WO2024105931A1 - Production assistance system, production assistance method, and program - Google Patents

Production assistance system, production assistance method, and program Download PDF

Info

Publication number
WO2024105931A1
WO2024105931A1 PCT/JP2023/026177 JP2023026177W WO2024105931A1 WO 2024105931 A1 WO2024105931 A1 WO 2024105931A1 JP 2023026177 W JP2023026177 W JP 2023026177W WO 2024105931 A1 WO2024105931 A1 WO 2024105931A1
Authority
WO
WIPO (PCT)
Prior art keywords
mounting
units
unit
probability
log
Prior art date
Application number
PCT/JP2023/026177
Other languages
French (fr)
Japanese (ja)
Inventor
淳 中薗
芳典 持田
弥由 石田
Original Assignee
パナソニックＩｐマネジメント株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by パナソニックＩｐマネジメント株式会社 filed Critical パナソニックＩｐマネジメント株式会社
Publication of WO2024105931A1 publication Critical patent/WO2024105931A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
    • H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
    • H05K13/00—Apparatus or processes specially adapted for manufacturing or adjusting assemblages of electric components
    • H—ELECTRICITY
    • H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
    • H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
    • H05K13/00—Apparatus or processes specially adapted for manufacturing or adjusting assemblages of electric components
    • H05K13/04—Mounting of components, e.g. of leadless components

Definitions

  • This disclosure relates to a production support system, a production support method, and a program.
  • Patent Document 1 discloses a mounting board manufacturing system that makes effective use of trace information and predicts fluctuations in manufacturing quality and equipment status to appropriately set parameters for mounting equipment (mounting machines) to achieve good manufacturing quality.
  • the present disclosure provides a production support system, production support method, and program that can help identify units that cause mounting errors while minimizing increases in cost.
  • a production support system is a production support system that estimates the probability that each of a plurality of units contributed to a mounting error that occurred in a mounting machine composed of a plurality of units, and includes an acquisition unit that acquires from the mounting machine a first mounting log containing information about the mounting error and for which the probability is to be estimated, a mounting error cause estimation unit that estimates the probability for each of the plurality of units based on the first mounting log and a first estimation model based on the relationship between the number of mounting errors in each of the plurality of units and malfunctions of the units, and an output unit that outputs the estimation result of the mounting error cause estimation unit, and the first mounting log contains information about the number of productions in the plurality of units and the number of mounting errors.
  • a production support method is a production support method for estimating the probability that each of a plurality of units contributed to a mounting error that occurred in a mounting machine composed of a plurality of units, the method comprising the steps of: acquiring a first mounting log from the mounting machine, the first mounting log including information about the mounting error and for which the probability is to be estimated; estimating the probability for each of the plurality of units based on the first mounting log and a first estimation model based on the relationship between the number of mounting errors in each of the plurality of units and malfunctions of the units; and outputting the estimated estimation result; the first mounting log including information about the number of units produced and the number of mounting errors in the plurality of units.
  • a program according to one aspect of the present disclosure is a program for causing a computer to execute the above-mentioned production support method.
  • FIG. 1 is a block diagram showing a functional configuration of a production support system according to an embodiment.
  • FIG. 2 is a diagram illustrating a first example of preprocessed data according to the embodiment.
  • FIG. 3 is a diagram illustrating a second example of preprocessed data according to the embodiment.
  • FIG. 4 is a diagram illustrating an example of the first regression coefficient information according to the embodiment.
  • FIG. 5 is a diagram showing an example of a correspondence table between tape feeding accuracy and accuracy rank according to the embodiment.
  • FIG. 6 is a first flowchart showing the operation of the production support system according to the embodiment.
  • FIG. 7 is a diagram for explaining the estimation and use of the first regression coefficient according to the embodiment.
  • FIG. 8 is a diagram for explaining the estimation and use of the second regression coefficient according to the embodiment.
  • FIG. 1 is a block diagram showing a functional configuration of a production support system according to an embodiment.
  • FIG. 2 is a diagram illustrating a first example of preprocessed data according to the
  • FIG. 9 is a second flowchart showing the operation of the production support system according to the embodiment.
  • FIG. 10 is a diagram showing a first example of a screen displayed by the display device according to the embodiment.
  • FIG. 11 is a diagram showing a second example of a screen displayed by the display device according to the embodiment.
  • a production support system is a production support system that estimates the probability that each of a plurality of units contributed to a mounting error that occurred in a mounting machine composed of a plurality of units, and includes an acquisition unit that acquires from the mounting machine a first mounting log containing information about the mounting error and for which the probability is to be estimated, a mounting error cause estimation unit that estimates the probability for each of the plurality of units based on the first mounting log and a first estimation model based on the relationship between the number of mounting errors in each of the plurality of units and malfunctions of the units, and an output unit that outputs the estimation result of the mounting error cause estimation unit, and the first mounting log contains information about the number of productions in the plurality of units and the number of mounting errors.
  • the production support system can support the manager, etc. in identifying the malfunctioning unit by outputting the estimation result.
  • the production support system since it uses information on the production volume and the number of mounting errors that are output by the mounting machine as a standard function, it is possible to estimate the probability without adding sensors, etc. to the mounting machine. Therefore, the production support system according to one aspect of the present disclosure can support the identification of units that are the cause of mounting errors while suppressing increases in costs.
  • the first estimation model may be a multiple regression model in which the information on the production volume and the first regression coefficient of each of the multiple units, which is based on the distribution of the number of mounting errors in each of the multiple units, are used as explanatory variables, and the probability is used as a response variable.
  • the system may further include a first coefficient estimation unit that estimates the first regression coefficient for each of the multiple units based on the distribution of the number of mounting errors and information related to the number of production errors contained in a second mounting log of the mounting machine acquired before the first mounting log.
  • the output unit may display the probability of the mounting error for each of the multiple units.
  • the multiple units may include a tape feeder that supplies components and a nozzle that picks up the components, and may further include a tape feed accuracy estimation unit that estimates the tape feed accuracy based on the first mounting log and a second estimation model based on the relationship between the tape feed accuracy of the tape feeder and the amount of misalignment of the pickup position of the component, and the first mounting log may further include information regarding a control amount for controlling the nozzle.
  • the manager of the mounting machine can further refer to information based on the estimated tape feed accuracy to identify the malfunctioning unit.
  • the production support system can further assist the manager in identifying the malfunctioning unit while preventing an increase in costs.
  • the second estimation model may be a simple regression model including a second regression coefficient indicating the relationship between the tape feed accuracy and the amount related to the pickup position deviation of the component.
  • the production support system can further assist managers in identifying malfunctioning units while minimizing the increase in the amount of processing required to estimate tape feed accuracy.
  • the system may further include a second coefficient estimation unit that estimates the second regression coefficient for each of the multiple units based on a distribution between a control amount for controlling the nozzle included in a third mounting log of the mounting machine acquired before the first mounting log and a measured value of the tape feed accuracy of the tape feeder.
  • the output unit may display information regarding the tape feed accuracy estimated by the tape feed accuracy estimation unit.
  • the mounting machine does not need to be equipped with a sensor that directly measures the state of the multiple units.
  • the mounting machine does not need to be equipped with a hardware sensor, making it possible to more reliably reduce the cost of the mounting machine.
  • the multiple units may include a head spindle, a nozzle, and a feeder
  • the mounting error cause estimation unit may estimate the probability of each of the head spindle, the nozzle, the feeder, and the components supplied by the feeder.
  • the production support system can estimate the probability of multiple units, including the head spindle, nozzle, and feeder, as well as each component.
  • the production support system can assist managers, etc. in determining whether the cause of a mounting error is the head spindle, nozzle, feeder, or component.
  • a production support method is a production support method for estimating the probability that each of a plurality of units contributed to a mounting error that occurred in a mounting machine composed of a plurality of units, the method comprising the steps of: acquiring a first mounting log from the mounting machine, the first mounting log including information about the mounting error and for which the probability is to be estimated; estimating the probability for each of the plurality of units based on the first mounting log and a first estimation model based on the relationship between the number of mounting errors in each of the plurality of units and malfunctions of the units; and outputting the estimated estimation result, the first mounting log including information about the number of productions in the plurality of units and the number of mounting errors.
  • a program is a program for causing a computer to execute the above production support method.
  • each figure is a schematic diagram and is not necessarily an exact illustration. Therefore, for example, the scales and the like do not necessarily match in each figure.
  • substantially the same configuration is given the same reference numerals, and duplicate explanations are omitted or simplified.
  • ordinal numbers such as “first” and “second” do not refer to the number or order of components, unless otherwise specified, but are used for the purpose of avoiding confusion between and distinguishing between components of the same type.
  • Fig. 1 is a block diagram showing the functional configuration of a production support system 1 according to the present embodiment.
  • the production support system 1 includes a coefficient estimation device 20, a factor probability estimation device 30, and a display device 40.
  • the production support system 1 is a system for supporting production using a mounting machine 10. Specifically, the production support system 1 indirectly estimates the factor probability (also written as error factor probability or mounting error factor probability) of a unit (equipment unit) for a mounting error that occurs in the mounting machine 10 without using data from a sensor that directly senses the unit. In addition, in this embodiment, the production support system 1 also indirectly estimates the tape feed accuracy of the feeder without using data from a sensor that directly senses the tape feed accuracy of the feeder.
  • the sensor is, for example, a sensor that measures multiple units, such as a sensor that measures the feeder's component supply position, component mounting position, etc.
  • the mounting machine 10 is an example of a production facility that constitutes a manufacturing line, and is a mounting facility (component mounting device) that mounts components on a target object (workpiece) such as a board.
  • the mounting machine 10 is composed of multiple units.
  • the mounting machine 10 has a drive control unit (hereinafter also referred to as a spindle), a component mounting head unit (hereinafter also referred to as a nozzle), and a component supply unit (hereinafter also referred to as a feeder) as units.
  • the drive control unit controls the rotation and movement of the component mounting head unit.
  • the drive control unit has a head spindle that controls the rotation of the component mounting head unit by driving a motor.
  • the component mounting head unit mounts (mounts) components supplied to the component supply position (component suction position) of the feeder on the board.
  • the component mounting head unit is composed of a mounting head (head) equipped with a component suction nozzle (nozzle) that can pick up components from the feeder and raise and lower them individually.
  • the head is equipped with, for example, multiple nozzles.
  • the component supply unit has one or more feeders arranged side by side, each of which supplies components to the component supply position.
  • the feeder is a tape feeder.
  • the mounting machine 10 periodically outputs the first mounting log L1 to the factor probability estimation device 30 during production.
  • the mounting machine 10 may output the first mounting log L1, for example, every time one component is mounted on the board, or every time a predetermined number of components are mounted on the board.
  • the first mounting log L1 includes information on the control of each unit acquired during the period from the operation of picking up a component from the feeder to the operation of mounting the component on the board in the mounting machine 10, and information indicating the production results.
  • the first mounting log L1 is a log output by the mounting machine 10 as a standard function.
  • the first mounting log L1 includes information on the control amount for controlling multiple units, information identifying the multiple units used in production, and information on the production results.
  • the information on the control amount includes, for example, information on the control amount (correction amount) for controlling the movement and rotation of the unit (e.g., nozzle) (e.g., pick-up correction amount and recognition correction amount described later).
  • the information indicating the production results includes information on the number of productions (e.g., the number of pick-up attempts) and the number of mounting errors.
  • the first mounting log L1 does not include data obtained by directly sensing the unit (i.e., data from a hard sensor).
  • the number of mounting machines 10 supported by the production support system 1 is not particularly limited, and may be one or more.
  • the components are electronic components, such as, but not limited to, resistors and capacitors.
  • the target object is not limited to a substrate, but may be any workpiece that can be subjected to a specified process.
  • the mounting machine 10 does not have to have sensors (hard sensors) that directly measure the status (e.g., operation) of the drive control unit, the component mounting head unit, and the component supply unit.
  • the sensors include, for example, sensors that are not standard equipment on the mounting machine 10 and are installed later. Whether or not they are standard equipment can be confirmed by referring to the catalog of the mounting machine 10, etc.
  • the coefficient estimation device 20 executes a process of estimating each regression coefficient using the second mounting log L2 acquired in advance from the mounting machine 10.
  • "In advance" means before the above estimation process is executed (for example, before the first mounting log L1 is acquired).
  • the second mounting log L2 is a mounting log for advance estimation used to estimate each regression coefficient in advance.
  • the second mounting log L2 is the same data as the first mounting log L1, and includes information on the control of each unit acquired in the mounting machine 10 from the operation of picking up a component from a feeder to the operation of mounting the component on a board.
  • the second mounting log L2 is a log output by the mounting machine 10 as a standard function.
  • the second mounting log L2 includes information on the control amount for controlling multiple units, the number of mounting errors, information identifying multiple units used in production, and information on production results.
  • the information on the control amount includes, for example, information on the correction amount for correcting the movement and rotation of a unit (for example, a nozzle) (for example, the pick-up correction amount and the recognition correction amount described later).
  • the information about production performance includes the number of productions (e.g., the number of pickup attempts) and the number of mounting errors.
  • the second mounting log L2 does not include data obtained by directly sensing the unit (i.e., data from a hardware sensor).
  • the second mounting log L2 may be used as a third mounting log.
  • the coefficient estimation device 20 includes a miss count preprocessing unit 21, a correction amount preprocessing unit 22, a nonlinear regression coefficient estimation unit 23, and a linear regression coefficient estimation unit 24.
  • the coefficient estimation device 20 can be realized by a CPU (Central Processing Unit) and a memory, etc. Furthermore, the processing by each of the functional blocks of the coefficient estimation device 20 is usually realized by a program execution unit such as a processor reading and executing software (programs) recorded on a recording medium such as a ROM.
  • the error count preprocessing unit 21 acquires the second mounting log L2 from the mounting machine 10, extracts data from the second mounting log L2 that is used to estimate the first regression coefficient in the nonlinear regression coefficient estimating unit 23, and outputs the extracted preprocessed data to the nonlinear regression coefficient estimating unit 23.
  • Figure 2 is a diagram showing a first example of preprocessed data according to this embodiment.
  • Figure 2 shows an example of preprocessed data output from the error count preprocessing unit 21 to the nonlinear regression coefficient estimating unit 23.
  • the pre-processed data includes "index,” “feeder serial number,” “head spindle number,” “nozzle serial number,” “component serial number,” “component size,” “number of pickup attempts,” and “number of mounting errors.”
  • the index is a number assigned to each combination of "feeder,” “head spindle,” “nozzle,” and “part size.”
  • the pre-processed data is aggregated for each combination of "feeder,” “head spindle,” “nozzle,” and “part size.”
  • the feeder serial is the identification information (e.g., identification number) for each feeder.
  • the head spindle number is an identification number used to identify the head spindle that controlled the rotation of the nozzle.
  • the nozzle serial number is identification information (e.g., an identification number) for each nozzle.
  • identification information e.g., an identification number
  • a single component mounting head unit is equipped with multiple nozzles, and each of the multiple nozzles is assigned a different identification number.
  • the component size indicates the width of the component used in production.
  • "1.0" in FIG. 2 indicates that the width of the component when viewed from above is 1 mm.
  • the width of a component is the length in the direction (X direction) perpendicular to the direction in which the component moves in the feeder (Y direction).
  • the X direction is the direction in which the board is transported in the mounting machine 10.
  • the part serial number is identification information (e.g., an identification number) used to identify the part supplied by the feeder.
  • the number of pickup attempts indicates the number of times a part is picked up by the nozzle.
  • the number of pickup attempts is the number of times the nozzle picks up a part during a specified period or during a specified number of production runs (e.g., 1 lot).
  • the number of mounting errors indicates the number of times a mounting error occurred out of the number of pickup attempts. Mounting errors include failure to pick up the component by the nozzle, failure to mount the component on the board, etc.
  • index "1" indicates that 12 mounting errors occurred when mounting a component with identification information "CP0001” and size "1.0" from a feeder with identification information "FD00001” 1000 times using a nozzle with identification information "NZ00001” whose rotation is controlled by a head spindle with identification number "1".
  • the preprocessed data includes information identifying the unit that mounted the component, information identifying the component to be mounted, and information related to production performance.
  • a malfunction is an alert that does not necessarily involve the stop of the mounting machine 10, and is, for example, a state in which it is suspected that a failure or deterioration has occurred in at least one of the feeder, head spindle, and nozzle.
  • the correction amount preprocessing unit 22 acquires the second mounting log L2 from the mounting machine 10, extracts data from the second mounting log L2 that is used to estimate the second regression coefficient in the linear regression coefficient estimating unit 24, and outputs the extracted preprocessed data to the linear regression coefficient estimating unit 24.
  • FIG. 3 is a diagram showing a second example of preprocessed data according to this embodiment.
  • FIG. 3 shows an example of preprocessed data output from the correction amount preprocessing unit 22 to the linear regression coefficient estimating unit 24.
  • the pre-processed data includes "index,” "feeder serial number,” “head spindle number,” “nozzle serial number,” “part serial number,” “part size,” “number of pickup attempts,” and "each correction amount.”
  • Each correction amount includes a recognition correction amount and a pickup correction amount.
  • the recognition correction amount and the pickup correction amount include a correction amount for the X coordinate and a correction amount for the Y coordinate, as well as the average, median, and standard deviation of the correction amounts.
  • the recognition correction amount indicates the correction amount of the nozzle's position in the X-axis and Y-axis directions after the nozzle picks up a component.
  • the recognition correction amount indicates, for example, the adjustment amount of the nozzle's position in the X-axis and Y-axis directions to mount the component at the mounting target position on the board.
  • the recognition correction amount is a value based on the difference between the position where the nozzle picks up the component and the pickup target position.
  • the suction correction amount indicates the amount of correction made to the nozzle position in the X-axis and Y-axis directions when the nozzle picks up a component.
  • the suction correction amount indicates, for example, the adjustment amount made when the nozzle position is adjusted so that the nozzle can pick up the component's suction target position (for example, the center position on the top surface of the component).
  • the suction correction amount is a value based on the difference between the suction target position of the component supplied by the feeder and the suction center of the nozzle.
  • each correction amount can be identified from an image captured by an imaging device provided in the mounting machine 10.
  • the correction amount preprocessing unit 22 may further calculate the adsorption position deviation statistics, which will be described later, based on the recognition correction amount and the adsorption correction amount.
  • the adsorption position deviation statistics may be included in the preprocessed data.
  • each correction amount is essential information in the pre-processed data output from the correction amount pre-processing unit 22.
  • the nonlinear regression coefficient estimator 23 estimates a first regression coefficient for estimating the probability of a unit being responsible for a mounting error based on the preprocessed data shown in FIG. 2.
  • the main elements in the component mounting process are the feeder, head spindle, nozzle, and component size.
  • the first regression coefficient is a coefficient used to identify whether a mounting error included in the first mounting log L1 is caused by the feeder, head spindle, nozzle, or component size.
  • the first mounting log L1 is a log that contains information on the same items as the second mounting log L2.
  • the nonlinear regression coefficient estimator 23 is an example of a first coefficient estimator.
  • the mounting error factor estimation unit 33 of the factor probability estimation device 30 uses "logistic regression analysis," a type of nonlinear regression analysis, as a method for determining the probability of each factor when a mounting error occurs from the feeder, head spindle, nozzle, and component size involved in the component mounting process. Therefore, the nonlinear regression coefficient estimation unit 23 estimates the first regression coefficient used in the logistic regression analysis. Specifically, the nonlinear regression coefficient estimation unit 23 estimates the first regression coefficient of the linear predictor included in the logistic function (see Equation 2 described below) used in the logistic regression analysis.
  • the nonlinear regression coefficient estimation unit 23 estimates the first regression coefficient of each element using the Markov Chain Monte Carlo (MCMC) method from the distribution of the number of pickup attempts and the number of mounting errors for the combination of the elements of the feeder, head spindle, nozzle, and component size.
  • the MCMC method is a method for obtaining samples (generating random numbers) from a multivariate probability distribution, and is a method that is often used when performing maximum likelihood estimation of multiple parameters (here, regression coefficients) that make up a statistical model, as in the present disclosure.
  • Each element includes, for example, a feeder, head spindle, nozzle, and component (component size).
  • the first regression coefficient is an explanatory variable in the first estimation model 33a.
  • FIG. 4 shows an example of the first regression coefficient information according to this embodiment.
  • index As shown in Figure 4, these include “index,” “feeder serial,” “head spindle number,” “nozzle serial,” “component serial,” “component size,” “number of pickup attempts,” “number of mounting errors,” “bias term,” and “regression coefficients.”
  • the bias term is used to calculate the linear predictor included in the logistic function.
  • the bias term is a preset constant (e.g., ⁇ ).
  • Each regression coefficient includes a feeder regression coefficient which is the first regression coefficient of the feeder, a head spindle regression coefficient which is the first regression coefficient of the head spindle, a nozzle regression coefficient which is the first regression coefficient of the nozzle, and a component size regression coefficient which is the first regression coefficient of the component size.
  • a feeder regression coefficient which is the first regression coefficient of the feeder
  • a head spindle regression coefficient which is the first regression coefficient of the head spindle
  • a nozzle regression coefficient which is the first regression coefficient of the nozzle
  • component size regression coefficient which is the first regression coefficient of the component size.
  • the first regression coefficient of a feeder with a feeder serial number of "FD00001” is ⁇ f [1]
  • the first regression coefficient of a feeder with a feeder serial number of "FD00002" is ⁇ f [2].
  • head spindle, the nozzle, and the component size is the same applies.
  • the linear regression coefficient estimation unit 24 estimates a second regression coefficient for estimating tape feed accuracy based on the preprocessed data shown in FIG. 3.
  • the tape feed accuracy indicates the position accuracy when the feeder (tape feeder) supplies components to the component supply position by tape feed.
  • the linear regression coefficient estimation unit 24 estimates a linear regression model and its second regression coefficient (linear regression coefficient) that associates statistics (suction position deviation statistics) obtained from each correction amount shown in FIG. 3 with the measurement value of the suction position deviation (for example, the measured value of the tape feed accuracy of the tape feeder) based on the distribution of the statistics. For example, the linear regression coefficient estimation unit 24 plots the suction position deviation statistics and the measurement value of the feed accuracy corresponding to the suction position deviation statistics with the horizontal axis representing the suction position deviation statistics and the vertical axis representing the feed accuracy (measurement value of the inspection device), and estimates the second regression coefficient based on the distribution of the plot.
  • the inspection device is configured to include a hardware sensor that directly measures the tape feed accuracy.
  • the linear regression coefficient estimation unit 24 is an example of a second coefficient estimation unit.
  • the linear regression coefficient estimation unit 24 estimates the second regression coefficient in the X direction based on the distribution of the X direction statistics (X direction suction position shift statistics) obtained from the correction amount in the X direction (X coordinate) among the correction amounts shown in FIG. 3, and the measurement value of the suction position shift in the X direction (for example, the X direction measurement value of the tape feed accuracy of the tape feeder). Also, for example, the linear regression coefficient estimation unit 24 estimates the second regression coefficient in the Y direction based on the distribution of the Y direction statistics (Y direction suction position shift statistics) obtained from the correction amount in the Y direction (Y coordinate) among the correction amounts shown in FIG. 3, and the measurement value of the suction position shift in the Y direction (for example, the Y direction measurement value of the tape feed accuracy of the tape feeder).
  • the second estimation model 34a generated by the linear regression coefficient estimation unit 24 is a simple regression model that includes a second regression coefficient that indicates the relationship between the tape feed accuracy and the amount of component pickup position deviation in each of the multiple units.
  • the linear regression coefficient estimation unit 24 calculates the adsorption position shift statistics based on the recognition correction amount and the adsorption correction amount.
  • the linear regression coefficient estimation unit 24 calculates the adsorption position shift statistics based on, for example, the average or median of the recognition correction amount and the average or median of the adsorption correction amount.
  • the adsorption position shift statistics may also be calculated using a standard deviation.
  • the adsorption position shift statistics are calculated for each of the X coordinate and the Y coordinate. In other words, a second regression coefficient is estimated for each of the X coordinate and the Y coordinate.
  • the factor probability estimation device 30 outputs an estimation result of the cause of the mounting error and the tape feed accuracy based on the first and second regression coefficients estimated by the coefficient estimation device 20 and the first mounting log L1.
  • the first mounting log L1 is a log of the measurement target (estimation target) acquired during production by the mounting machine 10.
  • the factor probability estimation device 30 outputs an estimation result of the cause of the mounting error and the tape feed accuracy using the first mounting log L1 acquired during production of the mounting machine 10. In this way, the factor probability estimation device 30 can assist the manager, etc. in determining malfunction of the unit during production of the mounting machine 10, making it possible for the manager, etc. to perform maintenance before the unit breaks down.
  • the factor probability estimation device 30 comprises an error count preprocessing unit 31, a correction amount preprocessing unit 32, a mounting error factor estimation unit 33, a tape feed accuracy estimation unit 34, and aggregation units 35 to 38.
  • the factor probability estimation device 30 can be realized by a CPU, memory, etc.
  • the processing by each of the functional blocks of the factor probability estimation device 30 is usually realized by a program execution unit such as a processor reading and executing software (programs) recorded on a recording medium such as a ROM.
  • the functions of the error count preprocessing unit 31 and the correction amount preprocessing unit 32 are similar to those of the error count preprocessing unit 21 and the correction amount preprocessing unit 22, and therefore a description thereof will be omitted.
  • the error count preprocessing unit 31 acquires the first mounting log L1 from the mounting machine 10, generates the preprocessed data shown in FIG. 2 from the acquired first mounting log L1, and outputs the preprocessed data including the data shown in FIG. 2 and pickup position deviation statistics from the acquired first mounting log L1, and outputs the preprocessed data to the tape feed accuracy estimation unit 34.
  • the implementation error cause estimation unit 33 estimates the cause probability of the unit for the implementation error contained in the preprocessed data based on the preprocessed data from the error count preprocessing unit 31 and the first regression coefficient from the nonlinear regression coefficient estimation unit 23.
  • the implementation error cause estimation unit 33 estimates the cause probability of the unit in the first implementation log L1 to be measured using a first estimation model 33a based on the first regression coefficient.
  • the mounting error cause estimation unit 33 calculates the probability that each element (e.g., each unit) was the cause of an error that occurred using a binomial distribution derived based on the preprocessed data and the first regression coefficient.
  • the probability p of y mounting errors occurring after N pick-ups is expressed as the following equation 1 as a binomial distribution model.
  • q indicates the probability of a mounting error factor per pickup attempt for each element.
  • the probability q of a mounting error factor is expressed as the following formula 2.
  • z is a linear predictor
  • ⁇ f is the first regression coefficient of the feeder
  • ⁇ n is the first regression coefficient of the nozzle
  • ⁇ s is the first regression coefficient of the head spindle
  • ⁇ c is the first regression coefficient of the part size
  • ⁇ is the bias term
  • chipW is the part size, which is expressed by the following equation 3.
  • the linear predictor z can be calculated from the preprocessed data from the error count preprocessing unit 31.
  • Equations 2 and 3 are examples of the first estimation model 33a.
  • the first estimation model 33a is a statistical model based on the relationship between the number of mounting errors in each of multiple units and the malfunction of the unit.
  • the first estimation model 33a can also be said to be an identification model for identifying a malfunctioning unit from multiple units.
  • the mounting error cause estimation unit 33 calculates the probability q of the mounting error cause by substituting the linear predictor z obtained by substituting the first regression coefficients of the feeder, nozzle, head spindle, and component size at the time when the mounting error occurred into Equation 3 into Equation 2.
  • the mounting error cause estimation unit 33 calculates the probability q of the mounting error cause for each of the feeder, nozzle, head spindle, and component size.
  • the probability q is the objective variable in the first estimation model 33a.
  • the first estimation model 33a is a multiple regression model in which the first regression coefficient (the regression coefficient) is an explanatory variable and the probability q is an objective variable.
  • the tape feed accuracy estimation unit 34 estimates the tape feed accuracy of the feeder of the mounting machine 10 based on the preprocessed data from the correction amount preprocessing unit 32 and the second regression coefficient from the linear regression coefficient estimation unit 24. A second estimation model 34a is generated including the second regression coefficient. The tape feed accuracy estimation unit 34 estimates the tape feed accuracy in the first mounting log L1 to be measured using the second estimation model 34a based on the relationship between the tape feed accuracy of the tape feeder and the component pickup position deviation statistics.
  • the tape feed accuracy estimation unit 34 uses the second regression coefficient to estimate the tape feed accuracy corresponding to the pickup position deviation statistics calculated based on the first mounting log L1 of the measurement target.
  • the tape feed accuracy is, for example, a distance.
  • the tape feed accuracy estimation unit 34 also estimates the accuracy rank of the feeder based on a correspondence table between tape feed accuracy and accuracy rank (see FIG. 5 below).
  • the accuracy rank is the accuracy rank at that time and may change over time.
  • FIG. 5 is a diagram showing an example of a correspondence table between tape feed accuracy and accuracy rank in this embodiment.
  • X-direction feed accuracy means tape feed accuracy in the X direction
  • Y-direction feed accuracy means tape feed accuracy in the Y direction.
  • one accuracy rank is associated with each X-direction feed accuracy and Y-direction feed accuracy.
  • the accuracy ranks are "A”, "B”, “C”, and "D", which indicate increasing feed accuracy in that order.
  • the accuracy rank is an example of information based on tape feed accuracy.
  • the aggregation unit 35 accumulates the error cause probability for each component size from the mounting error cause estimation unit 33, and outputs the error cause probability for each component serial number.
  • the aggregation unit 36 accumulates the error cause probability for each nozzle from the mounting error cause estimation unit 33 and outputs the error cause probability for each nozzle serial number.
  • the aggregation unit 37 accumulates the error cause probability for the head spindle from the mounting error cause estimation unit 33, and outputs the error cause probability for each head spindle number.
  • the aggregation unit 38 accumulates the error cause probability for the feeder from the mounting error cause estimation unit 33 and the tape feed accuracy from the tape feed accuracy estimation unit 34, and outputs the error cause probability and accuracy rank for each feeder serial.
  • the counting units 35 to 38 accumulate the error cause probabilities for a predetermined number of production runs (e.g., one lot), and calculate one error cause probability for the predetermined number of production runs based on the accumulated error cause probabilities.
  • the counting units 35 to 38 may, for example, accumulate the error cause probabilities for a predetermined number of production runs, and estimate the average value as the one error cause probability.
  • the error cause probability is an example of an estimation result.
  • the display device 40 displays various information.
  • the display device 40 displays the results of the estimation of the cause probability of mounting errors and the tape feed accuracy by the cause probability estimation device 30.
  • the display device 40 is a liquid crystal display device or the like, but is not limited to this.
  • the coefficient estimation device 20, the factor probability estimation device 30, and the display device 40 may each be realized as separate devices, or at least two of the devices may be realized as an integrated device.
  • the coefficient estimation device 20 and the factor probability estimation device 30 may be realized as an integrated device, or the coefficient estimation device 20, the factor probability estimation device 30, and the display device 40 may be realized as an integrated device.
  • Fig. 6 is a first flowchart showing the operation (production support method) of the production support system 1 according to this embodiment.
  • Fig. 6 shows the operation of estimating the first regression coefficient and the second regression coefficient. The process of Fig. 6 is executed by the coefficient estimation device 20.
  • each of the error count preprocessing unit 21 and the correction amount preprocessing unit 22 of the coefficient estimation device 20 acquires a second implementation log L2 for advance estimation (S10).
  • the error count preprocessing unit 21 and the correction amount preprocessing unit 22 function as an acquisition unit that acquires the second implementation log L2.
  • the error count preprocessing unit 21 and the correction amount preprocessing unit 22 each perform preprocessing (S20).
  • the error count preprocessing unit 21 performs preprocessing on the second mounting log L2 to generate, for example, preprocessed data shown in FIG. 2, and outputs the preprocessed data to the nonlinear regression coefficient estimating unit 23.
  • the correction amount preprocessing unit 22 performs preprocessing on the second mounting log L2 to generate, for example, preprocessed data shown in FIG. 3, and outputs the preprocessed data to the linear regression coefficient estimating unit 24.
  • the correction amount preprocessing unit 22 outputs the preprocessed data including the pickup position deviation statistics to the linear regression coefficient estimating unit 24.
  • the nonlinear regression coefficient estimation unit 23 estimates the first regression coefficient based on the preprocessed data from the error count preprocessing unit 21 (S30).
  • Figure 7 is a diagram for explaining the estimation and use of the first regression coefficient according to this embodiment. Note that the error count preprocessing units 21 and 31 are not shown in Figure 7.
  • the nonlinear regression coefficient estimation unit 23 estimates the first regression coefficient of each element using the MCMC method based on the second implementation log L2, and outputs the estimated first regression coefficient to the implementation error factor estimation unit 33 of the factor probability estimation device 30.
  • the implementation error factor estimation unit 33 functions as an acquisition unit that acquires the first regression coefficient.
  • the linear regression coefficient estimator 24 estimates the second regression coefficient based on the preprocessed data from the correction amount preprocessor 22 (S40).
  • FIG. 8 is a diagram for explaining the estimation and use of the second regression coefficient according to this embodiment.
  • the linear regression coefficient estimation unit 24 estimates the second regression coefficient based on the pickup position deviation statistics based on the second mounting log L2 and the distribution of the inspection measurement value M of the inspection device, and outputs the estimated second regression coefficient to the tape feed accuracy estimation unit 34 of the factor probability estimation device 30.
  • the tape feed accuracy estimation unit 34 functions as an acquisition unit that acquires the second regression coefficient.
  • first mounting log L1, the second mounting log L2, and the inspection measurement value M shown in FIG. 8 are data acquired using the same mounting machine 10.
  • FIG. 9 is a second flowchart showing the operation (production support method) of the production support system 1 according to this embodiment.
  • the process of steps S110 to S170 shown in FIG. 9 is performed by the factor probability estimation device 30, and step S180 is performed by the display device 40.
  • each of the error count preprocessing unit 31 and the correction amount preprocessing unit 32 of the factor probability estimation device 30 acquires the first implementation log L1 of the measurement target (S110).
  • the error count preprocessing unit 31 and the correction amount preprocessing unit 32 function as an acquisition unit that acquires the first implementation log L1.
  • each of the error count preprocessing unit 31 and the correction amount preprocessing unit 32 executes preprocessing (S120).
  • the error count preprocessing unit 31 executes preprocessing on the first mounting log L1 to generate, for example, preprocessed data shown in FIG. 2, and outputs the preprocessed data to the mounting error cause estimation unit 33.
  • the correction amount preprocessing unit 32 executes preprocessing on the first mounting log L1 to generate, for example, preprocessed data shown in FIG. 3, and outputs the preprocessed data to the tape feed accuracy estimation unit 34.
  • the correction amount preprocessing unit 32 outputs preprocessed data including the pickup position deviation statistics to the tape feed accuracy estimation unit 34.
  • the mounting error factor estimation unit 33 acquires the first regression coefficient from the nonlinear regression coefficient estimation unit 23 (S130) and estimates the error factor probability of each element (S140). As shown in FIG. 7, the mounting error factor estimation unit 33 estimates the error factor probability of each element based on the preprocessed data from the error count preprocessing unit 31 (preprocessed data based on the first mounting log L1), the first regression coefficient, and the above formulas 2 and 3.
  • FIG. 7 shows an example in which the mounting error factor estimation unit 33 outputs the feeder factor probability.
  • the mounting error factor estimation unit 33 outputs the error factor probability for each component serial number to the aggregation unit 35, outputs the error factor probability for each nozzle serial number to the aggregation unit 36, outputs the error factor probability for each head spindle number to the aggregation unit 37, and outputs the error factor probability for each feeder serial number to the aggregation unit 38.
  • the tape feed accuracy estimation unit 34 acquires the second regression coefficient from the linear regression coefficient estimation unit 24 (S150) and estimates the tape feed accuracy of the feeder (S160). As shown in FIG. 8, the tape feed accuracy estimation unit 34 estimates the tape feed accuracy of the feeder based on the suction position deviation statistics from the correction amount preprocessing unit 32 and the second regression coefficient. The tape feed accuracy estimation unit 34 estimates the tape feed accuracy in the X direction based on the suction position deviation statistics in the X direction and the second regression coefficient in the X direction, and estimates the tape feed accuracy in the Y direction based on the suction position deviation statistics in the Y direction and the second regression coefficient in the Y direction.
  • the tape feed accuracy estimation unit 34 estimates the accuracy rank of the feeder based on the estimated tape feed accuracy in the X direction and Y direction and the correspondence table shown in FIG. 5 (S170).
  • the tape feed accuracy estimation unit 34 outputs the accuracy rank to the aggregation unit 38.
  • Figure 10 is a diagram showing a first example of a screen displayed by the display device 40 according to this embodiment.
  • Figure 10 shows the results of determining the causes of mounting errors.
  • the display device 40 displays the error cause probability from the cause probability estimation device 30.
  • FIG. 10 shows an example in which the error cause probability for each of LOT01 to LOT03 at head spindle addresses "1" and "2" is displayed. The addresses correspond to the serial number. The probability that the head spindle at address "1" is the cause of the mounting error that occurred in LOT01 is 10%, the probability that it is the cause of the mounting error that occurred in LOT02 is 5%, and the probability that it is the cause of the mounting error that occurred in LOT03 is 8%.
  • the probability that the head spindle at address "2" is the cause of the mounting error that occurred in LOT01 is 90%
  • the probability that it is the cause of the mounting error that occurred in LOT02 is 80%
  • the probability that it is the cause of the mounting error that occurred in LOT03 is 100%.
  • the display device 40 may also display the average value of the error cause probability for each LOT (average over the period shown in FIG. 10). This makes it easier for the manager to determine which elements are normal and which elements are malfunctioning.
  • the sum of the probability of a miss cause for the head spindle at address "1" and the probability of a miss cause for each of the nozzles, parts, and feeders corresponding to the head spindle at address "1" is 100%.
  • FIG. 11 is a diagram showing a second example of a screen displayed by the display device 40 according to the present embodiment.
  • FIG. 11 shows the judgment result of the tape feed accuracy. Specifically, FIG. 11 shows the accuracy rank (rank shown in FIG. 11) of the tape feed accuracy of the feeder.
  • the display device 40 displays the judgment results of the tape feed accuracy from the factor probability estimation device 30.
  • FIG. 11 shows an example of displaying the judgment results of the tape feed accuracy for each of LOT01 to LOT03 at feeder addresses "1" and "2".
  • the addresses correspond to the serial numbers.
  • the accuracy rank of the feeder with address "1" (serial number: FD0001) in LOT01 is "B”
  • the accuracy rank of the feeder with address "2" (serial number: FD0002) in LOT01 is "D”
  • the accuracy rank of the feeder with address "2" (serial number: FD0002) in LOT01 is "C”
  • the accuracy rank of each lot of the feeder is displayed on one screen, which can help the manager of the mounting machine 10 to determine which feeders are normal and which are malfunctioning.
  • the display device 40 may display the error cause probability and the accuracy rank on one screen.
  • the display device 40 may also display the estimated value of the tape feeding accuracy instead of or together with the accuracy rank.
  • the state of the mounting machine 10 (the state of each unit) can be estimated with high accuracy without increasing costs (without adding hardware sensors). This enables pinpoint maintenance, and reduces equipment performance losses (e.g., short or long stoppages of the mounting machine 10) at low cost.
  • the mounting error cause estimation unit estimates the cause probability of a mounting error using logistic regression analysis, but the cause probability of a mounting error may be estimated using other nonlinear regression analyses.
  • the mounting error cause estimation unit may estimate the cause probability of a mounting error using, for example, polynomial regression analysis, support vector regression analysis, etc.
  • the feeder was a tape feeder, but it may be another feeder, such as a bulk feeder.
  • the factor probability estimation device does not need to be equipped with a tape feed accuracy estimation unit.
  • each of the coefficient estimation device and the factor probability estimation device may be a terminal device located in a factory or the like where the mounting machine is located, or may be a server device located remotely from the factory.
  • first regression coefficient and the second regression coefficient according to the above embodiment may be estimated only once, for example, or may be estimated periodically, and the first regression coefficient and the second regression coefficient used in the factor probability estimation device may be updated periodically. Furthermore, the first regression coefficient and the second regression coefficient may be estimated after the occurrence of a specified event, for example, replacing a unit with a new one or repairing a malfunction.
  • first implementation log and the second implementation log in the above embodiment are also referred to as equipment logs.
  • the tape feed accuracy was estimated based on the suction position deviation statistics, but the tape feed accuracy may also be estimated based on, for example, either the recognition correction amount or the suction correction amount.
  • each component may be configured with dedicated hardware, or may be realized by executing a software program suitable for each component.
  • Each component may be realized by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory.
  • the division of functional blocks in the block diagram is one example, and multiple functional blocks may be realized as one functional block, one functional block may be divided into multiple blocks, or some functions may be transferred to other functional blocks. Furthermore, the functions of multiple functional blocks having similar functions may be processed in parallel or in a time-shared manner by a single piece of hardware or software.
  • the production support system may be realized as a single device, or may be realized by multiple devices.
  • each component of the production support system may be allocated in any manner to the multiple devices.
  • the communication method between the multiple devices is not particularly limited, and may be wireless communication or wired communication. Furthermore, wireless communication and wired communication may be combined between the devices.
  • each component described in the above embodiment may be realized as software, or may be realized as an LSI, which is typically an integrated circuit. These may be individually integrated into one chip, or may be integrated into one chip to include some or all of them.
  • LSI is used, but depending on the degree of integration, it may be called IC, system LSI, super LSI, or ultra LSI.
  • the method of integration is not limited to LSI, and may be realized with a dedicated circuit (a general-purpose circuit that executes a dedicated program) or a general-purpose processor. After LSI manufacture, a programmable FPGA (Field Programmable Gate Array) or a reconfigurable processor that can reconfigure the connection or settings of the circuit cells inside the LSI may be used.
  • a programmable FPGA Field Programmable Gate Array
  • reconfigurable processor that can reconfigure the connection or settings of the circuit cells inside the LSI may be used.
  • an integrated circuit technology that replaces LSI appears due to advances in semiconductor technology or a
  • a system LSI is an ultra-multifunctional LSI manufactured by integrating multiple processing functions onto a single chip, and is specifically a computer system that includes a microprocessor, ROM (Read Only Memory), RAM (Random Access Memory), etc. Computer programs are stored in the ROM. The system LSI achieves its functions when the microprocessor operates according to the computer program.
  • Another aspect of the present disclosure may be a computer program that causes a computer to execute each of the characteristic steps included in the production support method shown in either FIG. 6 or FIG. 9.
  • the program may be a program to be executed by a computer.
  • one aspect of the present disclosure may be a non-transitory computer-readable recording medium on which such a program is recorded.
  • such a program may be recorded on a recording medium and distributed or circulated.
  • the distributed program may be installed in a device having another processor, and the program may be executed by that processor, thereby making it possible to cause that device to perform each of the above processes.
  • a production support system that estimates a probability that each of a plurality of units caused a mounting error that occurred in a mounting machine configured with the plurality of units, the system comprising: an acquisition unit that acquires, from the mounting machine, a first mounting log that includes information about the mounting error and is a target for estimating the probability; a mounting error cause estimation unit that estimates the probability for each of the plurality of units based on the first mounting log and a first estimation model based on a relationship between the number of mounting errors in each of the plurality of units and a malfunction of the unit; an output unit that outputs an estimation result of the mounting error cause estimation unit;
  • the first mounting log includes information regarding the number of productions in the plurality of units and the number of mounting errors.
  • the first estimation model is a multiple regression model in which a first regression coefficient of each of the plurality of units based on information on the production volume and a distribution of the number of mounting errors in each of the plurality of units is used as an explanatory variable, and the probability is used as a target variable.
  • the plurality of units include a tape feeder that supplies components and a nozzle that picks up the components; a tape feeding accuracy estimation unit that estimates the tape feeding accuracy based on the first mounting log and a second estimation model that is based on a relationship between a tape feeding accuracy of the tape feeder and an amount related to a pickup position deviation of the component,
  • the production support system according to any one of techniques 1 to 4, wherein the first mounting log further includes information regarding a control amount for controlling the nozzle.
  • the plurality of units include a head spindle, a nozzle, and a feeder;
  • the production support system according to any one of Techniques 1 to 9, wherein the mounting error cause estimation unit estimates the probability of each of the head spindle, the nozzle, the feeder, and the components supplied by the feeder.
  • a production support method for estimating a probability that each of a plurality of units caused a mounting error that occurred in a mounting machine configured with the plurality of units comprising: acquiring, from the mounting machine, a first mounting log that includes information about the mounting error and is a target for estimating the probability; estimating the probability for each of the plurality of units based on the first mounting log and a first estimation model based on a relationship between the number of mounting errors in each of the plurality of units and a malfunction of the unit; Output the estimated estimation results,
  • the first mounting log includes information regarding the number of productions in the plurality of units and the number of mounting errors.
  • This disclosure is useful for support systems that support production using mounting machines.

Landscapes

  • Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Supply And Installment Of Electrical Components (AREA)

Abstract

A production assistance system (1) estimates the probability of each of a plurality of units, of which a mounting machine (10) is composed, being the cause of a mounting error that has occurred in the mounting machine (10). The production assistance system comprises: an acquisition unit (for example, an error count preprocessing unit (31) and a correction amount preprocessing unit (32)) that acquires, from the mounting machine (10), a mounting log that includes information about a mounting error and from which the probability is to be estimated; a mounting error cause estimation unit (33) that, on the basis of the mounting log and a first estimation model based on the relationship, in each of the plurality of units, between a mounting error count and malfunction of the unit, estimates the probability in each of the plurality of units; and an output unit (for example, a display device (40)) that outputs a result of the estimation by the mounting error cause estimation unit (33). The mounting log includes information about a production quantity in each of the plurality of unit and the mounting error count.

Description

生産支援システム、生産支援方法及びプログラムProduction support system, production support method and program
　本開示は、生産支援システム、生産支援方法及びプログラムに関する。 This disclosure relates to a production support system, a production support method, and a program.
　特許文献１には、トレース情報の有効利用を図るとともに、製造品質や設備状態の変動を予測して実装用設備（実装機）のパラメータの設定を適切に行い良好な製造品質を得ることができる実装基板製造システムが開示されている。 Patent Document 1 discloses a mounting board manufacturing system that makes effective use of trace information and predicts fluctuations in manufacturing quality and equipment status to appropriately set parameters for mounting equipment (mounting machines) to achieve good manufacturing quality.
特開２０２１－１２９７９号公報JP 2021-12979 A
　ところで、実装機における実装ミスの要因となるユニットの特定を、コストアップを抑制しつつ支援することが望まれることがある。 Incidentally, it is sometimes desirable to help identify units that cause mounting errors in mounting machines while minimizing increases in cost.
　そこで、本開示は、実装ミスの要因となるユニットの特定を、コストアップを抑制しつつ支援することができる生産支援システム、生産支援方法及びプログラムを提供する。 The present disclosure provides a production support system, production support method, and program that can help identify units that cause mounting errors while minimizing increases in cost.
　本開示の一態様に係る生産支援システムは、複数のユニットから構成される実装機において発生した実装ミスに対する、前記複数のユニットそれぞれが前記実装ミスの要因となった確率を推定する生産支援システムであって、前記実装ミスに関する情報を含み、前記確率を推定する対象の第１実装ログを前記実装機から取得する取得部と、前記第１実装ログと、前記複数のユニットそれぞれにおける、実装ミス回数及び当該ユニットの不調の関係性に基づく第１推定モデルとに基づいて、前記複数のユニットそれぞれにおける前記確率を推定する実装ミス要因推定部と、前記実装ミス要因推定部の推定結果を出力する出力部とを備え、前記第１実装ログは、前記複数のユニットにおける生産数に関する情報及び実装ミス回数を含む。 A production support system according to one aspect of the present disclosure is a production support system that estimates the probability that each of a plurality of units contributed to a mounting error that occurred in a mounting machine composed of a plurality of units, and includes an acquisition unit that acquires from the mounting machine a first mounting log containing information about the mounting error and for which the probability is to be estimated, a mounting error cause estimation unit that estimates the probability for each of the plurality of units based on the first mounting log and a first estimation model based on the relationship between the number of mounting errors in each of the plurality of units and malfunctions of the units, and an output unit that outputs the estimation result of the mounting error cause estimation unit, and the first mounting log contains information about the number of productions in the plurality of units and the number of mounting errors.
　本開示の一態様に係る生産支援方法は、複数のユニットから構成される実装機において発生した実装ミスに対する、前記複数のユニットそれぞれが前記実装ミスの要因となった確率を推定する生産支援方法であって、前記実装ミスに関する情報を含み、前記確率を推定する対象の第１実装ログを前記実装機から取得し、前記第１実装ログと、前記複数のユニットそれぞれにおける、実装ミス回数及び当該ユニットの不調の関係性に基づく第１推定モデルとに基づいて、前記複数のユニットそれぞれにおける前記確率を推定し、推定された推定結果を出力し、前記第１実装ログは、前記複数のユニットにおける生産数に関する情報及び実装ミス回数を含む。 A production support method according to one aspect of the present disclosure is a production support method for estimating the probability that each of a plurality of units contributed to a mounting error that occurred in a mounting machine composed of a plurality of units, the method comprising the steps of: acquiring a first mounting log from the mounting machine, the first mounting log including information about the mounting error and for which the probability is to be estimated; estimating the probability for each of the plurality of units based on the first mounting log and a first estimation model based on the relationship between the number of mounting errors in each of the plurality of units and malfunctions of the units; and outputting the estimated estimation result; the first mounting log including information about the number of units produced and the number of mounting errors in the plurality of units.
　本開示の一態様に係るプログラムは、上記の生産支援方法をコンピュータに実行させるためのプログラムである。 A program according to one aspect of the present disclosure is a program for causing a computer to execute the above-mentioned production support method.
　本開示の一態様によれば、実装ミスの要因となるユニットの特定を、コストアップを抑制しつつ支援することができる生産支援システム等を実現することができる。 According to one aspect of the present disclosure, it is possible to realize a production support system that can assist in identifying units that cause mounting errors while minimizing increases in costs.
図１は、実施の形態に係る生産支援システムの機能構成を示すブロック図である。FIG. 1 is a block diagram showing a functional configuration of a production support system according to an embodiment. 図２は、実施の形態に係る前処理後データの第１例を示す図である。FIG. 2 is a diagram illustrating a first example of preprocessed data according to the embodiment. 図３は、実施の形態に係る前処理後データの第２例を示す図である。FIG. 3 is a diagram illustrating a second example of preprocessed data according to the embodiment. 図４は、実施の形態に係る第１回帰係数情報の一例を示す図である。FIG. 4 is a diagram illustrating an example of the first regression coefficient information according to the embodiment. 図５は、実施の形態に係るテープ送り精度と精度ランクとの対応表の一例を示す図である。FIG. 5 is a diagram showing an example of a correspondence table between tape feeding accuracy and accuracy rank according to the embodiment. 図６は、実施の形態に係る生産支援システムの動作を示す第１のフローチャートである。FIG. 6 is a first flowchart showing the operation of the production support system according to the embodiment. 図７は、実施の形態に係る第１回帰係数の推定及び使用を説明するための図である。FIG. 7 is a diagram for explaining the estimation and use of the first regression coefficient according to the embodiment. 図８は、実施の形態に係る第２回帰係数の推定及び使用を説明するための図である。FIG. 8 is a diagram for explaining the estimation and use of the second regression coefficient according to the embodiment. 図９は、実施の形態に係る生産支援システムの動作を示す第２のフローチャートである。FIG. 9 is a second flowchart showing the operation of the production support system according to the embodiment. 図１０は、実施の形態に係る表示装置が表示する画面の第１例を示す図である。FIG. 10 is a diagram showing a first example of a screen displayed by the display device according to the embodiment. 図１１は、実施の形態に係る表示装置が表示する画面の第２例を示す図である。FIG. 11 is a diagram showing a second example of a screen displayed by the display device according to the embodiment.
　本開示の一態様に係る生産支援システムは、複数のユニットから構成される実装機において発生した実装ミスに対する、前記複数のユニットそれぞれが前記実装ミスの要因となった確率を推定する生産支援システムであって、前記実装ミスに関する情報を含み、前記確率を推定する対象の第１実装ログを前記実装機から取得する取得部と、前記第１実装ログと、前記複数のユニットそれぞれにおける、実装ミス回数及び当該ユニットの不調の関係性に基づく第１推定モデルとに基づいて、前記複数のユニットそれぞれにおける前記確率を推定する実装ミス要因推定部と、前記実装ミス要因推定部の推定結果を出力する出力部とを備え、前記第１実装ログは、前記複数のユニットにおける生産数に関する情報及び実装ミス回数を含む。 A production support system according to one aspect of the present disclosure is a production support system that estimates the probability that each of a plurality of units contributed to a mounting error that occurred in a mounting machine composed of a plurality of units, and includes an acquisition unit that acquires from the mounting machine a first mounting log containing information about the mounting error and for which the probability is to be estimated, a mounting error cause estimation unit that estimates the probability for each of the plurality of units based on the first mounting log and a first estimation model based on the relationship between the number of mounting errors in each of the plurality of units and malfunctions of the units, and an output unit that outputs the estimation result of the mounting error cause estimation unit, and the first mounting log contains information about the number of productions in the plurality of units and the number of mounting errors.
　これにより、推定された複数のユニットそれぞれにおける確率が推定結果として出力されるので、実装機の管理者等は当該推定結果を参考として不調のユニットを特定することができる。つまり、生産支援システムは、推定結果を出力することにより、管理者等が不調のユニットを特定することを支援することができる。また、実装機が標準機能として出力している生産数に関する情報及び実装ミス回数を用いるので、実装機にセンサ等を追加することなく、確率を推定することができる。よって、本開示の一態様に係る生産支援システムは、実装ミスの要因となるユニットの特定を、コストアップを抑制しつつ支援することができる。 As a result, the probability for each of the estimated multiple units is output as an estimation result, and the manager of the mounting machine, etc. can use the estimation result as a reference to identify the malfunctioning unit. In other words, the production support system can support the manager, etc. in identifying the malfunctioning unit by outputting the estimation result. In addition, since it uses information on the production volume and the number of mounting errors that are output by the mounting machine as a standard function, it is possible to estimate the probability without adding sensors, etc. to the mounting machine. Therefore, the production support system according to one aspect of the present disclosure can support the identification of units that are the cause of mounting errors while suppressing increases in costs.
　また、例えば、前記第１推定モデルは、前記複数のユニットそれぞれにおける、前記生産数に関する情報及び前記実装ミス回数の分布に基づく前記複数のユニットそれぞれの第１回帰係数を説明変数とし、前記確率を目的変数とする重回帰モデルであってもよい。 Also, for example, the first estimation model may be a multiple regression model in which the information on the production volume and the first regression coefficient of each of the multiple units, which is based on the distribution of the number of mounting errors in each of the multiple units, are used as explanatory variables, and the probability is used as a response variable.
　これにより、複数の要因（複数のユニット）を考慮して確率が推定されるので、確率の推定精度を高めることができる。 This allows the probability to be estimated taking into account multiple factors (multiple units), improving the accuracy of the probability estimation.
　また、例えば、前記第１実装ログより前に取得された前記実装機の第２実装ログに含まれる前記生産数に関する情報と前記実装ミス回数との分布に基づいて、前記複数のユニットそれぞれの前記第１回帰係数を推定する第１係数推定部をさらに備えてもよい。 The system may further include a first coefficient estimation unit that estimates the first regression coefficient for each of the multiple units based on the distribution of the number of mounting errors and information related to the number of production errors contained in a second mounting log of the mounting machine acquired before the first mounting log.
　これにより、生産支援システムは、第１推定モデルの生成から確率の推定までの一連の処理を実行することができる。 This allows the production support system to execute a series of processes from generating the first estimation model to estimating the probability.
　また、例えば、前記出力部は、前記実装ミスに対する前記複数のユニットそれぞれの前記確率を表示してもよい。 Also, for example, the output unit may display the probability of the mounting error for each of the multiple units.
　これにより、実装ミスの要因確率を可視化することができるので、実装機の管理者等が複数のユニットの不調を判断する際に当該表示された情報を参考にすることができる。よって、実装ミスの要因となるユニットの特定を効果的に支援することができる。 This makes it possible to visualize the probability of causes of mounting errors, so that managers of mounting machines can refer to the displayed information when determining whether multiple units are malfunctioning. This effectively helps identify the units that are the cause of mounting errors.
　また、例えば、前記複数のユニットは、部品を供給するテープフィーダと、前記部品を吸着するノズルとを含み、前記第１実装ログと、前記テープフィーダのテープ送り精度及び前記部品の吸着位置ずれに関する量の関係性に基づく第２推定モデルとに基づいて、前記テープ送り精度を推定するテープ送り精度推定部をさらに備え、前記第１実装ログは、さらに、前記ノズルを制御するための制御量に関する情報を含んでもよい。 Also, for example, the multiple units may include a tape feeder that supplies components and a nozzle that picks up the components, and may further include a tape feed accuracy estimation unit that estimates the tape feed accuracy based on the first mounting log and a second estimation model based on the relationship between the tape feed accuracy of the tape feeder and the amount of misalignment of the pickup position of the component, and the first mounting log may further include information regarding a control amount for controlling the nozzle.
　これにより、実装機の管理者等は、さらに推定されたテープの送り精度に基づく情報を参考として不調のユニットを特定することができる。つまり、生産支援システムは、テープの送り精度に基づく情報を出力することにより、管理者等が不調のユニットの特定することを、コストアップを抑制しつつさらに支援することができる。 As a result, the manager of the mounting machine can further refer to information based on the estimated tape feed accuracy to identify the malfunctioning unit. In other words, by outputting information based on the tape feed accuracy, the production support system can further assist the manager in identifying the malfunctioning unit while preventing an increase in costs.
　また、例えば、前記第２推定モデルは、前記テープ送り精度及び前記部品の吸着位置ずれに関する量の関係を示す第２回帰係数を含む単回帰モデルであってもよい。 Also, for example, the second estimation model may be a simple regression model including a second regression coefficient indicating the relationship between the tape feed accuracy and the amount related to the pickup position deviation of the component.
　これにより、生産支援システムは、テープ送り精度の推定に関する処理量の増加を抑制しつつ、管理者等が不調のユニットの特定することをさらに支援することができる。 As a result, the production support system can further assist managers in identifying malfunctioning units while minimizing the increase in the amount of processing required to estimate tape feed accuracy.
　また、例えば、前記第１実装ログより前に取得された前記実装機の第３実装ログに含まれる前記ノズルを制御するための制御量と、前記テープフィーダのテープ送り精度の測定値との分布に基づいて、前記複数のユニットそれぞれの前記第２回帰係数を推定する第２係数推定部をさらに備えてもよい。 The system may further include a second coefficient estimation unit that estimates the second regression coefficient for each of the multiple units based on a distribution between a control amount for controlling the nozzle included in a third mounting log of the mounting machine acquired before the first mounting log and a measured value of the tape feed accuracy of the tape feeder.
　これにより、生産支援システムは、第２推定モデルの生成からテープ送り精度の推定までの一連の処理を実行することができる。 This allows the production support system to execute a series of processes from generating the second estimation model to estimating tape feed accuracy.
　また、例えば、前記出力部は、前記テープ送り精度推定部により推定された前記テープ送り精度に関する情報を表示してもよい。 Also, for example, the output unit may display information regarding the tape feed accuracy estimated by the tape feed accuracy estimation unit.
　これにより、テープ送り精度に関する情報を可視化することができるので、実装機の管理者等がフィーダの不調を判断する際に当該表示された情報を参考にすることができる。よって、実装ミスの要因となるユニットの特定を効果的に支援することができる。 This makes it possible to visualize information related to tape feed accuracy, allowing the manager of the mounting machine to refer to the displayed information when determining if there is a problem with the feeder. This effectively helps identify the unit that is causing the mounting error.
　また、例えば、前記実装機は、前記複数のユニットの状態を直接的に計測するセンサを備えていなくてもよい。 Also, for example, the mounting machine does not need to be equipped with a sensor that directly measures the state of the multiple units.
　これにより、実装機がハードセンサを備えていなくてもよいので、実装機のコストをより確実に抑制することができる。 This means that the mounting machine does not need to be equipped with a hardware sensor, making it possible to more reliably reduce the cost of the mounting machine.
　また、例えば、前記複数のユニットは、ヘッドスピンドル、ノズル及びフィーダを含み、前記実装ミス要因推定部は、前記ヘッドスピンドル、前記ノズル、前記フィーダ及び前記フィーダが供給する部品それぞれの前記確率を推定してもよい。 Furthermore, for example, the multiple units may include a head spindle, a nozzle, and a feeder, and the mounting error cause estimation unit may estimate the probability of each of the head spindle, the nozzle, the feeder, and the components supplied by the feeder.
　これにより、生産支援システムは、ヘッドスピンドル、ノズル及びフィーダを含む複数のユニット、並びに、部品それぞれの確率を推定することができる。言い換えると、生産支援システムは、実装ミスの要因がヘッドスピンドル、ノズル、フィーダ及び部品のいずれであるかの管理者等による判断を支援することができる。 As a result, the production support system can estimate the probability of multiple units, including the head spindle, nozzle, and feeder, as well as each component. In other words, the production support system can assist managers, etc. in determining whether the cause of a mounting error is the head spindle, nozzle, feeder, or component.
　また、本開示の一態様に係る生産支援方法は、複数のユニットから構成される実装機において発生した実装ミスに対する、前記複数のユニットそれぞれが前記実装ミスの要因となった確率を推定する生産支援方法であって、前記実装ミスに関する情報を含み、前記確率を推定する対象の第１実装ログを前記実装機から取得し、前記第１実装ログと、前記複数のユニットそれぞれにおける、実装ミス回数及び当該ユニットの不調の関係性に基づく第１推定モデルとに基づいて、前記複数のユニットそれぞれにおける前記確率を推定し、推定された推定結果を出力し、前記第１実装ログは、前記複数のユニットにおける生産数に関する情報及び実装ミス回数を含む。また、本開示の一態様に係るプログラムは、上記の生産支援方法をコンピュータに実行させるためのプログラムである。 A production support method according to one aspect of the present disclosure is a production support method for estimating the probability that each of a plurality of units contributed to a mounting error that occurred in a mounting machine composed of a plurality of units, the method comprising the steps of: acquiring a first mounting log from the mounting machine, the first mounting log including information about the mounting error and for which the probability is to be estimated; estimating the probability for each of the plurality of units based on the first mounting log and a first estimation model based on the relationship between the number of mounting errors in each of the plurality of units and malfunctions of the units; and outputting the estimated estimation result, the first mounting log including information about the number of productions in the plurality of units and the number of mounting errors. A program according to one aspect of the present disclosure is a program for causing a computer to execute the above production support method.
　これにより、上記の生産支援システムと同様の効果を奏する。 This achieves the same effect as the production support system described above.
　なお、これらの全般的又は具体的な態様は、システム、方法、集積回路、コンピュータプログラム又はコンピュータで読み取り可能なＣＤ－ＲＯＭ等の非一時的記録媒体で実現されてもよく、システム、方法、集積回路、コンピュータプログラム又は記録媒体の任意な組み合わせで実現されてもよい。プログラムは、記録媒体に予め記憶されていてもよいし、インターネット等を含む広域通信網を介して記録媒体に供給されてもよい。 These general or specific aspects may be realized by a system, a method, an integrated circuit, a computer program, or a non-transitory recording medium such as a computer-readable CD-ROM, or by any combination of a system, a method, an integrated circuit, a computer program, or a recording medium. The program may be pre-stored in the recording medium, or may be supplied to the recording medium via a wide area communication network including the Internet.
　以下、実施の形態について、図面を参照しながら具体的に説明する。 The following describes the embodiment in detail with reference to the drawings.
　なお、以下で説明する実施の形態は、いずれも包括的又は具体的な例を示すものである。以下の実施の形態で示される数値、形状、構成要素、構成要素の配置位置及び接続形態、ステップ、ステップの順序などは、一例であり、本開示を限定する主旨ではない。また、以下の実施の形態における構成要素のうち、独立請求項に記載されていない構成要素については、任意の構成要素として説明される。 The embodiments described below are all comprehensive or specific examples. The numerical values, shapes, components, component placement and connection forms, steps, and order of steps shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Furthermore, among the components in the following embodiments, components that are not described in an independent claim are described as optional components.
　また、各図は、模式図であり、必ずしも厳密に図示されたものではない。したがって、例えば、各図において縮尺等は必ずしも一致しない。また、各図において、実質的に同一の構成については同一の符号を付しており、重複する説明は省略又は簡略化する。 In addition, each figure is a schematic diagram and is not necessarily an exact illustration. Therefore, for example, the scales and the like do not necessarily match in each figure. In addition, in each figure, substantially the same configuration is given the same reference numerals, and duplicate explanations are omitted or simplified.
　また、本明細書において、同じ等の要素間の関係性を示す用語、並びに、数値、及び、数値範囲は、厳格な意味のみを表す表現ではなく、実質的に同等な範囲、例えば数％程度（あるいは、１０％程度）の差異をも含むことを意味する表現である。 In addition, in this specification, terms that indicate relationships between elements such as the same, as well as numerical values and numerical ranges, are not expressions that express only the strict meaning, but are expressions that include a substantially equivalent range, for example, a difference of about a few percent (or about 10%).
　また、本明細書において、「第１」、「第２」などの序数詞は、特に断りの無い限り、構成要素の数又は順序を意味するものではなく、同種の構成要素の混同を避け、区別する目的で用いられている。 In addition, in this specification, ordinal numbers such as "first" and "second" do not refer to the number or order of components, unless otherwise specified, but are used for the purpose of avoiding confusion between and distinguishing between components of the same type.
　（実施の形態）
　以下、本実施の形態に係る生産支援装置を備える生産支援システムについて、図１～図１１を参照しながら説明する。 (Embodiment)
A production support system including a production support device according to this embodiment will be described below with reference to FIGS.
　［１．生産支援システムの構成］
　まず、本実施の形態に係る生産支援システムの構成について、図１を参照しながら説明する。図１は、本実施の形態に係る生産支援システム１の機能構成を示すブロック図である。 [1. Configuration of the production support system]
First, the configuration of a production support system according to the present embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the functional configuration of a production support system 1 according to the present embodiment.
　図１に示すように、生産支援システム１は、係数推定装置２０と、要因確率推定装置３０と、表示装置４０とを備える。生産支援システム１は、実装機１０を用いた生産を支援するためのシステムである。具体的には、生産支援システム１は、実装機１０で発生した実装ミスに対するユニット（設備ユニット）の要因確率（ミス要因確率又は実装ミス要因確率とも記載する）を、当該ユニットを直接センシングするセンサのデータを用いずに間接的に推定する。また、本実施の形態では、生産支援システム１は、さらにフィーダのテープ送り精度を、当該フィーダのテープ送り精度を直接センシングするセンサのデータを用いずに間接的に推定する。センサは、例えば、複数のユニットを計測するセンサであり、例えば、フィーダの部品の供給位置、部品の実装位置等を計測するセンサである。 As shown in FIG. 1, the production support system 1 includes a coefficient estimation device 20, a factor probability estimation device 30, and a display device 40. The production support system 1 is a system for supporting production using a mounting machine 10. Specifically, the production support system 1 indirectly estimates the factor probability (also written as error factor probability or mounting error factor probability) of a unit (equipment unit) for a mounting error that occurs in the mounting machine 10 without using data from a sensor that directly senses the unit. In addition, in this embodiment, the production support system 1 also indirectly estimates the tape feed accuracy of the feeder without using data from a sensor that directly senses the tape feed accuracy of the feeder. The sensor is, for example, a sensor that measures multiple units, such as a sensor that measures the feeder's component supply position, component mounting position, etc.
　実装機１０は、製造ラインを構成する生産設備の一例であり、基板等の対象物（ワーク）に部品を実装する実装設備（部品実装装置）である。実装機１０は、複数のユニットにより構成される。本実施の形態では、実装機１０は、ユニットとして、駆動制御ユニット（以降において、スピンドルとも記載する）、部品装着ヘッドユニット（以降において、ノズルとも記載する）及び部品供給ユニット（以降において、フィーダとも記載する）を有する。駆動制御ユニットは、部品装着ヘッドユニットの回転及び移動を制御する。駆動制御ユニットは、モータの駆動により、部品装着ヘッドユニットの回転を制御するヘッドスピンドルを有する。部品装着ヘッドユニットは、フィーダの部品供給位置（部品吸着位置）に供給された部品を基板に装着（実装）する。部品装着ヘッドユニットは、フィーダからの部品を吸着し個別に昇降可能な部品吸着ノズル（ノズル）が装着された装着ヘッド（ヘッド）等を含んで構成される。ヘッドには、例えば、複数のノズルが装着されている。部品供給ユニットは、１以上のフィーダが並んで配置されており、それぞれが部品供給位置に部品を供給する。本実施の形態では、フィーダは、テープフィーダである。 The mounting machine 10 is an example of a production facility that constitutes a manufacturing line, and is a mounting facility (component mounting device) that mounts components on a target object (workpiece) such as a board. The mounting machine 10 is composed of multiple units. In this embodiment, the mounting machine 10 has a drive control unit (hereinafter also referred to as a spindle), a component mounting head unit (hereinafter also referred to as a nozzle), and a component supply unit (hereinafter also referred to as a feeder) as units. The drive control unit controls the rotation and movement of the component mounting head unit. The drive control unit has a head spindle that controls the rotation of the component mounting head unit by driving a motor. The component mounting head unit mounts (mounts) components supplied to the component supply position (component suction position) of the feeder on the board. The component mounting head unit is composed of a mounting head (head) equipped with a component suction nozzle (nozzle) that can pick up components from the feeder and raise and lower them individually. The head is equipped with, for example, multiple nozzles. The component supply unit has one or more feeders arranged side by side, each of which supplies components to the component supply position. In this embodiment, the feeder is a tape feeder.
　実装機１０は、生産中に定期的に要因確率推定装置３０に第１実装ログＬ１を出力する。実装機１０は、例えば、１個の部品を基板に実装するたびに第１実装ログＬ１を出力してもよいし、所定個数の部品を基板に実装するたびに第１実装ログＬ１を出力してもよい。 The mounting machine 10 periodically outputs the first mounting log L1 to the factor probability estimation device 30 during production. The mounting machine 10 may output the first mounting log L1, for example, every time one component is mounted on the board, or every time a predetermined number of components are mounted on the board.
　なお、第１実装ログＬ１は、実装機１０における、フィーダから部品を吸着する動作から基板に当該部品を実装する動作までの間に取得された各ユニットの制御に関する情報及び生産実績を示す情報を含む。第１実装ログＬ１は、実装機１０が標準機能として出力しているログである。例えば、第１実装ログＬ１には、複数のユニットを制御するための制御量に関する情報、生産に用いられた複数のユニットを特定する情報及び生産実績に関する情報を含む。制御量に関する情報には、例えば、ユニット（例えば、ノズル）の移動及び回転を制御するための制御量（補正量）に関する情報（例えば、後述する吸着補正量及び認識補正量）が含まれる。生産実績を示す情報には、生産数に関する情報（例えば、吸着試行回数）及び実装ミス回数が含まれる。なお、第１実装ログＬ１には、ユニットを直接センシングして得られるデータ（つまり、ハードセンサのデータ）は含まれない。 The first mounting log L1 includes information on the control of each unit acquired during the period from the operation of picking up a component from the feeder to the operation of mounting the component on the board in the mounting machine 10, and information indicating the production results. The first mounting log L1 is a log output by the mounting machine 10 as a standard function. For example, the first mounting log L1 includes information on the control amount for controlling multiple units, information identifying the multiple units used in production, and information on the production results. The information on the control amount includes, for example, information on the control amount (correction amount) for controlling the movement and rotation of the unit (e.g., nozzle) (e.g., pick-up correction amount and recognition correction amount described later). The information indicating the production results includes information on the number of productions (e.g., the number of pick-up attempts) and the number of mounting errors. The first mounting log L1 does not include data obtained by directly sensing the unit (i.e., data from a hard sensor).
　なお、生産支援システム１が支援する実装機１０の数は特に限定されず、１つであってもよいし、複数であってもよい。 The number of mounting machines 10 supported by the production support system 1 is not particularly limited, and may be one or more.
　なお、部品は電子部品であり、例えば、抵抗、コンデンサ等であるがこれに限定されない。また、対象物は、基板に限定されず、所定の加工を行い得る被加工物であればよい。 The components are electronic components, such as, but not limited to, resistors and capacitors. The target object is not limited to a substrate, but may be any workpiece that can be subjected to a specified process.
　なお、実装機１０は、駆動制御ユニット、部品装着ヘッドユニット及び部品供給ユニットの状態（例えば、動作）を直接的に計測するセンサ（ハードセンサ）を有していなくてもよい。当該センサは、例えば、実装機１０に標準装備されておらず、後付けで設置されたセンサを含む。標準装備されているか否かは、実装機１０のカタログ等により確認可能である。 The mounting machine 10 does not have to have sensors (hard sensors) that directly measure the status (e.g., operation) of the drive control unit, the component mounting head unit, and the component supply unit. The sensors include, for example, sensors that are not standard equipment on the mounting machine 10 and are installed later. Whether or not they are standard equipment can be confirmed by referring to the catalog of the mounting machine 10, etc.
　係数推定装置２０は、実装機１０から事前に取得される第２実装ログＬ２を用いて、各回帰係数を推定する処理を実行する。事前とは、上記の推定処理を実行する前（例えば、第１実装ログＬ１を取得する前）を意味する。また、第２実装ログＬ２は、各回帰係数を事前に推定するために用いられる事前推定用の実装ログである。なお、第２実装ログＬ２は、第１実装ログＬ１と同様のデータであり、実装機１０における、フィーダから部品を吸着する動作から基板に当該部品を実装する動作までの間に取得された、各ユニットの制御に関する情報を含む。第２実装ログＬ２は、実装機１０が標準機能として出力しているログである。例えば、第２実装ログＬ２には、複数のユニットを制御するための制御量に関する情報、実装ミス回数、生産に用いられた複数のユニットを特定する情報及び生産実績に関する情報を含む。制御量に関する情報には、例えば、ユニット（例えば、ノズル）の移動及び回転を補正するための補正量に関する情報（例えば、後述する吸着補正量及び認識補正量）が含まれる。生産実績に関する情報には、生産数（例えば、吸着試行回数）及び実装ミス回数が含まれる。なお、第２実装ログＬ２には、ユニットを直接センシングして得られるデータ（つまり、ハードセンサのデータ）は含まれない。第２実装ログＬ２は、第３実装ログとして用いられてもよい。 The coefficient estimation device 20 executes a process of estimating each regression coefficient using the second mounting log L2 acquired in advance from the mounting machine 10. "In advance" means before the above estimation process is executed (for example, before the first mounting log L1 is acquired). The second mounting log L2 is a mounting log for advance estimation used to estimate each regression coefficient in advance. The second mounting log L2 is the same data as the first mounting log L1, and includes information on the control of each unit acquired in the mounting machine 10 from the operation of picking up a component from a feeder to the operation of mounting the component on a board. The second mounting log L2 is a log output by the mounting machine 10 as a standard function. For example, the second mounting log L2 includes information on the control amount for controlling multiple units, the number of mounting errors, information identifying multiple units used in production, and information on production results. The information on the control amount includes, for example, information on the correction amount for correcting the movement and rotation of a unit (for example, a nozzle) (for example, the pick-up correction amount and the recognition correction amount described later). The information about production performance includes the number of productions (e.g., the number of pickup attempts) and the number of mounting errors. Note that the second mounting log L2 does not include data obtained by directly sensing the unit (i.e., data from a hardware sensor). The second mounting log L2 may be used as a third mounting log.
　係数推定装置２０は、ミス回数前処理部２１と、補正量前処理部２２と、非線形回帰係数推定部２３と、線形回帰係数推定部２４とを備える。係数推定装置２０は、ＣＰＵ（Ｃｅｎｔｒａｌ　Ｐｒｏｃｅｓｓｉｎｇ　Ｕｎｉｔ）及びメモリ等によって実現可能である。また、係数推定装置２０の機能ブロックの各々による処理は、通常、プロセッサ等のプログラム実行部が、ＲＯＭ等の記録媒体に記録されたソフトウェア（プログラム）を読み出して実行することで実現される。 The coefficient estimation device 20 includes a miss count preprocessing unit 21, a correction amount preprocessing unit 22, a nonlinear regression coefficient estimation unit 23, and a linear regression coefficient estimation unit 24. The coefficient estimation device 20 can be realized by a CPU (Central Processing Unit) and a memory, etc. Furthermore, the processing by each of the functional blocks of the coefficient estimation device 20 is usually realized by a program execution unit such as a processor reading and executing software (programs) recorded on a recording medium such as a ROM.
　ミス回数前処理部２１は、実装機１０から第２実装ログＬ２を取得し、非線形回帰係数推定部２３において第１回帰係数を推定するために用いられるデータを第２実装ログＬ２から抽出し、抽出された前処理後データを非線形回帰係数推定部２３に出力する。図２は、本実施の形態に係る前処理後データの第１例を示す図である。図２は、ミス回数前処理部２１から非線形回帰係数推定部２３に出力される前処理後データの一例を示す。 The error count preprocessing unit 21 acquires the second mounting log L2 from the mounting machine 10, extracts data from the second mounting log L2 that is used to estimate the first regression coefficient in the nonlinear regression coefficient estimating unit 23, and outputs the extracted preprocessed data to the nonlinear regression coefficient estimating unit 23. Figure 2 is a diagram showing a first example of preprocessed data according to this embodiment. Figure 2 shows an example of preprocessed data output from the error count preprocessing unit 21 to the nonlinear regression coefficient estimating unit 23.
　図２に示すように、前処理後データには、「ｉｎｄｅｘ」、「フィーダシリアル」、「ヘッドスピンドル番号」、「ノズルシリアル」、「部品シリアル」、「部品サイズ」、「吸着試行回数」及び「実装ミス回数」が含まれる。 As shown in Figure 2, the pre-processed data includes "index," "feeder serial number," "head spindle number," "nozzle serial number," "component serial number," "component size," "number of pickup attempts," and "number of mounting errors."
　ｉｎｄｅｘは、「フィーダ」、「ヘッドスピンドル」、「ノズル」、「部品サイズ」の組み合わせごとに付される番号である。つまり、前処理後データは、「フィーダ」、「ヘッドスピンドル」、「ノズル」、「部品サイズ」の組み合わせごとに集約されたデータである。 The index is a number assigned to each combination of "feeder," "head spindle," "nozzle," and "part size." In other words, the pre-processed data is aggregated for each combination of "feeder," "head spindle," "nozzle," and "part size."
　フィーダシリアルは、フィーダそれぞれの識別情報（例えば、識別番号）である。 The feeder serial is the identification information (e.g., identification number) for each feeder.
　ヘッドスピンドル番号は、ノズルの回転を制御したヘッドスピンドルを識別するための識別番号である。 The head spindle number is an identification number used to identify the head spindle that controlled the rotation of the nozzle.
　ノズルシリアルは、ノズルそれぞれの識別情報（例えば、識別番号）である。１つの部品装着ヘッドユニットには複数のノズルが装着されており、複数のノズルのそれぞれに互いに異なる識別情報が割り当てられている。 The nozzle serial number is identification information (e.g., an identification number) for each nozzle. A single component mounting head unit is equipped with multiple nozzles, and each of the multiple nozzles is assigned a different identification number.
　部品サイズは、生産で使用された部品の幅を示す。図２に示す「１．０」は、例えば、部品を上面からみたときの幅が１ｍｍであることを示す。なお、部品の幅とは、フィーダにおける部品の進行方向（Ｙ方向）と直交する方向（Ｘ方向）の長さである。Ｘ方向は、実装機１０における基板の搬送方向である。 The component size indicates the width of the component used in production. For example, "1.0" in FIG. 2 indicates that the width of the component when viewed from above is 1 mm. Note that the width of a component is the length in the direction (X direction) perpendicular to the direction in which the component moves in the feeder (Y direction). The X direction is the direction in which the board is transported in the mounting machine 10.
　部品シリアルは、フィーダにより供給される部品を識別するための識別情報（例えば、識別番号）である。 The part serial number is identification information (e.g., an identification number) used to identify the part supplied by the feeder.
　吸着試行回数は、ノズルにより部品の吸着を行った回数を示す。吸着試行回数は、所定期間又は所定数（例えば、１ＬＯＴ）の生産において、ノズルが部品の吸着を実行した回数である。 The number of pickup attempts indicates the number of times a part is picked up by the nozzle. The number of pickup attempts is the number of times the nozzle picks up a part during a specified period or during a specified number of production runs (e.g., 1 lot).
　実装ミス回数は、吸着試行回数のうち実装ミスが発生した回数を示す。実装ミスには、ノズルによる部品の吸着ミス、基板に対する部品の実装ミス等が含まれる。 The number of mounting errors indicates the number of times a mounting error occurred out of the number of pickup attempts. Mounting errors include failure to pick up the component by the nozzle, failure to mount the component on the board, etc.
　例えば、ｉｎｄｅｘ「１」は、識別情報「ＦＤ００００１」のフィーダから、識別情報「ＣＰ０００１」でありサイズ「１．０」である部品を、識別番号「１」であるヘッドスピンドルにより回転が制御される識別情報「ＮＺ００００１」のノズルを用いて部品の実装を１０００回行った際に、１２回実装ミスが発生したことを示す。このように、当該前処理後データには、部品の実装を行ったユニットを識別する情報、実装対象の部品を識別する情報、及び、生産実績に関する情報が含まれる。 For example, index "1" indicates that 12 mounting errors occurred when mounting a component with identification information "CP0001" and size "1.0" from a feeder with identification information "FD00001" 1000 times using a nozzle with identification information "NZ00001" whose rotation is controlled by a head spindle with identification number "1". In this way, the preprocessed data includes information identifying the unit that mounted the component, information identifying the component to be mounted, and information related to production performance.
　詳細は後述するが、本願発明者らは、実装ミス回数と、ユニットの不調とに関係性があることを見出した。つまり、本願発明者らは、実装ミス回数からユニットの不調を推定可能であることを見出した。そのため、ミス回数前処理部２１から出力される前処理後データにおいて、実装ミス回数は必須の情報である。なお、不調とは、必ずしも実装機１０の停止を伴わないアラートが発生していることであり、例えば、フィーダ、ヘッドスピンドル、及びノズルの少なくとも１つの故障、劣化等が発生していると推測される状態である。 The details will be described later, but the inventors of the present application have found that there is a relationship between the number of mounting errors and malfunction of the unit. In other words, the inventors of the present application have found that it is possible to estimate malfunction of the unit from the number of mounting errors. Therefore, the number of mounting errors is essential information in the pre-processed data output from the error count pre-processing unit 21. Note that a malfunction is an alert that does not necessarily involve the stop of the mounting machine 10, and is, for example, a state in which it is suspected that a failure or deterioration has occurred in at least one of the feeder, head spindle, and nozzle.
　図１を再び参照して、補正量前処理部２２は、実装機１０から第２実装ログＬ２を取得し、線形回帰係数推定部２４において第２回帰係数を推定するために用いられるデータを第２実装ログＬ２から抽出し、抽出された前処理後データを線形回帰係数推定部２４に出力する。図３は、本実施の形態に係る前処理後データの第２例を示す図である。図３は、補正量前処理部２２から線形回帰係数推定部２４に出力される前処理後データの一例を示す。 Referring again to FIG. 1, the correction amount preprocessing unit 22 acquires the second mounting log L2 from the mounting machine 10, extracts data from the second mounting log L2 that is used to estimate the second regression coefficient in the linear regression coefficient estimating unit 24, and outputs the extracted preprocessed data to the linear regression coefficient estimating unit 24. FIG. 3 is a diagram showing a second example of preprocessed data according to this embodiment. FIG. 3 shows an example of preprocessed data output from the correction amount preprocessing unit 22 to the linear regression coefficient estimating unit 24.
　図３に示すように、前処理後データには、「ｉｎｄｅｘ」、「フィーダシリアル」、「ヘッドスピンドル番号」、「ノズルシリアル」、「部品シリアル」、「部品サイズ」、「吸着試行回数」及び「各補正量」が含まれる。 As shown in Figure 3, the pre-processed data includes "index," "feeder serial number," "head spindle number," "nozzle serial number," "part serial number," "part size," "number of pickup attempts," and "each correction amount."
　各補正量は、認識補正量と吸着補正量とを含む。認識補正量及び吸着補正量には、Ｘ座標に関する補正量、及び、Ｙ座標に関する補正量、並びに、補正量の平均値、中央値、標準偏差が含まれる。認識補正量は、ノズルによる部品の吸着後のノズルのＸ軸方向及びＹ軸方向における位置の補正量を示す。認識補正量は、例えば、部品を基板の実装ターゲット位置に実装するためのノズルのＸ軸方向及びＹ軸方向における位置の調整量を示す。例えば、認識補正量は、ノズルが部品を吸着した位置と吸着ターゲット位置との差分に基づく値である。 Each correction amount includes a recognition correction amount and a pickup correction amount. The recognition correction amount and the pickup correction amount include a correction amount for the X coordinate and a correction amount for the Y coordinate, as well as the average, median, and standard deviation of the correction amounts. The recognition correction amount indicates the correction amount of the nozzle's position in the X-axis and Y-axis directions after the nozzle picks up a component. The recognition correction amount indicates, for example, the adjustment amount of the nozzle's position in the X-axis and Y-axis directions to mount the component at the mounting target position on the board. For example, the recognition correction amount is a value based on the difference between the position where the nozzle picks up the component and the pickup target position.
　吸着補正量は、ノズルによる部品の吸着時に行ったノズルのＸ軸方向及びＹ軸方向における位置の補正量を示す。吸着補正量は、例えば、ノズルが部品の吸着ターゲット位置（例えば、部品の上面における中央の位置）を吸着できるように当該ノズルの位置を調整したときの調整量を示す。例えば、吸着補正量は、フィーダにより供給された部品の吸着ターゲット位置と、ノズルの吸着中心との差分に基づく値である。 The suction correction amount indicates the amount of correction made to the nozzle position in the X-axis and Y-axis directions when the nozzle picks up a component. The suction correction amount indicates, for example, the adjustment amount made when the nozzle position is adjusted so that the nozzle can pick up the component's suction target position (for example, the center position on the top surface of the component). For example, the suction correction amount is a value based on the difference between the suction target position of the component supplied by the feeder and the suction center of the nozzle.
　なお、認識補正量及び吸着補正量のそれぞれにおいて、平均値、中央値及び標準偏差の少なくとも１つが前処理後データに含まれていればよい。また、各補正量は、実装機１０に設けられた撮像装置で撮像された画像により特定可能である。 Note that for each of the recognition correction amount and the adsorption correction amount, at least one of the mean, median, and standard deviation may be included in the preprocessed data. Furthermore, each correction amount can be identified from an image captured by an imaging device provided in the mounting machine 10.
　また、補正量前処理部２２は、さらに、認識補正量及び吸着補正量に基づいて、後述する吸着位置ずれ統計量を算出してもよい。吸着位置ずれ統計量は、前処理後データに含まれてもよい。 The correction amount preprocessing unit 22 may further calculate the adsorption position deviation statistics, which will be described later, based on the recognition correction amount and the adsorption correction amount. The adsorption position deviation statistics may be included in the preprocessed data.
　詳細は後述するが、本願発明者らは、各補正量と、テープ送り精度とに関係性があることを見出した。つまり、本願発明者らは、各補正量からテープ送り精度を推定可能であることを見出した。そのため、補正量前処理部２２から出力される前処理後データにおいて、各補正量は必須の情報である。 The details will be described later, but the inventors of the present application have discovered that there is a relationship between each correction amount and tape feed accuracy. In other words, the inventors of the present application have discovered that it is possible to estimate tape feed accuracy from each correction amount. Therefore, each correction amount is essential information in the pre-processed data output from the correction amount pre-processing unit 22.
　図１を再び参照して、非線形回帰係数推定部２３は、図２に示す前処理後データに基づいて、実装ミスに対するユニットの要因確率を推定するための第１回帰係数を推定する。部品実装工程における主な要素としてフィーダ、ヘッドスピンドル、ノズル及び部品サイズがある。第１回帰係数は、第１実装ログＬ１に含まれる実装ミスに対し、その要因がフィーダ、ヘッドスピンドル、ノズル及び部品サイズのいずれの要素によるものかを識別するために用いられる係数である。第１実装ログＬ１は、第２実装ログＬ２と同じ項目の情報を含むログである。非線形回帰係数推定部２３は、第１係数推定部の一例である。 Referring again to FIG. 1, the nonlinear regression coefficient estimator 23 estimates a first regression coefficient for estimating the probability of a unit being responsible for a mounting error based on the preprocessed data shown in FIG. 2. The main elements in the component mounting process are the feeder, head spindle, nozzle, and component size. The first regression coefficient is a coefficient used to identify whether a mounting error included in the first mounting log L1 is caused by the feeder, head spindle, nozzle, or component size. The first mounting log L1 is a log that contains information on the same items as the second mounting log L2. The nonlinear regression coefficient estimator 23 is an example of a first coefficient estimator.
　本実施の形態では、要因確率推定装置３０の実装ミス要因推定部３３は、部品実装工程に関与するフィーダ、ヘッドスピンドル、ノズル及び部品サイズから、実装ミスが発生した場合におけるそれぞれの要因確率を求める手法として、非線形回帰分析の一つである「ロジスティック回帰分析」を用いる。そのため、非線形回帰係数推定部２３は、ロジスティック回帰分析に用いられる第１回帰係数を推定する。具体的には、非線形回帰係数推定部２３は、ロジスティック回帰分析で用いられるロジスティック関数（後述する式２を参照）に含まれる線形予測子の第１回帰係数を推定する。 In this embodiment, the mounting error factor estimation unit 33 of the factor probability estimation device 30 uses "logistic regression analysis," a type of nonlinear regression analysis, as a method for determining the probability of each factor when a mounting error occurs from the feeder, head spindle, nozzle, and component size involved in the component mounting process. Therefore, the nonlinear regression coefficient estimation unit 23 estimates the first regression coefficient used in the logistic regression analysis. Specifically, the nonlinear regression coefficient estimation unit 23 estimates the first regression coefficient of the linear predictor included in the logistic function (see Equation 2 described below) used in the logistic regression analysis.
　非線形回帰係数推定部２３は、フィーダ、ヘッドスピンドル、ノズル及び部品サイズの要素の組み合わせに対する吸着試行回数及び実装ミス回数の分布から、マルコフ連鎖モンテカルロ（ＭＣＭＣ）法を用いて、各要素の第１回帰係数を推定する。ＭＣＭＣ法は、多変量の確率分布からサンプルを得る（乱数を生成する）ための手法であり、本開示のように、統計モデルを構成する複数のパラメータ（ここでは編回帰係数）の最尤推定を行う場合によく用いられる手法である。各要素は、例えば、フィーダ、ヘッドスピンドル、ノズル及び部品（部品サイズ）を含む。なお、第１回帰係数は、第１推定モデル３３ａにおける説明変数である。 The nonlinear regression coefficient estimation unit 23 estimates the first regression coefficient of each element using the Markov Chain Monte Carlo (MCMC) method from the distribution of the number of pickup attempts and the number of mounting errors for the combination of the elements of the feeder, head spindle, nozzle, and component size. The MCMC method is a method for obtaining samples (generating random numbers) from a multivariate probability distribution, and is a method that is often used when performing maximum likelihood estimation of multiple parameters (here, regression coefficients) that make up a statistical model, as in the present disclosure. Each element includes, for example, a feeder, head spindle, nozzle, and component (component size). The first regression coefficient is an explanatory variable in the first estimation model 33a.
　図４は、本実施の形態に係る第１回帰係数情報の一例を示す図である。 FIG. 4 shows an example of the first regression coefficient information according to this embodiment.
　図４に示すように、「ｉｎｄｅｘ」、「フィーダシリアル」、「ヘッドスピンドル番号」、「ノズルシリアル」、「部品シリアル」、「部品サイズ」、「吸着試行回数」、「実装ミス回数」、「バイアス項」及び「各回帰係数」が含まれる。 As shown in Figure 4, these include "index," "feeder serial," "head spindle number," "nozzle serial," "component serial," "component size," "number of pickup attempts," "number of mounting errors," "bias term," and "regression coefficients."
　バイアス項は、ロジスティック関数に含まれる線形予測子を算出するために用いられる。バイアス項は、予め設定される定数（例えば、β）である。 The bias term is used to calculate the linear predictor included in the logistic function. The bias term is a preset constant (e.g., β).
　各回帰係数は、フィーダの第１回帰係数であるフィーダ回帰係数、ヘッドスピンドルの第１回帰係数であるヘッドスピンドル回帰係数、ノズルの第１回帰係数であるノズル回帰係数、及び、部品サイズの第１回帰係数である部品サイズ回帰係数を含む。例えば、フィーダがＮｆ本あり、ヘッドスピンドルＮｓ個あり、ノズルがＮｎ個あり、部品サイズがＮｃ個ある場合、それぞれの第１回帰係数もそれぞれの数だけ存在する。例えば、フィーダがＮｆ本ある場合、Ｎｆ本のフィーダのそれぞれに対して、個々に第１回帰係数が推定される。例えば、フィーダシリアルが「ＦＤ００００１」のフィーダの第１回帰係数はαｆ［１］であり、フィーダシリアルが「ＦＤ００００２」のフィーダの第１回帰係数はαｆ［２］である。ヘッドスピンドル、ノズル及び部品サイズも同様である。 Each regression coefficient includes a feeder regression coefficient which is the first regression coefficient of the feeder, a head spindle regression coefficient which is the first regression coefficient of the head spindle, a nozzle regression coefficient which is the first regression coefficient of the nozzle, and a component size regression coefficient which is the first regression coefficient of the component size. For example, when there are N f feeders, N s head spindles, N n nozzles, and N c component sizes, there are the same number of first regression coefficients for each of the feeders. For example, when there are N f feeders, a first regression coefficient is estimated for each of the N f feeders. For example, the first regression coefficient of a feeder with a feeder serial number of "FD00001" is α f [1], and the first regression coefficient of a feeder with a feeder serial number of "FD00002" is α f [2]. The same applies to the head spindle, the nozzle, and the component size.
　図１を再び参照して、線形回帰係数推定部２４は、図３に示す前処理後データに基づいて、テープ送り精度を推定するための第２回帰係数を推定する。テープ送り精度は、フィーダ（テープフィーダ）がテープ送りにより部品を部品供給位置に供給する際の位置精度を示す。 Referring again to FIG. 1, the linear regression coefficient estimation unit 24 estimates a second regression coefficient for estimating tape feed accuracy based on the preprocessed data shown in FIG. 3. The tape feed accuracy indicates the position accuracy when the feeder (tape feeder) supplies components to the component supply position by tape feed.
　線形回帰係数推定部２４は、図３に示す各補正量から得られる統計量（吸着位置ずれ統計量）と、吸着位置ずれの計測値（例えば、テープフィーダのテープ送り精度の測定値）との分布に基づいて、それぞれを対応付ける線形回帰モデルとその第２回帰係数（線形回帰係数）とを推定する。線形回帰係数推定部２４は、例えば、吸着位置ずれ統計量を横軸とし、送り精度（検査装置の計測値）を縦軸とし、吸着位置ずれ統計量と当該吸着位置ずれ統計量に対応する送り精度の計測値とをプロットし、そのプロットの分布に基づいて、第２回帰係数を推定する。検査装置は、テープ送り精度を直接計測するハードセンサを含んで構成される。線形回帰係数推定部２４は、第２係数推定部の一例である。 The linear regression coefficient estimation unit 24 estimates a linear regression model and its second regression coefficient (linear regression coefficient) that associates statistics (suction position deviation statistics) obtained from each correction amount shown in FIG. 3 with the measurement value of the suction position deviation (for example, the measured value of the tape feed accuracy of the tape feeder) based on the distribution of the statistics. For example, the linear regression coefficient estimation unit 24 plots the suction position deviation statistics and the measurement value of the feed accuracy corresponding to the suction position deviation statistics with the horizontal axis representing the suction position deviation statistics and the vertical axis representing the feed accuracy (measurement value of the inspection device), and estimates the second regression coefficient based on the distribution of the plot. The inspection device is configured to include a hardware sensor that directly measures the tape feed accuracy. The linear regression coefficient estimation unit 24 is an example of a second coefficient estimation unit.
　例えば、線形回帰係数推定部２４は、図３に示す各補正量のうちＸ方向（Ｘ座標）の補正量から得られるＸ方向の統計量（Ｘ方向の吸着位置ずれ統計量）と、Ｘ方向の吸着位置ずれの計測値（例えば、テープフィーダのテープ送り精度のＸ方向の測定値）との分布に基づいて、Ｘ方向の第２回帰係数を推定する。また、例えば、線形回帰係数推定部２４は、図３に示す各補正量のうちＹ方向（Ｙ座標）の補正量から得られるＹ方向の統計量（Ｙ方向の吸着位置ずれ統計量）と、Ｙ方向の吸着位置ずれの計測値（例えば、テープフィーダのテープ送り精度のＹ方向の測定値）との分布に基づいて、Ｙ方向の第２回帰係数を推定する。 For example, the linear regression coefficient estimation unit 24 estimates the second regression coefficient in the X direction based on the distribution of the X direction statistics (X direction suction position shift statistics) obtained from the correction amount in the X direction (X coordinate) among the correction amounts shown in FIG. 3, and the measurement value of the suction position shift in the X direction (for example, the X direction measurement value of the tape feed accuracy of the tape feeder). Also, for example, the linear regression coefficient estimation unit 24 estimates the second regression coefficient in the Y direction based on the distribution of the Y direction statistics (Y direction suction position shift statistics) obtained from the correction amount in the Y direction (Y coordinate) among the correction amounts shown in FIG. 3, and the measurement value of the suction position shift in the Y direction (for example, the Y direction measurement value of the tape feed accuracy of the tape feeder).
　線形回帰係数推定部２４が生成する第２推定モデル３４ａは、複数のユニットそれぞれにおける、テープ送り精度及び部品の吸着位置ずれに関する量の関係を示す第２回帰係数を含む単回帰モデルである。 The second estimation model 34a generated by the linear regression coefficient estimation unit 24 is a simple regression model that includes a second regression coefficient that indicates the relationship between the tape feed accuracy and the amount of component pickup position deviation in each of the multiple units.
　なお、線形回帰係数推定部２４は、認識補正量と吸着補正量とに基づいて、吸着位置ずれ統計量を算出する。線形回帰係数推定部２４は、例えば、認識補正量の平均値又は中央値と吸着補正量の平均値又は中央値とに基づいて、吸着位置ずれ統計量を算出する。また、吸着位置ずれ統計量は、さらに標準偏差も用いて算出されてもよい。また、吸着位置ずれ統計量は、Ｘ座標及びＹ座標のそれぞれに対して算出される。言い換えると、Ｘ座標及びＹ座標のそれぞれに対して第２回帰係数が推定される。 The linear regression coefficient estimation unit 24 calculates the adsorption position shift statistics based on the recognition correction amount and the adsorption correction amount. The linear regression coefficient estimation unit 24 calculates the adsorption position shift statistics based on, for example, the average or median of the recognition correction amount and the average or median of the adsorption correction amount. The adsorption position shift statistics may also be calculated using a standard deviation. The adsorption position shift statistics are calculated for each of the X coordinate and the Y coordinate. In other words, a second regression coefficient is estimated for each of the X coordinate and the Y coordinate.
　要因確率推定装置３０は、係数推定装置２０が推定した第１回帰係数及び第２回帰係数と、第１実装ログＬ１とに基づいて、実装ミスの要因及びテープ送り精度の推定結果を出力する。第１実装ログＬ１は、実装機１０による生産を行っているときに取得された計測対象（推定対象）のログである。要因確率推定装置３０は、実装機１０による生産と並行して、実装機１０の生産中に取得された第１実装ログＬ１を用いて実装ミスの要因及びテープ送り精度の推定結果を出力する。これにより、要因確率推定装置３０は、実装機１０の生産中にユニットの不調が管理者等により判断されることを支援することができるので、ユニットの故障前に管理者等によるメンテナンスを行うことが可能となる。 The factor probability estimation device 30 outputs an estimation result of the cause of the mounting error and the tape feed accuracy based on the first and second regression coefficients estimated by the coefficient estimation device 20 and the first mounting log L1. The first mounting log L1 is a log of the measurement target (estimation target) acquired during production by the mounting machine 10. In parallel with production by the mounting machine 10, the factor probability estimation device 30 outputs an estimation result of the cause of the mounting error and the tape feed accuracy using the first mounting log L1 acquired during production of the mounting machine 10. In this way, the factor probability estimation device 30 can assist the manager, etc. in determining malfunction of the unit during production of the mounting machine 10, making it possible for the manager, etc. to perform maintenance before the unit breaks down.
　要因確率推定装置３０は、ミス回数前処理部３１と、補正量前処理部３２と、実装ミス要因推定部３３と、テープ送り精度推定部３４と、集計部３５～３８とを備える。要因確率推定装置３０は、ＣＰＵ及びメモリ等によって実現可能である。また、要因確率推定装置３０の機能ブロックの各々による処理は、通常、プロセッサ等のプログラム実行部が、ＲＯＭ等の記録媒体に記録されたソフトウェア（プログラム）を読み出して実行することで実現される。 The factor probability estimation device 30 comprises an error count preprocessing unit 31, a correction amount preprocessing unit 32, a mounting error factor estimation unit 33, a tape feed accuracy estimation unit 34, and aggregation units 35 to 38. The factor probability estimation device 30 can be realized by a CPU, memory, etc. Furthermore, the processing by each of the functional blocks of the factor probability estimation device 30 is usually realized by a program execution unit such as a processor reading and executing software (programs) recorded on a recording medium such as a ROM.
　ミス回数前処理部３１及び補正量前処理部３２の機能は、ミス回数前処理部２１及び補正量前処理部２２と同様であり、説明を省略する。ミス回数前処理部３１は、実装機１０から第１実装ログＬ１を取得し、取得した第１実装ログＬ１から図２に示す前処理後データを生成し、実装ミス要因推定部３３に出力する。また、補正量前処理部３２は、実装機１０から第１実装ログＬ１を取得し、取得した第１実装ログＬ１から図２に示すデータ及び吸着位置ずれ統計量を含む前処理後データを生成し、テープ送り精度推定部３４に出力する。 The functions of the error count preprocessing unit 31 and the correction amount preprocessing unit 32 are similar to those of the error count preprocessing unit 21 and the correction amount preprocessing unit 22, and therefore a description thereof will be omitted. The error count preprocessing unit 31 acquires the first mounting log L1 from the mounting machine 10, generates the preprocessed data shown in FIG. 2 from the acquired first mounting log L1, and outputs the preprocessed data including the data shown in FIG. 2 and pickup position deviation statistics from the acquired first mounting log L1, and outputs the preprocessed data to the tape feed accuracy estimation unit 34.
　実装ミス要因推定部３３は、ミス回数前処理部３１からの前処理後データと、非線形回帰係数推定部２３からの第１回帰係数とに基づいて、前処理後データに含まれる実装ミスに対するユニットの要因確率を推定する。実装ミス要因推定部３３は、第１回帰係数に基づく第１推定モデル３３ａを用いて、計測対象の第１実装ログＬ１におけるユニットの要因確率を推定する。 The implementation error cause estimation unit 33 estimates the cause probability of the unit for the implementation error contained in the preprocessed data based on the preprocessed data from the error count preprocessing unit 31 and the first regression coefficient from the nonlinear regression coefficient estimation unit 23. The implementation error cause estimation unit 33 estimates the cause probability of the unit in the first implementation log L1 to be measured using a first estimation model 33a based on the first regression coefficient.
　実装ミス要因推定部３３は、前処理後データと、第１回帰係数とに基づいて導出される二項分布により、発生したミスに対して各要素（例えば、各ユニット）が要因となった確率を算出する。Ｎ回吸着してｙ回実装ミスが発生する確率ｐは、二項分布モデルとして以下の式１で表される。 The mounting error cause estimation unit 33 calculates the probability that each element (e.g., each unit) was the cause of an error that occurred using a binomial distribution derived based on the preprocessed data and the first regression coefficient. The probability p of y mounting errors occurring after N pick-ups is expressed as the following equation 1 as a binomial distribution model.
Figure JPOXMLDOC01-appb-M000001
Figure JPOXMLDOC01-appb-M000001
　なお、ｑは、各要素の１吸着試行当たりの実装ミス要因確率を示す。上記の式１を変形すると、実装ミス要因の確率ｑは以下の式２で表される。 Note that q indicates the probability of a mounting error factor per pickup attempt for each element. By modifying the above formula 1, the probability q of a mounting error factor is expressed as the following formula 2.
　ｑ＝１／（１＋ｅｘｐ（－ｚ））　　　・・・（式２） q = 1/(1 + exp(-z)) ... (Equation 2)
　ここで、ｚは線形予測子であり、αｆをフィーダの第１回帰係数、αｎをノズルの第１回帰係数、αｓをヘッドスピンドルの第１回帰係数、αｃを部品サイズの第１回帰係数、βをバイアス項、ｃｈｉｐＷを部品サイズとすると、以下の式３で表される。 Here, z is a linear predictor, αf is the first regression coefficient of the feeder, αn is the first regression coefficient of the nozzle, αs is the first regression coefficient of the head spindle, αc is the first regression coefficient of the part size, β is the bias term, and chipW is the part size, which is expressed by the following equation 3.
　ｚ＝β＋αｆ＋αｎ＋αｓ＋αｃ／ｃｈｉｐＷ　　　・・・（式３） z=β+ αf + αn + αs + αc /chipW (Equation 3)
　線形予測子ｚは、ミス回数前処理部３１からの前処理後データから算出可能である。式２及び式３は、第１推定モデル３３ａの一例である。第１推定モデル３３ａは、複数のユニットそれぞれにおける実装ミス回数及び当該ユニットの不調の関係性に基づく統計モデルである。第１推定モデル３３ａは、複数のユニットから不調のユニットを識別するための識別モデルであるとも言える。 The linear predictor z can be calculated from the preprocessed data from the error count preprocessing unit 31. Equations 2 and 3 are examples of the first estimation model 33a. The first estimation model 33a is a statistical model based on the relationship between the number of mounting errors in each of multiple units and the malfunction of the unit. The first estimation model 33a can also be said to be an identification model for identifying a malfunctioning unit from multiple units.
　実装ミス要因推定部３３は、実装ミスが発生したときのフィーダ、ノズル、ヘッドスピンドル及び部品サイズの第１回帰係数を式３に代入することで得られる線形予測子ｚを式２に代入することで、実装ミス要因の確率ｑを算出する。実装ミス要因推定部３３は、フィーダ、ノズル、ヘッドスピンドル及び部品サイズそれぞれの実装ミス要因の確率ｑを算出する。 The mounting error cause estimation unit 33 calculates the probability q of the mounting error cause by substituting the linear predictor z obtained by substituting the first regression coefficients of the feeder, nozzle, head spindle, and component size at the time when the mounting error occurred into Equation 3 into Equation 2. The mounting error cause estimation unit 33 calculates the probability q of the mounting error cause for each of the feeder, nozzle, head spindle, and component size.
　なお、確率ｑは、第１推定モデル３３ａにおける目的変数である。第１推定モデル３３ａは、第１回帰係数（編回帰係数）を説明変数とし、確率ｑを目的変数とする重回帰モデルである。 The probability q is the objective variable in the first estimation model 33a. The first estimation model 33a is a multiple regression model in which the first regression coefficient (the regression coefficient) is an explanatory variable and the probability q is an objective variable.
　テープ送り精度推定部３４は、補正量前処理部３２からの前処理後データと、線形回帰係数推定部２４からの第２回帰係数とに基づいて、実装機１０のフィーダのテープ送り精度を推定する。当該第２回帰係数を含んで第２推定モデル３４ａが生成される。テープ送り精度推定部３４は、テープフィーダのテープ送り精度及び部品の吸着位置ずれ統計量の関係性に基づく第２推定モデル３４ａを用いて、計測対象の第１実装ログＬ１におけるテープ送り精度を推定する。 The tape feed accuracy estimation unit 34 estimates the tape feed accuracy of the feeder of the mounting machine 10 based on the preprocessed data from the correction amount preprocessing unit 32 and the second regression coefficient from the linear regression coefficient estimation unit 24. A second estimation model 34a is generated including the second regression coefficient. The tape feed accuracy estimation unit 34 estimates the tape feed accuracy in the first mounting log L1 to be measured using the second estimation model 34a based on the relationship between the tape feed accuracy of the tape feeder and the component pickup position deviation statistics.
　テープ送り精度推定部３４は、第２回帰係数を用いて、計測対象の第１実装ログＬ１に基づいて算出された吸着位置ずれ統計量に対応するテープ送り精度を推定する。テープ送り精度は、例えば、距離である。 The tape feed accuracy estimation unit 34 uses the second regression coefficient to estimate the tape feed accuracy corresponding to the pickup position deviation statistics calculated based on the first mounting log L1 of the measurement target. The tape feed accuracy is, for example, a distance.
　また、テープ送り精度推定部３４は、さらに、テープ送り精度と精度ランクとの対応表（以下の図５を参照）に基づいて、フィーダの精度ランクを推定する。当該精度ランクは、その時点での精度ランクであり、経時的に変化し得る。 The tape feed accuracy estimation unit 34 also estimates the accuracy rank of the feeder based on a correspondence table between tape feed accuracy and accuracy rank (see FIG. 5 below). The accuracy rank is the accuracy rank at that time and may change over time.
　図５は、本実施の形態に係るテープ送り精度と精度ランクとの対応表の一例を示す図である。Ｘ方向送り精度は、Ｘ方向のテープ送り精度を意味し、Ｙ方向送り精度は、Ｙ方向のテープ送り精度を意味する。 FIG. 5 is a diagram showing an example of a correspondence table between tape feed accuracy and accuracy rank in this embodiment. X-direction feed accuracy means tape feed accuracy in the X direction, and Y-direction feed accuracy means tape feed accuracy in the Y direction.
　図５に示すように、対応表では、Ｘ方向送り精度及びＹ方向送り精度に対して、１つの精度ランクが対応付けられている。図５の例では、精度ランクは、「Ａ」、「Ｂ」、「Ｃ」及び「Ｄ」であり、この順に送り精度が高いことを意味する。 As shown in FIG. 5, in the correspondence table, one accuracy rank is associated with each X-direction feed accuracy and Y-direction feed accuracy. In the example of FIG. 5, the accuracy ranks are "A", "B", "C", and "D", which indicate increasing feed accuracy in that order.
　精度ランクは、テープ送り精度に基づく情報の一例である。 The accuracy rank is an example of information based on tape feed accuracy.
　図１を再び参照して、集計部３５は、実装ミス要因推定部３３からの部品サイズに対するミス要因確率を蓄積し、部品シリアルごとのミス要因確率を出力する。 Referring again to FIG. 1, the aggregation unit 35 accumulates the error cause probability for each component size from the mounting error cause estimation unit 33, and outputs the error cause probability for each component serial number.
　集計部３６は、実装ミス要因推定部３３からのノズルに対するミス要因確率を蓄積し、ノズルシリアルごとのミス要因確率を出力する。 The aggregation unit 36 accumulates the error cause probability for each nozzle from the mounting error cause estimation unit 33 and outputs the error cause probability for each nozzle serial number.
　集計部３７は、実装ミス要因推定部３３からのヘッドスピンドルに対するミス要因確率を蓄積し、ヘッドスピンドル番号ごとのミス要因確率を出力する。 The aggregation unit 37 accumulates the error cause probability for the head spindle from the mounting error cause estimation unit 33, and outputs the error cause probability for each head spindle number.
　集計部３８は、実装ミス要因推定部３３からのフィーダに対するミス要因確率、及び、テープ送り精度推定部３４からのテープ送り精度を蓄積し、フィーダシリアルごとのミス要因確率及び精度ランクを出力する。 The aggregation unit 38 accumulates the error cause probability for the feeder from the mounting error cause estimation unit 33 and the tape feed accuracy from the tape feed accuracy estimation unit 34, and outputs the error cause probability and accuracy rank for each feeder serial.
　集計部３５～３８は、所定生産数分（例えば、１ＬＯＴ分）のミス要因確率を蓄積し、蓄積されたミス要因確率に基づいて、所定生産数分の生産に対する１つのミス要因確率を算出する。集計部３５～３８は、例えば、所定生産数分のミス要因確率を集計し、その平均値を当該１つのミス要因確率として推定してもよい。ミス要因確率は、推定結果の一例である。 The counting units 35 to 38 accumulate the error cause probabilities for a predetermined number of production runs (e.g., one lot), and calculate one error cause probability for the predetermined number of production runs based on the accumulated error cause probabilities. The counting units 35 to 38 may, for example, accumulate the error cause probabilities for a predetermined number of production runs, and estimate the average value as the one error cause probability. The error cause probability is an example of an estimation result.
　表示装置４０は、各種情報を表示する。表示装置４０は、要因確率推定装置３０による実装ミスの要因確率及びテープ送り精度の推定結果を表示する。表示装置４０は、液晶表示装置等であるが、これに限定されない。 The display device 40 displays various information. The display device 40 displays the results of the estimation of the cause probability of mounting errors and the tape feed accuracy by the cause probability estimation device 30. The display device 40 is a liquid crystal display device or the like, but is not limited to this.
　なお、係数推定装置２０、要因確率推定装置３０及び表示装置４０はそれぞれ別体の装置として実現されてもよいし、少なくとも２つの装置は一体の装置として実現されてもよい。例えば、係数推定装置２０及び要因確率推定装置３０が一体の装置として実現されてもよいし、係数推定装置２０、要因確率推定装置３０及び表示装置４０が一体の装置として実現されてもよい。 The coefficient estimation device 20, the factor probability estimation device 30, and the display device 40 may each be realized as separate devices, or at least two of the devices may be realized as an integrated device. For example, the coefficient estimation device 20 and the factor probability estimation device 30 may be realized as an integrated device, or the coefficient estimation device 20, the factor probability estimation device 30, and the display device 40 may be realized as an integrated device.
　［２．生産支援システムの動作］
　続いて、上記のように構成される生産支援システム１の動作について、図６～図１１を参照しながら説明する。図６は、本実施の形態に係る生産支援システム１の動作（生産支援方法）を示す第１のフローチャートである。図６は、第１回帰係数及び第２回帰係数を推定する動作を示す。図６の処理は、係数推定装置２０が実行する。 [2. Operation of the Production Support System]
Next, the operation of the production support system 1 configured as above will be described with reference to Fig. 6 to Fig. 11. Fig. 6 is a first flowchart showing the operation (production support method) of the production support system 1 according to this embodiment. Fig. 6 shows the operation of estimating the first regression coefficient and the second regression coefficient. The process of Fig. 6 is executed by the coefficient estimation device 20.
　図６に示すように、係数推定装置２０のミス回数前処理部２１及び補正量前処理部２２のそれぞれは、事前推定用の第２実装ログＬ２を取得する（Ｓ１０）。ミス回数前処理部２１及び補正量前処理部２２は、第２実装ログＬ２を取得する取得部として機能する。 As shown in FIG. 6, each of the error count preprocessing unit 21 and the correction amount preprocessing unit 22 of the coefficient estimation device 20 acquires a second implementation log L2 for advance estimation (S10). The error count preprocessing unit 21 and the correction amount preprocessing unit 22 function as an acquisition unit that acquires the second implementation log L2.
　次に、ミス回数前処理部２１及び補正量前処理部２２のそれぞれは、前処理を実行する（Ｓ２０）。ミス回数前処理部２１は、第２実装ログＬ２に対して前処理を実行することで、例えば、図２に示す前処理後データを生成し、非線形回帰係数推定部２３に出力する。補正量前処理部２２は、第２実装ログＬ２に対して前処理を実行することで、例えば、図３に示す前処理後データを生成し、線形回帰係数推定部２４に出力する。なお、本実施の形態では、補正量前処理部２２は、吸着位置ずれ統計量を含む前処理後データを線形回帰係数推定部２４に出力する。 Next, the error count preprocessing unit 21 and the correction amount preprocessing unit 22 each perform preprocessing (S20). The error count preprocessing unit 21 performs preprocessing on the second mounting log L2 to generate, for example, preprocessed data shown in FIG. 2, and outputs the preprocessed data to the nonlinear regression coefficient estimating unit 23. The correction amount preprocessing unit 22 performs preprocessing on the second mounting log L2 to generate, for example, preprocessed data shown in FIG. 3, and outputs the preprocessed data to the linear regression coefficient estimating unit 24. In this embodiment, the correction amount preprocessing unit 22 outputs the preprocessed data including the pickup position deviation statistics to the linear regression coefficient estimating unit 24.
　次に、非線形回帰係数推定部２３は、ミス回数前処理部２１からの前処理後データに基づいて第１回帰係数を推定する（Ｓ３０）。図７は、本実施の形態に係る第１回帰係数の推定及び使用を説明するための図である。なお、図７では、ミス回数前処理部２１及び３１の図示を省略している。 Next, the nonlinear regression coefficient estimation unit 23 estimates the first regression coefficient based on the preprocessed data from the error count preprocessing unit 21 (S30). Figure 7 is a diagram for explaining the estimation and use of the first regression coefficient according to this embodiment. Note that the error count preprocessing units 21 and 31 are not shown in Figure 7.
　図７に示すように、非線形回帰係数推定部２３は、第２実装ログＬ２に基づいてＭＣＭＣ法を用いて各要素の第１回帰係数を推定し、推定した第１回帰係数を要因確率推定装置３０の実装ミス要因推定部３３に出力する。実装ミス要因推定部３３は、第１回帰係数を取得する取得部として機能する。 As shown in FIG. 7, the nonlinear regression coefficient estimation unit 23 estimates the first regression coefficient of each element using the MCMC method based on the second implementation log L2, and outputs the estimated first regression coefficient to the implementation error factor estimation unit 33 of the factor probability estimation device 30. The implementation error factor estimation unit 33 functions as an acquisition unit that acquires the first regression coefficient.
　図６を再び参照して、次に、線形回帰係数推定部２４は、補正量前処理部２２からの前処理後データに基づいて第２回帰係数を推定する（Ｓ４０）。図８は、本実施の形態に係る第２回帰係数の推定及び使用を説明するための図である。 Referring again to FIG. 6, next, the linear regression coefficient estimator 24 estimates the second regression coefficient based on the preprocessed data from the correction amount preprocessor 22 (S40). FIG. 8 is a diagram for explaining the estimation and use of the second regression coefficient according to this embodiment.
　図８に示すように、線形回帰係数推定部２４は、第２実装ログＬ２に基づく吸着位置ずれ統計量及び検査装置の検査計測値Ｍの分布に基づいて第２回帰係数を推定し、推定した第２回帰係数を要因確率推定装置３０のテープ送り精度推定部３４に出力する。テープ送り精度推定部３４は、第２回帰係数を取得する取得部として機能する。 As shown in FIG. 8, the linear regression coefficient estimation unit 24 estimates the second regression coefficient based on the pickup position deviation statistics based on the second mounting log L2 and the distribution of the inspection measurement value M of the inspection device, and outputs the estimated second regression coefficient to the tape feed accuracy estimation unit 34 of the factor probability estimation device 30. The tape feed accuracy estimation unit 34 functions as an acquisition unit that acquires the second regression coefficient.
　なお、図８に示す第１実装ログＬ１、第２実装ログＬ２、及び、検査計測値Ｍは、同一の実装機１０を用いて取得されたデータである。 Note that the first mounting log L1, the second mounting log L2, and the inspection measurement value M shown in FIG. 8 are data acquired using the same mounting machine 10.
　続いて、計測対象の生産に対する推定を実行する処理について説明する。図９は、本実施の形態に係る生産支援システム１の動作（生産支援方法）を示す第２のフローチャートである。図９に示すステップＳ１１０～Ｓ１７０の処理は、要因確率推定装置３０が実行し、ステップＳ１８０は、表示装置４０が実行する。 Next, the process of making an estimation for the production of the measurement target will be described. FIG. 9 is a second flowchart showing the operation (production support method) of the production support system 1 according to this embodiment. The process of steps S110 to S170 shown in FIG. 9 is performed by the factor probability estimation device 30, and step S180 is performed by the display device 40.
　図９に示すように、要因確率推定装置３０のミス回数前処理部３１及び補正量前処理部３２のそれぞれは、計測対象の第１実装ログＬ１を取得する（Ｓ１１０）。ミス回数前処理部３１及び補正量前処理部３２は、第１実装ログＬ１を取得する取得部として機能する。 As shown in FIG. 9, each of the error count preprocessing unit 31 and the correction amount preprocessing unit 32 of the factor probability estimation device 30 acquires the first implementation log L1 of the measurement target (S110). The error count preprocessing unit 31 and the correction amount preprocessing unit 32 function as an acquisition unit that acquires the first implementation log L1.
　次に、ミス回数前処理部３１及び補正量前処理部３２のそれぞれは、前処理を実行する（Ｓ１２０）。ミス回数前処理部３１は、第１実装ログＬ１に対して前処理を実行することで、例えば、図２に示す前処理後データを生成し、実装ミス要因推定部３３に出力する。また、補正量前処理部３２は、第１実装ログＬ１に対して前処理を実行することで、例えば、図３に示す前処理後データを生成し、テープ送り精度推定部３４に出力する。なお、本実施の形態では、補正量前処理部３２は、吸着位置ずれ統計量を含む前処理後データをテープ送り精度推定部３４に出力する。 Next, each of the error count preprocessing unit 31 and the correction amount preprocessing unit 32 executes preprocessing (S120). The error count preprocessing unit 31 executes preprocessing on the first mounting log L1 to generate, for example, preprocessed data shown in FIG. 2, and outputs the preprocessed data to the mounting error cause estimation unit 33. The correction amount preprocessing unit 32 executes preprocessing on the first mounting log L1 to generate, for example, preprocessed data shown in FIG. 3, and outputs the preprocessed data to the tape feed accuracy estimation unit 34. In this embodiment, the correction amount preprocessing unit 32 outputs preprocessed data including the pickup position deviation statistics to the tape feed accuracy estimation unit 34.
　次に、実装ミス要因推定部３３は、非線形回帰係数推定部２３からの第１回帰係数を取得し（Ｓ１３０）、各要素のミス要因確率を推定する（Ｓ１４０）。図７に示すように、実装ミス要因推定部３３は、ミス回数前処理部３１からの前処理後データ（第１実装ログＬ１に基づく前処理後データ）と、第１回帰係数と、上記の式２及び式３とに基づいて、各要素のミス要因確率を推定する。図７では、実装ミス要因推定部３３がフィーダ要因確率を出力する例を示している。実装ミス要因推定部３３は、部品シリアルごとのミス要因確率を集計部３５に出力し、ノズルシリアルごとのミス要因確率を集計部３６に出力し、ヘッドスピンドル番号ごとのミス要因確率を集計部３７に出力し、フィーダシリアルごとのミス要因確率を集計部３８に出力する。 Next, the mounting error factor estimation unit 33 acquires the first regression coefficient from the nonlinear regression coefficient estimation unit 23 (S130) and estimates the error factor probability of each element (S140). As shown in FIG. 7, the mounting error factor estimation unit 33 estimates the error factor probability of each element based on the preprocessed data from the error count preprocessing unit 31 (preprocessed data based on the first mounting log L1), the first regression coefficient, and the above formulas 2 and 3. FIG. 7 shows an example in which the mounting error factor estimation unit 33 outputs the feeder factor probability. The mounting error factor estimation unit 33 outputs the error factor probability for each component serial number to the aggregation unit 35, outputs the error factor probability for each nozzle serial number to the aggregation unit 36, outputs the error factor probability for each head spindle number to the aggregation unit 37, and outputs the error factor probability for each feeder serial number to the aggregation unit 38.
　図９を再び参照して、次に、テープ送り精度推定部３４は、線形回帰係数推定部２４からの第２回帰係数を取得し（Ｓ１５０）、フィーダのテープ送り精度を推定する（Ｓ１６０）。図８に示すように、テープ送り精度推定部３４は、補正量前処理部３２からの吸着位置ずれ統計量と、第２回帰係数とに基づいて、フィーダのテープ送り精度を推定する。テープ送り精度推定部３４は、Ｘ方向の吸着位置ずれ統計量と、Ｘ方向の第２回帰係数とに基づいて、Ｘ方向のテープ送り精度を推定し、Ｙ方向の吸着位置ずれ統計量と、Ｙ方向の第２回帰係数とに基づいて、Ｙ方向のテープ送り精度を推定する。 Referring again to FIG. 9, next, the tape feed accuracy estimation unit 34 acquires the second regression coefficient from the linear regression coefficient estimation unit 24 (S150) and estimates the tape feed accuracy of the feeder (S160). As shown in FIG. 8, the tape feed accuracy estimation unit 34 estimates the tape feed accuracy of the feeder based on the suction position deviation statistics from the correction amount preprocessing unit 32 and the second regression coefficient. The tape feed accuracy estimation unit 34 estimates the tape feed accuracy in the X direction based on the suction position deviation statistics in the X direction and the second regression coefficient in the X direction, and estimates the tape feed accuracy in the Y direction based on the suction position deviation statistics in the Y direction and the second regression coefficient in the Y direction.
　図９を再び参照して、次に、テープ送り精度推定部３４は、推定したＸ方向及びＹ方向のテープ送り精度と、図５に示す対応表とに基づいて、フィーダの精度ランクを推定する（Ｓ１７０）。テープ送り精度推定部３４は、精度ランクを集計部３８に出力する。 Referring again to FIG. 9, next, the tape feed accuracy estimation unit 34 estimates the accuracy rank of the feeder based on the estimated tape feed accuracy in the X direction and Y direction and the correspondence table shown in FIG. 5 (S170). The tape feed accuracy estimation unit 34 outputs the accuracy rank to the aggregation unit 38.
　次に、表示装置４０は、各集計部３５～３８からの情報を表示する（Ｓ１８０）。図１０は、本実施の形態に係る表示装置４０が表示する画面の第１例を示す図である。図１０は、実装ミス要因の判定結果を示す。 Next, the display device 40 displays information from each of the counting units 35 to 38 (S180). Figure 10 is a diagram showing a first example of a screen displayed by the display device 40 according to this embodiment. Figure 10 shows the results of determining the causes of mounting errors.
　図１０に示すように、表示装置４０は、要因確率推定装置３０からのミス要因確率を表示する。図１０では、ヘッドスピンドルのアドレス「１」及び「２」におけるＬＯＴ０１～ＬＯＴ０３それぞれのミス要因確率を表示している例を示している。アドレスは、シリアルに対応する。アドレス「１」のヘッドスピンドルが、ＬＯＴ０１で発生した実装ミスの要因である確率は１０％であり、ＬＯＴ０２で発生した実装ミスの要因である確率は５％であり、ＬＯＴ０３で発生した実装ミスの要因である確率は８％である。また、アドレス「２」のヘッドスピンドルが、ＬＯＴ０１で発生した実装ミスの要因である確率は９０％であり、ＬＯＴ０２で発生した実装ミスの要因である確率は８０％であり、ＬＯＴ０３で発生した実装ミスの要因である確率は１００％である。このように、各ＬＯＴのミス要因確率が一画面上に表示されることで、生産支援システム１は、実装機１０の管理者が正常な要素及び不調である要素を判断することを支援することができる。要因確率は、例えば、ユニットごとに表示されるが、これに限定されない。 As shown in FIG. 10, the display device 40 displays the error cause probability from the cause probability estimation device 30. FIG. 10 shows an example in which the error cause probability for each of LOT01 to LOT03 at head spindle addresses "1" and "2" is displayed. The addresses correspond to the serial number. The probability that the head spindle at address "1" is the cause of the mounting error that occurred in LOT01 is 10%, the probability that it is the cause of the mounting error that occurred in LOT02 is 5%, and the probability that it is the cause of the mounting error that occurred in LOT03 is 8%. In addition, the probability that the head spindle at address "2" is the cause of the mounting error that occurred in LOT01 is 90%, the probability that it is the cause of the mounting error that occurred in LOT02 is 80%, and the probability that it is the cause of the mounting error that occurred in LOT03 is 100%. In this way, by displaying the error cause probability for each LOT on one screen, the production support system 1 can support the manager of the mounting machine 10 in determining which elements are normal and which elements are malfunctioning. The factor probability is displayed, for example, by unit, but is not limited to this.
　また、表示装置４０は、各ＬＯＴのミス要因確率の平均値（図１０に示す期間平均）を表示してもよい。これにより、管理者による正常な要素及び不調である要素の判断をより容易にし得る。 The display device 40 may also display the average value of the error cause probability for each LOT (average over the period shown in FIG. 10). This makes it easier for the manager to determine which elements are normal and which elements are malfunctioning.
　なお、例えば、ＬＯＴ０１の場合、アドレス「１」のヘッドスピンドルのミス要因確率と、当該アドレス「１」のヘッドスピンドルに対応するノズル、部品及びフィーダそれぞれのミス要因確率の合計は、１００％となる。 For example, in the case of LOT01, the sum of the probability of a miss cause for the head spindle at address "1" and the probability of a miss cause for each of the nozzles, parts, and feeders corresponding to the head spindle at address "1" is 100%.
　図１１は、本実施の形態に係る表示装置４０が表示する画面の第２例を示す図である。図１１は、テープ送り精度の判定結果を示す。具体的には、図１１は、フィーダのテープ送り精度の精度ランク（図１１に示すランク）を示す。 FIG. 11 is a diagram showing a second example of a screen displayed by the display device 40 according to the present embodiment. FIG. 11 shows the judgment result of the tape feed accuracy. Specifically, FIG. 11 shows the accuracy rank (rank shown in FIG. 11) of the tape feed accuracy of the feeder.
　図１１に示すように、表示装置４０は、要因確率推定装置３０からのテープ送り精度の判定結果を表示する。図１１では、フィーダのアドレス「１」及び「２」におけるＬＯＴ０１～ＬＯＴ０３それぞれのテープ送り精度の判定結果を表示している例を示している。アドレスは、シリアルに対応する。アドレス「１」（シリアル：ＦＤ０００１）のフィーダの、ＬＯＴ０１における精度ランクが「Ｂ」であり、ＬＯＴ０２及びＬＯＴ０３における精度ランクが「Ａ」である。また、アドレス「２」（シリアル：ＦＤ０００２）のフィーダの、ＬＯＴ０１における精度ランクが「Ｄ」であり、ＬＯＴ０２における精度ランクが「Ｃ」であり、ＬＯＴ０３における精度ランクが「Ｄ」である。このように、フィーダの各ＬＯＴの精度ランクが一画面上に表示されることで、実装機１０の管理者が、正常なフィーダ及び不調であるフィーダを判断することを支援することができる。 As shown in FIG. 11, the display device 40 displays the judgment results of the tape feed accuracy from the factor probability estimation device 30. FIG. 11 shows an example of displaying the judgment results of the tape feed accuracy for each of LOT01 to LOT03 at feeder addresses "1" and "2". The addresses correspond to the serial numbers. The accuracy rank of the feeder with address "1" (serial number: FD0001) in LOT01 is "B", and the accuracy rank of the feeder with address "2" (serial number: FD0002) in LOT01 is "D", the accuracy rank of the feeder with address "2" (serial number: FD0002) in LOT01 is "C", and the accuracy rank of the feeder with address "D" in LOT03. In this way, the accuracy rank of each lot of the feeder is displayed on one screen, which can help the manager of the mounting machine 10 to determine which feeders are normal and which are malfunctioning.
　また、表示装置４０は、フィーダの推定結果を表示する場合、ミス要因確率と精度ランクとを一画面上してもよい。また、表示装置４０は、精度ランクに替えて又は精度ランクとともにテープ送り精度の推定値を表示してもよい。 When displaying the feeder estimation results, the display device 40 may display the error cause probability and the accuracy rank on one screen. The display device 40 may also display the estimated value of the tape feeding accuracy instead of or together with the accuracy rank.
　上記のようにミス要因確率及びテープ送り精度が推定されることで、コストを上げず（ハードセンサを追加せず）に、実装機１０の状態（各ユニットの状態）を高精度で推定することができる。これにより、ピンポイントでのメンテナンスが可能となるので、低コストで設備性能ロス（例えば、短期間又は長期間の実装機１０の停止）を低減することができる。 By estimating the probability of error factors and tape feed accuracy as described above, the state of the mounting machine 10 (the state of each unit) can be estimated with high accuracy without increasing costs (without adding hardware sensors). This enables pinpoint maintenance, and reduces equipment performance losses (e.g., short or long stoppages of the mounting machine 10) at low cost.
　（その他の実施の形態）
　以上、一つ又は複数の態様に係る生産支援システム等について、実施の形態に基づいて説明したが、本開示は、この実施の形態に限定されるものではない。本開示の趣旨を逸脱しない限り、当業者が思いつく各種変形を本実施の形態に施したものや、異なる実施の形態における構成要素を組み合わせて構築される形態も、本開示に含まれてもよい。 (Other embodiments)
Although the production support system according to one or more aspects has been described based on the embodiment, the present disclosure is not limited to this embodiment. As long as it does not deviate from the gist of the present disclosure, various modifications conceived by a person skilled in the art to this embodiment and forms constructed by combining components in different embodiments may also be included in the present disclosure.
　例えば、上記実施の形態では、実装ミス要因推定部は、ロジスティック回帰分析により実装ミスの要因確率を推定する例について説明したが、他の非線形回帰分析を用いて実装ミスの要因確率を推定してもよい。実装ミス要因推定部は、例えば、多項式回帰分析、サポートベクトル回帰分析等により実装ミスの要因確率を推定してもよい。 For example, in the above embodiment, an example has been described in which the mounting error cause estimation unit estimates the cause probability of a mounting error using logistic regression analysis, but the cause probability of a mounting error may be estimated using other nonlinear regression analyses. The mounting error cause estimation unit may estimate the cause probability of a mounting error using, for example, polynomial regression analysis, support vector regression analysis, etc.
　また、上記実施の形態では、フィーダがテープフィーダである例について説明したが、例えば、バルクフィーダ等の他のフィーダであってもよい。この場合、要因確率推定装置は、テープ送り精度推定部を備えていなくてもよい。 In addition, in the above embodiment, an example was described in which the feeder was a tape feeder, but it may be another feeder, such as a bulk feeder. In this case, the factor probability estimation device does not need to be equipped with a tape feed accuracy estimation unit.
　また、上記実施の形態に係る係数推定装置及び要因確率推定装置のそれぞれは、実装機が配置される工場等に配置される端末装置であってもよいし、当該工場から遠隔に配置されるサーバ装置であってもよい。 In addition, each of the coefficient estimation device and the factor probability estimation device according to the above-described embodiment may be a terminal device located in a factory or the like where the mounting machine is located, or may be a server device located remotely from the factory.
　また、上記実施の形態に係る第１回帰係数及び第２回帰係数は、例えば、１回のみ推定されてもよいし、定期的に推定され、要因確率推定装置で用いられる第１回帰係数及び第２回帰係数が定期的に更新されてもよい。また、第１回帰係数及び第２回帰係数は、例えば、ユニットを新品と交換した、故障を修理した等の所定のイベントが発生した後に推定されてもよい。 Furthermore, the first regression coefficient and the second regression coefficient according to the above embodiment may be estimated only once, for example, or may be estimated periodically, and the first regression coefficient and the second regression coefficient used in the factor probability estimation device may be updated periodically. Furthermore, the first regression coefficient and the second regression coefficient may be estimated after the occurrence of a specified event, for example, replacing a unit with a new one or repairing a malfunction.
　また、上記実施の形態に係る第１実装ログ及び第２実装ログは、設備ログとも称される。 In addition, the first implementation log and the second implementation log in the above embodiment are also referred to as equipment logs.
　また、上記実施の形態では、吸着位置ずれ統計量に基づいてテープ送り精度が推定される例について説明したが、例えば、認識補正量及び吸着補正量の一方に基づいて、テープ送り精度が推定されてもよい。 In the above embodiment, an example was described in which the tape feed accuracy was estimated based on the suction position deviation statistics, but the tape feed accuracy may also be estimated based on, for example, either the recognition correction amount or the suction correction amount.
　また、上記実施の形態等において、各構成要素は、専用のハードウェアで構成されるか、各構成要素に適したソフトウェアプログラムを実行することによって実現されてもよい。各構成要素は、ＣＰＵ又はプロセッサなどのプログラム実行部が、ハードディスク又は半導体メモリなどの記録媒体に記録されたソフトウェアプログラムを読み出して実行することによって実現されてもよい。 Furthermore, in the above embodiments, each component may be configured with dedicated hardware, or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory.
　また、フローチャートにおける各ステップが実行される順序は、本開示を具体的に説明するために例示するためのものであり、上記以外の順序であってもよい。また、上記ステップの一部が他のステップと同時（並列）に実行されてもよいし、上記ステップの一部は実行されなくてもよい。 The order in which each step in the flowchart is executed is merely an example to specifically explain the present disclosure, and orders other than those described above may also be used. Some of the steps may also be executed simultaneously (in parallel) with other steps, and some of the steps may not be executed.
　また、ブロック図における機能ブロックの分割は一例であり、複数の機能ブロックを一つの機能ブロックとして実現したり、一つの機能ブロックを複数に分割したり、一部の機能を他の機能ブロックに移してもよい。また、類似する機能を有する複数の機能ブロックの機能を単一のハードウェア又はソフトウェアが並列又は時分割に処理してもよい。 Furthermore, the division of functional blocks in the block diagram is one example, and multiple functional blocks may be realized as one functional block, one functional block may be divided into multiple blocks, or some functions may be transferred to other functional blocks. Furthermore, the functions of multiple functional blocks having similar functions may be processed in parallel or in a time-shared manner by a single piece of hardware or software.
　また、上記実施の形態等に係る生産支援システムは、単一の装置として実現されてもよいし、複数の装置により実現されてもよい。生産支援システムが複数の装置によって実現される場合、当該生産支援システムが有する各構成要素は、複数の装置にどのように振り分けられてもよい。生産支援システムが複数の装置で実現される場合、当該複数の装置間の通信方法は、特に限定されず、無線通信であってもよいし、有線通信であってもよい。また、装置間では、無線通信及び有線通信が組み合わされてもよい。 In addition, the production support system according to the above-mentioned embodiments may be realized as a single device, or may be realized by multiple devices. When the production support system is realized by multiple devices, each component of the production support system may be allocated in any manner to the multiple devices. When the production support system is realized by multiple devices, the communication method between the multiple devices is not particularly limited, and may be wireless communication or wired communication. Furthermore, wireless communication and wired communication may be combined between the devices.
　また、上記実施の形態等で説明した各構成要素は、ソフトウェアとして実現されても良いし、典型的には、集積回路であるＬＳＩとして実現されてもよい。これらは、個別に１チップ化されてもよいし、一部又は全てを含むように１チップ化されてもよい。ここでは、ＬＳＩとしたが、集積度の違いにより、ＩＣ、システムＬＳＩ、スーパーＬＳＩ、ウルトラＬＳＩと呼称されることもある。また、集積回路化の手法はＬＳＩに限るものではなく、専用回路（専用のプログラムを実行する汎用回路）又は汎用プロセッサで実現してもよい。ＬＳＩ製造後に、プログラムすることが可能なＦＰＧＡ（Ｆｉｅｌｄ　Ｐｒｏｇｒａｍｍａｂｌｅ　Ｇａｔｅ　Ａｒｒａｙ）又は、ＬＳＩ内部の回路セルの接続若しくは設定を再構成可能なリコンフィギュラブル・プロセッサを利用してもよい。更には、半導体技術の進歩又は派生する別技術によりＬＳＩに置き換わる集積回路化の技術が登場すれば、当然、その技術を用いて構成要素の集積化を行ってもよい。 Furthermore, each component described in the above embodiment may be realized as software, or may be realized as an LSI, which is typically an integrated circuit. These may be individually integrated into one chip, or may be integrated into one chip to include some or all of them. Here, LSI is used, but depending on the degree of integration, it may be called IC, system LSI, super LSI, or ultra LSI. Furthermore, the method of integration is not limited to LSI, and may be realized with a dedicated circuit (a general-purpose circuit that executes a dedicated program) or a general-purpose processor. After LSI manufacture, a programmable FPGA (Field Programmable Gate Array) or a reconfigurable processor that can reconfigure the connection or settings of the circuit cells inside the LSI may be used. Furthermore, if an integrated circuit technology that replaces LSI appears due to advances in semiconductor technology or a different derived technology, it is natural that the components may be integrated using that technology.
　システムＬＳＩは、複数の処理部を１個のチップ上に集積して製造された超多機能ＬＳＩであり、具体的には、マイクロプロセッサ、ＲＯＭ（Ｒｅａｄ　Ｏｎｌｙ　Ｍｅｍｏｒｙ）、ＲＡＭ（Ｒａｎｄｏｍ　Ａｃｃｅｓｓ　Ｍｅｍｏｒｙ）などを含んで構成されるコンピュータシステムである。ＲＯＭには、コンピュータプログラムが記憶されている。マイクロプロセッサが、コンピュータプログラムに従って動作することにより、システムＬＳＩは、その機能を達成する。 A system LSI is an ultra-multifunctional LSI manufactured by integrating multiple processing functions onto a single chip, and is specifically a computer system that includes a microprocessor, ROM (Read Only Memory), RAM (Random Access Memory), etc. Computer programs are stored in the ROM. The system LSI achieves its functions when the microprocessor operates according to the computer program.
　また、本開示の一態様は、図６及び図９のいずれかに示される生産支援方法に含まれる特徴的な各ステップをコンピュータに実行させるコンピュータプログラムであってもよい。 Another aspect of the present disclosure may be a computer program that causes a computer to execute each of the characteristic steps included in the production support method shown in either FIG. 6 or FIG. 9.
　また、例えば、プログラムは、コンピュータに実行させるためのプログラムであってもよい。また、本開示の一態様は、そのようなプログラムが記録された、コンピュータ読み取り可能な非一時的な記録媒体であってもよい。例えば、そのようなプログラムを記録媒体に記録して頒布又は流通させてもよい。例えば、頒布されたプログラムを、他のプロセッサを有する装置にインストールして、そのプログラムをそのプロセッサに実行させることで、その装置に、上記各処理を行わせることが可能となる。 Furthermore, for example, the program may be a program to be executed by a computer. Furthermore, one aspect of the present disclosure may be a non-transitory computer-readable recording medium on which such a program is recorded. For example, such a program may be recorded on a recording medium and distributed or circulated. For example, the distributed program may be installed in a device having another processor, and the program may be executed by that processor, thereby making it possible to cause that device to perform each of the above processes.
　（付記）
　以上の実施の形態の記載により、下記の技術が開示される。 (Additional Note)
The above description of the embodiments discloses the following techniques.
　（技術１）
　複数のユニットから構成される実装機において発生した実装ミスに対する、前記複数のユニットそれぞれが前記実装ミスの要因となった確率を推定する生産支援システムであって、
　前記実装ミスに関する情報を含み、前記確率を推定する対象の第１実装ログを前記実装機から取得する取得部と、
　前記第１実装ログと、前記複数のユニットそれぞれにおける、実装ミス回数及び当該ユニットの不調の関係性に基づく第１推定モデルとに基づいて、前記複数のユニットそれぞれにおける前記確率を推定する実装ミス要因推定部と、
　前記実装ミス要因推定部の推定結果を出力する出力部とを備え、
　前記第１実装ログは、前記複数のユニットにおける生産数に関する情報及び実装ミス回数を含む
　生産支援システム。 (Technique 1)
1. A production support system that estimates a probability that each of a plurality of units caused a mounting error that occurred in a mounting machine configured with the plurality of units, the system comprising:
an acquisition unit that acquires, from the mounting machine, a first mounting log that includes information about the mounting error and is a target for estimating the probability;
a mounting error cause estimation unit that estimates the probability for each of the plurality of units based on the first mounting log and a first estimation model based on a relationship between the number of mounting errors in each of the plurality of units and a malfunction of the unit;
an output unit that outputs an estimation result of the mounting error cause estimation unit;
The first mounting log includes information regarding the number of productions in the plurality of units and the number of mounting errors.
　（技術２）
　前記第１推定モデルは、前記複数のユニットそれぞれにおける、前記生産数に関する情報及び前記実装ミス回数の分布に基づく前記複数のユニットそれぞれの第１回帰係数を説明変数とし、前記確率を目的変数とする重回帰モデルである
　技術１に記載の生産支援システム。 (Technique 2)
The first estimation model is a multiple regression model in which a first regression coefficient of each of the plurality of units based on information on the production volume and a distribution of the number of mounting errors in each of the plurality of units is used as an explanatory variable, and the probability is used as a target variable.
　（技術３）
　前記第１実装ログより前に取得された前記実装機の第２実装ログに含まれる前記生産数に関する情報と前記実装ミス回数との分布に基づいて、前記複数のユニットそれぞれの前記第１回帰係数を推定する第１係数推定部をさらに備える
　技術２に記載の生産支援システム。 (Technique 3)
The production support system according to Technology 2, further comprising a first coefficient estimation unit that estimates the first regression coefficient for each of the plurality of units based on a distribution of information relating to the production volume and the number of mounting errors included in a second mounting log of the mounting machine acquired before the first mounting log.
　（技術４）
　前記出力部は、前記実装ミスに対する前記複数のユニットそれぞれの前記確率を表示する
　技術１～３のいずれかに記載の生産支援システム。 (Technique 4)
The production support system according to any one of techniques 1 to 3, wherein the output unit displays the probability of the mounting error for each of the plurality of units.
　（技術５）
　前記複数のユニットは、部品を供給するテープフィーダと、前記部品を吸着するノズルとを含み、
　前記第１実装ログと、前記テープフィーダのテープ送り精度及び前記部品の吸着位置ずれに関する量の関係性に基づく第２推定モデルとに基づいて、前記テープ送り精度を推定するテープ送り精度推定部をさらに備え、
　前記第１実装ログは、さらに、前記ノズルを制御するための制御量に関する情報を含む
　技術１～４のいずれかに記載の生産支援システム。 (Technique 5)
the plurality of units include a tape feeder that supplies components and a nozzle that picks up the components;
a tape feeding accuracy estimation unit that estimates the tape feeding accuracy based on the first mounting log and a second estimation model that is based on a relationship between a tape feeding accuracy of the tape feeder and an amount related to a pickup position deviation of the component,
The production support system according to any one of techniques 1 to 4, wherein the first mounting log further includes information regarding a control amount for controlling the nozzle.
　（技術６）
　前記第２推定モデルは、前記テープ送り精度及び前記部品の吸着位置ずれに関する量の関係を示す第２回帰係数を含む単回帰モデルである
　技術５に記載の生産支援システム。 (Technique 6)
The production support system according to technology 5, wherein the second estimation model is a simple regression model including a second regression coefficient indicating a relationship between the tape feeding accuracy and an amount related to a pickup position deviation of the component.
　（技術７）
　前記第１実装ログより前に取得された前記実装機の第３実装ログに含まれる前記ノズルを制御するための制御量と、前記テープフィーダのテープ送り精度の測定値との分布に基づいて、前記複数のユニットそれぞれの前記第２回帰係数を推定する第２係数推定部をさらに備える
　技術６に記載の生産支援システム。 (Technique 7)
The production support system described in Technology 6, further comprising a second coefficient estimating unit that estimates the second regression coefficient for each of the plurality of units based on a distribution of a control amount for controlling the nozzle included in a third mounting log of the mounting machine acquired before the first mounting log, and a distribution of measured values of tape feeding accuracy of the tape feeder.
　（技術８）
　前記出力部は、前記テープ送り精度推定部により推定された前記テープ送り精度に関する情報を表示する
　技術５～７のいずれかに記載の生産支援システム。 (Technique 8)
The production support system according to any one of claims 5 to 7, wherein the output unit displays information regarding the tape feed accuracy estimated by the tape feed accuracy estimation unit.
　（技術９）
　前記実装機は、前記複数のユニットの状態を直接的に計測するセンサを備えていない
　技術１～８のいずれかに記載の生産支援システム。 (Technique 9)
The production support system according to any one of techniques 1 to 8, wherein the mounting machine does not include a sensor that directly measures the states of the multiple units.
　（技術１０）
　前記複数のユニットは、ヘッドスピンドル、ノズル及びフィーダを含み、
　前記実装ミス要因推定部は、前記ヘッドスピンドル、前記ノズル、前記フィーダ及び前記フィーダが供給する部品それぞれの前記確率を推定する
　技術１～９のいずれかに記載の生産支援システム。 (Technique 10)
the plurality of units include a head spindle, a nozzle, and a feeder;
The production support system according to any one of Techniques 1 to 9, wherein the mounting error cause estimation unit estimates the probability of each of the head spindle, the nozzle, the feeder, and the components supplied by the feeder.
　（技術１１）
　複数のユニットから構成される実装機において発生した実装ミスに対する、前記複数のユニットそれぞれが前記実装ミスの要因となった確率を推定する生産支援方法であって、
　前記実装ミスに関する情報を含み、前記確率を推定する対象の第１実装ログを前記実装機から取得し、
　前記第１実装ログと、前記複数のユニットそれぞれにおける、実装ミス回数及び当該ユニットの不調の関係性に基づく第１推定モデルとに基づいて、前記複数のユニットそれぞれにおける前記確率を推定し、
　推定された推定結果を出力し、
　前記第１実装ログは、前記複数のユニットにおける生産数に関する情報及び実装ミス回数を含む
　生産支援方法。 (Technique 11)
1. A production support method for estimating a probability that each of a plurality of units caused a mounting error that occurred in a mounting machine configured with the plurality of units, the method comprising:
acquiring, from the mounting machine, a first mounting log that includes information about the mounting error and is a target for estimating the probability;
estimating the probability for each of the plurality of units based on the first mounting log and a first estimation model based on a relationship between the number of mounting errors in each of the plurality of units and a malfunction of the unit;
Output the estimated estimation results,
The first mounting log includes information regarding the number of productions in the plurality of units and the number of mounting errors.
　（技術１２）
　技術１１に記載の生産支援方法をコンピュータに実行させるためのプログラム。 (Technique 12)
A program for causing a computer to execute the production support method described in Technology 11.
　本開示は、実装機を用いた生産を支援する支援システム等に有用である。 This disclosure is useful for support systems that support production using mounting machines.
　１　　生産支援システム
　１０　　実装機
　２０　　係数推定装置
　２１、３１　　ミス回数前処理部
　２２、３２　　補正量前処理部
　２３　　非線形回帰係数推定部（第１係数推定部）
　２４　　線形回帰係数推定部（第２係数推定部）
　３０　　要因確率推定装置
　３３　　実装ミス要因推定部
　３３ａ　　第１推定モデル
　３４　　テープ送り精度推定部
　３４ａ　　第２推定モデル
　３５、３６、３７、３８　　集計部
　４０　　表示装置
　Ｌ１　　第１実装ログ
　Ｌ２　　第２実装ログ（第３実装ログ）
　Ｍ　　検査計測値 REFERENCE SIGNS LIST 1 Production support system 10 Mounting machine 20 Coefficient estimation device 21, 31 Error count preprocessing unit 22, 32 Correction amount preprocessing unit 23 Nonlinear regression coefficient estimating unit (first coefficient estimating unit)
24 Linear regression coefficient estimator (second coefficient estimator)
30: Factor probability estimation device 33: Mounting error factor estimation unit 33a: First estimation model 34: Tape feed accuracy estimation unit 34a: Second estimation model 35, 36, 37, 38: Counting unit 40: Display device L1: First mounting log L2: Second mounting log (third mounting log)
M Inspection measurement value

Claims (12)

  1. 　複数のユニットから構成される実装機において発生した実装ミスに対する、前記複数のユニットそれぞれが前記実装ミスの要因となった確率を推定する生産支援システムであって、
    　前記実装ミスに関する情報を含み、前記確率を推定する対象の第１実装ログを前記実装機から取得する取得部と、
    　前記第１実装ログと、前記複数のユニットそれぞれにおける、実装ミス回数及び当該ユニットの不調の関係性に基づく第１推定モデルとに基づいて、前記複数のユニットそれぞれにおける前記確率を推定する実装ミス要因推定部と、
    　前記実装ミス要因推定部の推定結果を出力する出力部とを備え、
    　前記第１実装ログは、前記複数のユニットにおける生産数に関する情報及び実装ミス回数を含む
    　生産支援システム。     1. A production support system that estimates a probability that each of a plurality of units caused a mounting error that occurred in a mounting machine configured with the plurality of units, the system comprising:
    an acquisition unit that acquires, from the mounting machine, a first mounting log that includes information about the mounting error and is a target for estimating the probability;
    a mounting error cause estimation unit that estimates the probability for each of the plurality of units based on the first mounting log and a first estimation model based on a relationship between the number of mounting errors in each of the plurality of units and a malfunction of the unit;
    an output unit that outputs an estimation result of the mounting error cause estimation unit;
    The first mounting log includes information regarding the number of productions in the plurality of units and the number of mounting errors.
  2. 　前記第１推定モデルは、前記複数のユニットそれぞれにおける、前記生産数に関する情報及び前記実装ミス回数の分布に基づく前記複数のユニットそれぞれの第１回帰係数を説明変数とし、前記確率を目的変数とする重回帰モデルである
    　請求項１に記載の生産支援システム。     2. The production support system according to claim 1, wherein the first estimation model is a multiple regression model in which a first regression coefficient of each of the plurality of units based on information on the production volume and a distribution of the number of mounting errors in each of the plurality of units is used as an explanatory variable, and the probability is used as a target variable.
  3. 　前記第１実装ログより前に取得された前記実装機の第２実装ログに含まれる前記生産数に関する情報と前記実装ミス回数との分布に基づいて、前記複数のユニットそれぞれの前記第１回帰係数を推定する第１係数推定部をさらに備える
    　請求項２に記載の生産支援システム。     3. The production support system according to claim 2, further comprising a first coefficient estimator that estimates the first regression coefficient for each of the plurality of units based on a distribution of information related to the production volume and the number of mounting errors included in a second mounting log of the mounting machine acquired prior to the first mounting log.
  4. 　前記出力部は、前記実装ミスに対する前記複数のユニットそれぞれの前記確率を表示する
    　請求項１～３のいずれか１項に記載の生産支援システム。     4. The production support system according to claim 1, wherein the output unit displays the probability of the mounting error for each of the plurality of units.
  5. 　前記複数のユニットは、部品を供給するテープフィーダと、前記部品を吸着するノズルとを含み、
    　前記第１実装ログと、前記テープフィーダのテープ送り精度及び前記部品の吸着位置ずれに関する量の関係性に基づく第２推定モデルとに基づいて、前記テープ送り精度を推定するテープ送り精度推定部をさらに備え、
    　前記第１実装ログは、さらに、前記ノズルを制御するための制御量に関する情報を含む
    　請求項１～３のいずれか１項に記載の生産支援システム。     the plurality of units include a tape feeder that supplies components and a nozzle that picks up the components;
    a tape feeding accuracy estimation unit that estimates the tape feeding accuracy based on the first mounting log and a second estimation model that is based on a relationship between a tape feeding accuracy of the tape feeder and an amount related to a pickup position deviation of the component,
    4. The production support system according to claim 1, wherein the first mounting log further includes information regarding a control amount for controlling the nozzle.
  6. 　前記第２推定モデルは、前記テープ送り精度及び前記部品の吸着位置ずれに関する量の関係を示す第２回帰係数を含む単回帰モデルである
    　請求項５に記載の生産支援システム。     6. The production support system according to claim 5, wherein the second estimation model is a simple regression model including a second regression coefficient indicating a relationship between the tape feeding accuracy and an amount related to a deviation in the component pickup position.
  7. 　前記第１実装ログより前に取得された前記実装機の第３実装ログに含まれる前記ノズルを制御するための制御量と、前記テープフィーダのテープ送り精度の測定値との分布に基づいて、前記複数のユニットそれぞれの前記第２回帰係数を推定する第２係数推定部をさらに備える
    　請求項６に記載の生産支援システム。     7. The production support system according to claim 6, further comprising a second coefficient estimator that estimates the second regression coefficient for each of the plurality of units based on a distribution of a control amount for controlling the nozzle included in a third mounting log of the mounting machine acquired before the first mounting log, and a distribution of measured values of tape feeding accuracy of the tape feeder.
  8. 　前記出力部は、前記テープ送り精度推定部により推定された前記テープ送り精度に関する情報を表示する
    　請求項５に記載の生産支援システム。     The production support system according to claim 5 , wherein the output unit displays information regarding the tape feeding accuracy estimated by the tape feeding accuracy estimation unit.
  9. 　前記実装機は、前記複数のユニットの状態を直接的に計測するセンサを備えていない
    　請求項１～３のいずれか１項に記載の生産支援システム。     4. The production support system according to claim 1, wherein the mounting machine does not include a sensor that directly measures the states of the plurality of units.
  10. 　前記複数のユニットは、ヘッドスピンドル、ノズル及びフィーダを含み、
    　前記実装ミス要因推定部は、前記ヘッドスピンドル、前記ノズル、前記フィーダ及び前記フィーダが供給する部品それぞれの前記確率を推定する
    　請求項１～３のいずれか１項に記載の生産支援システム。     the plurality of units include a head spindle, a nozzle, and a feeder;
    4. The production support system according to claim 1, wherein the mounting error cause estimation unit estimates the probability of each of the head spindle, the nozzle, the feeder, and the components supplied by the feeder.
  11. 　複数のユニットから構成される実装機において発生した実装ミスに対する、前記複数のユニットそれぞれが前記実装ミスの要因となった確率を推定する生産支援方法であって、
    　前記実装ミスに関する情報を含み、前記確率を推定する対象の第１実装ログを前記実装機から取得し、
    　前記第１実装ログと、前記複数のユニットそれぞれにおける、実装ミス回数及び当該ユニットの不調の関係性に基づく第１推定モデルとに基づいて、前記複数のユニットそれぞれにおける前記確率を推定し、
    　推定された推定結果を出力し、
    　前記第１実装ログは、前記複数のユニットにおける生産数に関する情報及び実装ミス回数を含む
    　生産支援方法。     1. A production support method for estimating a probability that each of a plurality of units caused a mounting error that occurred in a mounting machine configured with the plurality of units, the method comprising:
    acquiring, from the mounting machine, a first mounting log that includes information about the mounting error and is a target for estimating the probability;
    estimating the probability for each of the plurality of units based on the first mounting log and a first estimation model based on a relationship between a number of mounting errors in each of the plurality of units and a malfunction of the unit;
    Output the estimated estimation results,
    The first mounting log includes information regarding the number of productions in the plurality of units and the number of mounting errors.
  12. 　請求項１１に記載の生産支援方法をコンピュータに実行させるためのプログラム。 A program for causing a computer to execute the production support method described in claim 11.
PCT/JP2023/026177 2022-11-17 2023-07-18 Production assistance system, production assistance method, and program WO2024105931A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2022-184454 2022-11-17
JP2022184454 2022-11-17

Publications (1)

Publication Number Publication Date
WO2024105931A1 true WO2024105931A1 (en) 2024-05-23

Family

ID=91084422

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2023/026177 WO2024105931A1 (en) 2022-11-17 2023-07-18 Production assistance system, production assistance method, and program

Country Status (1)

Country Link
WO (1) WO2024105931A1 (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009063740A1 (en) * 2007-11-14 2009-05-22 Yamaha Motor Co., Ltd. Component feeding method, surface mounting machine, feeder and carriage
WO2019013196A1 (en) * 2017-07-14 2019-01-17 パナソニックＩｐマネジメント株式会社 Manufacturing management device, manufacturing system, and manufacturing management method
WO2019167845A1 (en) * 2018-02-27 2019-09-06 パナソニックＩｐマネジメント株式会社 Management device, management method, and component mount system
JP2020136381A (en) * 2019-02-15 2020-08-31 パナソニックＩｐマネジメント株式会社 Component loading device and component loading method
WO2021235201A1 (en) * 2020-05-19 2021-11-25 パナソニックＩｐマネジメント株式会社 Quality change detection method, quality change detection system, and program
JP2022096212A (en) * 2020-12-17 2022-06-29 パナソニックＩｐマネジメント株式会社 State estimation device, mounting system, and state estimation method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009063740A1 (en) * 2007-11-14 2009-05-22 Yamaha Motor Co., Ltd. Component feeding method, surface mounting machine, feeder and carriage
WO2019013196A1 (en) * 2017-07-14 2019-01-17 パナソニックＩｐマネジメント株式会社 Manufacturing management device, manufacturing system, and manufacturing management method
WO2019167845A1 (en) * 2018-02-27 2019-09-06 パナソニックＩｐマネジメント株式会社 Management device, management method, and component mount system
JP2020136381A (en) * 2019-02-15 2020-08-31 パナソニックＩｐマネジメント株式会社 Component loading device and component loading method
WO2021235201A1 (en) * 2020-05-19 2021-11-25 パナソニックＩｐマネジメント株式会社 Quality change detection method, quality change detection system, and program
JP2022096212A (en) * 2020-12-17 2022-06-29 パナソニックＩｐマネジメント株式会社 State estimation device, mounting system, and state estimation method

Similar Documents

Publication Publication Date Title
CN107734955B (en) Inspection device for surface mounting line, quality management system, and recording medium
US8406503B2 (en) Mounted component inspection apparatus, component mounting machine comprising the mounted component inspection apparatus, and mounted component inspection method
JP5926881B2 (en) Image processing component data creation method and image processing component data creation device
CN104684270A (en) System for monitoring and estimating disorder of SMT device and method of operating same
US9891975B2 (en) Failure prediction system of controller
JP5959444B2 (en) Defect cause estimation (classification) method by printing inspection equipment
JP2007194253A (en) Mounting system
CN104684271A (en) A system for monitoring and predicting faults of SMT equipment and a method for operating the same
US11503753B2 (en) Substrate processing management system
JP2019021008A (en) Equipment element maintenance analysis system and facility element maintenance analysis method
JP3772906B1 (en) Information processing apparatus, information processing method, program, and computer-readable recording medium recording the program
JP2002031606A (en) Apparatus and method for evaluating quality, apparatus and method for displaying quality, and quality evaluation system
WO2024105931A1 (en) Production assistance system, production assistance method, and program
EP3944730B1 (en) Device for estimating cause of mounting error, and method for estimating cause of mounting error
US8689435B2 (en) Mounting system for mounting electronic components
JP2002251212A (en) Method for quality control and system for the same and recording medium with its program recorded
WO2019013196A1 (en) Manufacturing management device, manufacturing system, and manufacturing management method
JP6870031B2 (en) Cream solder printing process inspection system
KR101640936B1 (en) Method of Analyzing Defect in Printing Process and Computer Readable Media Storing The Same
JP2007194252A (en) Mounting system
JP7122508B2 (en) Equipment element maintenance analysis system and equipment element maintenance analysis method
JP7462509B2 (en) Factor estimation device, factor estimation system, and program
JP7466746B2 (en) Countermeasure information presentation device and countermeasure information presentation method
JP7478958B2 (en) Component mounting system, component mounting method, management device, and program
KR101012703B1 (en) Method for detecting of lead frame scrap badness

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: 23891093

Country of ref document: EP

Kind code of ref document: A1