that requires maintenance of the component, or a second prescribed deteriorated state that requires preparation for the maintenance. That is, the first specified deterioration state is the deterioration state of the component when the maintenance warning information is generated for the component and the content of the maintenance warning information is presented from the presentation unit 33 . The second prescribed deterioration state is the deterioration state of the component when the maintenance forecast information described above is generated for the component and the content of the maintenance forecast information is presented from the presentation unit 33 .
　具体的には、予測部１０３は、将来の劣化度が、第１規定劣化状態に対応する第１閾値に到達する到達時期、または、第２規定劣化状態に対応する第２閾値に到達する到達時期を、生産計画情報ｄ２に基づいて予測する。つまり、予測部１０３は、劣化近似曲線において劣化度が第１閾値であるときの装着回数ｍ１を特定する。そして、予測部１０３は、生産計画情報ｄ２を参照し、現時点の装着回数ｍ０から装着回数ｍ１に至るまでの期間Ｔ１をその生産計画情報ｄ２から特定する。なお、生産計画情報ｄ２には、ノズルユニット９ごとの時間経過と装着回数との関係が示されている。予測部１０３は、現時点からその特定された期間Ｔ１経過後のタイミングを、構成部材の将来の劣化状態が第１規定劣化状態に到達する到達時期として予測する。この到達時期は、メンテナンス実施時期とも呼ばれる。 Specifically, the prediction unit 103 predicts the arrival time when the future deterioration degree reaches the first threshold value corresponding to the first specified deterioration state, or the arrival time when the future deterioration degree reaches the second threshold value corresponding to the second specified deterioration state. The timing is predicted based on the production plan information d2. In other words, the prediction unit 103 specifies the number m1 of wearing times when the degree of deterioration is the first threshold on the deterioration approximation curve. Then, the prediction unit 103 refers to the production plan information d2, and specifies the period T1 from the current mounting number m0 to the mounting number m1 from the production planning information d2. The production plan information d2 shows the relationship between the elapsed time and the number of mounting times for each nozzle unit 9 . The prediction unit 103 predicts the timing after the elapse of the specified period T1 from the current time as the arrival time when the future deterioration state of the constituent member reaches the first specified deterioration state. This arrival time is also called maintenance implementation time.
　同様に、予測部１０３は、劣化近似曲線において劣化度が第２閾値であるときの装着回数ｍ２を特定する。なお、第２閾値は、第１閾値よりも小さい値である。そして、予測部１０３は、生産計画情報ｄ２を参照し、現時点の装着回数ｍ０から装着回数ｍ２に至るまでの期間Ｔ２をその生産計画情報ｄ２から特定する。予測部１０３は、現時点からその特定された期間Ｔ２経過後のタイミングを、構成部材の将来の劣化状態が第２規定劣化状態に到達する到達時期として予測する。この到達時期は、メンテナンス準備時期とも呼ばれる。なお、上述のメンテナンス実施時期およびメンテナンス準備時期は、メンテナンス時期と総称される。また、到達時期情報は、そのメンテナンス時期を示す。 Similarly, the prediction unit 103 specifies the number of wearing times m2 when the degree of deterioration is the second threshold on the deterioration approximation curve. Note that the second threshold is a value smaller than the first threshold. Then, the prediction unit 103 refers to the production plan information d2, and specifies a period T2 from the current mounting number m0 to the mounting number m2 from the production planning information d2. The prediction unit 103 predicts the timing after the elapse of the specified period T2 from the current time as the arrival time when the future deterioration state of the constituent member reaches the second specified deterioration state. This arrival time is also called a maintenance preparation time. Note that the above-described maintenance implementation timing and maintenance preparation timing are collectively referred to as maintenance timing. Also, the arrival time information indicates the maintenance time.
　このように、本実施の形態では、劣化した構成部材のメンテナンスの実施が必要となる時期、またはそのメンテナンスの実施のための準備が必要となる時期が到達時期として予測され、その到達時期を示す到達時期情報が出力される。したがって、生産設備である部品装着装置１を用いて作業を行う作業者は、その到達時期、すなわちメンテナンス実施時期またはメンテナンス準備時期を把握することができる。その結果、作業者は、それらの時期を見越して作業を行うことができ、作業効率を向上することができる。また、メンテナンスの効率化を図ることができる。このように、作業者による生産設備のメンテナンスをより適切に支援することができる。 As described above, in the present embodiment, the timing at which maintenance of the deteriorated component member is required or the timing at which preparation for the maintenance is required is predicted as the arrival time, and the arrival time is indicated. Arrival time information is output. Therefore, a worker who performs work using the component mounting apparatus 1, which is a production facility, can grasp the arrival time, that is, the maintenance execution time or the maintenance preparation time. As a result, the worker can perform work in anticipation of those times, and can improve work efficiency. Also, efficiency of maintenance can be improved. In this way, maintenance of production equipment by workers can be more appropriately supported.
　［診断システムの処理の流れ］
　図１１は、診断システム１００による劣化状態の特定に関する処理動作の一例を示すフローチャートである。 [Flow of diagnostic system processing]
FIG. 11 is a flowchart showing an example of a processing operation regarding identification of a deterioration state by the diagnostic system 100. As shown in FIG.
　まず、診断システム１００の取得部１０１は、流量情報ｄ１を取得する（ステップＳ１）。次に、劣化特定部１３０の特徴量抽出部１３１は、その流量情報ｄ１から特徴量を抽出することによって特徴量データｄａ１を生成する（ステップＳ２）。 First, the acquisition unit 101 of the diagnostic system 100 acquires the flow rate information d1 (step S1). Next, the feature amount extraction unit 131 of the deterioration identification unit 130 generates feature amount data da1 by extracting the feature amount from the flow rate information d1 (step S2).
　そして、劣化特定部１３０の特定処理部１３２は、ステップＳ３、Ｓ４およびＳ５の処理を実行する。つまり、特定処理部１３２の異常処理部１３２ａは、ノズルユニット９に異常があるか否かを判定する（ステップＳ３）。特定処理部１３２の分類処理部１３２ｂは、ノズルユニット９に含まれる各構成部材の状態を異常と正常とに分類する（ステップＳ４）。特定処理部１３２の劣化度処理部１３２ｃは、ノズルユニット９に含まれる各構成部材の劣化度を推定する（ステップＳ５）。 Then, the identification processing unit 132 of the deterioration identification unit 130 executes the processing of steps S3, S4 and S5. That is, the abnormality processing section 132a of the specific processing section 132 determines whether or not there is an abnormality in the nozzle unit 9 (step S3). The classification processing unit 132b of the specific processing unit 132 classifies the state of each component included in the nozzle unit 9 into abnormal and normal (step S4). The deterioration degree processing unit 132c of the specific processing unit 132 estimates the deterioration degree of each component included in the nozzle unit 9 (step S5).
　出力部１０４は、その劣化特定部１３０の特定処理部１３２によって行われたステップＳ３、Ｓ４およびＳ５の処理の結果を示す劣化情報ｄｂを、診断結果として提示部３３に出力する（ステップＳ６）。これにより、劣化情報ｄｂの内容が提示部３３から提示される。 The output unit 104 outputs the deterioration information db indicating the results of the processing of steps S3, S4 and S5 performed by the identification processing unit 132 of the deterioration identification unit 130 to the presentation unit 33 as a diagnosis result (step S6). As a result, the presentation unit 33 presents the content of the deterioration information db.
　図１２は、診断システム１００によるメンテナンス指示に関する処理動作の一例を示すフローチャートである。 FIG. 12 is a flowchart showing an example of a processing operation regarding a maintenance instruction by the diagnostic system 100. FIG.
　まず、診断システム１００は、診断処理を実行する（ステップＳ１０）。この診断処理は、図１１のフローチャートに含まれるステップＳ１～Ｓ５の処理である。 First, the diagnostic system 100 executes diagnostic processing (step S10). This diagnosis process is the process of steps S1 to S5 included in the flowchart of FIG.
　そして、診断システム１００のメンテナンス処理部１０２は、ステップＳ１０の診断処理で得られた各構成部材の劣化度が第１閾値よりも大きいか否かを判定する（ステップＳ１１）。ここで、メンテナンス処理部１０２は、構成部材の劣化度が第１閾値よりも大きいと判定すると（ステップＳ１１のＹｅｓ）、出力部１０４および提示部３３を介してメンテナンスの実行を作業者に指示する（ステップＳ１２）。つまり、メンテナンス処理部１０２は、ノズルユニット９に含まれる複数の構成部材のそれぞれについて、当該構成部材に対して推定された劣化度が第１閾値を超えるか否かを判定する。そして、メンテナンス処理部１０２は、第１閾値を超えると判定された劣化度を有する構成部材のメンテナンスの実施を促す内容のメンテナンス警報情報を生成する。その後、メンテナンス処理部１０２は、そのメンテナンス警報情報を出力部１０４に出力し、出力部１０４は、そのメンテナンス警報情報を提示部３３に出力する。これにより、提示部３３からはそのメンテナンス警報情報の内容が提示される。 Then, the maintenance processing unit 102 of the diagnostic system 100 determines whether or not the degree of deterioration of each component obtained in the diagnostic process of step S10 is greater than the first threshold (step S11). When the maintenance processing unit 102 determines that the degree of deterioration of the component is greater than the first threshold value (Yes in step S11), the maintenance processing unit 102 instructs the operator to perform maintenance via the output unit 104 and the presentation unit 33. (Step S12). That is, the maintenance processing unit 102 determines whether or not the degree of deterioration estimated for each of the plurality of constituent members included in the nozzle unit 9 exceeds the first threshold. Then, the maintenance processing unit 102 generates maintenance warning information that prompts maintenance of the component having the degree of deterioration determined to exceed the first threshold. After that, the maintenance processing unit 102 outputs the maintenance warning information to the output unit 104 , and the output unit 104 outputs the maintenance warning information to the presentation unit 33 . As a result, the content of the maintenance warning information is presented from the presentation unit 33 .
　このように、本実施の形態では、例えば激しく劣化した構成部材に対しては、その構成部材のメンテナンスの実施を促す内容のメンテナンス警報情報が生成されて出力される。その結果、メンテナンス警報情報が作業者に通知され、作業者は、その構成部材のメンテナンスを迅速かつ適切に行うことができる。 Thus, in the present embodiment, for example, for severely deteriorated structural members, maintenance warning information is generated and output to prompt maintenance of the structural member. As a result, maintenance warning information is notified to the worker, and the worker can quickly and appropriately perform maintenance on the component.
　一方、ステップＳ１１において、メンテナンス処理部１０２は、構成部材の劣化度が第１閾値以下であると判定すると（ステップＳ１１のＮｏ）、さらに、その劣化度が第２閾値よりも大きいか否かを判定する（ステップＳ１３）。ここで、メンテナンス処理部１０２は、構成部材の劣化度が第２閾値よりも大きいと判定すると（ステップＳ１３のＹｅｓ）、出力部１０４および提示部３３を介してメンテナンスの準備を作業者に指示する（ステップＳ１４）。この第２閾値は、第１閾値未満の数値である。つまり、メンテナンス処理部１０２は、ノズルユニット９に含まれる複数の構成部材のそれぞれについて、当該構成部材に対して推定された劣化度が第１閾値以下であり、かつ、その劣化度が第１閾値よりも小さい第２閾値を超えるか否かを判定する。そして、メンテナンス処理部１０２は、第１閾値以下で第２閾値を超えると判定された劣化度を有する構成部材のメンテナンスの実施のための準備を促す内容のメンテナンス予報情報を生成する。その後、メンテナンス処理部１０２は、そのメンテナンス予報情報を出力部１０４に出力し、出力部１０４は、そのメンテナンス予報情報を提示部３３に出力する。これにより、提示部３３からはそのメンテナンス予報情報の内容が提示される。 On the other hand, in step S11, when the maintenance processing unit 102 determines that the degree of deterioration of the component is equal to or less than the first threshold (No in step S11), it further determines whether the degree of deterioration is greater than the second threshold. Determine (step S13). Here, when the maintenance processing unit 102 determines that the degree of deterioration of the component is greater than the second threshold value (Yes in step S13), the maintenance processing unit 102 instructs the operator to prepare for maintenance via the output unit 104 and the presentation unit 33. (Step S14). This second threshold is a numerical value less than the first threshold. That is, the maintenance processing unit 102 determines that the degree of deterioration estimated for each of the plurality of constituent members included in the nozzle unit 9 is equal to or lower than the first threshold, and the degree of deterioration is equal to or lower than the first threshold. It is determined whether or not a second threshold smaller than is exceeded. Then, the maintenance processing unit 102 generates maintenance forecast information that prompts preparation for performing maintenance on the constituent member having the degree of deterioration determined to be equal to or less than the first threshold value and to exceed the second threshold value. After that, the maintenance processing unit 102 outputs the maintenance forecast information to the output unit 104 , and the output unit 104 outputs the maintenance forecast information to the presentation unit 33 . As a result, the content of the maintenance forecast information is presented from the presentation unit 33 .
　このように、本実施の形態では、例えば、激しく劣化していなくても、激しい劣化の状態に近づいている構成部材に対しては、その構成部材のメンテナンスの実施のための準備を促す内容のメンテナンス予報情報が生成されて出力される。その結果、メンテナンス予報情報が作業者に通知され、作業者は、その構成部材のメンテナンスの準備を事前に余裕をもって適切に行うことができる。 As described above, in the present embodiment, for example, even if the component is not severely degraded, it is likely that the component is approaching the state of severe degradation. Maintenance forecast information is generated and output. As a result, the maintenance forecast information is notified to the worker, and the worker can appropriately prepare for the maintenance of the constituent member well in advance.
　さらに、出力部１０４は、ステップＳ１０の診断処理の結果を示す劣化情報ｄｂを、診断結果として提示部３３に出力する（ステップＳ６）。これにより、劣化情報ｄｂの内容が提示部３３から提示される。 Furthermore, the output unit 104 outputs the deterioration information db indicating the result of the diagnosis processing in step S10 to the presentation unit 33 as a diagnosis result (step S6). As a result, the presentation unit 33 presents the content of the deterioration information db.
　図１３は、診断システム１００によるメンテナンス時期予測に関する処理動作の一例を示すフローチャートである。 FIG. 13 is a flow chart showing an example of processing operations related to maintenance timing prediction by the diagnosis system 100. FIG.
　まず、診断システム１００は、診断処理を実行する（ステップＳ１０）。この診断処理は、図１１のフローチャートに含まれるステップＳ１～Ｓ５の処理である。 First, the diagnostic system 100 executes diagnostic processing (step S10). This diagnosis process is the process of steps S1 to S5 included in the flowchart of FIG.
　そして、診断システム１００の取得部１０１は、生産計画情報ｄ２を取得し（ステップＳ２１）、生産実績情報ｄ３を取得する（ステップＳ２２）。予測部１０３は、その取得された生産実績情報ｄ３に基づいて、ノズルユニット９に含まれる各構成部材の将来の劣化度を推定する（ステップＳ２３）。この将来の劣化度は、そのノズルユニット９が将来の部品Ｄの装着に用いられる装着回数に対して推定される。そして、予測部１０３は、その将来の劣化度と、ステップＳ２１で取得された生産計画情報ｄ２とに基づいて、ノズルユニット９の各構成部材のメンテナンス時期を予測する（ステップＳ２４）。このメンテナンス時期は、将来の劣化度が第１規定劣化状態に対応する第１閾値に到達するメンテナンス実施時期、または、将来の劣化度が第２規定劣化状態に対応する第２閾値に到達するメンテナンス準備時期である。 Then, the acquisition unit 101 of the diagnostic system 100 acquires the production plan information d2 (step S21) and acquires the actual production information d3 (step S22). The prediction unit 103 estimates the future degree of deterioration of each component included in the nozzle unit 9 based on the acquired production performance information d3 (step S23). This future degree of deterioration is estimated with respect to the number of mounting times that the nozzle unit 9 will be used to mount the component D in the future. Then, the prediction unit 103 predicts the maintenance timing of each component of the nozzle unit 9 based on the future deterioration degree and the production plan information d2 acquired in step S21 (step S24). This maintenance timing is the maintenance execution timing when the future deterioration degree reaches a first threshold value corresponding to the first specified deterioration state, or the maintenance execution timing when the future deterioration degree reaches the second threshold value corresponding to the second specified deterioration state. It's time to prepare.
　次に、出力部１０４は、ステップＳ２４で予測されたメンテナンス時期を示す到達時期情報を提示部３３に出力する（ステップＳ２５）。これにより、到達時期情報の内容（すなわちメンテナンス時期）が提示部３３から提示される。 Next, the output unit 104 outputs arrival time information indicating the maintenance time predicted in step S24 to the presentation unit 33 (step S25). As a result, the presentation unit 33 presents the content of the arrival time information (that is, the maintenance time).
　以上のように、本実施の形態における診断システム１００では、移載ヘッド８に含まれる少なくとも１つの構成部材のそれぞれの劣化状態が特定されて、その劣化状態を示す劣化情報ｄｂが出力される。その結果、生産設備である部品装着装置１の作業者によるメンテナンスをより適切に支援することができる。 As described above, in the diagnostic system 100 of the present embodiment, the deterioration state of each of at least one component included in the transfer head 8 is specified, and the deterioration information db indicating the deterioration state is output. As a result, it is possible to more appropriately support the maintenance of the component mounting apparatus 1, which is production equipment, by the operator.
　また、劣化特定部１３０は、構成部材の劣化の度合いを示す劣化度を推定することによって、その構成部材の劣化状態を特定する。これにより、作業者は劣化状態をより詳細に把握することができる。 Further, the deterioration identifying unit 130 identifies the deterioration state of the constituent member by estimating the degree of deterioration indicating the degree of deterioration of the constituent member. This allows the operator to grasp the deterioration state in more detail.
　また、劣化特定部１３０は、移載ヘッド８に含まれる１つ以上の構成部材のそれぞれに異常があるか否かを判定し、その１つ以上の構成部材のうち、異常があると判定された少なくとも１つの構成部材のそれぞれの劣化度を推定してもよい。これにより、異常と判定された構成部材に対して劣化度が推定されるため、劣化している可能性が比較的に高いと想定される構成部材に対して劣化度を推定し、劣化している可能性が比較的に低いと想定される構成部材に対する劣化度の推定を省くことができる。その結果、劣化度の推定の処理負担を軽減することができる。また、異常と判定された構成部材に対して劣化度が推定されるため、作業者は、その異常と判定された構成部材に対して、どのようなメンテナンスが必要か、あるいはメンテナンスが不要かを容易に把握することができる。例えば、構成部材の経過観察、構成部材の清掃、構成部材の補修、構成部材に含まれる部品の交換、構成部材そのものの交換など、必要とされるメンテナンスの態様を容易に把握することができる。 Further, the deterioration identifying unit 130 determines whether or not there is an abnormality in each of one or more constituent members included in the transfer head 8, and determines that one or more constituent members have an abnormality. A degree of deterioration of each of the at least one component may be estimated. As a result, the degree of deterioration is estimated for the component determined to be abnormal. It is possible to omit the estimation of the degree of deterioration for components assumed to be less likely to be damaged. As a result, the processing load for estimating the degree of deterioration can be reduced. In addition, since the degree of deterioration is estimated for the component determined to be abnormal, the operator can determine what kind of maintenance is required or whether maintenance is unnecessary for the component determined to be abnormal. can be easily grasped. For example, it is possible to easily grasp the form of required maintenance such as follow-up observation of the constituent members, cleaning of the constituent members, repair of the constituent members, replacement of parts included in the constituent members, and replacement of the constituent members themselves.
　また、メンテナンス処理部１０２は、少なくとも１つの構成部材のそれぞれについて、当該構成部材に対して推定された劣化度が閾値を超えるか否かを判定し、閾値を超えると判定された劣化度を有する構成部材のメンテナンスに関するメンテナンス情報を生成する。そして、出力部１０４は、そのメンテナンス情報を出力する。これにより、例えば劣化した構成部材に対しては、その構成部材のメンテナンスに関するメンテナンス情報が生成されて出力される。その結果、メンテナンス情報が作業者に通知され、作業者は、その構成部材のメンテナンスを迅速に、あるいは適切に行うことができる。 In addition, the maintenance processing unit 102 determines whether or not the degree of deterioration estimated for each of the at least one constituent members exceeds a threshold, and determines whether the degree of deterioration is determined to exceed the threshold. Generate maintenance information about component maintenance. Then, the output unit 104 outputs the maintenance information. As a result, for example, for a degraded component, maintenance information regarding maintenance of the component is generated and output. As a result, the maintenance information is notified to the operator, and the operator can quickly or appropriately perform maintenance on the component.
　また、劣化特定部１３０は、流量情報ｄ１と少なくとも１つの構成部材のそれぞれの劣化状態との関係を示す診断モデル１２１を用いることによって、劣化状態を特定する。これにより、適切に劣化状態を特定することができる。 The deterioration identifying unit 130 also identifies the deterioration state by using the diagnostic model 121 that indicates the relationship between the flow rate information d1 and the deterioration state of each of at least one component. This makes it possible to appropriately identify the deterioration state.
　また、その診断モデル１２１は、流量情報ｄ１の入力に対して少なくとも１つの構成部材のそれぞれの劣化状態を示す情報が出力されるように機械学習を行うことによって生成されている。これにより、機械学習を適切に行うことによって、劣化状態の特定の精度を高めることができる。 In addition, the diagnostic model 121 is generated by performing machine learning so that information indicating the deterioration state of each of at least one component is output in response to the input of the flow rate information d1. Accordingly, by appropriately performing machine learning, it is possible to improve the accuracy of identifying the deterioration state.
　また、本実施の形態における診断システム１００では、劣化した構成部材のメンテナンスの実施が必要となる時期、またはそのメンテナンスの実施のための準備が必要となる時期が到達時期として予測され、その到達時期を示す到達時期情報が出力される。したがって、作業者による生産設備のメンテナンスをより適切に支援することができる。 Further, in the diagnostic system 100 of the present embodiment, the timing at which maintenance of the deteriorated component member is required or the timing at which preparation for the maintenance is required is predicted as the arrival time. is output. Therefore, it is possible to more appropriately support maintenance of production equipment by workers.
　また、劣化情報ｄｂは、複数の過去の時点のそれぞれにおける構成部材の劣化状態を示す。これにより、劣化状態の経時的な変化に基づいて将来の劣化状態を適切に推定することができ、その結果、到達時期の予測精度を向上することができる。 Also, the deterioration information db indicates the deterioration state of the constituent member at each of a plurality of past points in time. As a result, it is possible to appropriately estimate the future deterioration state based on the temporal change of the deterioration state, and as a result, it is possible to improve the prediction accuracy of the arrival time.
　また、診断システム１００では、移載ヘッド８に含まれる構成部材の劣化状態が流量情報ｄ１に基づいて特定されて、その特定された劣化状態が到達時期の予測に用いられる。したがって、その劣化状態を適切に特定することができ、到達時期の予測精度を向上することができる。 Also, in the diagnostic system 100, the deterioration state of the constituent members included in the transfer head 8 is specified based on the flow rate information d1, and the identified deterioration state is used to predict the arrival time. Therefore, the deterioration state can be appropriately specified, and the prediction accuracy of arrival time can be improved.
　また、診断システム１００では、劣化状態が劣化度としてより詳細に推定されるため、到達時期の予測精度をさらに向上することができる。 In addition, in the diagnostic system 100, the deterioration state is estimated in more detail as the degree of deterioration, so it is possible to further improve the prediction accuracy of the arrival time.
　また、診断システム１００では、異常と判定された構成部材に対して劣化度が推定される場合には、劣化の兆候があると想定される構成部材に対して到達時期を予測し、劣化の兆候がないと想定される構成部材に対する到達時期の予測を省くことができる。その結果、到達時期の予測の処理負担を軽減することができる。 Further, in the diagnostic system 100, when the degree of deterioration is estimated for a component determined to be abnormal, the arrival time of a component assumed to have signs of deterioration is predicted, and the signs of deterioration are predicted. It is possible to omit the prediction of arrival times for components assumed to be absent. As a result, it is possible to reduce the processing load of predicting the arrival time.
　また、生産実績情報ｄ３は、移載ヘッド８によって部品Ｄが基板３に装着された装着回数を示す装着回数情報を含み、予測部１０３は、装着回数情報と劣化情報ｄｂとに基づいて構成部材の将来の劣化状態を推定する。これにより、過去の装着回数に対する劣化度に基づいて、将来の装着回数に対する劣化度を適切に推定することができる。 Further, the actual production information d3 includes placement number information indicating the number of placement times that the component D has been placed on the substrate 3 by the transfer head 8, and the prediction unit 103 predicts the number of component parts based on the placement number information and the deterioration information db. Estimate the future state of deterioration of This makes it possible to appropriately estimate the degree of deterioration with respect to the number of times of wearing in the future based on the degree of deterioration with respect to the number of times of wearing in the past.
　（その他の形態）
　以上、本開示に係る診断システムおよび診断方法などについて、上記実施の形態に基づいて説明したが、本開示は、この実施の形態に限定されるものではない。本開示の趣旨を逸脱しない限り、当業者が思いつく各種変形を上記実施の形態に施したものも、本開示の範囲に含まれてもよい。 (Other forms)
As described above, the diagnostic system and diagnostic method according to the present disclosure have been described based on the above embodiments, but the present disclosure is not limited to these embodiments. As long as they do not deviate from the spirit of the present disclosure, various modifications conceived by those skilled in the art may be included in the scope of the present disclosure.
　例えば、上記実施の形態では、診断システム１００は、部品装着装置１の内部に備えられているが、部品装着装置１の外部に備えられていてもよく、部品装着装置１に接続された例えばパーソナルコンピュータとして構成されていてもよい。 For example, although the diagnosis system 100 is provided inside the component mounting apparatus 1 in the above embodiment, it may be provided outside the component mounting apparatus 1, for example, a personal computer connected to the component mounting apparatus 1. It may be configured as a computer.
　例えば、上記実施の形態では、移載ヘッド８には複数のノズルユニット９が備えられているが、移載ヘッド８に備えられるノズルユニット９の数は、１つであってもよい。また、上記実施の形態では、ノズルユニット９に含まれるエアチューブ４０、フィルタ４１、バルブなどの複数の構成部材のそれぞれについて、劣化状態が特定され、メンテナンス時期が予測されるが、１つの構成部材に対して劣化度の特定、メンテナンス時期の予測などが行われてもよい。言い換えれば、移載ヘッド８に含まれる少なくとも１つの構成部材に対して特定、予測などの各処理が行われてもよい。 For example, in the above embodiment, the transfer head 8 is provided with a plurality of nozzle units 9, but the number of nozzle units 9 provided in the transfer head 8 may be one. Further, in the above embodiment, the deterioration state is specified for each of the plurality of constituent members such as the air tube 40, the filter 41, and the valve included in the nozzle unit 9, and the maintenance time is predicted. Deterioration degree identification, maintenance timing prediction, and the like may be performed for each. In other words, each process such as identification and prediction may be performed on at least one component included in the transfer head 8 .
　また、上記実施の形態では、学習部１１０が特徴量抽出部１１１を備え、劣化特定部１３０が特徴量抽出部１３１を備えるが、特徴量抽出部１１１および１３１は備えられていなくてもよい。言い換えれば、上記実施の形態は、流量情報ｄ１から各種の特徴量が抽出され、それらの特徴量を示す特徴量データｄａ１が、学習処理部１１２および特定処理部１３２に用いられる。しかし、流量情報ｄ１が学習処理部１１２および特定処理部１３２に直接用いられてもよい。つまり、流量情報ｄ１に示される流量波形が、機械学習に直接用いられてもよく、劣化状態の特定などに直接用いられてもよい。 Also, in the above embodiment, the learning unit 110 includes the feature amount extraction unit 111 and the deterioration identification unit 130 includes the feature amount extraction unit 131, but the feature amount extraction units 111 and 131 may not be provided. In other words, in the above embodiment, various feature amounts are extracted from the flow rate information d1, and the feature amount data da1 representing these feature amounts are used by the learning processing section 112 and the specific processing section 132. FIG. However, the flow rate information d1 may be directly used by the learning processing unit 112 and the specific processing unit 132. FIG. That is, the flow rate waveform indicated by the flow rate information d1 may be directly used for machine learning, or may be directly used for identifying the deterioration state.
　また、上記実施の形態では、劣化特定部１３０に異常処理部１３２ａおよび分類処理部１３２ｂが備えられているが、これらの構成要素が備えられていなくてもよい。つまり、移載ヘッド８の少なくとも１つの構成部材に対して劣化度が推定されれば、ノズルユニット９が異常であるか否かの判定、および、それらの構成部材の異常または正常の分類は、行われなくてもよい。また、異常処理部１３２ａによって判定される異常、および、分類処理部１３２ｂによって分類される異常は、構成部材の劣化に起因する異常であってよく、劣化と異なる要因に基づく異常であってもよい。 Also, in the above embodiment, the deterioration identifying unit 130 includes the abnormality processing unit 132a and the classification processing unit 132b, but these components may not be included. In other words, if the degree of deterioration is estimated for at least one component of the transfer head 8, the determination of whether the nozzle unit 9 is abnormal and the classification of those components as abnormal or normal are It does not have to be done. Further, the abnormality determined by the abnormality processing unit 132a and the abnormality classified by the classification processing unit 132b may be an abnormality caused by deterioration of the constituent members, or may be an abnormality based on a factor other than deterioration. .
　また、上記実施の形態では、部品装着装置１は生産設備の一例であるが、生産設備は、部品装着装置１と異なる装置であってもよい。また、生産設備は、作業設備と呼ばれてもよい。さらに、上記実施の形態では、生産設備を用いて生産を行う作業者に対して各種の情報が提示されて、その作業者が生産設備のメンテナンスを行うが、そのような作業者以外の人にそれらの情報が提示され、作業者以外の人がメンテナンスを行ってもよい。 Also, in the above embodiment, the component mounting device 1 is an example of production equipment, but the production equipment may be a device different from the component mounting device 1. A production facility may also be referred to as a work facility. Furthermore, in the above embodiment, various information is presented to a worker who performs production using the production equipment, and the worker performs maintenance of the production equipment. Such information may be presented and maintenance may be performed by a person other than the operator.
　また、上記実施の形態では、診断システム１００は、メンテナンス処理部１０２および予測部１０３を備えているが、これらのうちの一方のみを備えていてもよい。また、図１２に示す、メンテナンス処理部１０２に用いられる第１閾値および第２閾値と、図１０に示す、予測部１０３に用いられる第１閾値および第２閾値とは、それぞれ同一であっても異なっていてもよい。 Also, in the above embodiment, the diagnosis system 100 includes the maintenance processing unit 102 and the prediction unit 103, but may include only one of them. Further, even if the first threshold and the second threshold used in the maintenance processing unit 102 shown in FIG. 12 and the first threshold and the second threshold used in the prediction unit 103 shown in FIG. can be different.
　また、上記実施の形態では、診断モデル１２１は、機械学習モデルであるが、各種の特徴量とノズルユニット９の状態とを関連付けて示すテーブルであってもよい。ノズルユニット９の状態は、ノズルユニット９の正常または異常であってもよく、ノズルユニット９に含まれる各構成部材の正常または異常であってもよく、その各構成部材の劣化度であってもよい。 In addition, in the above embodiment, the diagnostic model 121 is a machine learning model, but it may be a table that associates various feature amounts with the state of the nozzle unit 9 . The state of the nozzle unit 9 may be the normality or abnormality of the nozzle unit 9, the normality or abnormality of each component included in the nozzle unit 9, or the degree of deterioration of each component. good.
　なお、上記実施の形態において、各構成要素は、専用のハードウェアで構成されるか、各構成要素に適したソフトウェアプログラムを実行することによって実現されてもよい。各構成要素は、ＣＰＵ（Central Processing Unit）またはプロセッサなどのプログラム実行部が、ハードディスクまたは半導体メモリなどの記録媒体に記録されたソフトウェアプログラムを読み出して実行することによって実現されてもよい。ここで、上記実施の形態の診断システム１００などを実現するソフトウェアは、図１１～図１３に示すフローチャートに含まれる各ステップをコンピュータに実行させるプログラムである。 In addition, in the above embodiment, each component may be configured by dedicated hardware or implemented by executing a software program suitable for each component. Each component may be implemented by a program execution unit such as a CPU (Central Processing Unit) or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory. Here, the software that implements the diagnostic system 100 and the like of the above embodiment is a program that causes a computer to execute each step included in the flowcharts shown in FIGS. 11 to 13. FIG.
　なお、以下のような場合も本開示に含まれる。 The following cases are also included in this disclosure.
　（１）上記の各装置は、具体的には、マイクロプロセッサ、ＲＯＭ、ＲＡＭ、ハードディスクユニット、ディスプレイユニット、キーボード、マウスなどから構成されるコンピュータシステムである。前記ＲＡＭまたはハードディスクユニットには、コンピュータプログラムが記憶されている。前記マイクロプロセッサが、前記コンピュータプログラムにしたがって動作することにより、各装置は、その機能を達成する。ここでコンピュータプログラムは、所定の機能を達成するために、コンピュータに対する指令を示す命令コードが複数個組み合わされて構成されたものである。 (1) Each of the above devices is specifically a computer system composed of a microprocessor, ROM, RAM, hard disk unit, display unit, keyboard, mouse, and the like. A computer program is stored in the RAM or hard disk unit. Each device achieves its function by the microprocessor operating according to the computer program. Here, the computer program is constructed by combining a plurality of instruction codes indicating instructions to the computer in order to achieve a predetermined function.
　（２）上記の各装置を構成する構成要素の一部または全部は、１個のシステムＬＳＩ（Ｌａｒｇｅ　Ｓｃａｌｅ　Ｉｎｔｅｇｒａｔｉｏｎ：大規模集積回路）から構成されているとしてもよい。システムＬＳＩは、複数の構成部を１個のチップ上に集積して製造された超多機能ＬＳＩであり、具体的には、マイクロプロセッサ、ＲＯＭ、ＲＡＭなどを含んで構成されるコンピュータシステムである。前記ＲＡＭには、コンピュータプログラムが記憶されている。前記マイクロプロセッサが、前記コンピュータプログラムにしたがって動作することにより、システムＬＳＩは、その機能を達成する。 (2) A part or all of the components constituting each of the devices described above may be configured from one system LSI (Large Scale Integration). A system LSI is an ultra-multifunctional LSI manufactured by integrating multiple components on a single chip. Specifically, it is a computer system that includes a microprocessor, ROM, RAM, etc. . A computer program is stored in the RAM. The system LSI achieves its functions by the microprocessor operating according to the computer program.
　（３）上記の各装置を構成する構成要素の一部または全部は、各装置に脱着可能なＩＣカードまたは単体のモジュールから構成されているとしてもよい。前記ＩＣカードまたは前記モジュールは、マイクロプロセッサ、ＲＯＭ、ＲＡＭなどから構成されるコンピュータシステムである。前記ＩＣカードまたは前記モジュールは、上記の超多機能ＬＳＩを含むとしてもよい。マイクロプロセッサが、コンピュータプログラムにしたがって動作することにより、前記ＩＣカードまたは前記モジュールは、その機能を達成する。このＩＣカードまたはこのモジュールは、耐タンパ性を有するとしてもよい。 (3) Some or all of the components that make up each device described above may be configured from an IC card or a single module that can be attached to and removed from each device. The IC card or module is a computer system composed of a microprocessor, ROM, RAM and the like. The IC card or the module may include the super multifunctional LSI. The IC card or the module achieves its function by the microprocessor operating according to the computer program. This IC card or this module may be tamper resistant.
　（４）本開示は、上記に示す方法であるとしてもよい。また、これらの方法をコンピュータにより実現するコンピュータプログラムであるとしてもよいし、前記コンピュータプログラムからなるデジタル信号であるとしてもよい。 (4) The present disclosure may be the method shown above. Moreover, it may be a computer program for realizing these methods by a computer, or it may be a digital signal composed of the computer program.
　また、本開示は、前記コンピュータプログラムまたは前記デジタル信号をコンピュータ読み取り可能な記録媒体、例えば、フレキシブルディスク、ハードディスク、ＣＤ－ＲＯＭ、ＭＯ、ＤＶＤ、ＤＶＤ－ＲＯＭ、ＤＶＤ－ＲＡＭ、ＢＤ（Ｂｌｕ－ｒａｙ（登録商標）　Ｄｉｓｃ）、半導体メモリなどに記録したものとしてもよい。また、これらの記録媒体に記録されている前記デジタル信号であるとしてもよい。 In addition, the present disclosure includes a computer-readable recording medium for the computer program or the digital signal, such as a flexible disk, hard disk, CD-ROM, MO, DVD, DVD-ROM, DVD-RAM, BD (Blu-ray ( (Registered Trademark) Disc), semiconductor memory, or the like. Moreover, it may be the digital signal recorded on these recording media.
　また、本開示は、前記コンピュータプログラムまたは前記デジタル信号を、電気通信回線、無線または有線通信回線、インターネットを代表とするネットワーク、データ放送等を経由して伝送するものとしてもよい。 Further, according to the present disclosure, the computer program or the digital signal may be transmitted via an electric communication line, a wireless or wired communication line, a network represented by the Internet, data broadcasting, or the like.
　また、本開示は、マイクロプロセッサとメモリを備えたコンピュータシステムであって、前記メモリは、上記コンピュータプログラムを記憶しており、前記マイクロプロセッサは、前記コンピュータプログラムにしたがって動作するとしてもよい。 The present disclosure may also be a computer system comprising a microprocessor and memory, the memory storing the computer program, and the microprocessor operating according to the computer program.
　また、前記プログラムまたは前記デジタル信号を前記記録媒体に記録して移送することにより、または前記プログラムまたは前記デジタル信号を前記ネットワーク等を経由して移送することにより、独立した他のコンピュータシステムにより実施するとしてもよい。 Also, by recording the program or the digital signal on the recording medium and transferring it, or by transferring the program or the digital signal via the network or the like, it is implemented by another independent computer system. may be
　（５）上記実施の形態及びその他の形態を組み合わせてもよい。 (5) The above embodiment and other forms may be combined.
　本開示は、例えば生産設備を管理するシステムなどに利用可能である。 The present disclosure can be used, for example, for systems that manage production equipment.
１　　部品装着装置
１ａ　　基台
２　　基板搬送機構
３　　基板
４　　部品供給部
５　　テープフィーダ
６　　Ｙ軸ビーム
７　　Ｘ軸ビーム
８　　移載ヘッド
８ａ　　結合プレート
９　　ノズルユニット
９ａ　　ノズル駆動部
１０　　ヘッド移動機構
１１　　部品認識カメラ
１２　　基板認識カメラ
１３　　ノズル軸
１４　　ノズル装着部
１５　　吸着ノズル
１５ａ　　吸着保持面
１６　　流量センサ
１７　　出力経路
１８　　切換バルブ
１９　　真空ポンプ
２０　　ブローバルブ
２１　　エア供給源
２２　　大気供給源
２３　　ノズル制御部
３０　　装置制御部
３１　　装置記憶部
３２　　入力部
３３　　提示部
４０　　エアチューブ
４１　　フィルタ
１００　　診断システム
１０１　　取得部
１０２　　メンテナンス処理部
１０３　　予測部
１０４　　出力部
１１０　　学習部
１１１　　特徴量抽出部
１１２　　学習処理部
１１２ａ　　異常学習部
１１２ｂ　　分類学習部
１１２ｃ　　劣化度学習部
１２０　　モデル格納部
１２１　　診断モデル
１２１ａ　　異常判定モデル
１２１ｂ　　異常分類モデル
１２１ｃ　　劣化度推定モデル
１３０　　劣化特定部
１３１　　特徴量抽出部
１３２　　特定処理部
１３２ａ　　異常処理部
１３２ｂ　　分類処理部
１３２ｃ　　劣化度処理部
ｄ１　　流量情報
ｄ２　　生産計画情報
ｄ３　　生産実績情報
ｄａ１　　特徴量データ
ｄｂ　　劣化情報
ｄｂ１　　異常判定結果情報
ｄｂ２　　異常分類情報
ｄｂ３　　劣化度情報 1 component mounting device 1a base 2 substrate transport mechanism 3 substrate 4 component supply unit 5 tape feeder 6 Y-axis beam 7 X-axis beam 8 transfer head 8a coupling plate 9 nozzle unit 9a nozzle drive unit 10 head movement mechanism 11 component recognition camera 12 Board Recognition Camera 13 Nozzle Shaft 14 Nozzle Mounting Part 15 Suction Nozzle 15a Suction Holding Surface 16 Flow Sensor 17 Output Path 18 Switching Valve 19 Vacuum Pump 20 Blow Valve 21 Air Supply Source 22 Air Supply Source 23 Nozzle Control Unit 30 Device Control Unit 31 Device storage unit 32 Input unit 33 Presentation unit 40 Air tube 41 Filter 100 Diagnosis system 101 Acquisition unit 102 Maintenance processing unit 103 Prediction unit 104 Output unit 110 Learning unit 111 Feature quantity extraction unit 112 Learning processing unit 112a Abnormal learning unit 112b Classification learning unit 112c Deterioration degree learning unit 120 Model storage unit 121 Diagnosis model 121a Abnormality determination model 121b Abnormality classification model 121c Deterioration degree estimation model 130 Deterioration identification unit 131 Feature amount extraction unit 132 Identification processing unit 132a Abnormality processing unit 132b Classification processing unit 132c Deterioration degree processing Part d1 Flow rate information d2 Production plan information d3 Actual production information da1 Feature amount data db Degradation information db1 Abnormality determination result information db2 Abnormality classification information db3 Deterioration degree information

Claims (9)

  1. 　（ｉ）部品が装着された基板である装着基板を、生産設備を用いて生産する生産計画を示す生産計画情報と、（ｉｉ）前記生産設備を用いて前記装着基板が生産された実績を示す生産実績情報とを取得する取得部と、
    　前記生産設備に含まれる構成部材の過去または現在の劣化状態を示す劣化情報と、前記取得部によって取得された前記生産計画情報および前記生産実績情報とに基づいて、前記構成部材の将来の劣化状態が、予め定められた劣化状態である規定劣化状態に到達する到達時期を予測する予測部と、
    　予測された前記到達時期を示す到達時期情報を出力する出力部と、
    　を備える診断システム。     (i) production plan information indicating a production plan for producing a mounted board, which is a board on which components are mounted, using production equipment; an acquisition unit that acquires production performance information;
    The future deterioration state of the constituent members based on the deterioration information indicating the past or present deterioration state of the constituent members included in the production equipment, and the production plan information and the production performance information acquired by the acquisition unit. A prediction unit that predicts the arrival time of reaching a specified deterioration state, which is a predetermined deterioration state;
    an output unit that outputs arrival time information indicating the predicted arrival time;
    diagnostic system.
  2. 　前記劣化情報は、複数の過去の時点のそれぞれにおける前記構成部材の劣化状態を示す、
    　請求項１に記載の診断システム。     the deterioration information indicates the deterioration state of the constituent member at each of a plurality of past points in time;
    The diagnostic system of Claim 1.
  3. 　前記生産設備は、
    　移載ヘッドによって部品を吸着して基板に装着する部品装着装置であり、
    　前記診断システムは、さらに、
    　前記移載ヘッドに流れるエアの流量に関する流量情報に基づいて、前記移載ヘッドに含まれる前記構成部材の劣化状態を特定する劣化特定部を備え、
    　前記予測部は、
    　前記劣化特定部によって特定された劣化状態を示す情報を前記劣化情報として取得する、
    　請求項１に記載の診断システム。     The production facility is
    A component mounting device that picks up a component with a transfer head and mounts it on a substrate,
    The diagnostic system further comprises:
    a deterioration identifying unit that identifies a deterioration state of the constituent members included in the transfer head based on flow rate information about the flow rate of air flowing through the transfer head;
    The prediction unit
    Acquiring, as the deterioration information, information indicating the deterioration state identified by the deterioration identification unit;
    The diagnostic system of Claim 1.
  4. 　前記劣化特定部は、
    　前記構成部材の劣化の度合いを示す劣化度を推定することによって、前記構成部材の劣化状態を特定する、
    　請求項３に記載の診断システム。     The deterioration specifying unit
    identifying the deterioration state of the constituent member by estimating the degree of deterioration indicating the degree of deterioration of the constituent member;
    4. The diagnostic system of claim 3.
  5. 　前記劣化特定部は、
    　前記構成部材に異常があるか否かを判定し、異常があると判定した場合に、前記構成部材の前記劣化度を推定する、
    　請求項４に記載の診断システム。     The deterioration specifying unit
    Determining whether or not there is an abnormality in the constituent member, and estimating the degree of deterioration of the constituent member when it is determined that there is an abnormality;
    5. The diagnostic system of claim 4.
  6. 　前記生産実績情報は、
    　前記移載ヘッドによって部品が基板に装着された装着回数を示す装着回数情報を含み、
    　前記予測部は、
    　前記装着回数情報と前記劣化情報とに基づいて前記構成部材の将来の劣化状態を推定する、
    　請求項３に記載の診断システム。     The production performance information is
    including mounting number information indicating the number of times the component has been mounted on the substrate by the transfer head;
    The prediction unit
    estimating a future state of deterioration of the constituent member based on the mounting number information and the deterioration information;
    4. The diagnostic system of claim 3.
  7. 　前記規定劣化状態は、
    　前記構成部材のメンテナンスの実施が必要な第１規定劣化状態、または、前記メンテナンスの実施のための準備が必要な第２規定劣化状態である、
    　請求項１～６のいずれか１項に記載の診断システム。     The specified deterioration state is
    A first prescribed deterioration state that requires maintenance of the component member, or a second prescribed deterioration state that requires preparation for the maintenance.
    A diagnostic system according to any one of claims 1-6.
  8. 　前記予測部は、
    　前記構成部材の将来の劣化状態として、前記構成部材の劣化の度合いが大きいほど大きい値を示す将来の劣化度を推定し、
    　前記将来の劣化度が、前記第１規定劣化状態に対応する第１閾値に到達する到達時期、または、前記第２規定劣化状態に対応する第２閾値に到達する到達時期を、前記生産計画情報に基づいて予測する、
    　請求項７に記載の診断システム。     The prediction unit
    estimating a future deterioration degree indicating a larger value as the degree of deterioration of the constituent member increases, as the future deterioration state of the constituent member;
    The arrival time at which the future deterioration degree reaches a first threshold value corresponding to the first prescribed deterioration state or the arrival time at which a second threshold value corresponding to the second prescribed deterioration state is reached is set in the production plan information. predict based on
    A diagnostic system according to claim 7 .
  9. 　（ｉ）部品が装着された基板である装着基板を、生産設備を用いて生産する生産計画を示す生産計画情報と、（ｉｉ）前記生産設備を用いて前記装着基板が生産された実績を示す生産実績情報とを取得し、
    　前記生産設備に含まれる構成部材の過去または現在の劣化状態を示す劣化情報と、取得された前記生産計画情報および前記生産実績情報とに基づいて、前記構成部材の将来の劣化状態が、予め定められた劣化状態である規定劣化状態に到達する到達時期を予測し、
    　予測された前記到達時期を示す到達時期情報を出力する、
    　診断方法。     (i) production plan information indicating a production plan for producing a mounted board, which is a board on which components are mounted, using production equipment; Acquire production performance information and
    The future deterioration state of the constituent members is determined in advance based on the deterioration information indicating the past or present deterioration state of the constituent members included in the production equipment, and the acquired production plan information and production performance information. Predict the arrival time to reach the specified deterioration state, which is the deterioration state obtained by
    outputting arrival time information indicating the predicted arrival time;
    diagnostic method.
PCT/JP2022/029991 2021-10-29 2022-08-04 Diagnostic system and diagnostic method WO2023074079A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-177549 2021-10-29
JP2021177549 2021-10-29

Publications (1)

Publication Number Publication Date
WO2023074079A1 true WO2023074079A1 (en) 2023-05-04

Family

ID=86159317

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/029991 WO2023074079A1 (en) 2021-10-29 2022-08-04 Diagnostic system and diagnostic method

Country Status (1)

Country Link
WO (1) WO2023074079A1 (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014049766A1 (en) * 2012-09-27 2014-04-03 富士機械製造株式会社 Recognition device for substrate processing machine
WO2014196002A1 (en) * 2013-06-03 2014-12-11 富士機械製造株式会社 Nozzle management system
WO2018131136A1 (en) * 2017-01-13 2018-07-19 株式会社Ｆｕｊｉ Manufacturing management device

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014049766A1 (en) * 2012-09-27 2014-04-03 富士機械製造株式会社 Recognition device for substrate processing machine
WO2014196002A1 (en) * 2013-06-03 2014-12-11 富士機械製造株式会社 Nozzle management system
WO2018131136A1 (en) * 2017-01-13 2018-07-19 株式会社Ｆｕｊｉ Manufacturing management device

Similar Documents

Publication Publication Date Title
JP7093442B2 (en) Semiconductor manufacturing equipment, failure prediction methods for semiconductor manufacturing equipment, and failure prediction programs for semiconductor manufacturing equipment
CN103687469A (en) Electronic component mounting apparatus
CN115078392A (en) Semiconductor chip defect detection equipment and method
JP5925540B2 (en) Electronic component mounting equipment
JP6633616B2 (en) Information management apparatus and information management method
JP2018120983A (en) Semiconductor manufacturing equipment and semiconductor device manufacturing method
JP2021015405A (en) Learning device, diagnostic device, and learning method
JP4995745B2 (en) Component mounting equipment
WO2023074079A1 (en) Diagnostic system and diagnostic method
JP6002938B2 (en) Electronic component mounting equipment
JP4504240B2 (en) Electronic component mounting method and electronic component mounting apparatus
JP2023066626A (en) Diagnostic system and diagnostic method
JP4651581B2 (en) Component mounting method
JP5684057B2 (en) Electronic component mounting device
CN105704944A (en) Circuit board transplantation double-sided automatic alignment device
CN112788945A (en) Mounting condition estimation device, learning device, and mounting condition estimation method
JP2018056306A (en) Information management device and information management method
JP2012064781A (en) Method for checking component recognition camera state, and electronic component mounting apparatus having function to check component recognition camera state
JP4815377B2 (en) Component mounting method
JP5223818B2 (en) Electronic component mounting equipment
JP2018101674A (en) Component mounting device and component mounting method
JP2022096212A (en) State estimation device, mounting system, and state estimation method
JP5788246B2 (en) Electronic component mounting system
JP2017152420A (en) Electronic component mounting apparatus and electronic component mounting method
JP2008021822A (en) Electronic component mounting apparatus, method for mounting electronic component, and substrate production method

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22886414

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023556135

Country of ref document: JP