WO2020059735A1 - Control device and control system - Google Patents
Control device and control system Download PDFInfo
- Publication number
- WO2020059735A1 WO2020059735A1 PCT/JP2019/036493 JP2019036493W WO2020059735A1 WO 2020059735 A1 WO2020059735 A1 WO 2020059735A1 JP 2019036493 W JP2019036493 W JP 2019036493W WO 2020059735 A1 WO2020059735 A1 WO 2020059735A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- frame
- abnormality
- control device
- monitoring
- Prior art date
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
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
Definitions
- the present technology relates to a control device and a control system that can determine whether or not there is an abnormality in a control target.
- FA Fractory Automation
- PLC programmable controller
- Patent Document 1 discloses equipment such as equipment operation information of a machine tool / manufacturing apparatus, internal information of the equipment, and measurement information of a measurement apparatus such as a sensor for performing necessary measurement of the machine tool.
- a device information collection / distribution device for the purpose of monitoring information, improving efficiency of device maintenance, production management, and the like is disclosed.
- Patent Document 1 The configuration disclosed in Patent Document 1 described above is a configuration in which an abnormality in a machine tool or a manufacturing apparatus itself is determined based on information collected in a data center or the like. For such a configuration, there is a need to immediately detect an abnormality occurring at the production site.
- the present technology provides a configuration capable of ex-post analysis and verification of the behavior in a control device and a control system that can determine whether or not there is an abnormality in a control target.
- a control device for controlling a control target.
- the control device includes, for each frame defined based on the first process value related to the control target, an abnormality monitoring unit that determines whether there is an abnormality in the control target, and a second monitor related to the control target in each frame.
- a feature value calculation unit that calculates a feature value for each frame based on the process value and outputs the feature value to the abnormality monitoring unit; a storage unit that stores data relating to processing performed by the abnormality monitoring unit and the feature value calculation unit; and a storage unit that stores the data.
- a data transmission unit for transmitting data to be transmitted to the outside.
- the abnormality monitoring unit is configured such that, when the feature amount for each frame is input from the feature amount calculation unit, a monitoring result including a determination result of the presence or absence of an abnormality in the control target is output for each frame.
- the data transmission unit includes first data including time-series data of the first process value and the second process value, and second data including time-series data of a feature calculated by the feature calculation unit for each frame. It is configured to be able to transmit data and third data including time-series data of the monitoring result output by the abnormality monitoring unit.
- the feature value is associated with a first process value that defines a frame corresponding to each feature value.
- the monitoring result is associated with a first process value that defines a frame corresponding to each monitoring result.
- the first process value that defines the frame is commonly associated with the first data, the second data, and the third data.
- the time series data associated with the frame can be easily specified.
- the abnormality monitoring unit calculates a monitoring score, which is a degree indicating the possibility of abnormality, based on the feature amount of each frame, and determines whether there is an abnormality in the control target based on the magnitude of the calculated monitoring score. to decide.
- a monitoring score which is a degree indicating the possibility of abnormality
- the monitoring result of the third data includes a monitoring score and a value indicating the presence or absence of an abnormality based on the monitoring score.
- the monitoring score and the value indicating the presence or absence of the abnormality based on the monitoring score are associated with each other, it is possible to easily perform the ex-post evaluation of the control device determining that the abnormality has occurred.
- the data transmitting unit is configured to be able to further transmit fourth data including time-series data of one or more specific process values.
- the feature amount calculation unit calculates the feature amount based on a temporal change of a second process value in a subframe defined based on a third process value related to a control target in each frame. It is configured.
- the first data further includes time-series data of a third process value.
- each of the first data, the second data, and the third data is provided with a time stamp managed by a common timer for each record.
- each of the first data, the second data, and the third data has an index that is incremented or decremented for each record.
- the data transmission unit transmits the data using at least one communication protocol of HTTP (Hypertext Transfer Protocol), HTTPS (Hypertext Transfer Protocol Secure), FTP (File Transfer Protocol), and SMB (Server Message Block). I do.
- HTTP Hypertext Transfer Protocol
- HTTPS Hypertext Transfer Protocol Secure
- FTP File Transfer Protocol
- SMB Server Message Block
- the data transmitting section transmits the first data, the second data, and the third data in a CSV (Comma-Separated $ Values) format.
- CSV Common-Separated $ Values
- a general-purpose application can be used in various information processing apparatuses.
- a control system includes a control device that controls a control target and a server device that receives data from the control device.
- the control device includes, for each frame defined based on the first process value related to the control target, an abnormality monitoring unit that determines whether there is an abnormality in the control target, and a second monitor related to the control target in each frame.
- a feature value calculation unit that calculates a feature value for each frame based on the process value and outputs the feature value to the abnormality monitoring unit; a storage unit that stores data relating to processing performed by the abnormality monitoring unit and the feature value calculation unit; and a storage unit that stores the data.
- a data transmission unit for transmitting data to be transmitted to the outside.
- the abnormality monitoring unit is configured such that, when the feature amount for each frame is input from the feature amount calculation unit, a monitoring result including a determination result of the presence or absence of an abnormality in the control target is output for each frame.
- the data transmission unit includes first data including time-series data of the first process value and the second process value, and second data including time-series data of a feature calculated by the feature calculation unit for each frame. It is configured to be able to transmit data and third data including time-series data of the monitoring result output by the abnormality monitoring unit.
- the feature value is associated with a first process value that defines a frame corresponding to each feature value.
- the monitoring result is associated with a first process value that defines a frame corresponding to each monitoring result.
- the first process value that defines the frame is commonly associated with the first data, the second data, and the third data.
- the time series data associated with the frame can be easily specified.
- the present technology it is possible to analyze and verify the behavior of the control device and the control system that can determine the presence / absence of an abnormality in the control target after the fact.
- FIG. 1 is a schematic diagram illustrating an example of the overall configuration of a control system according to the present embodiment.
- FIG. 2 is a block diagram illustrating a hardware configuration example of a control device configuring the control system according to the present embodiment.
- FIG. 2 is a block diagram illustrating a functional configuration example of a control device included in the control system according to the present embodiment.
- FIG. 6 is a schematic diagram illustrating an example of a frame and a sub-frame set in the packaging machine illustrated in FIG. 5.
- FIG. 3 is a schematic diagram for describing an outline of data collection and data management in the control device according to the present embodiment.
- FIG. 3 is a diagram schematically illustrating a data management structure in the control device according to the present embodiment.
- FIG. 3 is a schematic diagram for explaining an outline of data processing related to an abnormality monitoring function in the control device according to the present embodiment.
- FIG. 9 is a diagram for explaining an example of an analysis procedure using data transmitted from the control device according to the present embodiment.
- FIG. 1 is a schematic diagram illustrating an outline of a functional configuration of a control device 100 included in a control system 1 according to the present embodiment.
- control device 100 controls a control target including an arbitrary facility or machine.
- the control device 100 can employ a PLC (programmable controller) or the like.
- the control device 100 can determine whether there is an abnormality in the control target.
- the control device 100 includes an abnormality monitoring module 170 and a feature amount calculation module 176.
- the abnormality monitoring module 170 corresponds to the abnormality monitoring unit, and determines the presence or absence of an abnormality in the control target for each frame defined based on the first process value related to the control target.
- the feature amount calculation module 176 corresponds to a feature amount calculation unit, calculates a feature amount for each frame based on a second process value related to a control target in each frame, and outputs the calculated feature amount to the abnormality monitoring module 170.
- the abnormality monitoring module 170 is configured such that, when the feature amount for each frame is input from the feature amount calculation module 176, a monitoring result including a determination result of the presence or absence of an abnormality in the control target is output for each frame.
- the control device 100 further includes an internal database (hereinafter, also referred to as “internal DB 130”) and a data transmission module 134.
- internal DB 130 an internal database
- data transmission module 134 a data transmission module
- the internal DB 130 corresponds to a storage unit, and stores data relating to processing by the abnormality monitoring module 170 and the feature amount calculation module 176.
- the data transmission module 134 corresponds to a data transmission unit, and transmits data stored in the internal DB 130 to the outside.
- the internal DB 130 stores analysis data 182, feature amount data 184, and monitoring result data 186.
- the data transmission module 134 can transmit these data stored in the internal DB 130.
- the analysis data 182 corresponds to the first data, and includes time-series data of the first process value and the second process value.
- the feature data 184 corresponds to the second data, and includes time-series data of the feature calculated by the feature calculation module 176 for each frame.
- the monitoring result data 186 includes time-series data of the monitoring result output by the abnormality monitoring module 170.
- the feature is associated with a first process value that defines a frame corresponding to each feature.
- the monitoring result is associated with a first process value that defines a frame corresponding to each monitoring result.
- the second process value, the feature amount, and the monitoring result corresponding to each frame are used by using the first process value. Can be associated with each other.
- the “process value” is a general term for data handled by the control device 100, and is input information obtained from the control target, output information output to the control target, operating state of the control device. And internal information used for control calculations in the control device.
- the control device 100 employs a variable programming environment, and the description will be made assuming that “variable” refers to any process value.
- the technical scope of the present invention is not limited to the environment of variable programming, but may be a format in which a memory address or the like where a process value is stored is directly specified.
- FIG. 2 is a schematic diagram showing an example of the overall configuration of the control system 1 according to the present embodiment.
- control system 1 includes, as main components, control device 100 for controlling a control target, server device 200, and display device 300.
- the control device 100 may be embodied as a kind of computer such as a PLC.
- the control device 100 is connected to the field device group 10 via the field network 2 and to one or a plurality of display devices 300 via the field network 4. Further, the control device 100 is connected to the server device 200 via the local network 6.
- the control device 100 exchanges data with connected devices via respective networks.
- the control device 100 executes a control operation for controlling equipment or a machine to be controlled.
- the control device 100 has a collection function of collecting process values measured by the field device group 10 and transferred to the control device 100 when executing the control calculation. Further, the control device 100 has an abnormality monitoring function for monitoring the presence or absence of an abnormality based on the collected process values.
- the internal DB 130 mounted on the control device 100 provides a collection function
- the machine learning engine 140 mounted on the control device 100 provides an abnormality monitoring function. Details of the internal DB 130 and the machine learning engine 140 will be described later.
- the field network 2 and the field network 4 adopt an industrial network.
- industrial networks EtherCAT (registered trademark), EtherNet / IP (registered trademark), DeviceNet (registered trademark), CompoNet (registered trademark), and the like are known.
- the field device group 10 includes devices that collect process values from equipment, machines, and the like to be controlled (hereinafter, also collectively referred to as “fields”). As an apparatus for collecting such a process value, an input relay, various sensors, and the like are assumed. The field device group 10 further includes a device that gives some action to the field based on the command value generated by the control device 100. An output relay, a contactor, a servo driver, a servo motor, or any other actuator is assumed as a device that exerts some action on such a field. These field device groups 10 exchange data including process values and command values with the control device 100 via the field network 2.
- the field device group 10 includes a remote I / O (Input / Output) device 12, a relay group 14, an image sensor 18, a camera 20, a servo driver 22, and a servo motor 24. Including. However, it is not necessary to arrange all of these field devices.
- the remote I / O device 12 communicates via the field network 2 and an input / output unit (hereinafter, also referred to as an “I / O unit”) for acquiring a process value and outputting a command value. And Process values and command values are exchanged between the control device 100 and the field via such an I / O unit.
- FIG. 2 shows an example in which digital signals are exchanged as process values and command values via the relay group 14.
- the I / O unit may be directly connected to the field network.
- FIG. 2 shows an example in which the I / O unit 16 is directly connected to the field network 2.
- the image sensor 18 performs image measurement processing such as pattern matching on the image data captured by the camera 20, and transmits the processing result to the control device 100.
- the servo driver 22 drives the servo motor 24 according to a command value (for example, a position command) from the control device 100.
- a command value for example, a position command
- the display device 300 connected to the control device 100 via the field network 4 receives a user's operation, transmits a command corresponding to the user's operation, and the like to the control device 100, and performs an operation in the control device 100. Display the results graphically.
- the server device 200 is connected to the control device 100 via the local network 6, and exchanges necessary data with the control device 100.
- results are transmitted from control device 100 to server device 200. That is, server device 200 receives data from control device 100.
- the local network 6 may be implemented with a general-purpose protocol such as Ethernet (registered trademark). That is, the data transmission cycle or update cycle in the local network 6 may be slower than the data transmission cycle or update cycle in the field network (the field network 2 and the field network 4). However, the local network 6 may be able to transmit more data at one time than the field network.
- Ethernet registered trademark
- Example of hardware configuration of control device 100> Next, an example of a hardware configuration of the control device 100 configuring the control system 1 according to the present embodiment will be described.
- FIG. 3 is a block diagram illustrating a hardware configuration example of the control device 100 included in the control system 1 according to the present embodiment.
- control device 100 includes a processor 102 such as a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit), a chipset 104, a main storage device 106, a secondary storage device 108, , A local network controller 110, a USB (Universal Serial Bus) controller 112, a memory card interface 114, an internal bus controller 122, field bus controllers 118 and 120, and local I / O units 124-1, 124-2,... And a timer 126.
- processor 102 such as a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit)
- chipset 104 such as a central processing unit (Central Processing Unit) or an MPU (Micro-Processing Unit)
- main storage device 106 such as a main storage device 106, a secondary storage device 108, ,
- the processor 102 reads out various programs stored in the secondary storage device 108, expands and executes the programs in the main storage device 106, and thereby realizes control according to a control target and various processes described below. .
- the chipset 104 controls the processor 102 and each component to realize processing of the control device 100 as a whole.
- the secondary storage device 108 stores, in addition to the system program, a control program that operates on an execution environment provided by the system program. Further, the secondary storage device 108 also stores a system program for implementing the internal DB 130 and the machine learning engine 140.
- the local network controller 110 controls data exchange with other devices via the local network 6.
- the USB controller 112 controls exchange of data with a support device via a USB connection.
- the memory card interface 114 is configured so that the memory card 116 can be attached and detached, so that data can be written to the memory card 116 and various data (including the above-described results) can be read from the memory card 116. ing.
- the fieldbus controller 118 controls data exchange with other devices via the field network 2.
- the fieldbus controller 120 controls data exchange with other devices via the field network 4.
- the internal bus controller 122 is an interface for exchanging data with the local I / O units 124-1, 124-2,... Mounted on the control device 100.
- the timer 126 manages timing for synchronizing processing between the local I / O units 124-1, 124-2,... And devices connected via the field network 2 or the field network 4. Further, the timer 126 may manage time information as described later.
- FIG. 3 illustrates a configuration example in which the processor 102 provides necessary functions by executing a program.
- some or all of the provided functions may be replaced by a dedicated hardware circuit (for example, an ASIC). (Application Specific Integrated Circuit) or FPGA (Field-Programmable Gate Array) or the like.
- the main part of the control device 100 may be realized using hardware that conforms to a general-purpose architecture (for example, an industrial personal computer based on a general-purpose personal computer).
- a plurality of OSs (Operating Systems) having different applications may be executed in parallel using virtualization technology, and a required application may be executed on each OS.
- OSs Operating Systems
- FIG. 4 is a block diagram illustrating a functional configuration example of the control device 100 included in the control system 1 according to the present embodiment.
- control device 100 includes an OS 150 and a scheduler 152 executed on OS 150.
- the scheduler 152 controls the execution timing of the functions of the control device 100 and the like. More specifically, the scheduler 152 manages the cyclic update of the variable by the variable manager 154 and the cyclic execution of the control program 160.
- the variable manager 154 manages data updated by the I / O refresh processing cyclically executed by the control device 100 as variables.
- the variables managed by the variable manager 154 include a system variable 156 including a data group indicating an operation state of each unit of the control device 100, and a user variable / device including a variable managed by the control program 160 and a process value to be controlled. Includes variable 158.
- the control program 160 corresponds to a user program that can be arbitrarily created by the user, and typically includes a sequence program 162 and a motion program 164.
- the instructions of the programs constituting the control program 160 may be described as an integrated program, or may be separately described in a plurality of programs.
- the control device 100 includes an abnormality monitoring module 170 and a feature amount calculation module 176 for the machine learning engine 140.
- the feature amount calculation module 176 cyclically calculates the feature amount using the designated variables of the user variables and the device variables 158 according to the feature amount calculation method designated in advance.
- the abnormality monitoring module 170 calculates a monitoring score, which is a degree indicating the possibility of abnormality, based on the feature amount of each frame, and determines whether there is an abnormality in the control target based on the magnitude of the calculated monitoring score. . More specifically, the abnormality monitoring module 170 refers to the learning data 172 prepared in advance, and based on the characteristic amount calculated by the characteristic amount calculating module 176, the degree of indicating the possibility of abnormality (hereinafter, “ Also referred to as “monitoring score”). The abnormality monitoring module 170 compares the calculated monitoring score with a threshold value 174, which is a judgment value of abnormality monitoring prepared in advance, to determine whether there is an abnormality. When detecting the abnormality, the abnormality monitoring module 170 notifies the control program 160 and the data writing module 132 of the detection.
- a monitoring score which is a degree indicating the possibility of abnormality
- the learning data 172 includes the feature amount of the equipment or machine to be monitored for abnormality when the equipment is normal.
- the abnormality monitoring module 170 calculates a monitoring score based on the degree of deviation between the feature calculated by the feature calculation module 176 and the feature included in the learning data 172 at the time of normality.
- the control device 100 includes a data writing module 132 and a data transmission module 134 for the internal DB 130.
- the data writing module 132 writes various data generated inside the control device 100 into the internal DB 130.
- the internal DB 130 may be realized using a part of the data area provided by the main storage device 106 (see FIG. 3) of the control device 100, or may be realized by using the secondary storage device 108 (see FIG. 3) of the control device 100. It may be realized using a part of the data area provided, or may be realized using a part of the data area provided by the memory card 116 (see FIG. 3) attached to the memory card interface 114. Further, it may be realized by using a part of a data area provided by another storage medium (not shown).
- the internal DB 130 stores raw data 180, analysis data 182, feature data 184, and monitoring result data 186.
- the raw data 180 includes time-series data of one or more specific process values (typically, device variables).
- the raw data 180 preferably includes time-series data of variables used by the feature value calculation module 176 to calculate the feature values.
- the time-series data included in the raw data 180 is preferably data for each cycle of the I / O refresh processing.
- the analysis data 182 includes information such as an event occurrence time for specifying a period to be monitored for abnormality.
- the feature amount data 184 includes time-series data of the feature amount calculated by the feature amount calculation module 176.
- the time-series data included in the feature amount data 184 is preferably data for each cycle of the I / O refresh processing, like the time-series data included in the raw data 180.
- the monitoring result data 186 includes a result of the abnormality monitoring module 170 determining whether or not there is an abnormality.
- the data transmission module 134 transmits the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186 stored in the internal DB 130 according to a predetermined condition or in response to some request. Part or all of them are transmitted to the outside (typically, the server device 200 shown in FIG. 2) as result results.
- the data transmission module 134 transmits the result to the outside, so that the operation state and suitability of the abnormality monitoring function in the control device 100 can be evaluated ex post facto.
- the result of the result transmitted to the display device 300 can be analyzed using the analysis device 400 or the like.
- the analysis by the analysis device 400 enables the type of the feature amount used for the abnormality monitoring, the threshold value, the update of the learning data, and the like.
- the data transmission module 134 transmits the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186 stored in the internal DB 130 to the outside of the server device 200 or the like.
- the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186 may be stored as files for each predetermined time length or for each predetermined size.
- the data transmission module 134 transmits each file sequentially or collectively to the outside.
- a text format such as a CSV (Comma-Separated Value) format or an XML (extensible markup language) format is adopted.
- a binary format may be adopted. When the binary format is used, data compressed by a known compression method may be used.
- the data transmission module 134 may transmit the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186 in a CSV format.
- Known communication protocols for the data transmission module 134 to transmit data to the outside such as HTTP (Hypertext Transfer Protocol), HTTPS (Hypertext Transfer Protocol Secure), FTP (File Transfer Protocol), and SMB (Server Message Block).
- Communication protocol can be adopted. That is, the data transmission module 134 transmits data using at least one communication protocol among HTTP, HTTPS, FTP, and SMB.
- the communication protocol employed by the data transmission module 134 is not limited to the above-described one, and any communication protocol may be used as long as data can be transmitted. Adopting a communication protocol developed in the future can also be included in the technical scope of the present invention.
- a certificate necessary for realizing secure communication may be obtained in advance, or may be obtained from an authentication server or the like.
- the data transmission module 134 may transmit the target data to the outside according to predetermined conditions or settings (active transmission), or transmit the requested data in response to a request from the outside. (Passive transmission / on-demand transmission).
- the creation of a file may be used as the transmission start condition, or the creation of a file of a predetermined number or the cumulative size may be used as the transmission start condition.
- the target files may be transmitted sequentially according to a predetermined rule, or may be transmitted collectively.
- the data transmission module 134 may have a server function such as a Web server or an FTP server.
- control program 160 is cyclically executed at a predetermined cycle, and the data transmission module 134 transmits data at a timing and frequency that does not hinder the cyclic execution of the control program 160. You may.
- FIG. 5 is a schematic diagram showing an application example of the abnormality monitoring function of control device 100 according to the present embodiment.
- FIG. 5 shows a packaging machine 600 as a target of abnormality monitoring.
- packaging machine 600 sequentially seals and / or cuts package body 604 conveyed in a predetermined conveyance direction by a pair of rotors.
- the packaging machine 600 has a pair of rotors 610 and 620, and the rotors 610 and 620 rotate in synchronization.
- Each rotor is arranged such that the tangential direction of the outer periphery at the position in contact with the package 604 matches the transport direction.
- Each rotor is provided with a heater and a cutter at predetermined positions. When the heater and the cutter come into contact with the package 604, a sealing process and a cutting process for the package 604 are realized.
- the rotors 610 and 620 of the packaging machine 600 are rotationally driven by the two servomotors 24 around the rotation shafts 612 and 622, respectively.
- Processing mechanisms 614 and 624 are provided on the surfaces of the rotors 610 and 620, respectively.
- the processing mechanism 614 includes heaters 615 and 616 disposed in front and rear in the circumferential direction (rotation direction), a heater 615 and a heater 615. 616 and a cutter 617 disposed therebetween.
- the processing mechanism 624 includes heaters 625 and 626 disposed in the circumferential direction and a cutter 627 disposed between the heaters 625 and 626.
- the rotors 610 and 620 include cutters 617 and 627 disposed on the outer peripheral surface thereof for cutting the package 604.
- the surfaces (upper surface and lower surface) facing each other (upper surface and lower surface) at the right side of the paper surface of the package 604 are sealed (adhered) by the heaters 615 and 625.
- the opposing surfaces (upper surface and lower surface) of the package 604 are sealed (adhered) by the heater 616 and the heater 626 at the position on the left side of the paper surface of the package 604.
- the package 604 is cut by the cutter 617 and the cutter 627.
- the two servo motors 24 that rotate the rotors 610 and 620 are controlled in rotational speed and torque by the respective servo drivers 22.
- the control device 100 can collect the process values of the servo motor 24, that is, the actual values of the rotors 610 and 620, from the servo driver 22.
- the process values of the servo driver 22 include (1) rotational position (phase / rotation angle), (2) speed, (3) acceleration, (4) torque value, and (5) ) Current value, (6) voltage value, and the like.
- ⁇ As an abnormality occurring in the packaging machine 600, it is assumed that a foreign substance is caught or the like.
- the foreign substance can be caught by the displacement of the package 604 itself, the displacement of the packaged object 605 included in the package 604, and the like.
- a larger torque is generated in the two servomotors 24 that rotationally drive the rotors 610 and 620.
- the occurrence of a foreign object bite is detected.
- FIG. 6 is a schematic view showing an example of a frame and a sub-frame set in the packaging machine 600 shown in FIG. FIG. 6 shows the time change of the rotation angle of the rotors 610 and 620.
- the packaging machine 600 it is determined for each of the packaging bodies 604 whether or not foreign matter has been caught.
- one rotation of the rotors 610 and 620 is set in a time section (hereinafter, also referred to as a "frame") that defines one monitoring target. Can be set.
- a time section hereinafter, also referred to as a "frame”
- the presence or absence of foreign matter biting is determined not by the process value of the entire time section of the frame but by the process value of the partial section where the heater and the cutter contact the package 604. is important. Therefore, a time section in which a process value used for abnormality monitoring should be collected (in the packaging machine 600, a time section before and after the heater and the cutter reach the lowest point) can be set in the frame. Such a partial section is also referred to as a “subframe”.
- frame is used as a term indicating a unit time section (or a unit period) to be monitored for abnormality.
- sub-frame is used as a term indicating a partial time interval (or a partial period) for calculating a feature amount used for abnormality monitoring in a corresponding “frame”.
- a plurality of different subframes can be set in a frame. That is, when a plurality of process values are used for abnormality monitoring, monitoring accuracy can be further improved by setting subframes corresponding to each process value.
- FIG. 7 is a schematic diagram showing the processing content of the abnormality monitoring function of control device 100 according to the present embodiment.
- a feature amount is calculated based on a temporal change of a process value of a subframe set in the frame.
- the feature amounts 1 and 2 are calculated based on the time change of the process values of the subframe 1 and the subframe 2 respectively set with respect to the time change of the two process values.
- the characteristic amount calculation module 176 of the control device 100 determines the characteristic based on the time change of one or a plurality of process values in the sub-frame defined based on another process value related to the control target in each frame. Calculate the amount.
- both the feature values 1 and 2 are scalar values (one-dimensional values)
- the corresponding positions (feature value vectors) can be plotted on the two-dimensional coordinates composed of the feature values 1 and 2.
- the learning data 172 includes a group of feature amounts (feature amount vectors) in a normal state, and a monitoring score is calculated based on the degree of deviation from the group of these feature amounts. Then, the presence or absence of an abnormality is determined by comparing the calculated monitoring score with a threshold value 174 prepared in advance.
- the control device 100 has the above-described abnormality monitoring function, and the data transmitted by the data transmission module 134 has a data structure that allows the monitoring result by the abnormality monitoring function of the control device 100 to be evaluated afterwards. Adopted.
- FIG. 8 is a schematic diagram for explaining an outline of data collection and data management in control device 100 according to the present embodiment.
- device event is identification information for specifying a target of abnormality monitoring. For example, assume that a maximum of 128 device events can be set. The maximum set number of device events can be appropriately designed according to the resources of the control device 100 and the like.
- Each device event is associated with one of the preset “frames”. That is, in each device event, the presence or absence of an abnormality is determined for each specific frame.
- a plurality of process values (a plurality of process values 1, 2,..., 16 in the example shown in FIG. 8) are associated with each device event. For each process value, a specific subframe associated with the corresponding frame is set. Note that different subframes may be set for the same frame for each process value.
- FIG. 9 is a diagram schematically showing the structure of data management in control device 100 according to the present embodiment.
- data definition set 510 is set for each device event.
- the data definition set 510 for each device event includes the definition of a frame variable 512, an output frame variable 514 of a feature value, and an output frame variable 530 of a monitoring result.
- the frame variable 512 specifies a variable name that is a reference destination of information used for specifying a frame to be subjected to the abnormality monitoring function.
- the start and end of the target frame are specified based on the value (process value) of a variable defined as the frame variable 512 or its change.
- the feature frame output frame variable 514 is a variable used for associating the calculated feature with the frame.
- the variable defined as the output frame variable 514 of the feature value stores the value of the corresponding frame variable 512 in addition to the calculation of the feature value.
- the output frame variable 530 of the monitoring result is a variable used for associating the monitoring result (a calculated monitoring score or the like) with the frame.
- the value of the corresponding frame variable 512 is stored together with the output of the monitoring result.
- the data definition set 510 for each device event further includes a plurality of feature amount definition sets 520.
- Each of the feature amount definition sets 520 defines a feature amount calculation method used to calculate a monitoring score. More specifically, each of the feature quantity definition sets 520 includes a feature quantity definition 522, a process value 524, and a definition of a subframe variable 526.
- the feature amount definition 522 specifies the type of the feature amount to be calculated (for example, the maximum value, the minimum value, the average value, and the like in a frame).
- the process value 524 defines a variable name indicating a process value used for calculating a feature amount.
- the subframe variable 526 specifies a variable name that is a reference destination of information used to specify a subframe for calculating a feature amount.
- the feature value definition set 520 defines a feature value calculation target and a calculation method for calculating a monitoring score.
- the data definition set 510 for each device event further includes a monitoring result definition 540.
- the monitoring result definition 540 includes a definition regarding a monitoring score calculated based on a plurality of calculated feature amounts and an output destination of a determination result with respect to the monitoring score. More specifically, the monitoring result definition 540 includes a determination result definition 542 and a monitoring score definition 544.
- the determination result definition 542 specifies the destination where the determination result obtained by comparing the calculated monitoring score with the threshold value is stored.
- the monitoring score definition 544 specifies where the monitoring score calculated based on the plurality of feature amounts is stored.
- FIG. 10 is a schematic diagram for explaining an outline of data processing related to the abnormality monitoring function in control device 100 according to the present embodiment.
- a frame is specified based on a change in a value indicated by a frame variable (“AAAAA”, “BBBBB”,..., Etc.).
- A) As the frame variable for example, work identification information notified from an operation management server or the like may be used, or time information latched at the start of processing of a specific work may be used. You may.
- process values are collected cyclically during a period in which (c) a collection condition based on a subframe variable is enabled (typically, (c) a subframe variable is TRUE). Is done.
- the feature amount is calculated based on the process values collected in the frame. Along with the calculation of the feature value, (d) the output frame variable of the feature value, (a) the value indicated by the frame variable associated with the corresponding frame (“AAAAA”, “BBBBB”,..., Etc.) Is stored.
- the monitoring score is calculated, and (g) a monitoring result is output by comparing the calculated monitoring score value with the threshold value.
- the output frame variable of the monitoring result includes (a) the value indicated by the frame variable associated with the corresponding frame (“AAAAA”, “BBBBB”,..., Etc.) Is stored.
- the feature value and (g) the monitoring result are associated with the same value as the value indicated by the frame variable (a) associated with the frame in which the process value is collected ((d) the feature value). Output frame variable and (f) output frame variable of monitoring result).
- the feature amount and (g) the monitoring result are calculated after the time of the corresponding frame elapses. However, since information for specifying the corresponding frame is added, an ex-post analysis is performed. And evaluation can be easily realized.
- the data structure described below is adopted so that the relationship between the device event, the process value, the frame, and the subframe as shown in FIGS. 8 to 10 can be analyzed ex post facto.
- FIG. 11 is a schematic diagram showing an example of the result of the result transmitted from control device 100 according to the present embodiment.
- 11A shows an example of the data structure of the raw data 180
- FIG. 11B shows an example of the data structure of the analysis data 182
- FIG. 11C shows the data of the feature amount data 184
- FIG. 11D shows an example of the structure of the monitoring result data 186.
- the raw data 180 shown in FIG. 11A includes time-series data 1803 of process values collected in each collection cycle (I / O refresh processing cycle), which is associated with the index 1801 and the time stamp 1802.
- the index 1801 is information for specifying each record, and is a unique value arbitrarily assigned in the control device 100. Typically, the index 1801 is incremented or decremented every collection cycle. By using the value to be incremented or decremented, it can be determined whether or not data is missing.
- the time stamp 1802 is time information managed by the timer 126 (FIG. 3) of the control device 100.
- the value stored as the time stamp 1802 is shared with other data. Therefore, the value stored in the time stamp 1802 can be used as a common key and associated with other time-series data.
- the analysis data 182 shown in FIG. 11B is time-series data of the value indicated by the frame variable, which is collected for each collection cycle (I / O refresh processing cycle) and is associated with the index 1821 and the time stamp 1822. 1823, time-series data 1824 of a value indicated by a subframe variable, time-series data 1825 of a value indicated by a label variable, time-series data 1825 of a value indicated by a label variable, and time-series data 1826 of a process value. .
- the index 1821 is information for specifying each record, and is a unique value arbitrarily assigned in the control device 100.
- time stamp 1822 the same source information as the time stamp 1802 included in the raw data 180 of FIG. 11A is used.
- the analysis data 182 includes the time-series data of the process value defining the frame (the time-series data 1823 of the value indicated by the frame variable) and the time-series data of the process value defining the sub-frame (the sub-frame variable Includes time-series data 1824) of the value indicated by.
- the time series data 1825 of the value indicated by the ⁇ ⁇ label variable is additional information for facilitating subsequent analysis and evaluation, and includes a time change of the value indicated by the variable arbitrarily selected by the user.
- the process value time-series data 1826 is intended to be used for calculating a feature amount in any device event.
- the feature data 184 shown in FIG. 11C includes a feature calculation result 1843 for each device event, which is associated with the index 1841 and the time stamp 1842.
- the index 1841 is information for specifying each record, and is a unique value arbitrarily assigned in the control device 100.
- time stamp 1842 the same source information as the time stamp 1802 included in the raw data 180 in FIG. 11A is used.
- the feature amount calculation result 1843 for each device event includes a feature amount index 1844, time-series data 1845 of a value indicated by an output frame variable of the feature amount, and time-series data 1846 of each feature amount used for calculating a monitoring score. Including.
- the feature index 1844 stores information for identifying the calculated feature. Typically, identification information for specifying a device event using each feature amount is stored.
- the time-series data 1845 of the value indicated by the output frame variable of the feature value includes a value (corresponding frame variable value) for specifying the collection target section of the process value used for calculating the feature value.
- the time-series data 1846 of each feature used in the calculation of the monitoring score includes the time-series data of each feature included in the feature vector.
- the monitoring result data 186 shown in FIG. 11D includes the monitoring result 1863 for each device event, which is associated with the index 1861 and the time stamp 1862.
- the index 1861 is information for specifying each record, and is a unique value arbitrarily assigned in the control device 100.
- time stamp 1862 the same source information as the time stamp 1802 included in the raw data 180 of FIG. 11A is used.
- the monitoring result 1863 for each device event includes a device event index 1864, time-series data 1865 of the value indicated by the output frame variable of the monitoring result, time-series data 1866 of the determination result, and time-series data 1867 of the monitoring score. .
- the device event index 1864 stores identification information for specifying a target device event.
- the time-series data 1865 of the value indicated by the output frame variable of the monitoring result includes a value (a value of the corresponding frame variable) for specifying the collection section of the process value used for calculating the monitoring score.
- the time series data 1866 of the determination result includes the time series data of the determination result (a value indicating the presence or absence of an abnormality based on the monitoring score) determined by comparing the monitoring score with the threshold.
- the monitoring score time-series data 1867 includes the monitoring score time-series data cyclically calculated using the target feature amount.
- the monitoring result data 186 includes the monitoring score and the value indicating the presence or absence of the abnormality based on the monitoring score.
- each of the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186 includes indexes 1801, 1821, 1841, which are incremented or decremented for each record. 1861 is assigned to each record.
- each of the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186 is a time stamp managed by a timer 126 common to each record. 1802, 1822, 1842, and 1862. That is, the control device 100 adds the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data obtained by adding the time stamps 1802, 1822, 1842, and 1862 managed by the common timer 126 to each record. 186 is output.
- the time stamps 1802, 1822, 1842, and 1862 the time axis of the time-series data included in each data can be matched.
- the feature amount data 184 and the monitoring result data 186 include, as information for specifying the target frame, the value indicated by the frame variable included in the analysis data 182 in the target frame. By adopting such information, it is easy to analyze the feature amount and the monitoring result calculated with a delay with respect to the original process value.
- FIG. 12 is a diagram for describing an example of an analysis procedure using data transmitted from control device 100 according to the present embodiment.
- control device 100 determines that an abnormality has occurred at a certain timing.
- An example in which the cause of the determination of the abnormality and the suitability of the abnormality will be described.
- the value of the corresponding time section of the monitoring score time-series data 1867 may be acquired.
- a value corresponding to the time section specified as a verification target of the time-series data 1865 of the value indicated by the output frame variable of the monitoring result is acquired ((2) acquisition of the value of the corresponding frame variable).
- “CCCCC” is assumed.
- a time section indicating the same value as the previously acquired frame variable is identified from the time series data 1823 of the value indicated by the frame variable included in the analysis data 182. ((5) Identification of a time section showing the same value). Then, of the time-series data 1825 of the value indicated by the label variable, a value corresponding to the specified time section is acquired ((6) acquisition of a corresponding process value).
- a control device (100) for controlling a control target An abnormality monitoring unit (170) that determines, for each frame defined based on a first process value (1823) related to the control target, whether there is an abnormality in the control target;
- a feature value calculation unit (176) that calculates a feature value for each frame based on a second process value (1826) related to the control target in each frame and outputs the feature value to the abnormality monitoring unit;
- a storage unit (130) for storing data relating to processing by the abnormality monitoring unit and the feature amount calculation unit;
- the abnormality monitoring unit is configured to, when a feature amount for each frame is input from the feature amount calculation unit, output a monitoring result including a determination result of the presence or absence of an abnormality in the control target for each frame.
- the feature value (1846) is associated with the first process value (1845) that defines a frame corresponding to each feature value
- the control device wherein, in the third data, the monitoring result (1866, 1867) is associated with the first process value (1865) defining a frame corresponding to each monitoring result.
- the abnormality monitoring unit calculates a monitoring score, which is a degree indicating the possibility of abnormality, based on the feature amount of each frame, and determines whether there is an abnormality in the control target based on the magnitude of the calculated monitoring score. 3.
- the control device according to Configuration 1 [Configuration 3] The control device according to Configuration 2, wherein the monitoring result of the third data includes the monitoring score (1867) and a value (1866) indicating the presence or absence of an abnormality based on the monitoring score.
- the data transmission unit is further configured to be capable of transmitting fourth data (180) including time-series data of one or more specific process values. apparatus.
- the feature amount calculation unit calculates the feature amount based on a temporal change of the second process value in a subframe defined based on a third process value (1824) related to the control target in each frame. Is configured to calculate, The control device according to any one of Configurations 1 to 4, wherein the first data further includes time-series data of the third process value.
- the control device according to any one of claims 1 to 7.
- the feature value (1846) is associated with the first process value (1845) that defines a frame corresponding to each feature value
- the control system wherein, in the third data, the monitoring result (1866, 1867) is associated with the first process value (1865) that defines a frame corresponding to each monitoring result.
- control device between analysis data 182, feature amount data 184, and monitoring result data 186 output from control device 100, a value indicated by a variable defining a frame By using a variable that defines such a frame as a common key and is stored in common, a monitoring result, a feature amount used to output the monitoring result, and a feature amount for calculating the feature amount.
- a variable that defines such a frame By using a variable that defines such a frame as a common key and is stored in common, a monitoring result, a feature amount used to output the monitoring result, and a feature amount for calculating the feature amount.
- Each time series data of the process value can be easily associated.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
Provided is a configuration which makes it possible to analyze and verify an action after the fact in a control device and control system which make it possible to determine whether an abnormality is present in a control target. A data transmission unit is configured so as to be capable of transmitting: first data which includes time-series data of a first process value and a second process value; second data which includes time-series data of characteristics calculated for each frame by a characteristic calculation unit; and third data which includes time-series data of monitoring results outputted by an abnormality monitoring unit. The characteristics are associated with first process values which specify a frame corresponding to each characteristic in the second data. The monitoring results are associated with first process values which specify a frame corresponding to each monitoring result in the third data.
Description
本技術は、制御対象での異常の有無を判断できる制御装置および制御システムに関する。
[5] The present technology relates to a control device and a control system that can determine whether or not there is an abnormality in a control target.
様々な生産現場において、PLC(プログラマブルコントローラ)などの制御装置を用いたFA(Factory Automation)技術が広く普及している。近年の情報通信技術(ICT:Information and Communication Technology)の発展に伴って、このようなFA分野における制御装置もますます高性能化および高機能化している。
FAAt various production sites, FA (Factory Automation) technology using a control device such as a PLC (programmable controller) is widely used. With the recent development of ICT (Information and Communication Technology), such control devices in the FA field have been increasingly sophisticated and sophisticated.
このような技術発展に伴って、より多くの製造現場からの情報を活用することが提案されている。例えば、特開2004-062276号公報(特許文献1)は、工作機械・製造装置などの機器稼動情報、機器内部情報および工作機械の必要な測定を行うセンサなどの測定装置の測定情報等の機器情報の監視、機器のメンテナンスや生産管理などの効率化を目的とする機器情報収集配信装置などを開示する。
伴 っ With such technological development, it has been proposed to utilize information from more production sites. For example, Japanese Patent Application Laid-Open No. 2004-062276 (Patent Document 1) discloses equipment such as equipment operation information of a machine tool / manufacturing apparatus, internal information of the equipment, and measurement information of a measurement apparatus such as a sensor for performing necessary measurement of the machine tool. A device information collection / distribution device for the purpose of monitoring information, improving efficiency of device maintenance, production management, and the like is disclosed.
上述の特許文献1に開示される構成は、データセンタなどに収集される情報に基づいて、工作機械や製造装置自体の異常を判断する構成である。このような構成に対して、生産現場で生じる異常を即座に検知したいというニーズがある。
The configuration disclosed in Patent Document 1 described above is a configuration in which an abnormality in a machine tool or a manufacturing apparatus itself is determined based on information collected in a data center or the like. For such a configuration, there is a need to immediately detect an abnormality occurring at the production site.
このようなニーズに対して、制御装置自体で制御対象での異常の有無を判断可能な構成が提案されている。このような異常の有無を判断可能な制御装置を実現した場合には、事後的に制御装置での挙動を検証したい場合も生じ得る。上述の特許文献1に開示される構成では、このような挙動の検証を行うという目的を達することはできない。
に 対 し て In response to such needs, there has been proposed a configuration in which the control device itself can determine whether there is an abnormality in the control target. When a control device capable of determining the presence or absence of such an abnormality is realized, there may be a case where the behavior of the control device needs to be verified ex post facto. With the configuration disclosed in Patent Document 1 described above, the purpose of verifying such behavior cannot be achieved.
本技術は、制御対象での異常の有無を判断できる制御装置および制御システムにおける挙動を事後的に解析および検証できる構成を提供する。
(4) The present technology provides a configuration capable of ex-post analysis and verification of the behavior in a control device and a control system that can determine whether or not there is an abnormality in a control target.
本発明のある局面によれば、制御対象を制御する制御装置が提供される。制御装置は、制御対象に関連する第1のプロセス値に基づいて規定されるフレーム毎に、制御対象での異常の有無を判断する異常監視部と、各フレームにおける制御対象に関連する第2のプロセス値に基づいてフレーム毎に特徴量を算出して異常監視部へ出力する特徴量算出部と、異常監視部および特徴量算出部による処理に係るデータを格納する記憶部と、記憶部に格納されるデータを外部へ送信するデータ送信部とを含む。異常監視部は、特徴量算出部からフレーム毎の特徴量が入力されると、制御対象での異常の有無の判断結果を含む監視結果をフレーム毎に出力するように構成されている。データ送信部は、第1のプロセス値および第2のプロセス値の時系列データを含む第1のデータと、特徴量算出部によりフレーム毎に算出される特徴量の時系列データを含む第2のデータと、異常監視部により出力される監視結果の時系列データを含む第3のデータとを送信可能に構成されている。第2のデータにおいては、特徴量と、各特徴量に対応するフレームを規定する第1のプロセス値とが関連付けられている。第3のデータにおいては、監視結果と、各監視結果に対応するフレームを規定する第1のプロセス値とが関連付けられている。
According to an aspect of the present invention, a control device for controlling a control target is provided. The control device includes, for each frame defined based on the first process value related to the control target, an abnormality monitoring unit that determines whether there is an abnormality in the control target, and a second monitor related to the control target in each frame. A feature value calculation unit that calculates a feature value for each frame based on the process value and outputs the feature value to the abnormality monitoring unit; a storage unit that stores data relating to processing performed by the abnormality monitoring unit and the feature value calculation unit; and a storage unit that stores the data. And a data transmission unit for transmitting data to be transmitted to the outside. The abnormality monitoring unit is configured such that, when the feature amount for each frame is input from the feature amount calculation unit, a monitoring result including a determination result of the presence or absence of an abnormality in the control target is output for each frame. The data transmission unit includes first data including time-series data of the first process value and the second process value, and second data including time-series data of a feature calculated by the feature calculation unit for each frame. It is configured to be able to transmit data and third data including time-series data of the monitoring result output by the abnormality monitoring unit. In the second data, the feature value is associated with a first process value that defines a frame corresponding to each feature value. In the third data, the monitoring result is associated with a first process value that defines a frame corresponding to each monitoring result.
この局面によれば、第1のデータ、第2のデータ、第3のデータの各々においては、フレームを規定する第1のプロセス値が共通に関連付けられているので、それぞれのデータに含まれる特定のフレームに関連付けられる時系列データを容易に特定できる。
According to this aspect, in each of the first data, the second data, and the third data, the first process value that defines the frame is commonly associated with the first data, the second data, and the third data. The time series data associated with the frame can be easily specified.
好ましくは、異常監視部は、フレーム毎の特徴量に基づいて異常の可能性を示す度合いである監視スコアを算出し、当該算出した監視スコアの大きさに基づいて制御対象での異常の有無を判断する。
Preferably, the abnormality monitoring unit calculates a monitoring score, which is a degree indicating the possibility of abnormality, based on the feature amount of each frame, and determines whether there is an abnormality in the control target based on the magnitude of the calculated monitoring score. to decide.
この局面によれば、数値化された監視スコアの大きさおよび変化などに基づいて、制御装置による異常の発生との判断の事後的な評価を容易化できる。
According to this aspect, it is possible to easily perform the ex-post evaluation of the control device determining that an abnormality has occurred based on the magnitude and change of the digitized monitoring score.
好ましくは、第3のデータの監視結果は、監視スコアと、監視スコアに基づく異常の有無を示す値とを含む。
{Preferably, the monitoring result of the third data includes a monitoring score and a value indicating the presence or absence of an abnormality based on the monitoring score.
この局面によれば、監視スコアと、監視スコアに基づく異常の有無を示す値とが関連付けられているので、制御装置による異常の発生との判断の事後的な評価を容易化できる。
According to this aspect, since the monitoring score and the value indicating the presence or absence of the abnormality based on the monitoring score are associated with each other, it is possible to easily perform the ex-post evaluation of the control device determining that the abnormality has occurred.
好ましくは、データ送信部は、特定の1または複数のプロセス値の時系列データを含む第4のデータをさらに送信可能に構成されている。
Preferably, the data transmitting unit is configured to be able to further transmit fourth data including time-series data of one or more specific process values.
この局面によれば、特徴量を算出するために用いられたプロセス値の時系列データを確認することが容易化する。
According to this aspect, it is easy to confirm the time-series data of the process values used for calculating the feature amount.
好ましくは、特徴量算出部は、各フレーム内の制御対象に関連する第3のプロセス値に基づいて規定されるサブフレームにおける第2のプロセス値の時間変化に基づいて特徴量を算出するように構成されている。第1のデータは、第3のプロセス値の時系列データをさらに含む。
Preferably, the feature amount calculation unit calculates the feature amount based on a temporal change of a second process value in a subframe defined based on a third process value related to a control target in each frame. It is configured. The first data further includes time-series data of a third process value.
この局面によれば、フレーム内の特に異常の有無を判断するのに適したサブフレームで判断でき、その判断結果を事後的に評価することが容易化する。
According to this aspect, it is possible to make a determination in a sub-frame that is particularly suitable for determining the presence or absence of an abnormality in a frame, and it is easy to evaluate the determination result ex-post.
好ましくは、第1のデータ、第2のデータ、第3のデータの各々は、各レコードに共通のタイマで管理されるタイムスタンプが付与されている。
{Preferably, each of the first data, the second data, and the third data is provided with a time stamp managed by a common timer for each record.
この局面によれば、共通の時間軸で、第1のデータ、第2のデータ、第3のデータの間を比較できる。
According to this aspect, it is possible to compare the first data, the second data, and the third data on a common time axis.
好ましくは、第1のデータ、第2のデータ、第3のデータの各々は、レコード毎にインクリメントまたはデクリメントされるインデックスが各レコードに付与されている。
{Preferably, each of the first data, the second data, and the third data has an index that is incremented or decremented for each record.
この局面によれば、各データのレコードのうち、欠落しているレコードの有無を判断できる。
According to this aspect, it is possible to determine the presence or absence of a missing record among the records of each data.
好ましくは、データ送信部は、HTTP(Hypertext Transfer Protocol)、HTTPS(Hypertext Transfer Protocol Secure)、FTP(File Transfer Protocol)、および、SMB(Server Message Block)のうち、少なくとも1つの通信プロトコルでデータを送信する。
Preferably, the data transmission unit transmits the data using at least one communication protocol of HTTP (Hypertext Transfer Protocol), HTTPS (Hypertext Transfer Protocol Secure), FTP (File Transfer Protocol), and SMB (Server Message Block). I do.
この局面によれば、汎用的な通信プロトコルを利用できるので、各種の情報処理装置との間でデータを容易に遣り取りできる。
According to this aspect, since a general-purpose communication protocol can be used, data can be easily exchanged with various information processing apparatuses.
好ましくは、データ送信部は、第1のデータ、第2のデータ、第3のデータをCSV(Comma-Separated Values)形式で送信する。
{Preferably, the data transmitting section transmits the first data, the second data, and the third data in a CSV (Comma-Separated $ Values) format.
この局面によれば、汎用的なデータ形式を利用できるので、各種の情報処理装置において汎用的なアプリケーションを利用できる。
According to this aspect, since a general-purpose data format can be used, a general-purpose application can be used in various information processing apparatuses.
本発明の別の局面によれば、制御システムは、制御対象を制御する制御装置と、制御装置からのデータを受付けるサーバ装置とを含む。制御装置は、制御対象に関連する第1のプロセス値に基づいて規定されるフレーム毎に、制御対象での異常の有無を判断する異常監視部と、各フレームにおける制御対象に関連する第2のプロセス値に基づいてフレーム毎に特徴量を算出して異常監視部へ出力する特徴量算出部と、異常監視部および特徴量算出部による処理に係るデータを格納する記憶部と、記憶部に格納されるデータを外部へ送信するデータ送信部とを含む。異常監視部は、特徴量算出部からフレーム毎の特徴量が入力されると、制御対象での異常の有無の判断結果を含む監視結果をフレーム毎に出力するように構成されている。データ送信部は、第1のプロセス値および第2のプロセス値の時系列データを含む第1のデータと、特徴量算出部によりフレーム毎に算出される特徴量の時系列データを含む第2のデータと、異常監視部により出力される監視結果の時系列データを含む第3のデータとを送信可能に構成されている。第2のデータにおいては、特徴量と、各特徴量に対応するフレームを規定する第1のプロセス値とが関連付けられている。第3のデータにおいては、監視結果と、各監視結果に対応するフレームを規定する第1のプロセス値とが関連付けられている。
According to another aspect of the present invention, a control system includes a control device that controls a control target and a server device that receives data from the control device. The control device includes, for each frame defined based on the first process value related to the control target, an abnormality monitoring unit that determines whether there is an abnormality in the control target, and a second monitor related to the control target in each frame. A feature value calculation unit that calculates a feature value for each frame based on the process value and outputs the feature value to the abnormality monitoring unit; a storage unit that stores data relating to processing performed by the abnormality monitoring unit and the feature value calculation unit; and a storage unit that stores the data. And a data transmission unit for transmitting data to be transmitted to the outside. The abnormality monitoring unit is configured such that, when the feature amount for each frame is input from the feature amount calculation unit, a monitoring result including a determination result of the presence or absence of an abnormality in the control target is output for each frame. The data transmission unit includes first data including time-series data of the first process value and the second process value, and second data including time-series data of a feature calculated by the feature calculation unit for each frame. It is configured to be able to transmit data and third data including time-series data of the monitoring result output by the abnormality monitoring unit. In the second data, the feature value is associated with a first process value that defines a frame corresponding to each feature value. In the third data, the monitoring result is associated with a first process value that defines a frame corresponding to each monitoring result.
この局面によれば、第1のデータ、第2のデータ、第3のデータの各々においては、フレームを規定する第1のプロセス値が共通に関連付けられているので、それぞれのデータに含まれる特定のフレームに関連付けられる時系列データを容易に特定できる。
According to this aspect, in each of the first data, the second data, and the third data, the first process value that defines the frame is commonly associated with the first data, the second data, and the third data. The time series data associated with the frame can be easily specified.
本技術によれば、制御対象での異常の有無を判断できる制御装置および制御システムにおける挙動を事後的に解析および検証できる。
According to the present technology, it is possible to analyze and verify the behavior of the control device and the control system that can determine the presence / absence of an abnormality in the control target after the fact.
本発明の実施の形態について、図面を参照しながら詳細に説明する。なお、図中の同一または相当部分については、同一符号を付してその説明は繰返さない。
Embodiments of the present invention will be described in detail with reference to the drawings. The same or corresponding parts in the drawings have the same reference characters allotted, and description thereof will not be repeated.
<A.適用例>
まず、本発明が適用される場面の一例について説明する。図1は、本実施の形態に係る制御システム1を構成する制御装置100の機能構成の概要を示す模式図である。図1を参照して、制御装置100は、任意の設備または機械を含む制御対象を制御する。制御装置100は、PLC(プログラマブルコントローラ)などを採用できる。 <A. Application example>
First, an example of a scene to which the present invention is applied will be described. FIG. 1 is a schematic diagram illustrating an outline of a functional configuration of acontrol device 100 included in a control system 1 according to the present embodiment. Referring to FIG. 1, control device 100 controls a control target including an arbitrary facility or machine. The control device 100 can employ a PLC (programmable controller) or the like.
まず、本発明が適用される場面の一例について説明する。図1は、本実施の形態に係る制御システム1を構成する制御装置100の機能構成の概要を示す模式図である。図1を参照して、制御装置100は、任意の設備または機械を含む制御対象を制御する。制御装置100は、PLC(プログラマブルコントローラ)などを採用できる。 <A. Application example>
First, an example of a scene to which the present invention is applied will be described. FIG. 1 is a schematic diagram illustrating an outline of a functional configuration of a
制御装置100は、制御対象での異常の有無を判断できる。このような機能を提供するための機能構成として、制御装置100は、異常監視モジュール170と、特徴量算出モジュール176とを含む。
(4) The control device 100 can determine whether there is an abnormality in the control target. As a functional configuration for providing such a function, the control device 100 includes an abnormality monitoring module 170 and a feature amount calculation module 176.
異常監視モジュール170は、異常監視部に相当し、制御対象に関連する第1のプロセス値に基づいて規定されるフレーム毎に、制御対象での異常の有無を判断する。特徴量算出モジュール176は、特徴量算出部に相当し、各フレームにおける制御対象に関連する第2のプロセス値に基づいてフレーム毎に特徴量を算出して異常監視モジュール170へ出力する。異常監視モジュール170は、特徴量算出モジュール176からフレーム毎の特徴量が入力されると、制御対象での異常の有無の判断結果を含む監視結果をフレーム毎に出力するように構成されている。
(4) The abnormality monitoring module 170 corresponds to the abnormality monitoring unit, and determines the presence or absence of an abnormality in the control target for each frame defined based on the first process value related to the control target. The feature amount calculation module 176 corresponds to a feature amount calculation unit, calculates a feature amount for each frame based on a second process value related to a control target in each frame, and outputs the calculated feature amount to the abnormality monitoring module 170. The abnormality monitoring module 170 is configured such that, when the feature amount for each frame is input from the feature amount calculation module 176, a monitoring result including a determination result of the presence or absence of an abnormality in the control target is output for each frame.
さらに、制御装置100は、内部データベース(以下、「内部DB130」とも記す。)およびデータ送信モジュール134を有している。
The control device 100 further includes an internal database (hereinafter, also referred to as “internal DB 130”) and a data transmission module 134.
内部DB130は、記憶部に相当し、異常監視モジュール170および特徴量算出モジュール176による処理に係るデータを格納する。データ送信モジュール134は、データ送信部に相当し、内部DB130に格納されるデータを外部へ送信する。
The internal DB 130 corresponds to a storage unit, and stores data relating to processing by the abnormality monitoring module 170 and the feature amount calculation module 176. The data transmission module 134 corresponds to a data transmission unit, and transmits data stored in the internal DB 130 to the outside.
より具体的には、内部DB130には、分析用データ182と、特徴量データ184と、監視結果データ186とが格納される。データ送信モジュール134は、内部DB130に格納されるこれらのデータを送信可能になっている。
More specifically, the internal DB 130 stores analysis data 182, feature amount data 184, and monitoring result data 186. The data transmission module 134 can transmit these data stored in the internal DB 130.
分析用データ182は、第1のデータに相当し、第1のプロセス値および第2のプロセス値の時系列データを含む。特徴量データ184は、第2のデータに相当し、特徴量算出モジュール176によりフレーム毎に算出される特徴量の時系列データを含む。監視結果データ186は、異常監視モジュール170により出力される監視結果の時系列データを含む。
The analysis data 182 corresponds to the first data, and includes time-series data of the first process value and the second process value. The feature data 184 corresponds to the second data, and includes time-series data of the feature calculated by the feature calculation module 176 for each frame. The monitoring result data 186 includes time-series data of the monitoring result output by the abnormality monitoring module 170.
特徴量データ184においては、特徴量と、各特徴量に対応するフレームを規定する第1のプロセス値とが関連付けられている。同様に、監視結果データ186においては、監視結果と、各監視結果に対応するフレームを規定する第1のプロセス値とが関連付けられている。
In the feature data 184, the feature is associated with a first process value that defines a frame corresponding to each feature. Similarly, in the monitoring result data 186, the monitoring result is associated with a first process value that defines a frame corresponding to each monitoring result.
このように、それぞれのデータの間で、共通の第1のプロセス値が関連付けられているので、第1のプロセス値を用いて、各フレームに対応する第2のプロセス値、特徴量、監視結果を互いに関連付けることができる。
As described above, since the common first process value is associated with each data, the second process value, the feature amount, and the monitoring result corresponding to each frame are used by using the first process value. Can be associated with each other.
本明細書において、「プロセス値」は、制御装置100で扱われるデータを総称する湯王後であり、制御対象から取得される入力情報、制御対象へ出力される出力情報、制御装置の動作状態を示す状態情報、制御装置での制御演算に使用される内部情報などを包含する。典型例として、本実施の形態に係る制御装置100では、変数プログラミングの環境を採用しており、「変数」は、いずれかのプロセス値を参照するものとして説明を行う。但し、本発明の技術的範囲は、変数プログラミングの環境に限られず、プロセス値が格納されるメモリアドレスなどを直接指定するような形式であってもよい。
In the present specification, the “process value” is a general term for data handled by the control device 100, and is input information obtained from the control target, output information output to the control target, operating state of the control device. And internal information used for control calculations in the control device. As a typical example, the control device 100 according to the present embodiment employs a variable programming environment, and the description will be made assuming that “variable” refers to any process value. However, the technical scope of the present invention is not limited to the environment of variable programming, but may be a format in which a memory address or the like where a process value is stored is directly specified.
<B.制御システムの全体構成例>
まず、本実施の形態に係る制御装置を含む制御システム1の全体構成例について説明する。 <B. Example of overall configuration of control system>
First, an example of the overall configuration of thecontrol system 1 including the control device according to the present embodiment will be described.
まず、本実施の形態に係る制御装置を含む制御システム1の全体構成例について説明する。 <B. Example of overall configuration of control system>
First, an example of the overall configuration of the
図2は、本実施の形態に係る制御システム1の全体構成例を示す模式図である。図2を参照して、本実施の形態に係る制御システム1は、主たる構成要素として、制御対象を制御する制御装置100と、サーバ装置200と、表示装置300とを含む。
FIG. 2 is a schematic diagram showing an example of the overall configuration of the control system 1 according to the present embodiment. Referring to FIG. 2, control system 1 according to the present embodiment includes, as main components, control device 100 for controlling a control target, server device 200, and display device 300.
制御装置100は、PLCなどの一種のコンピュータとして具現化されてもよい。制御装置100は、フィールドネットワーク2を介してフィールド装置群10と接続されるとともに、フィールドネットワーク4を介して1または複数の表示装置300と接続される。さらに、制御装置100は、ローカルネットワーク6を介してサーバ装置200に接続される。制御装置100は、それぞれのネットワークを介して、接続された装置との間でデータを遣り取りする。
The control device 100 may be embodied as a kind of computer such as a PLC. The control device 100 is connected to the field device group 10 via the field network 2 and to one or a plurality of display devices 300 via the field network 4. Further, the control device 100 is connected to the server device 200 via the local network 6. The control device 100 exchanges data with connected devices via respective networks.
制御装置100は、制御対象である設備や機械を制御するための制御演算を実行する。制御装置100は、制御演算を実行するにあたって、フィールド装置群10にて計測され、制御装置100へ転送されるプロセス値を収集する収集機能を有している。さらに、制御装置100は、収集したプロセス値に基づく異常の有無を監視する異常監視機能を有している。
(4) The control device 100 executes a control operation for controlling equipment or a machine to be controlled. The control device 100 has a collection function of collecting process values measured by the field device group 10 and transferred to the control device 100 when executing the control calculation. Further, the control device 100 has an abnormality monitoring function for monitoring the presence or absence of an abnormality based on the collected process values.
具体的には、制御装置100に実装される内部DB130が収集機能を提供し、制御装置100に実装される機械学習エンジン140が異常監視機能を提供する。内部DB130および機械学習エンジン140の詳細については後述する。
{Specifically, the internal DB 130 mounted on the control device 100 provides a collection function, and the machine learning engine 140 mounted on the control device 100 provides an abnormality monitoring function. Details of the internal DB 130 and the machine learning engine 140 will be described later.
フィールドネットワーク2およびフィールドネットワーク4は、産業用ネットワークを採用することが好ましい。このような産業用ネットワークとしては、EtherCAT(登録商標)、EtherNet/IP(登録商標)、DeviceNet(登録商標)、CompoNet(登録商標)などが知られている。
It is preferable that the field network 2 and the field network 4 adopt an industrial network. As such industrial networks, EtherCAT (registered trademark), EtherNet / IP (registered trademark), DeviceNet (registered trademark), CompoNet (registered trademark), and the like are known.
フィールド装置群10は、制御対象である設備や機械など(以下、「フィールド」とも総称する。)からプロセス値を収集する装置を含む。このようなプロセス値を収集する装置としては、入力リレーや各種センサなどが想定される。フィールド装置群10は、さらに、制御装置100にて生成される指令値に基づいて、フィールドに対して何らかの作用を与える装置を含む。このようなフィールドに対して何らかの作用を与える装置としては、出力リレー、コンタクタ、サーボドライバおよびサーボモータ、その他任意のアクチュエータが想定される。これらのフィールド装置群10は、フィールドネットワーク2を介して、制御装置100との間で、プロセス値および指令値を含むデータを遣り取りする。
The field device group 10 includes devices that collect process values from equipment, machines, and the like to be controlled (hereinafter, also collectively referred to as “fields”). As an apparatus for collecting such a process value, an input relay, various sensors, and the like are assumed. The field device group 10 further includes a device that gives some action to the field based on the command value generated by the control device 100. An output relay, a contactor, a servo driver, a servo motor, or any other actuator is assumed as a device that exerts some action on such a field. These field device groups 10 exchange data including process values and command values with the control device 100 via the field network 2.
図2に示す構成例においては、フィールド装置群10は、リモートI/O(Input/Output)装置12と、リレー群14と、画像センサ18およびカメラ20と、サーボドライバ22およびサーボモータ24とを含む。但し、これらのフィールド装置のすべてを配置する必要はない。
In the configuration example shown in FIG. 2, the field device group 10 includes a remote I / O (Input / Output) device 12, a relay group 14, an image sensor 18, a camera 20, a servo driver 22, and a servo motor 24. Including. However, it is not necessary to arrange all of these field devices.
リモートI/O装置12は、フィールドネットワーク2を介して通信を行う通信部と、プロセス値の取得および指令値の出力を行うための入出力部(以下、「I/Oユニット」とも称す。)とを含む。このようなI/Oユニットを介して、制御装置100とフィールドとの間でプロセス値および指令値が遣り取りされる。図2には、リレー群14を介して、プロセス値および指令値として、デジタル信号が遣り取りされる例が示されている。
The remote I / O device 12 communicates via the field network 2 and an input / output unit (hereinafter, also referred to as an “I / O unit”) for acquiring a process value and outputting a command value. And Process values and command values are exchanged between the control device 100 and the field via such an I / O unit. FIG. 2 shows an example in which digital signals are exchanged as process values and command values via the relay group 14.
I/Oユニットは、フィールドネットワークに直接接続されるようにしてもよい。図2には、フィールドネットワーク2にI/Oユニット16が直接接続されている例を示す。
The I / O unit may be directly connected to the field network. FIG. 2 shows an example in which the I / O unit 16 is directly connected to the field network 2.
画像センサ18は、カメラ20によって撮像された画像データに対して、パターンマッチングなどの画像計測処理を行って、その処理結果を制御装置100へ送信する。
The image sensor 18 performs image measurement processing such as pattern matching on the image data captured by the camera 20, and transmits the processing result to the control device 100.
サーボドライバ22は、制御装置100からの指令値(例えば、位置指令など)に従って、サーボモータ24を駆動する。
The servo driver 22 drives the servo motor 24 according to a command value (for example, a position command) from the control device 100.
上述のように、フィールドネットワーク2を介して、制御装置100とフィールド装置群10との間でデータが遣り取りされることになるが、これらの遣り取りされるデータは、数百μsecオーダ~数十msecオーダのごく短い周期で更新されることになる。なお、このような遣り取りされるデータの更新処理を、「I/Oリフレッシュ処理」と称することもある。
As described above, data is exchanged between the control device 100 and the field device group 10 via the field network 2, and the exchanged data is in the order of several hundred μsec to several tens msec. It will be updated in a very short cycle of the order. It should be noted that such a process of updating the exchanged data may be referred to as an “I / O refresh process”.
フィールドネットワーク4を介して制御装置100と接続される表示装置300は、ユーザからの操作を受けて、制御装置100に対してユーザ操作に応じたコマンドなどを送信するとともに、制御装置100での演算結果などをグラフィカルに表示する。
The display device 300 connected to the control device 100 via the field network 4 receives a user's operation, transmits a command corresponding to the user's operation, and the like to the control device 100, and performs an operation in the control device 100. Display the results graphically.
サーバ装置200は、制御装置100とローカルネットワーク6を介して接続され、制御装置100との間で必要なデータを遣り取りする。本実施の形態に係る制御システム1においては、制御装置100からサーバ装置200へ実績結果が送信される。すなわち、サーバ装置200は、制御装置100からのデータを受付ける。
The server device 200 is connected to the control device 100 via the local network 6, and exchanges necessary data with the control device 100. In control system 1 according to the present embodiment, results are transmitted from control device 100 to server device 200. That is, server device 200 receives data from control device 100.
ローカルネットワーク6には、イーサネット(登録商標)などの汎用プロトコルが実装されてもよい。すなわち、ローカルネットワーク6におけるデータの送信周期または更新周期は、フィールドネットワーク(フィールドネットワーク2およびフィールドネットワーク4)におけるデータの送信周期または更新周期より遅くてもよい。但し、ローカルネットワーク6は、フィールドネットワークに比較して、一度により多くのデータを送信することができるようにしてもよい。
The local network 6 may be implemented with a general-purpose protocol such as Ethernet (registered trademark). That is, the data transmission cycle or update cycle in the local network 6 may be slower than the data transmission cycle or update cycle in the field network (the field network 2 and the field network 4). However, the local network 6 may be able to transmit more data at one time than the field network.
<C.制御装置100のハードウェア構成例>
次に、本実施の形態に係る制御システム1を構成する制御装置100のハードウェア構成例について説明する。 <C. Example of hardware configuration ofcontrol device 100>
Next, an example of a hardware configuration of thecontrol device 100 configuring the control system 1 according to the present embodiment will be described.
次に、本実施の形態に係る制御システム1を構成する制御装置100のハードウェア構成例について説明する。 <C. Example of hardware configuration of
Next, an example of a hardware configuration of the
図3は、本実施の形態に係る制御システム1を構成する制御装置100のハードウェア構成例を示すブロック図である。図3を参照して、制御装置100は、CPU(Central Processing Unit)やMPU(Micro-Processing Unit)などのプロセッサ102と、チップセット104と、主記憶装置106と、二次記憶装置108と、ローカルネットワークコントローラ110と、USB(Universal Serial Bus)コントローラ112と、メモリカードインターフェイス114と、内部バスコントローラ122と、フィールドバスコントローラ118,120と、ローカルI/Oユニット124-1,124-2,…と、タイマ126とを含む。
FIG. 3 is a block diagram illustrating a hardware configuration example of the control device 100 included in the control system 1 according to the present embodiment. Referring to FIG. 3, control device 100 includes a processor 102 such as a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit), a chipset 104, a main storage device 106, a secondary storage device 108, , A local network controller 110, a USB (Universal Serial Bus) controller 112, a memory card interface 114, an internal bus controller 122, field bus controllers 118 and 120, and local I / O units 124-1, 124-2,... And a timer 126.
プロセッサ102は、二次記憶装置108に格納された各種プログラムを読み出して、主記憶装置106に展開して実行することで、制御対象に応じた制御、および、後述するような各種処理を実現する。チップセット104は、プロセッサ102と各コンポーネントを制御することで、制御装置100全体としての処理を実現する。
The processor 102 reads out various programs stored in the secondary storage device 108, expands and executes the programs in the main storage device 106, and thereby realizes control according to a control target and various processes described below. . The chipset 104 controls the processor 102 and each component to realize processing of the control device 100 as a whole.
二次記憶装置108には、システムプログラムに加えて、システムプログラムが提供する実行環境上で動作する制御プログラムが格納される。さらに、二次記憶装置108には、内部DB130および機械学習エンジン140を実現するためのシステムプログラムも格納される。
The secondary storage device 108 stores, in addition to the system program, a control program that operates on an execution environment provided by the system program. Further, the secondary storage device 108 also stores a system program for implementing the internal DB 130 and the machine learning engine 140.
ローカルネットワークコントローラ110は、ローカルネットワーク6を介した他の装置との間のデータの遣り取りを制御する。USBコントローラ112は、USB接続を介してサポート装置との間のデータの遣り取りを制御する。
The local network controller 110 controls data exchange with other devices via the local network 6. The USB controller 112 controls exchange of data with a support device via a USB connection.
メモリカードインターフェイス114は、メモリカード116を着脱可能に構成されており、メモリカード116に対してデータを書込み、メモリカード116から各種データ(上述の実績結果を含む)を読出すことが可能になっている。
The memory card interface 114 is configured so that the memory card 116 can be attached and detached, so that data can be written to the memory card 116 and various data (including the above-described results) can be read from the memory card 116. ing.
フィールドバスコントローラ118は、フィールドネットワーク2を介した他の装置との間のデータの遣り取りを制御する。同様に、フィールドバスコントローラ120は、フィールドネットワーク4を介した他の装置との間のデータの遣り取りを制御する。
The fieldbus controller 118 controls data exchange with other devices via the field network 2. Similarly, the fieldbus controller 120 controls data exchange with other devices via the field network 4.
内部バスコントローラ122は、制御装置100に搭載されるローカルI/Oユニット124-1,124-2,…との間でデータを遣り取りするインターフェイスである。
The internal bus controller 122 is an interface for exchanging data with the local I / O units 124-1, 124-2,... Mounted on the control device 100.
タイマ126は、ローカルI/Oユニット124-1,124-2,…、ならびに、フィールドネットワーク2またはフィールドネットワーク4を介して接続されるデバイスとの間で処理を同期させるためのタイミングを管理する。また、タイマ126は、後述するような時刻情報を管理するようにしてもよい。
The timer 126 manages timing for synchronizing processing between the local I / O units 124-1, 124-2,... And devices connected via the field network 2 or the field network 4. Further, the timer 126 may manage time information as described later.
図3には、プロセッサ102がプログラムを実行することで必要な機能が提供される構成例を示したが、これらの提供される機能の一部または全部を、専用のハードウェア回路(例えば、ASIC(Application Specific Integrated Circuit)またはFPGA(Field-Programmable Gate Array)など)を用いて実装してもよい。あるいは、制御装置100の主要部を、汎用的なアーキテクチャに従うハードウェア(例えば、汎用パソコンをベースとした産業用パソコン)を用いて実現してもよい。この場合には、仮想化技術を用いて、用途の異なる複数のOS(Operating System)を並列的に実行させるとともに、各OS上で必要なアプリケーションを実行させるようにしてもよい。
FIG. 3 illustrates a configuration example in which the processor 102 provides necessary functions by executing a program. However, some or all of the provided functions may be replaced by a dedicated hardware circuit (for example, an ASIC). (Application Specific Integrated Circuit) or FPGA (Field-Programmable Gate Array) or the like. Alternatively, the main part of the control device 100 may be realized using hardware that conforms to a general-purpose architecture (for example, an industrial personal computer based on a general-purpose personal computer). In this case, a plurality of OSs (Operating Systems) having different applications may be executed in parallel using virtualization technology, and a required application may be executed on each OS.
<D.制御装置100の機能構成例>
次に、本実施の形態に係る制御システム1を構成する制御装置100の機能構成例について説明する。 <D. Example of functional configuration ofcontrol device 100>
Next, an example of a functional configuration of thecontrol device 100 configuring the control system 1 according to the present embodiment will be described.
次に、本実施の形態に係る制御システム1を構成する制御装置100の機能構成例について説明する。 <D. Example of functional configuration of
Next, an example of a functional configuration of the
図4は、本実施の形態に係る制御システム1を構成する制御装置100の機能構成例を示すブロック図である。図4を参照して、制御装置100は、OS150およびOS150上に実行されるスケジューラ152を含む。スケジューラ152は、制御装置100が有する機能の実行タイミングなどを制御する。より具体的には、スケジューラ152は、変数マネジャ154による変数のサイクリック更新、および、制御プログラム160のサイクリック実行を管理する。
FIG. 4 is a block diagram illustrating a functional configuration example of the control device 100 included in the control system 1 according to the present embodiment. Referring to FIG. 4, control device 100 includes an OS 150 and a scheduler 152 executed on OS 150. The scheduler 152 controls the execution timing of the functions of the control device 100 and the like. More specifically, the scheduler 152 manages the cyclic update of the variable by the variable manager 154 and the cyclic execution of the control program 160.
変数マネジャ154は、制御装置100によりサイクリック実行されるI/Oリフレッシュ処理によって更新されるデータを変数として管理する。変数マネジャ154により管理される変数としては、制御装置100の各部の動作状態を示すデータ群を含むシステム変数156、ならびに、制御プログラム160が管理する変数および制御対象のプロセス値を含むユーザ変数・デバイス変数158を含む。
The variable manager 154 manages data updated by the I / O refresh processing cyclically executed by the control device 100 as variables. The variables managed by the variable manager 154 include a system variable 156 including a data group indicating an operation state of each unit of the control device 100, and a user variable / device including a variable managed by the control program 160 and a process value to be controlled. Includes variable 158.
制御プログラム160は、ユーザが任意に作成可能なユーザプログラムに相当し、典型的には、シーケンスプログラム162およびモーションプログラム164を含む。制御プログラム160を構成するプログラムの命令は、一体のプログラムとして記述されてもよいし、複数のプログラムにそれぞれ分離して記述されてもよい。
The control program 160 corresponds to a user program that can be arbitrarily created by the user, and typically includes a sequence program 162 and a motion program 164. The instructions of the programs constituting the control program 160 may be described as an integrated program, or may be separately described in a plurality of programs.
制御装置100は、機械学習エンジン140に関して、異常監視モジュール170と、特徴量算出モジュール176とを含む。
The control device 100 includes an abnormality monitoring module 170 and a feature amount calculation module 176 for the machine learning engine 140.
特徴量算出モジュール176は、予め指定された特徴量の算出手法に従って、ユーザ変数・デバイス変数158の指定された変数を用いて特徴量をサイクリックに算出する。
The feature amount calculation module 176 cyclically calculates the feature amount using the designated variables of the user variables and the device variables 158 according to the feature amount calculation method designated in advance.
異常監視モジュール170は、フレーム毎の特徴量に基づいて異常の可能性を示す度合いである監視スコアを算出し、当該算出した監視スコアの大きさに基づいて制御対象での異常の有無を判断する。より具体的には、異常監視モジュール170は、予め用意された学習データ172を参照して、特徴量算出モジュール176により算出される特徴量に基づいて、異常の可能性を示す度合い(以下、「監視スコア」とも称す。)を算出する。異常監視モジュール170は、算出される監視スコアと予め用意された異常監視の判定値であるしきい値174とを比較して、異常の有無を判断する。異常監視モジュール170は、異常を検知すると、その旨を制御プログラム160およびデータ書込モジュール132へ通知する。
The abnormality monitoring module 170 calculates a monitoring score, which is a degree indicating the possibility of abnormality, based on the feature amount of each frame, and determines whether there is an abnormality in the control target based on the magnitude of the calculated monitoring score. . More specifically, the abnormality monitoring module 170 refers to the learning data 172 prepared in advance, and based on the characteristic amount calculated by the characteristic amount calculating module 176, the degree of indicating the possibility of abnormality (hereinafter, “ Also referred to as “monitoring score”). The abnormality monitoring module 170 compares the calculated monitoring score with a threshold value 174, which is a judgment value of abnormality monitoring prepared in advance, to determine whether there is an abnormality. When detecting the abnormality, the abnormality monitoring module 170 notifies the control program 160 and the data writing module 132 of the detection.
本実施の形態に係る制御システム1において、学習データ172は、異常監視の対象となる設備や機械の正常時の特徴量を含む。異常監視モジュール170は、特徴量算出モジュール176により算出される特徴量と、学習データ172に含まれる正常時の特徴量との乖離の度合いに基づいて、監視スコアを算出する。
In the control system 1 according to the present embodiment, the learning data 172 includes the feature amount of the equipment or machine to be monitored for abnormality when the equipment is normal. The abnormality monitoring module 170 calculates a monitoring score based on the degree of deviation between the feature calculated by the feature calculation module 176 and the feature included in the learning data 172 at the time of normality.
制御装置100は、内部DB130に関して、データ書込モジュール132およびデータ送信モジュール134を含む。
The control device 100 includes a data writing module 132 and a data transmission module 134 for the internal DB 130.
データ書込モジュール132は、制御装置100の内部で生成される各種データを内部DB130に書込む。内部DB130は、制御装置100の主記憶装置106(図3参照)が提供するデータ領域の一部を用いて実現されてもよいし、制御装置100の二次記憶装置108(図3参照)が提供するデータ領域の一部を用いて実現されてもよいし、メモリカードインターフェイス114に装着されるメモリカード116(図3参照)が提供するデータ領域の一部を用いて実現されてもよい。さらに、図示しない別の記憶媒体が提供するデータ領域の一部を用いて実現してもよい。
The data writing module 132 writes various data generated inside the control device 100 into the internal DB 130. The internal DB 130 may be realized using a part of the data area provided by the main storage device 106 (see FIG. 3) of the control device 100, or may be realized by using the secondary storage device 108 (see FIG. 3) of the control device 100. It may be realized using a part of the data area provided, or may be realized using a part of the data area provided by the memory card 116 (see FIG. 3) attached to the memory card interface 114. Further, it may be realized by using a part of a data area provided by another storage medium (not shown).
典型的には、内部DB130には、生データ180と、分析用データ182と、特徴量データ184と、監視結果データ186とが格納される。生データ180は、特定の1または複数のプロセス値(典型的には、デバイス変数)の時系列データを含む。生データ180は、特徴量算出モジュール176が特徴量を算出するための用いる変数の時系列データを含めることが好ましい。生データ180に含まれる時系列データは、I/Oリフレッシュ処理の周期毎のデータであることが好ましい。
Typically, the internal DB 130 stores raw data 180, analysis data 182, feature data 184, and monitoring result data 186. The raw data 180 includes time-series data of one or more specific process values (typically, device variables). The raw data 180 preferably includes time-series data of variables used by the feature value calculation module 176 to calculate the feature values. The time-series data included in the raw data 180 is preferably data for each cycle of the I / O refresh processing.
分析用データ182は、異常監視の対象となる期間を特定するためのイベント発生時刻などの情報を含む。
The analysis data 182 includes information such as an event occurrence time for specifying a period to be monitored for abnormality.
特徴量データ184は、特徴量算出モジュール176により算出される特徴量の時系列データを含む。特徴量データ184に含まれる時系列データは、生データ180に含まれる時系列データと同様に、I/Oリフレッシュ処理の周期毎のデータであることが好ましい。
The feature amount data 184 includes time-series data of the feature amount calculated by the feature amount calculation module 176. The time-series data included in the feature amount data 184 is preferably data for each cycle of the I / O refresh processing, like the time-series data included in the raw data 180.
監視結果データ186は、異常監視モジュール170による異常の有無の判断結果を含む。
The monitoring result data 186 includes a result of the abnormality monitoring module 170 determining whether or not there is an abnormality.
データ送信モジュール134は、予め定められた条件に従って、あるいは、何らかの要求に応答して、内部DB130に格納されている生データ180、分析用データ182、特徴量データ184、および、監視結果データ186のうち一部または全部を実績結果として外部(典型的には、図2に示すサーバ装置200)へ送信する。
The data transmission module 134 transmits the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186 stored in the internal DB 130 according to a predetermined condition or in response to some request. Part or all of them are transmitted to the outside (typically, the server device 200 shown in FIG. 2) as result results.
データ送信モジュール134が外部へ実績結果を送信することで、制御装置100における異常監視機能の動作状態や適性などを事後的に評価できる。
(4) The data transmission module 134 transmits the result to the outside, so that the operation state and suitability of the abnormality monitoring function in the control device 100 can be evaluated ex post facto.
図2に示すように、表示装置300に送信される実績結果は、解析装置400などを用いて解析することができる。解析装置400による解析によって、異常監視に用いられる特徴量の種別、しきい値の値、学習データの更新なども可能になる。
実 績 As shown in FIG. 2, the result of the result transmitted to the display device 300 can be analyzed using the analysis device 400 or the like. The analysis by the analysis device 400 enables the type of the feature amount used for the abnormality monitoring, the threshold value, the update of the learning data, and the like.
<E.制御装置100のデータ送信モジュール134>
次に、制御装置100のデータ送信モジュール134について説明する。 <E.Data transmission module 134 of control device 100>
Next, thedata transmission module 134 of the control device 100 will be described.
次に、制御装置100のデータ送信モジュール134について説明する。 <E.
Next, the
データ送信モジュール134は、内部DB130に格納されている生データ180、分析用データ182、特徴量データ184、および監視結果データ186などを、サーバ装置200などの外部へ送信する。
The data transmission module 134 transmits the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186 stored in the internal DB 130 to the outside of the server device 200 or the like.
生データ180、分析用データ182、特徴量データ184、および監視結果データ186は、所定時間長毎あるいは所定サイズ毎にファイルとして格納されるようにしてもよい。このような場合、データ送信モジュール134は、各ファイルを順次または一括して外部へ送信する。
The raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186 may be stored as files for each predetermined time length or for each predetermined size. In such a case, the data transmission module 134 transmits each file sequentially or collectively to the outside.
生データ180、分析用データ182、特徴量データ184、および監視結果データ186を格納するファイルとしては、例えば、CSV(Comma-Separated Values)形式やXML(extensible markup language)形式などのテキスト形式を採用してもよいし、バイナリ形式を採用してもよい。バイナリ形式を採用する場合には、公知の圧縮方式で圧縮したデータを採用してもよい。
As a file for storing the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186, for example, a text format such as a CSV (Comma-Separated Value) format or an XML (extensible markup language) format is adopted. Alternatively, a binary format may be adopted. When the binary format is used, data compressed by a known compression method may be used.
すなわち、データ送信モジュール134は、典型的には、生データ180、分析用データ182、特徴量データ184、および監視結果データ186をCSV形式で送信するようにしてもよい。
That is, typically, the data transmission module 134 may transmit the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186 in a CSV format.
データ送信モジュール134が外部へデータを送信するための通信プロトコルとしては、HTTP(Hypertext Transfer Protocol)、HTTPS(Hypertext Transfer Protocol Secure)、FTP(File Transfer Protocol)、SMB(Server Message Block)などの公知の通信プロコトルを採用できる。すなわち、データ送信モジュール134は、HTTP、HTTPS、FTP、および、SMBのうち、少なくとも1つの通信プロトコルでデータを送信する。
Known communication protocols for the data transmission module 134 to transmit data to the outside, such as HTTP (Hypertext Transfer Protocol), HTTPS (Hypertext Transfer Protocol Secure), FTP (File Transfer Protocol), and SMB (Server Message Block). Communication protocol can be adopted. That is, the data transmission module 134 transmits data using at least one communication protocol among HTTP, HTTPS, FTP, and SMB.
なお、データ送信モジュール134が採用する通信プロトコルは上述したものに限られず、データを送信さえできれば、どのような通信プロトコルであってもよい。また、将来的に開発される通信プロトコルを採用することも、本願発明の技術的範囲に含まれ得る。
The communication protocol employed by the data transmission module 134 is not limited to the above-described one, and any communication protocol may be used as long as data can be transmitted. Adopting a communication protocol developed in the future can also be included in the technical scope of the present invention.
なお、例えば、通信プロトコルとしてHTTPSを採用した場合には、セキュア通信を実現するために必要な証明書を事前に取得、あるいは、認証サーバなどから取得するようにしてもよい。
For example, when HTTPS is adopted as the communication protocol, a certificate necessary for realizing secure communication may be obtained in advance, or may be obtained from an authentication server or the like.
データ送信モジュール134は、予め定められた条件または設定に従って、外部へ対象のデータを送信するようにしてもよいし(アクティブ送信)、外部からの要求に応答して、要求されたデータを送信するようにしてもよい(パッシブ送信/オンデマンド送信)。
The data transmission module 134 may transmit the target data to the outside according to predetermined conditions or settings (active transmission), or transmit the requested data in response to a request from the outside. (Passive transmission / on-demand transmission).
予め定められた条件または設定としては、ファイルが生成されることを送信開始条件としてもよいし、予め定められた数または累積サイズのファイルが生成されることを送信開始条件としてもよい。複数のファイルを送信する場合には、所定規則に従って、対象のファイルを順次送信するようにしてもよいし、一括して送信するようにしてもよい。
As the predetermined condition or setting, the creation of a file may be used as the transmission start condition, or the creation of a file of a predetermined number or the cumulative size may be used as the transmission start condition. When transmitting a plurality of files, the target files may be transmitted sequentially according to a predetermined rule, or may be transmitted collectively.
外部からの要求に応答してデータを送信する場合には、データ送信モジュール134は、WebサーバあるいはFTPサーバのようなサーバ機能が実装されていてもよい。
When transmitting data in response to an external request, the data transmission module 134 may have a server function such as a Web server or an FTP server.
制御装置100においては制御プログラム160が予め定められた周期でサイクリック実行されており、データ送信モジュール134は、制御プログラム160のサイクリック実行を妨げないようなタイミングおよび頻度でデータを送信するようにしてもよい。
In the control device 100, the control program 160 is cyclically executed at a predetermined cycle, and the data transmission module 134 transmits data at a timing and frequency that does not hinder the cyclic execution of the control program 160. You may.
<F.応用例>
次に、本実施の形態に係る制御装置100の異常監視機能の応用例について説明する。 <F. Application>
Next, an application example of the abnormality monitoring function of thecontrol device 100 according to the present embodiment will be described.
次に、本実施の形態に係る制御装置100の異常監視機能の応用例について説明する。 <F. Application>
Next, an application example of the abnormality monitoring function of the
図5は、本実施の形態に係る制御装置100の異常監視機能の応用例を示す模式図である。図5には、異常監視の対象として包装機600を示す。
FIG. 5 is a schematic diagram showing an application example of the abnormality monitoring function of control device 100 according to the present embodiment. FIG. 5 shows a packaging machine 600 as a target of abnormality monitoring.
図5を参照して、包装機600は、所定の搬送方向に搬送される包装体604を、一対のロータによりシールおよび切断の少なくとも一方を順次行う。包装機600は、一対のロータ610,620を有しており、ロータ610,620は、同期して回転する。各ロータは、包装体604に接する位置での外周の接線方向が搬送方向と一致するように配置されている。各ロータには、予め定められた位置にヒータおよびカッターが配置されており、これらのヒータおよびカッターが包装体604に接触することで、包装体604に対するシール処理および切断処理が実現される。
参照 Referring to FIG. 5, packaging machine 600 sequentially seals and / or cuts package body 604 conveyed in a predetermined conveyance direction by a pair of rotors. The packaging machine 600 has a pair of rotors 610 and 620, and the rotors 610 and 620 rotate in synchronization. Each rotor is arranged such that the tangential direction of the outer periphery at the position in contact with the package 604 matches the transport direction. Each rotor is provided with a heater and a cutter at predetermined positions. When the heater and the cutter come into contact with the package 604, a sealing process and a cutting process for the package 604 are realized.
包装機600のロータ610,620は、2つのサーボモータ24によって、それぞれ回転軸612,622を中心に同期して回転駆動される。ロータ610,620の表面には、それぞれ処理機構614,624が設けられており、処理機構614は、円周方向(回転方向)に前後して配置されたヒータ615,616と、ヒータ615とヒータ616との間に配置されたカッター617とを含む。同様に、処理機構624は、円周方向に前後して配置されたヒータ625,626と、ヒータ625とヒータ626との間に配置されたカッター627とを含む。ロータ610,620は、その外周面上に配置された、包装体604を切断するためのカッター617,627を含む。
The rotors 610 and 620 of the packaging machine 600 are rotationally driven by the two servomotors 24 around the rotation shafts 612 and 622, respectively. Processing mechanisms 614 and 624 are provided on the surfaces of the rotors 610 and 620, respectively. The processing mechanism 614 includes heaters 615 and 616 disposed in front and rear in the circumferential direction (rotation direction), a heater 615 and a heater 615. 616 and a cutter 617 disposed therebetween. Similarly, the processing mechanism 624 includes heaters 625 and 626 disposed in the circumferential direction and a cutter 627 disposed between the heaters 625 and 626. The rotors 610 and 620 include cutters 617 and 627 disposed on the outer peripheral surface thereof for cutting the package 604.
ロータ610,620が包装体604の搬送速度と同期して回転することで、ヒータ615とヒータ625とによって、包装体604の紙面右側の位置において対向する面同士(上面と下面)がシール(接着)されるとともに、ヒータ616とヒータ626とによって、包装体604の紙面左側の位置において対向する面同士(上面と下面)がシール(接着)される。これらのシール処理と並行して、カッター617とカッター627とによって包装体604が切断される。このような一連の処理が繰返されることで、被包装物605を含む包装体604に対して、シールおよび切断が繰返し実行されて、個別包装体606が順次製造される。
When the rotors 610 and 620 rotate in synchronization with the transport speed of the package 604, the surfaces (upper surface and lower surface) facing each other (upper surface and lower surface) at the right side of the paper surface of the package 604 are sealed (adhered) by the heaters 615 and 625. At the same time, the opposing surfaces (upper surface and lower surface) of the package 604 are sealed (adhered) by the heater 616 and the heater 626 at the position on the left side of the paper surface of the package 604. In parallel with these sealing processes, the package 604 is cut by the cutter 617 and the cutter 627. By repeating such a series of processes, sealing and cutting are repeatedly performed on the package 604 including the article to be packaged 605, and the individual package 606 is sequentially manufactured.
ロータ610,620を回転駆動する2つのサーボモータ24は、それぞれのサーボドライバ22によって回転速度やトルクなどが制御される。制御装置100は、サーボドライバ22から、サーボモータ24のプロセス値、すなわちロータ610,620の実績値を収集することができる。サーボドライバ22のプロセス値(または、ロータ610,620の実績値)としては、(1)回転位置(位相/回転角度)、(2)速度、(3)加速度、(4)トルク値、(5)電流値、(6)電圧値、などを含む。
The two servo motors 24 that rotate the rotors 610 and 620 are controlled in rotational speed and torque by the respective servo drivers 22. The control device 100 can collect the process values of the servo motor 24, that is, the actual values of the rotors 610 and 620, from the servo driver 22. The process values of the servo driver 22 (or the actual values of the rotors 610 and 620) include (1) rotational position (phase / rotation angle), (2) speed, (3) acceleration, (4) torque value, and (5) ) Current value, (6) voltage value, and the like.
包装機600に生じる異常としては、異物の噛み込みなどが想定される。異物の噛み込みは、包装体604自体の位置ずれや、包装体604に包含される被包装物605の位置ずれなどによって生じ得る。異物噛み込みが発生することで、ロータ610,620を回転駆動する2つのサーボモータ24にはより大きなトルクが発生することになる。このようなトルク変化の関連するプロセス値から算出される特徴量を監視することで、異物噛み込みの発生を検知する。
異常 As an abnormality occurring in the packaging machine 600, it is assumed that a foreign substance is caught or the like. The foreign substance can be caught by the displacement of the package 604 itself, the displacement of the packaged object 605 included in the package 604, and the like. When the foreign matter is caught, a larger torque is generated in the two servomotors 24 that rotationally drive the rotors 610 and 620. By monitoring a feature value calculated from a process value related to such a torque change, the occurrence of a foreign object bite is detected.
図6は、図5に示される包装機600に設定されるフレームおよびサブフレームの一例を示す模式図である。図6には、ロータ610,620の回転角度の時間変化を示す。包装機600においては、包装体604毎に異物の噛み込みが発生したか否かが判断される。ここで、ロータ610,620の1回転毎に包装体604が製造されるので、ロータ610,620の1回転分を1つの監視対象を規定する時間区間(以下、「フレーム」とも称す。)に設定できる。
FIG. 6 is a schematic view showing an example of a frame and a sub-frame set in the packaging machine 600 shown in FIG. FIG. 6 shows the time change of the rotation angle of the rotors 610 and 620. In the packaging machine 600, it is determined for each of the packaging bodies 604 whether or not foreign matter has been caught. Here, since the package 604 is manufactured for each rotation of the rotors 610 and 620, one rotation of the rotors 610 and 620 is set in a time section (hereinafter, also referred to as a "frame") that defines one monitoring target. Can be set.
監視対象の時間区間(フレーム)において、異物の噛み込みの発生有無を判断するには、フレームの全時間区間のプロセス値ではなく、ヒータおよびカッターが包装体604に接触する部分区間のプロセス値が重要である。そのため、異常監視に用いられるプロセス値を収集すべき時間区間(包装機600においては、ヒータおよびカッターが最下点に到達する前後の時間区間)をフレーム内に設定できる。このような部分区間を「サブフレーム」とも称す。
In the monitoring target time section (frame), the presence or absence of foreign matter biting is determined not by the process value of the entire time section of the frame but by the process value of the partial section where the heater and the cutter contact the package 604. is important. Therefore, a time section in which a process value used for abnormality monitoring should be collected (in the packaging machine 600, a time section before and after the heater and the cutter reach the lowest point) can be set in the frame. Such a partial section is also referred to as a “subframe”.
このように、本明細書において、「フレーム」との用語を、異常監視の対象となる単位時間区間(あるいは、単位期間)を示す用語として用いる。「サブフレーム」との用語を、対応する「フレーム」内において、異常監視に用いられる特徴量を算出する部分的な時間区間(あるいは、部分的な期間)を示す用語として用いる。
As described above, in this specification, the term “frame” is used as a term indicating a unit time section (or a unit period) to be monitored for abnormality. The term “sub-frame” is used as a term indicating a partial time interval (or a partial period) for calculating a feature amount used for abnormality monitoring in a corresponding “frame”.
なお、フレーム内には複数の異なるサブフレームを設定することもできる。すなわち、異常監視に複数のプロセス値を用いる場合には、各プロセス値に応じたサブフレームを設定することで、より監視精度を高めることができる。
A plurality of different subframes can be set in a frame. That is, when a plurality of process values are used for abnormality monitoring, monitoring accuracy can be further improved by setting subframes corresponding to each process value.
図7は、本実施の形態に係る制御装置100の異常監視機能の処理内容を示す模式図である。図7を参照して、何らかの監視対象に対して設定されたフレーム毎に、フレーム内に設定されたサブフレームのプロセス値の時間変化に基づいて特徴量が算出される。図7に示す例では、2つのプロセス値の時間変化に対してそれぞれ設定されたサブフレーム1およびサブフレーム2のプロセス値の時間変化に基づいて、特徴量1および特徴量2がそれぞれ算出される。このように、制御装置100の特徴量算出モジュール176は、各フレーム内の制御対象に関連する別のプロセス値に基づいて規定されるサブフレームにおける1または複数のプロセス値の時間変化に基づいて特徴量を算出する。
FIG. 7 is a schematic diagram showing the processing content of the abnormality monitoring function of control device 100 according to the present embodiment. Referring to FIG. 7, for each frame set for a certain monitoring target, a feature amount is calculated based on a temporal change of a process value of a subframe set in the frame. In the example illustrated in FIG. 7, the feature amounts 1 and 2 are calculated based on the time change of the process values of the subframe 1 and the subframe 2 respectively set with respect to the time change of the two process values. . As described above, the characteristic amount calculation module 176 of the control device 100 determines the characteristic based on the time change of one or a plurality of process values in the sub-frame defined based on another process value related to the control target in each frame. Calculate the amount.
特徴量1および特徴量2がいずれもスカラ量(1次元の値)であるとすれば、特徴量1および特徴量2からなる2次元座標上に対応する位置(特徴量ベクトル)をプロットできる。
Assuming that both the feature values 1 and 2 are scalar values (one-dimensional values), the corresponding positions (feature value vectors) can be plotted on the two-dimensional coordinates composed of the feature values 1 and 2.
学習データ172は、正常時の特徴量(特徴量ベクトル)の群を含んでおり、これらの特徴量の群からの乖離の度合いに基づいて、監視スコアが算出される。そして、算出される監視スコアと予め用意されたしきい値174との比較によって、異常の有無が判断される。
The learning data 172 includes a group of feature amounts (feature amount vectors) in a normal state, and a monitoring score is calculated based on the degree of deviation from the group of these feature amounts. Then, the presence or absence of an abnormality is determined by comparing the calculated monitoring score with a threshold value 174 prepared in advance.
<G.データ構造>
次に、制御装置100のデータ送信モジュール134により送信されるデータの詳細について説明する。制御装置100は上述したような異常監視機能を有しており、データ送信モジュール134により送信されるデータについても、制御装置100の異常監視機能による監視結果を事後的に評価できる形のデータ構造が採用される。 <G. Data Structure>
Next, details of data transmitted by thedata transmission module 134 of the control device 100 will be described. The control device 100 has the above-described abnormality monitoring function, and the data transmitted by the data transmission module 134 has a data structure that allows the monitoring result by the abnormality monitoring function of the control device 100 to be evaluated afterwards. Adopted.
次に、制御装置100のデータ送信モジュール134により送信されるデータの詳細について説明する。制御装置100は上述したような異常監視機能を有しており、データ送信モジュール134により送信されるデータについても、制御装置100の異常監視機能による監視結果を事後的に評価できる形のデータ構造が採用される。 <G. Data Structure>
Next, details of data transmitted by the
図8は、本実施の形態に係る制御装置100におけるデータ収集およびデータ管理の概要を説明するための模式図である。図8を参照して、「装置イベント」は、異常監視の対象を特定する識別情報である。例えば、最大128個の装置イベントが設定できるとする。なお、装置イベントの最大設定数は、制御装置100のリソースなどに応じて、適宜設計できる。
FIG. 8 is a schematic diagram for explaining an outline of data collection and data management in control device 100 according to the present embodiment. Referring to FIG. 8, “device event” is identification information for specifying a target of abnormality monitoring. For example, assume that a maximum of 128 device events can be set. The maximum set number of device events can be appropriately designed according to the resources of the control device 100 and the like.
各装置イベントには、予め設定されたいずれかの「フレーム」が関連付けられる。すなわち、各装置イベントにおいては、特定のフレーム毎に異常の有無が判断されることになる。
Each device event is associated with one of the preset “frames”. That is, in each device event, the presence or absence of an abnormality is determined for each specific frame.
各装置イベントには、複数のプロセス値(図8に示す例では、複数のプロセス値1,2,・・・,16)が関連付けられる。各プロセス値に対しては、対応するフレームに関連付けられる特定のサブフレームが設定される。なお、同一のフレームに対して、プロセス値毎に異なるサブフレームが設定されてもよい。
A plurality of process values (a plurality of process values 1, 2,..., 16 in the example shown in FIG. 8) are associated with each device event. For each process value, a specific subframe associated with the corresponding frame is set. Note that different subframes may be set for the same frame for each process value.
図9は、本実施の形態に係る制御装置100におけるデータ管理の構造を模式的に示す図である。図9を参照して、制御装置100においては、装置イベント毎にデータ定義セット510が設定される。
FIG. 9 is a diagram schematically showing the structure of data management in control device 100 according to the present embodiment. Referring to FIG. 9, in control device 100, data definition set 510 is set for each device event.
装置イベント毎のデータ定義セット510は、フレーム変数512と、特徴量の出力フレーム変数514と、監視結果の出力フレーム変数530との定義を含む。
The data definition set 510 for each device event includes the definition of a frame variable 512, an output frame variable 514 of a feature value, and an output frame variable 530 of a monitoring result.
フレーム変数512は、異常監視機能の対象となるフレームを特定するために用いる情報の参照先となる変数名を特定する。制御装置100の異常監視機能においては、フレーム変数512として規定された変数の値(プロセス値)またはその変化に基づいて、対象となるフレームの開始および終了が特定される。
The frame variable 512 specifies a variable name that is a reference destination of information used for specifying a frame to be subjected to the abnormality monitoring function. In the abnormality monitoring function of the control device 100, the start and end of the target frame are specified based on the value (process value) of a variable defined as the frame variable 512 or its change.
特徴量の出力フレーム変数514は、算出される特徴量とフレームとの関連付けに用いられる変数である。特徴量の出力フレーム変数514として規定される変数には、特徴量の算出に併せて、対応するフレーム変数512の値が格納される。
The feature frame output frame variable 514 is a variable used for associating the calculated feature with the frame. The variable defined as the output frame variable 514 of the feature value stores the value of the corresponding frame variable 512 in addition to the calculation of the feature value.
監視結果の出力フレーム変数530は、監視結果(算出される監視スコアなど)とフレームとの関連付けに用いられる変数である。監視結果の出力フレーム変数530として規定される変数には、監視結果の出力に併せて、対応するフレーム変数512の値が格納される。
The output frame variable 530 of the monitoring result is a variable used for associating the monitoring result (a calculated monitoring score or the like) with the frame. In the variable defined as the output frame variable 530 of the monitoring result, the value of the corresponding frame variable 512 is stored together with the output of the monitoring result.
装置イベント毎のデータ定義セット510は、複数の特徴量定義セット520をさらに含む。特徴量定義セット520の各々は、監視スコアを算出するために用いられる特徴量の算出方法を規定する。より具体的には、特徴量定義セット520の各々は、特徴量定義522と、プロセス値524と、サブフレーム変数526の定義を含む。
The data definition set 510 for each device event further includes a plurality of feature amount definition sets 520. Each of the feature amount definition sets 520 defines a feature amount calculation method used to calculate a monitoring score. More specifically, each of the feature quantity definition sets 520 includes a feature quantity definition 522, a process value 524, and a definition of a subframe variable 526.
特徴量定義522は、算出される特徴量の種類(例えば、フレーム内の最大値、最小値、平均値など)を規定する。プロセス値524は、特徴量の算出に用いられるプロセス値を示す変数名を規定する。サブフレーム変数526は、特徴量を算出するためのサブフレームを特定するために用いる情報の参照先となる変数名を特定する。
The feature amount definition 522 specifies the type of the feature amount to be calculated (for example, the maximum value, the minimum value, the average value, and the like in a frame). The process value 524 defines a variable name indicating a process value used for calculating a feature amount. The subframe variable 526 specifies a variable name that is a reference destination of information used to specify a subframe for calculating a feature amount.
これらの特徴量定義セット520によって、監視スコアを算出するための特徴量の算出対象および算出方法が規定される。
(4) The feature value definition set 520 defines a feature value calculation target and a calculation method for calculating a monitoring score.
装置イベント毎のデータ定義セット510は、監視結果定義540をさらに含む。監視結果定義540は、算出される複数の特徴量に基づいて算出される監視スコアおよび当該監視スコアに対する判定結果の出力先に関する定義を含む。より具体的には、監視結果定義540は、判定結果定義542および監視スコア定義544を含む。
The data definition set 510 for each device event further includes a monitoring result definition 540. The monitoring result definition 540 includes a definition regarding a monitoring score calculated based on a plurality of calculated feature amounts and an output destination of a determination result with respect to the monitoring score. More specifically, the monitoring result definition 540 includes a determination result definition 542 and a monitoring score definition 544.
判定結果定義542は、算出される監視スコアとしきい値との比較によって得られる判定結果が格納される先を規定する。監視スコア定義544は、複数の特徴量に基づいて算出される監視スコアが格納される先を規定する。
The determination result definition 542 specifies the destination where the determination result obtained by comparing the calculated monitoring score with the threshold value is stored. The monitoring score definition 544 specifies where the monitoring score calculated based on the plurality of feature amounts is stored.
図10は、本実施の形態に係る制御装置100における異常監視機能に係るデータ処理の概要を説明するための模式図である。図10を参照して、(a)フレーム変数が示す値の変化(「AAAAA」、「BBBBB」、・・・など)に基づいて、フレームが特定される。(a)フレーム変数としては、例えば、操業管理サーバなどから通知されるワーク識別情報などを用いるようにしてもよいし、あるいは、特定のワークの処理開始時にラッチされる時刻情報などを用いるようにしてもよい。
FIG. 10 is a schematic diagram for explaining an outline of data processing related to the abnormality monitoring function in control device 100 according to the present embodiment. Referring to FIG. 10, (a) a frame is specified based on a change in a value indicated by a frame variable (“AAAAA”, “BBBBB”,..., Etc.). (A) As the frame variable, for example, work identification information notified from an operation management server or the like may be used, or time information latched at the start of processing of a specific work may be used. You may.
各フレームにおいて、(c)サブフレーム変数に基づく収集条件が有効化されている期間(典型的には、(c)サブフレーム変数がTRUEの期間)において、(b)プロセス値がサイクリックに収集される。
In each frame, (b) process values are collected cyclically during a period in which (c) a collection condition based on a subframe variable is enabled (typically, (c) a subframe variable is TRUE). Is done.
各フレームが終了すると、当該フレームにおいて収集されたプロセス値に基づいて(e)特徴量が算出される。この特徴量の算出に併せて、(d)特徴量の出力フレーム変数には、対応するフレームに関連付けられた(a)フレーム変数が示す値(「AAAAA」、「BBBBB」、・・・など)が格納される。
(4) When each frame is completed, (e) the feature amount is calculated based on the process values collected in the frame. Along with the calculation of the feature value, (d) the output frame variable of the feature value, (a) the value indicated by the frame variable associated with the corresponding frame (“AAAAA”, “BBBBB”,..., Etc.) Is stored.
さらに、特徴量の算出が完了すると、監視スコアが算出されるとともに、算出される監視スコアの値としきい値との比較によって、(g)監視結果が出力される。この監視結果の出力に併せて、(f)監視結果の出力フレーム変数には、対応するフレームに関連付けられた(a)フレーム変数が示す値(「AAAAA」、「BBBBB」、・・・など)が格納される。
(5) When the calculation of the feature amount is completed, the monitoring score is calculated, and (g) a monitoring result is output by comparing the calculated monitoring score value with the threshold value. Along with the output of the monitoring result, (f) the output frame variable of the monitoring result includes (a) the value indicated by the frame variable associated with the corresponding frame (“AAAAA”, “BBBBB”,..., Etc.) Is stored.
このように、(e)特徴量および(g)監視結果には、プロセス値を収集したフレームに対応付けられる(a)フレーム変数が示す値と同じ値が対応付けられる((d)特徴量の出力フレーム変数、および、(f)監視結果の出力フレーム変数)。(e)特徴量および(g)監視結果は、対応するフレームの時間が経過した後に算出されることになるが、対応するフレームを特定するための情報が付加されているので、事後的な解析および評価を容易に実現できる。
As described above, (e) the feature value and (g) the monitoring result are associated with the same value as the value indicated by the frame variable (a) associated with the frame in which the process value is collected ((d) the feature value). Output frame variable and (f) output frame variable of monitoring result). (E) The feature amount and (g) the monitoring result are calculated after the time of the corresponding frame elapses. However, since information for specifying the corresponding frame is added, an ex-post analysis is performed. And evaluation can be easily realized.
図8~図10に示すような装置イベント、プロセス値、フレーム、サブフレームの関係を事後的に解析できるように、以下に説明するようなデータ構造が採用される。
The data structure described below is adopted so that the relationship between the device event, the process value, the frame, and the subframe as shown in FIGS. 8 to 10 can be analyzed ex post facto.
図11は、本実施の形態に係る制御装置100から送信される実績結果の一例を示す模式図である。図11(A)には生データ180のデータ構造の一例を示し、図11(B)には分析用データ182のデータ構造の一例を示し、図11(C)には特徴量データ184のデータ構造の一例を示し、図11(D)には監視結果データ186のデータ構造の一例を示す。
FIG. 11 is a schematic diagram showing an example of the result of the result transmitted from control device 100 according to the present embodiment. 11A shows an example of the data structure of the raw data 180, FIG. 11B shows an example of the data structure of the analysis data 182, and FIG. 11C shows the data of the feature amount data 184. FIG. 11D shows an example of the structure of the monitoring result data 186.
図11(A)に示される生データ180は、インデックス1801およびタイムスタンプ1802に関連付けられた、収集周期(I/Oリフレッシュ処理周期)毎に収集されるプロセス値の時系列データ1803を含む。
生 The raw data 180 shown in FIG. 11A includes time-series data 1803 of process values collected in each collection cycle (I / O refresh processing cycle), which is associated with the index 1801 and the time stamp 1802.
インデックス1801は、各レコードを特定するための情報であり、制御装置100において任意に付与されるユニークな値である。典型的には、インデックス1801は、収集周期毎にインクリメントまたはデクリメントされる。インクリメントまたはデクリメントされる値を用いることで、データの欠落の有無を判断できる。
The index 1801 is information for specifying each record, and is a unique value arbitrarily assigned in the control device 100. Typically, the index 1801 is incremented or decremented every collection cycle. By using the value to be incremented or decremented, it can be determined whether or not data is missing.
タイムスタンプ1802は、制御装置100のタイマ126(図3)が管理する時刻情報である。タイムスタンプ1802として格納される値は、他のデータと共通化されている。そのため、タイムスタンプ1802に格納される値を共通のキーとして、他の時系列データと対応付けることができる。
The time stamp 1802 is time information managed by the timer 126 (FIG. 3) of the control device 100. The value stored as the time stamp 1802 is shared with other data. Therefore, the value stored in the time stamp 1802 can be used as a common key and associated with other time-series data.
図11(B)に示される分析用データ182は、インデックス1821およびタイムスタンプ1822に関連付けられた、収集周期(I/Oリフレッシュ処理周期)毎に収集される、フレーム変数が示す値の時系列データ1823と、サブフレーム変数が示す値の時系列データ1824と、ラベル変数が示す値の時系列データ1825と、ラベル変数が示す値の時系列データ1825と、プロセス値の時系列データ1826とを含む。
The analysis data 182 shown in FIG. 11B is time-series data of the value indicated by the frame variable, which is collected for each collection cycle (I / O refresh processing cycle) and is associated with the index 1821 and the time stamp 1822. 1823, time-series data 1824 of a value indicated by a subframe variable, time-series data 1825 of a value indicated by a label variable, time-series data 1825 of a value indicated by a label variable, and time-series data 1826 of a process value. .
インデックス1821は、各レコードを特定するための情報であり、制御装置100において任意に付与されるユニークな値である。
The index 1821 is information for specifying each record, and is a unique value arbitrarily assigned in the control device 100.
タイムスタンプ1822は、図11(A)の生データ180に含まれるタイムスタンプ1802と同じソースの情報が用いられる。
As the time stamp 1822, the same source information as the time stamp 1802 included in the raw data 180 of FIG. 11A is used.
フレーム変数が示す値の時系列データ1823およびサブフレーム変数が示す値の時系列データ1824としては、いずれかの装置イベントで利用されるものが対象とされる。このように、分析用データ182は、フレームを規定するプロセス値の時系列データ(フレーム変数が示す値の時系列データ1823)、および、サブフレームを規定するプロセス値の時系列データ(サブフレーム変数が示す値の時系列データ1824)を含む。
As the time-series data 1823 of the value indicated by the frame variable and the time-series data 1824 of the value indicated by the subframe variable, data used in any device event is targeted. As described above, the analysis data 182 includes the time-series data of the process value defining the frame (the time-series data 1823 of the value indicated by the frame variable) and the time-series data of the process value defining the sub-frame (the sub-frame variable Includes time-series data 1824) of the value indicated by.
ラベル変数が示す値の時系列データ1825は、事後的な解析および評価を容易にするための付加的な情報であり、ユーザが任意に選択した変数が示す値の時間変化を含む。
The time series data 1825 of the value indicated by the 変 数 label variable is additional information for facilitating subsequent analysis and evaluation, and includes a time change of the value indicated by the variable arbitrarily selected by the user.
プロセス値の時系列データ1826は、いずれかの装置イベントで特徴量の算出に用いられるものが対象とされる。
The process value time-series data 1826 is intended to be used for calculating a feature amount in any device event.
図11(C)に示される特徴量データ184は、インデックス1841およびタイムスタンプ1842に関連付けられた、装置イベント毎の特徴量算出結果1843を含む。
特 徴 The feature data 184 shown in FIG. 11C includes a feature calculation result 1843 for each device event, which is associated with the index 1841 and the time stamp 1842.
インデックス1841は、各レコードを特定するための情報であり、制御装置100において任意に付与されるユニークな値である。
The index 1841 is information for specifying each record, and is a unique value arbitrarily assigned in the control device 100.
タイムスタンプ1842は、図11(A)の生データ180に含まれるタイムスタンプ1802と同じソースの情報が用いられる。
As the time stamp 1842, the same source information as the time stamp 1802 included in the raw data 180 in FIG. 11A is used.
装置イベント毎の特徴量算出結果1843は、特徴量インデックス1844と、特徴量の出力フレーム変数が示す値の時系列データ1845と、監視スコアの算出に用いられる各特徴量の時系列データ1846とを含む。
The feature amount calculation result 1843 for each device event includes a feature amount index 1844, time-series data 1845 of a value indicated by an output frame variable of the feature amount, and time-series data 1846 of each feature amount used for calculating a monitoring score. Including.
特徴量インデックス1844には、算出される特徴量を識別するための情報が格納される。典型的には、各特徴量を用いる装置イベントを特定するための識別情報が格納される。
The feature index 1844 stores information for identifying the calculated feature. Typically, identification information for specifying a device event using each feature amount is stored.
特徴量の出力フレーム変数が示す値の時系列データ1845は、特徴量を算出するために用いたプロセス値の収集対象区間を特定するための値(対応するフレーム変数の値)を含む。
The time-series data 1845 of the value indicated by the output frame variable of the feature value includes a value (corresponding frame variable value) for specifying the collection target section of the process value used for calculating the feature value.
監視スコアの算出に用いられる各特徴量の時系列データ1846は、特徴量ベクトルに含まれる各特徴量の時系列データを含む。
The time-series data 1846 of each feature used in the calculation of the monitoring score includes the time-series data of each feature included in the feature vector.
図11(D)に示される監視結果データ186は、インデックス1861およびタイムスタンプ1862に関連付けられた、装置イベント毎の監視結果1863を含む。
監視 The monitoring result data 186 shown in FIG. 11D includes the monitoring result 1863 for each device event, which is associated with the index 1861 and the time stamp 1862.
インデックス1861は、各レコードを特定するための情報であり、制御装置100において任意に付与されるユニークな値である。
The index 1861 is information for specifying each record, and is a unique value arbitrarily assigned in the control device 100.
タイムスタンプ1862は、図11(A)の生データ180に含まれるタイムスタンプ1802と同じソースの情報が用いられる。
As the time stamp 1862, the same source information as the time stamp 1802 included in the raw data 180 of FIG. 11A is used.
装置イベント毎の監視結果1863は、装置イベントインデックス1864と、監視結果の出力フレーム変数が示す値の時系列データ1865と、判定結果の時系列データ1866と、監視スコアの時系列データ1867とを含む。
The monitoring result 1863 for each device event includes a device event index 1864, time-series data 1865 of the value indicated by the output frame variable of the monitoring result, time-series data 1866 of the determination result, and time-series data 1867 of the monitoring score. .
装置イベントインデックス1864には、対象となる装置イベントを特定するための識別情報が格納される。
The device event index 1864 stores identification information for specifying a target device event.
監視結果の出力フレーム変数が示す値の時系列データ1865は、監視スコアを算出するために用いたプロセス値の収集対象区間を特定するための値(対応するフレーム変数の値)を含む。
(4) The time-series data 1865 of the value indicated by the output frame variable of the monitoring result includes a value (a value of the corresponding frame variable) for specifying the collection section of the process value used for calculating the monitoring score.
判定結果の時系列データ1866は、監視スコアとしきい値との比較によって決定される判定結果(監視スコアに基づく異常の有無を示す値)の時系列データを含む。監視スコアの時系列データ1867は、対象の特徴量を用いてサイクリックに算出される監視スコアの時系列データを含む。このように、監視結果データ186は、監視スコアと、監視スコアに基づく異常の有無を示す値とを含む。
The time series data 1866 of the determination result includes the time series data of the determination result (a value indicating the presence or absence of an abnormality based on the monitoring score) determined by comparing the monitoring score with the threshold. The monitoring score time-series data 1867 includes the monitoring score time-series data cyclically calculated using the target feature amount. As described above, the monitoring result data 186 includes the monitoring score and the value indicating the presence or absence of the abnormality based on the monitoring score.
本実施の形態に係る制御装置100において、生データ180、分析用データ182、特徴量データ184、および、監視結果データ186の各々は、レコード毎にインクリメントまたはデクリメントされるインデックス1801,1821,1841,1861が各レコードに付与されている。
In the control device 100 according to the present embodiment, each of the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186 includes indexes 1801, 1821, 1841, which are incremented or decremented for each record. 1861 is assigned to each record.
また、本実施の形態に係る制御装置100において、生データ180、分析用データ182、特徴量データ184、および、監視結果データ186の各々は、各レコードに共通のタイマ126で管理されるタイムスタンプ1802,1822,1842,1862が付与されている。すなわち、制御装置100は、共通のタイマ126により管理されるタイムスタンプ1802,1822,1842,1862を各レコードに付与した、生データ180、分析用データ182、特徴量データ184、および、監視結果データ186を出力する。タイムスタンプ1802,1822,1842,1862を参照することで、各データに含まれる時系列データの時間軸を合せることができる。
Further, in the control device 100 according to the present embodiment, each of the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data 186 is a time stamp managed by a timer 126 common to each record. 1802, 1822, 1842, and 1862. That is, the control device 100 adds the raw data 180, the analysis data 182, the feature data 184, and the monitoring result data obtained by adding the time stamps 1802, 1822, 1842, and 1862 managed by the common timer 126 to each record. 186 is output. By referring to the time stamps 1802, 1822, 1842, and 1862, the time axis of the time-series data included in each data can be matched.
また、特徴量データ184および監視結果データ186は、対象となるフレームを特定するための情報として、分析用データ182に含まれるフレーム変数が対象となるフレームにおいて示していた値を含む。このような情報を採用することで、時間的に遅れて算出される特徴量および監視結果を元のプロセス値と対応付けた解析が容易化する。
{Circle around (2)} The feature amount data 184 and the monitoring result data 186 include, as information for specifying the target frame, the value indicated by the frame variable included in the analysis data 182 in the target frame. By adopting such information, it is easy to analyze the feature amount and the monitoring result calculated with a delay with respect to the original process value.
<H.解析手順例>
次に、上述したようなデータを用いた解析手順の一例について説明する。 <H. Analysis procedure example>
Next, an example of an analysis procedure using the above-described data will be described.
次に、上述したようなデータを用いた解析手順の一例について説明する。 <H. Analysis procedure example>
Next, an example of an analysis procedure using the above-described data will be described.
図12は、本実施の形態に係る制御装置100から送信されるデータを用いた解析手順の一例を説明するための図である。
FIG. 12 is a diagram for describing an example of an analysis procedure using data transmitted from control device 100 according to the present embodiment.
図12を参照して、例えば、制御装置100の異常監視機能があるタイミングで異常の発生と判断したとする。この異常であるとの判断が生じた原因および適否などを解析する例について説明する。
Referring to FIG. 12, for example, it is assumed that an abnormality monitoring function of control device 100 determines that an abnormality has occurred at a certain timing. An example in which the cause of the determination of the abnormality and the suitability of the abnormality will be described.
まず、監視結果データ186に含まれる、判定結果の時系列データ1866を参照して、「TRUE」(図12の例では、「TRUE」が異常発生を示すものとする)になっている時間区間を検証対象として特定する((1)検証対象の特定)。併せて、監視スコアの時系列データ1867の対応する時間区間の値を取得してもよい。そして、監視結果の出力フレーム変数が示す値の時系列データ1865の検証対象として特定された時間区間に対応する値を取得する((2)対応するフレーム変数の値の取得)。この例では、「CCCCC」であるとする。
First, referring to the time-series data 1866 of the determination result included in the monitoring result data 186, a time section in which “TRUE” (“TRUE” indicates an abnormal occurrence in the example of FIG. 12) Is specified as a verification target ((1) specification of a verification target). At the same time, the value of the corresponding time section of the monitoring score time-series data 1867 may be acquired. Then, a value corresponding to the time section specified as a verification target of the time-series data 1865 of the value indicated by the output frame variable of the monitoring result is acquired ((2) acquisition of the value of the corresponding frame variable). In this example, “CCCCC” is assumed.
続いて、特徴量データ184を参照し、特徴量データ184に含まれる、特徴量の出力フレーム変数が示す値の時系列データ1845のうち、取得されたフレーム変数と同一の値を示す時間区間を特定する((3)同一の値を示す時間区間の特定)。そして、監視スコアの算出に用いられる各特徴量の時系列データ1846のうち、特定された時間区間に対応する値を取得する((4)対応する特徴量の取得)。
Subsequently, with reference to the feature amount data 184, a time section indicating the same value as the acquired frame variable in the time-series data 1845 of the value indicated by the output frame variable of the feature amount included in the feature amount data 184. Identify ((3) Identify time sections showing the same value). Then, of the time-series data 1846 of each feature used for calculating the monitoring score, a value corresponding to the specified time section is obtained ((4) Acquisition of the corresponding feature).
続いて、分析用データ182を参照し、分析用データ182に含まれる、フレーム変数が示す値の時系列データ1823のうち、先に取得されているフレーム変数と同一の値を示す時間区間を特定する((5)同一の値を示す時間区間の特定)。そして、ラベル変数が示す値の時系列データ1825のうち、特定された時間区間に対応する値を取得する((6)対応するプロセス値の取得)。
Subsequently, with reference to the analysis data 182, a time section indicating the same value as the previously acquired frame variable is identified from the time series data 1823 of the value indicated by the frame variable included in the analysis data 182. ((5) Identification of a time section showing the same value). Then, of the time-series data 1825 of the value indicated by the label variable, a value corresponding to the specified time section is acquired ((6) acquisition of a corresponding process value).
以上のような手順によって、異常監視機能の動作状態や適性などを事後的に評価できる。
に よ っ て By the above procedure, the operating state and suitability of the abnormality monitoring function can be evaluated ex post facto.
<I.付記>
[構成1]
制御対象を制御する制御装置(100)であって、
前記制御対象に関連する第1のプロセス値(1823)に基づいて規定されるフレーム毎に、前記制御対象での異常の有無を判断する異常監視部(170)と、
各フレームにおける前記制御対象に関連する第2のプロセス値(1826)に基づいてフレーム毎に特徴量を算出して前記異常監視部へ出力する特徴量算出部(176)と、
前記異常監視部および前記特徴量算出部による処理に係るデータを格納する記憶部(130)と、
前記記憶部に格納されるデータを外部へ送信するデータ送信部(134)とを備え、
前記異常監視部は、前記特徴量算出部からフレーム毎の特徴量が入力されると、前記制御対象での異常の有無の判断結果を含む監視結果をフレーム毎に出力するように構成されており、
前記データ送信部は、
前記第1のプロセス値および前記第2のプロセス値の時系列データを含む第1のデータ(182)と、
前記特徴量算出部によりフレーム毎に算出される前記特徴量の時系列データを含む第2のデータ(184)と、
前記異常監視部により出力される前記監視結果の時系列データを含む第3のデータ(186)とを送信可能に構成されており、
前記第2のデータにおいては、前記特徴量(1846)と、各特徴量に対応するフレームを規定する前記第1のプロセス値(1845)とが関連付けられており、
前記第3のデータにおいては、前記監視結果(1866,1867)と、各監視結果に対応するフレームを規定する前記第1のプロセス値(1865)とが関連付けられている、制御装置。
[構成2]
前記異常監視部は、フレーム毎の特徴量に基づいて異常の可能性を示す度合いである監視スコアを算出し、当該算出した監視スコアの大きさに基づいて前記制御対象での異常の有無を判断する、構成1に記載の制御装置。
[構成3]
前記第3のデータの前記監視結果は、前記監視スコア(1867)と、前記監視スコアに基づく異常の有無を示す値(1866)とを含む、構成2に記載の制御装置。
[構成4]
前記データ送信部は、特定の1または複数のプロセス値の時系列データを含む第4のデータ(180)をさらに送信可能に構成されている、構成1~3のいずれか1項に記載の制御装置。
[構成5]
前記特徴量算出部は、各フレーム内の前記制御対象に関連する第3のプロセス値(1824)に基づいて規定されるサブフレームにおける前記第2のプロセス値の時間変化に基づいて前記特徴量を算出するように構成されており、
前記第1のデータは、前記第3のプロセス値の時系列データをさらに含む、構成1~4のいずれか1項に記載の制御装置。
[構成6]
前記第1のデータ、前記第2のデータ、前記第3のデータの各々は、各レコードに共通のタイマで管理されるタイムスタンプ(1822,1842,1862)が付与されている、構成1~5のいずれか1項に記載の制御装置。
[構成7]
前記第1のデータ、前記第2のデータ、前記第3のデータの各々は、レコード毎にインクリメントまたはデクリメントされるインデックス(1821,1841,1861)が各レコードに付与されている、構成1~6のいずれか1項に記載の制御装置。
[構成8]
前記データ送信部は、HTTP(Hypertext Transfer Protocol)、HTTPS(Hypertext Transfer Protocol Secure)、FTP(File Transfer Protocol)、および、SMB(Server Message Block)のうち、少なくとも1つの通信プロトコルでデータを送信する、構成1~7のいずれか1項に記載の制御装置。
[構成9]
前記データ送信部は、前記第1のデータ、前記第2のデータ、前記第3のデータをCSV(Comma-Separated Values)形式で送信する、構成1~8のいずれか1項に記載の制御装置。
[構成10]
制御対象を制御する制御装置(100)と、
前記制御装置からのデータを受付けるサーバ装置(200)とを備え、
前記制御装置は、
前記制御対象に関連する第1のプロセス値(1823)に基づいて規定されるフレーム毎に、前記制御対象での異常の有無を判断する異常監視部(170)と、
各フレームにおける前記制御対象に関連する第2のプロセス値(1826)に基づいてフレーム毎に特徴量を算出して前記異常監視部へ出力する特徴量算出部(176)と、
前記異常監視部および前記特徴量算出部による処理に係るデータを格納する記憶部(130)と、
前記記憶部に格納されるデータを外部へ送信するデータ送信部(134)とを備え、
前記異常監視部は、前記特徴量算出部からフレーム毎の特徴量が入力されると、前記制御対象での異常の有無の判断結果を含む監視結果をフレーム毎に出力するように構成されており、
前記データ送信部は、
前記第1のプロセス値および前記第2のプロセス値の時系列データを含む第1のデータ(182)と、
前記特徴量算出部によりフレーム毎に算出される前記特徴量の時系列データを含む第2のデータ(184)と、
前記異常監視部により出力される前記監視結果の時系列データを含む第3のデータ(186)とを送信可能に構成されており、
前記第2のデータにおいては、前記特徴量(1846)と、各特徴量に対応するフレームを規定する前記第1のプロセス値(1845)とが関連付けられており、
前記第3のデータにおいては、前記監視結果(1866,1867)と、各監視結果に対応するフレームを規定する前記第1のプロセス値(1865)とが関連付けられている、制御システム。 <I. Appendix>
[Configuration 1]
A control device (100) for controlling a control target,
An abnormality monitoring unit (170) that determines, for each frame defined based on a first process value (1823) related to the control target, whether there is an abnormality in the control target;
A feature value calculation unit (176) that calculates a feature value for each frame based on a second process value (1826) related to the control target in each frame and outputs the feature value to the abnormality monitoring unit;
A storage unit (130) for storing data relating to processing by the abnormality monitoring unit and the feature amount calculation unit;
A data transmission unit (134) for transmitting data stored in the storage unit to the outside,
The abnormality monitoring unit is configured to, when a feature amount for each frame is input from the feature amount calculation unit, output a monitoring result including a determination result of the presence or absence of an abnormality in the control target for each frame. ,
The data transmission unit,
First data (182) including time-series data of the first process value and the second process value;
Second data (184) including time-series data of the feature amount calculated for each frame by the feature amount calculation unit;
Third data (186) including time-series data of the monitoring result output by the abnormality monitoring unit is configured to be able to be transmitted;
In the second data, the feature value (1846) is associated with the first process value (1845) that defines a frame corresponding to each feature value,
The control device, wherein, in the third data, the monitoring result (1866, 1867) is associated with the first process value (1865) defining a frame corresponding to each monitoring result.
[Configuration 2]
The abnormality monitoring unit calculates a monitoring score, which is a degree indicating the possibility of abnormality, based on the feature amount of each frame, and determines whether there is an abnormality in the control target based on the magnitude of the calculated monitoring score. 3. The control device according toConfiguration 1,
[Configuration 3]
The control device according toConfiguration 2, wherein the monitoring result of the third data includes the monitoring score (1867) and a value (1866) indicating the presence or absence of an abnormality based on the monitoring score.
[Configuration 4]
The control according to any one ofConfigurations 1 to 3, wherein the data transmission unit is further configured to be capable of transmitting fourth data (180) including time-series data of one or more specific process values. apparatus.
[Configuration 5]
The feature amount calculation unit calculates the feature amount based on a temporal change of the second process value in a subframe defined based on a third process value (1824) related to the control target in each frame. Is configured to calculate,
The control device according to any one ofConfigurations 1 to 4, wherein the first data further includes time-series data of the third process value.
[Configuration 6]
Configurations 1 to 5 in which each of the first data, the second data, and the third data has a time stamp (1822, 1842, 1862) managed by a common timer for each record. The control device according to any one of claims 1 to 7.
[Configuration 7]
In each of the first data, the second data, and the third data, an index (1821, 1841, 1861) that is incremented or decremented for each record is added to each record. The control device according to any one ofclaims 1 to 7.
[Configuration 8]
The data transmission unit transmits data by at least one communication protocol among HTTP (Hypertext Transfer Protocol), HTTPS (Hypertext Transfer Protocol Secure), FTP (File Transfer Protocol), and SMB (Server Message Block). 8. The control device according to any one ofconfigurations 1 to 7.
[Configuration 9]
The control device according to any one ofConfigurations 1 to 8, wherein the data transmission unit transmits the first data, the second data, and the third data in a CSV (Comma-Separated Values) format. .
[Configuration 10]
A control device (100) for controlling a control target;
A server device (200) for receiving data from the control device,
The control device includes:
An abnormality monitoring unit (170) that determines, for each frame defined based on a first process value (1823) related to the control target, whether there is an abnormality in the control target;
A feature value calculation unit (176) that calculates a feature value for each frame based on a second process value (1826) related to the control target in each frame and outputs the feature value to the abnormality monitoring unit;
A storage unit (130) for storing data relating to processing by the abnormality monitoring unit and the feature amount calculation unit;
A data transmission unit (134) for transmitting data stored in the storage unit to the outside,
The abnormality monitoring unit is configured to, when a feature amount for each frame is input from the feature amount calculation unit, output a monitoring result including a determination result of the presence or absence of an abnormality in the control target for each frame. ,
The data transmission unit,
First data (182) including time-series data of the first process value and the second process value;
Second data (184) including time-series data of the feature amount calculated for each frame by the feature amount calculation unit;
Third data (186) including time-series data of the monitoring result output by the abnormality monitoring unit is configured to be able to be transmitted;
In the second data, the feature value (1846) is associated with the first process value (1845) that defines a frame corresponding to each feature value,
The control system, wherein, in the third data, the monitoring result (1866, 1867) is associated with the first process value (1865) that defines a frame corresponding to each monitoring result.
[構成1]
制御対象を制御する制御装置(100)であって、
前記制御対象に関連する第1のプロセス値(1823)に基づいて規定されるフレーム毎に、前記制御対象での異常の有無を判断する異常監視部(170)と、
各フレームにおける前記制御対象に関連する第2のプロセス値(1826)に基づいてフレーム毎に特徴量を算出して前記異常監視部へ出力する特徴量算出部(176)と、
前記異常監視部および前記特徴量算出部による処理に係るデータを格納する記憶部(130)と、
前記記憶部に格納されるデータを外部へ送信するデータ送信部(134)とを備え、
前記異常監視部は、前記特徴量算出部からフレーム毎の特徴量が入力されると、前記制御対象での異常の有無の判断結果を含む監視結果をフレーム毎に出力するように構成されており、
前記データ送信部は、
前記第1のプロセス値および前記第2のプロセス値の時系列データを含む第1のデータ(182)と、
前記特徴量算出部によりフレーム毎に算出される前記特徴量の時系列データを含む第2のデータ(184)と、
前記異常監視部により出力される前記監視結果の時系列データを含む第3のデータ(186)とを送信可能に構成されており、
前記第2のデータにおいては、前記特徴量(1846)と、各特徴量に対応するフレームを規定する前記第1のプロセス値(1845)とが関連付けられており、
前記第3のデータにおいては、前記監視結果(1866,1867)と、各監視結果に対応するフレームを規定する前記第1のプロセス値(1865)とが関連付けられている、制御装置。
[構成2]
前記異常監視部は、フレーム毎の特徴量に基づいて異常の可能性を示す度合いである監視スコアを算出し、当該算出した監視スコアの大きさに基づいて前記制御対象での異常の有無を判断する、構成1に記載の制御装置。
[構成3]
前記第3のデータの前記監視結果は、前記監視スコア(1867)と、前記監視スコアに基づく異常の有無を示す値(1866)とを含む、構成2に記載の制御装置。
[構成4]
前記データ送信部は、特定の1または複数のプロセス値の時系列データを含む第4のデータ(180)をさらに送信可能に構成されている、構成1~3のいずれか1項に記載の制御装置。
[構成5]
前記特徴量算出部は、各フレーム内の前記制御対象に関連する第3のプロセス値(1824)に基づいて規定されるサブフレームにおける前記第2のプロセス値の時間変化に基づいて前記特徴量を算出するように構成されており、
前記第1のデータは、前記第3のプロセス値の時系列データをさらに含む、構成1~4のいずれか1項に記載の制御装置。
[構成6]
前記第1のデータ、前記第2のデータ、前記第3のデータの各々は、各レコードに共通のタイマで管理されるタイムスタンプ(1822,1842,1862)が付与されている、構成1~5のいずれか1項に記載の制御装置。
[構成7]
前記第1のデータ、前記第2のデータ、前記第3のデータの各々は、レコード毎にインクリメントまたはデクリメントされるインデックス(1821,1841,1861)が各レコードに付与されている、構成1~6のいずれか1項に記載の制御装置。
[構成8]
前記データ送信部は、HTTP(Hypertext Transfer Protocol)、HTTPS(Hypertext Transfer Protocol Secure)、FTP(File Transfer Protocol)、および、SMB(Server Message Block)のうち、少なくとも1つの通信プロトコルでデータを送信する、構成1~7のいずれか1項に記載の制御装置。
[構成9]
前記データ送信部は、前記第1のデータ、前記第2のデータ、前記第3のデータをCSV(Comma-Separated Values)形式で送信する、構成1~8のいずれか1項に記載の制御装置。
[構成10]
制御対象を制御する制御装置(100)と、
前記制御装置からのデータを受付けるサーバ装置(200)とを備え、
前記制御装置は、
前記制御対象に関連する第1のプロセス値(1823)に基づいて規定されるフレーム毎に、前記制御対象での異常の有無を判断する異常監視部(170)と、
各フレームにおける前記制御対象に関連する第2のプロセス値(1826)に基づいてフレーム毎に特徴量を算出して前記異常監視部へ出力する特徴量算出部(176)と、
前記異常監視部および前記特徴量算出部による処理に係るデータを格納する記憶部(130)と、
前記記憶部に格納されるデータを外部へ送信するデータ送信部(134)とを備え、
前記異常監視部は、前記特徴量算出部からフレーム毎の特徴量が入力されると、前記制御対象での異常の有無の判断結果を含む監視結果をフレーム毎に出力するように構成されており、
前記データ送信部は、
前記第1のプロセス値および前記第2のプロセス値の時系列データを含む第1のデータ(182)と、
前記特徴量算出部によりフレーム毎に算出される前記特徴量の時系列データを含む第2のデータ(184)と、
前記異常監視部により出力される前記監視結果の時系列データを含む第3のデータ(186)とを送信可能に構成されており、
前記第2のデータにおいては、前記特徴量(1846)と、各特徴量に対応するフレームを規定する前記第1のプロセス値(1845)とが関連付けられており、
前記第3のデータにおいては、前記監視結果(1866,1867)と、各監視結果に対応するフレームを規定する前記第1のプロセス値(1865)とが関連付けられている、制御システム。 <I. Appendix>
[Configuration 1]
A control device (100) for controlling a control target,
An abnormality monitoring unit (170) that determines, for each frame defined based on a first process value (1823) related to the control target, whether there is an abnormality in the control target;
A feature value calculation unit (176) that calculates a feature value for each frame based on a second process value (1826) related to the control target in each frame and outputs the feature value to the abnormality monitoring unit;
A storage unit (130) for storing data relating to processing by the abnormality monitoring unit and the feature amount calculation unit;
A data transmission unit (134) for transmitting data stored in the storage unit to the outside,
The abnormality monitoring unit is configured to, when a feature amount for each frame is input from the feature amount calculation unit, output a monitoring result including a determination result of the presence or absence of an abnormality in the control target for each frame. ,
The data transmission unit,
First data (182) including time-series data of the first process value and the second process value;
Second data (184) including time-series data of the feature amount calculated for each frame by the feature amount calculation unit;
Third data (186) including time-series data of the monitoring result output by the abnormality monitoring unit is configured to be able to be transmitted;
In the second data, the feature value (1846) is associated with the first process value (1845) that defines a frame corresponding to each feature value,
The control device, wherein, in the third data, the monitoring result (1866, 1867) is associated with the first process value (1865) defining a frame corresponding to each monitoring result.
[Configuration 2]
The abnormality monitoring unit calculates a monitoring score, which is a degree indicating the possibility of abnormality, based on the feature amount of each frame, and determines whether there is an abnormality in the control target based on the magnitude of the calculated monitoring score. 3. The control device according to
[Configuration 3]
The control device according to
[Configuration 4]
The control according to any one of
[Configuration 5]
The feature amount calculation unit calculates the feature amount based on a temporal change of the second process value in a subframe defined based on a third process value (1824) related to the control target in each frame. Is configured to calculate,
The control device according to any one of
[Configuration 6]
[Configuration 7]
In each of the first data, the second data, and the third data, an index (1821, 1841, 1861) that is incremented or decremented for each record is added to each record. The control device according to any one of
[Configuration 8]
The data transmission unit transmits data by at least one communication protocol among HTTP (Hypertext Transfer Protocol), HTTPS (Hypertext Transfer Protocol Secure), FTP (File Transfer Protocol), and SMB (Server Message Block). 8. The control device according to any one of
[Configuration 9]
The control device according to any one of
[Configuration 10]
A control device (100) for controlling a control target;
A server device (200) for receiving data from the control device,
The control device includes:
An abnormality monitoring unit (170) that determines, for each frame defined based on a first process value (1823) related to the control target, whether there is an abnormality in the control target;
A feature value calculation unit (176) that calculates a feature value for each frame based on a second process value (1826) related to the control target in each frame and outputs the feature value to the abnormality monitoring unit;
A storage unit (130) for storing data relating to processing by the abnormality monitoring unit and the feature amount calculation unit;
A data transmission unit (134) for transmitting data stored in the storage unit to the outside,
The abnormality monitoring unit is configured to, when a feature amount for each frame is input from the feature amount calculation unit, output a monitoring result including a determination result of the presence or absence of an abnormality in the control target for each frame. ,
The data transmission unit,
First data (182) including time-series data of the first process value and the second process value;
Second data (184) including time-series data of the feature amount calculated for each frame by the feature amount calculation unit;
Third data (186) including time-series data of the monitoring result output by the abnormality monitoring unit is configured to be able to be transmitted;
In the second data, the feature value (1846) is associated with the first process value (1845) that defines a frame corresponding to each feature value,
The control system, wherein, in the third data, the monitoring result (1866, 1867) is associated with the first process value (1865) that defines a frame corresponding to each monitoring result.
<J.利点>
本実施の形態に係る制御装置によれば、制御装置100から出力される、分析用データ182、特徴量データ184、および、監視結果データ186の間には、フレームを規定する変数が示す値が共通に格納されており、そのようなフレームを規定する変数を共通のキーとすることで、監視結果、当該監視結果を出力されるために用いられた特徴量、当該特徴量を算出するためのプロセス値の各時系列データを容易に関連付けることができる。 <J. Advantages>
According to the control device according to the present embodiment, betweenanalysis data 182, feature amount data 184, and monitoring result data 186 output from control device 100, a value indicated by a variable defining a frame By using a variable that defines such a frame as a common key and is stored in common, a monitoring result, a feature amount used to output the monitoring result, and a feature amount for calculating the feature amount. Each time series data of the process value can be easily associated.
本実施の形態に係る制御装置によれば、制御装置100から出力される、分析用データ182、特徴量データ184、および、監視結果データ186の間には、フレームを規定する変数が示す値が共通に格納されており、そのようなフレームを規定する変数を共通のキーとすることで、監視結果、当該監視結果を出力されるために用いられた特徴量、当該特徴量を算出するためのプロセス値の各時系列データを容易に関連付けることができる。 <J. Advantages>
According to the control device according to the present embodiment, between
これによって、制御装置100の異常監視機能の挙動に対する事後的な評価を容易化できる。
This makes it easy to perform ex-post evaluation of the behavior of the abnormality monitoring function of the control device 100.
今回開示された実施の形態はすべての点で例示であって制限的なものではないと考えられるべきである。本発明の範囲は、上記した説明ではなく、請求の範囲によって示され、請求の範囲と均等の意味および範囲内でのすべての変更が含まれることが意図される。
The embodiments disclosed this time are to be considered in all respects as illustrative and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.
1 制御システム、2,4 フィールドネットワーク、6 ローカルネットワーク、10 フィールド装置群、12 リモートI/O装置、14 リレー群、16 I/Oユニット、18 画像センサ、20 カメラ、22 サーボドライバ、24 サーボモータ、100 制御装置、102 プロセッサ、104 チップセット、106 主記憶装置、108 二次記憶装置、110 ローカルネットワークコントローラ、112 USBコントローラ、114 メモリカードインターフェイス、116 メモリカード、118,120 フィールドバスコントローラ、122 内部バスコントローラ、124 ローカルI/Oユニット、126 タイマ、130 内部DB、132 データ書込モジュール、134 データ送信モジュール、140 機械学習エンジン、150 OS、152 スケジューラ、154 変数マネジャ、156 システム変数、158 デバイス変数、160 制御プログラム、162 シーケンスプログラム、164 モーションプログラム、170 異常監視モジュール、172 学習データ、174 きい値、176 特徴量算出モジュール、180 生データ、182 分析用データ、184 特徴量データ、186 監視結果データ、200 サーバ装置、300 表示装置、400 解析装置、510 データ定義セット、512 フレーム変数、514 特徴量の出力フレーム変数、520 特徴量定義セット、522 特徴量定義、524 プロセス値、526 サブフレーム変数、530 監視結果の出力フレーム変数、540 監視結果定義、542 判定結果定義、544 監視スコア定義、600 包装機、604 包装体、605 被包装物、606 個別包装体、610,620 ロータ、612,622 回転軸、614,624 処理機構、615,616,625,626 ヒータ、617,627 カッター、1801,1821,1841,1861 インデックス、1802,1822,1842,1862 タイムスタンプ、1803,1826 プロセス値の時系列データ、1823 フレーム変数が示す値の時系列データ、1824 サブフレーム変数が示す値の時系列データ、1825 ラベル変数が示す値の時系列データ、1843 特徴量算出結果、1844 特徴量インデックス、1845 特徴量の出力フレーム変数が示す値の時系列データ、1846 特徴量の時系列データ、1863 監視結果、1864 装置イベントインデックス、1865 監視結果の出力フレーム変数が示す値の時系列データ、1866 判定結果の時系列データ、1867 監視スコアの時系列データ。
1 control system, 2, 4 field network, 6 local network, 10 field device group, 12 remote I / O device, 14 relay group, 16 I / O unit, 18 image sensor, 20 camera, 22 servo driver, 24 servo motor , 100 controller, 102 processor, 104 chipset, 106 main storage, 108 secondary storage, 110 local network controller, 112 USB controller, 114 memory card interface, 116 memory card, 118, 120 fieldbus controller, 122 internal Bus controller, 124 local I / O unit, 126 timer, 130 internal DB, 132 data writing module, 134 data transmission module 140, machine learning engine, 150 OS, 152 scheduler, 154 variable manager, 156 system variable, 158 device variable, 160 control program, 162 sequence program, 164 motion program, 170 abnormality monitoring module, 172 learning data, 174 threshold, 176 feature data calculation module, 180 raw data, 182 data for analysis, 184 feature data, 186 monitoring result data, 200 server device, 300 display device, 400 analyzer device, 510 data definition set, 512 frame variables, 514 feature data Output frame variables, 520 feature value definition set, 522 feature value definition, 524 process value, 526 subframe variable, 530 monitor output frame variable, 5 0 monitoring result definition, 542 determination result definition, 544 monitoring score definition, 600 packaging machine, 604 packaging, 605 packaged object, 606 individual packaging, 610,620 rotor, 612,622 rotation axis, 614,624 processing mechanism, 615, 616, 625, 626 {heater, 617, 627} cutter, 1801, 1821, 1841, 1861} index, 1802, 1822, 1842, 1862 {time stamp, 1803, 1826} time series data of process value, 1823 {value of frame variable Time-series data, 1824 time-series data of the value indicated by the subframe variable, 1825 time-series data of the value indicated by the label variable, 1843 feature amount calculation result, 1844 feature amount index, 1845 output frame variable of the feature amount Time series data of values, 1846 time series data of feature quantity, 1863 monitoring result, 1864 device event index, 1865 time series data of value indicated by output frame variable of monitoring result, 1866 time series data of judgment result, 1867 monitoring score Data in chronological order.
Claims (10)
- 制御対象を制御する制御装置であって、
前記制御対象に関連する第1のプロセス値に基づいて規定されるフレーム毎に、前記制御対象での異常の有無を判断する異常監視部と、
各フレームにおける前記制御対象に関連する第2のプロセス値に基づいてフレーム毎に特徴量を算出して前記異常監視部へ出力する特徴量算出部と、
前記異常監視部および前記特徴量算出部による処理に係るデータを格納する記憶部と、
前記記憶部に格納されるデータを外部へ送信するデータ送信部とを備え、
前記異常監視部は、前記特徴量算出部からフレーム毎の特徴量が入力されると、前記制御対象での異常の有無の判断結果を含む監視結果をフレーム毎に出力するように構成されており、
前記データ送信部は、
前記第1のプロセス値および前記第2のプロセス値の時系列データを含む第1のデータと、
前記特徴量算出部によりフレーム毎に算出される前記特徴量の時系列データを含む第2のデータと、
前記異常監視部により出力される前記監視結果の時系列データを含む第3のデータとを送信可能に構成されており、
前記第2のデータにおいては、前記特徴量と、各特徴量に対応するフレームを規定する前記第1のプロセス値とが関連付けられており、
前記第3のデータにおいては、前記監視結果と、各監視結果に対応するフレームを規定する前記第1のプロセス値とが関連付けられている、制御装置。 A control device for controlling a control target,
For each frame defined based on the first process value related to the control target, an abnormality monitoring unit that determines whether there is an abnormality in the control target,
A feature value calculation unit that calculates a feature value for each frame based on a second process value related to the control target in each frame and outputs the feature value to the abnormality monitoring unit;
A storage unit that stores data relating to processing by the abnormality monitoring unit and the feature amount calculation unit,
A data transmission unit that transmits data stored in the storage unit to the outside,
The abnormality monitoring unit is configured to, when a feature amount for each frame is input from the feature amount calculation unit, output a monitoring result including a determination result of the presence or absence of an abnormality in the control target for each frame. ,
The data transmission unit,
First data including time-series data of the first process value and the second process value;
Second data including time-series data of the feature amount calculated for each frame by the feature amount calculation unit;
And configured to be able to transmit third data including time-series data of the monitoring result output by the abnormality monitoring unit,
In the second data, the feature amount is associated with the first process value that defines a frame corresponding to each feature amount,
The control device, wherein, in the third data, the monitoring result is associated with the first process value that defines a frame corresponding to each monitoring result. - 前記異常監視部は、フレーム毎の特徴量に基づいて異常の可能性を示す度合いである監視スコアを算出し、当該算出した監視スコアの大きさに基づいて前記制御対象での異常の有無を判断する、請求項1に記載の制御装置。 The abnormality monitoring unit calculates a monitoring score, which is a degree indicating the possibility of abnormality, based on the feature amount of each frame, and determines whether there is an abnormality in the control target based on the magnitude of the calculated monitoring score. The control device according to claim 1, wherein:
- 前記第3のデータの前記監視結果は、前記監視スコアと、前記監視スコアに基づく異常の有無を示す値とを含む、請求項2に記載の制御装置。 3. The control device according to claim 2, wherein the monitoring result of the third data includes the monitoring score and a value indicating presence or absence of an abnormality based on the monitoring score. 4.
- 前記データ送信部は、特定の1または複数のプロセス値の時系列データを含む第4のデータをさらに送信可能に構成されている、請求項1~3のいずれか1項に記載の制御装置。 The control device according to any one of claims 1 to 3, wherein the data transmission unit is further configured to be able to further transmit fourth data including time-series data of one or more specific process values.
- 前記特徴量算出部は、各フレーム内の前記制御対象に関連する第3のプロセス値に基づいて規定されるサブフレームにおける前記第2のプロセス値の時間変化に基づいて前記特徴量を算出するように構成されており、
前記第1のデータは、前記第3のプロセス値の時系列データをさらに含む、請求項1~4のいずれか1項に記載の制御装置。 The feature amount calculation unit calculates the feature amount based on a time change of the second process value in a subframe defined based on a third process value related to the control target in each frame. It is composed of
The control device according to claim 1, wherein the first data further includes time-series data of the third process value. - 前記第1のデータ、前記第2のデータ、前記第3のデータの各々は、各レコードに共通のタイマで管理されるタイムスタンプが付与されている、請求項1~5のいずれか1項に記載の制御装置。 The record according to any one of claims 1 to 5, wherein each of the first data, the second data, and the third data is provided with a time stamp managed by a common timer for each record. The control device as described.
- 前記第1のデータ、前記第2のデータ、前記第3のデータの各々は、レコード毎にインクリメントまたはデクリメントされるインデックスが各レコードに付与されている、請求項1~6のいずれか1項に記載の制御装置。 7. The method according to claim 1, wherein each of the first data, the second data, and the third data has an index that is incremented or decremented for each record. The control device as described.
- 前記データ送信部は、HTTP(Hypertext Transfer Protocol)、HTTPS(Hypertext Transfer Protocol Secure)、FTP(File Transfer Protocol)、および、SMB(Server Message Block)のうち、少なくとも1つの通信プロトコルでデータを送信する、請求項1~7のいずれか1項に記載の制御装置。 The data transmitting unit transmits data using at least one communication protocol of HTTP (Hypertext Transfer Protocol), HTTPS (Hypertext Transfer Protocol Secure), FTP (File Transfer Protocol), and SMB (Server Message Block). The control device according to any one of claims 1 to 7.
- 前記データ送信部は、前記第1のデータ、前記第2のデータ、前記第3のデータをCSV(Comma-Separated Values)形式で送信する、請求項1~8のいずれか1項に記載の制御装置。 The control according to any one of claims 1 to 8, wherein the data transmission unit transmits the first data, the second data, and the third data in a CSV (Comma-Separated Values) format. apparatus.
- 制御対象を制御する制御装置と、
前記制御装置からのデータを受付けるサーバ装置とを備え、
前記制御装置は、
前記制御対象に関連する第1のプロセス値に基づいて規定されるフレーム毎に、前記制御対象での異常の有無を判断する異常監視部と、
各フレームにおける前記制御対象に関連する第2のプロセス値に基づいてフレーム毎に特徴量を算出して前記異常監視部へ出力する特徴量算出部と、
前記異常監視部および前記特徴量算出部による処理に係るデータを格納する記憶部と、
前記記憶部に格納されるデータを外部へ送信するデータ送信部とを備え、
前記異常監視部は、前記特徴量算出部からフレーム毎の特徴量が入力されると、前記制御対象での異常の有無の判断結果を含む監視結果をフレーム毎に出力するように構成されており、
前記データ送信部は、
前記第1のプロセス値および前記第2のプロセス値の時系列データを含む第1のデータと、
前記特徴量算出部によりフレーム毎に算出される前記特徴量の時系列データを含む第2のデータと、
前記異常監視部により出力される前記監視結果の時系列データを含む第3のデータとを送信可能に構成されており、
前記第2のデータにおいては、前記特徴量と、各特徴量に対応するフレームを規定する前記第1のプロセス値とが関連付けられており、
前記第3のデータにおいては、前記監視結果と、各監視結果に対応するフレームを規定する前記第1のプロセス値とが関連付けられている、制御システム。 A control device for controlling a control target;
A server device that receives data from the control device,
The control device includes:
For each frame defined based on the first process value related to the control target, an abnormality monitoring unit that determines whether there is an abnormality in the control target,
A feature value calculation unit that calculates a feature value for each frame based on a second process value related to the control target in each frame and outputs the feature value to the abnormality monitoring unit;
A storage unit that stores data relating to processing by the abnormality monitoring unit and the feature amount calculation unit,
A data transmission unit that transmits data stored in the storage unit to the outside,
The abnormality monitoring unit is configured to, when a feature amount for each frame is input from the feature amount calculation unit, output a monitoring result including a determination result of the presence or absence of an abnormality in the control target for each frame. ,
The data transmission unit,
First data including time-series data of the first process value and the second process value;
Second data including time-series data of the feature amount calculated for each frame by the feature amount calculation unit;
And configured to be able to transmit third data including time-series data of the monitoring result output by the abnormality monitoring unit,
In the second data, the feature amount is associated with the first process value that defines a frame corresponding to each feature amount,
The control system, wherein in the third data, the monitoring result is associated with the first process value that defines a frame corresponding to each monitoring result.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2018175862A JP7063212B2 (en) | 2018-09-20 | 2018-09-20 | Controls and control systems |
JP2018-175862 | 2018-09-20 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020059735A1 true WO2020059735A1 (en) | 2020-03-26 |
Family
ID=69887235
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2019/036493 WO2020059735A1 (en) | 2018-09-20 | 2019-09-18 | Control device and control system |
Country Status (2)
Country | Link |
---|---|
JP (1) | JP7063212B2 (en) |
WO (1) | WO2020059735A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2023051402A (en) * | 2021-09-30 | 2023-04-11 | オムロン株式会社 | Control system, information processing method, and information processing device |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018116545A (en) * | 2017-01-19 | 2018-07-26 | オムロン株式会社 | Prediction model creating device, production facility monitoring system, and production facility monitoring method |
JP2018133037A (en) * | 2017-02-17 | 2018-08-23 | オムロン株式会社 | Control device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008116545A (en) * | 2006-11-01 | 2008-05-22 | Seiko Epson Corp | Image forming apparatus, image forming method and image forming system |
-
2018
- 2018-09-20 JP JP2018175862A patent/JP7063212B2/en active Active
-
2019
- 2019-09-18 WO PCT/JP2019/036493 patent/WO2020059735A1/en active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018116545A (en) * | 2017-01-19 | 2018-07-26 | オムロン株式会社 | Prediction model creating device, production facility monitoring system, and production facility monitoring method |
JP2018133037A (en) * | 2017-02-17 | 2018-08-23 | オムロン株式会社 | Control device |
Also Published As
Publication number | Publication date |
---|---|
JP7063212B2 (en) | 2022-05-09 |
JP2020047041A (en) | 2020-03-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6919186B2 (en) | Control system, control program and control method | |
CN109983412B (en) | Control device, computer-readable recording medium, and control method | |
JP6965798B2 (en) | Control system and control method | |
JP6504190B2 (en) | Control device and information processing method | |
JP6468313B2 (en) | Control device, control program, and control method | |
EP3822726A1 (en) | Monitoring components of manufacturing application systems with respect to application-specific metrics | |
JP2018159981A (en) | Control system, control apparatus, control program, and control method | |
US20190116100A1 (en) | Machine-to-machine (m2m) communication monitoring | |
JP7352354B2 (en) | Automatic tamper detection in network control systems | |
US10503154B2 (en) | Control device having function of collecting and saving time series data | |
WO2020129545A1 (en) | Control device and program | |
JP7168567B2 (en) | Method and Apparatus for Collecting Motion Data for Industrial Robot Applications | |
WO2020059735A1 (en) | Control device and control system | |
JP7063229B2 (en) | Controllers and control programs | |
Zimmerman et al. | Metrics and key performance indicators for robotic cybersecurity performance analysis | |
JP7028133B2 (en) | Control system and control method | |
JP7102801B2 (en) | Control system, control device and display device | |
JP2021132279A (en) | Production system, communication method, and program | |
JP7524784B2 (en) | Information processing device, control system, and report output method | |
WO2020240945A1 (en) | Control system, control device, and control program | |
EP3470945A1 (en) | Machine-to-machine (m2m) communication monitoring | |
JP2023151933A (en) | Data collection device, control system, method, and program | |
JP2022091323A (en) | Data management device and program | |
CN116894544A (en) | Data collection device, recording medium, and method | |
CN117546105A (en) | Control device, system program, and 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: 19863928 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19863928 Country of ref document: EP Kind code of ref document: A1 |