CN114747307A

CN114747307A - Production data generation device, production data generation method, and program

Info

Publication number: CN114747307A
Application number: CN202080080081.4A
Authority: CN
Inventors: 志垣荣滋; 山崎琢也; 横井敬明; 岩田维里; 谭陨林; 清水太一
Original assignee: Panasonic Intellectual Property Management Co Ltd
Current assignee: Panasonic Intellectual Property Management Co Ltd
Priority date: 2019-12-02
Filing date: 2020-11-16
Publication date: 2022-07-12
Also published as: WO2021111851A1; DE112020005919T5; JPWO2021111851A1; JP7531127B2

Abstract

Provided is a production data generation device capable of setting an appropriate operation parameter. A production data generation device (100) is provided with: a model selection unit (103) that selects at least 1 operating parameter model (Pm) from a plurality of operating parameter models (Pm) that are different from each other; a parameter estimation unit (105) that estimates an operation parameter (M) that is an operation condition of a component mounting device (M4) or (M5) for mounting a component (P) to a board (B), on the basis of the selected at least 1 operation parameter model (Pm) and component information (d) relating to the component (P) to be mounted on the board (B); and a data generation unit (102) that generates production data (Dp) including the part data (Dc) having the part information (d) and the operation parameter (m).

Description

Production data generation device, production data generation method, and program

Technical Field

The present disclosure relates to an apparatus, a method, and a program and the like for generating production data for producing a mounting substrate.

Background

A component mounting line including at least 1 component mounting device produces a mounting substrate by mounting a component on a substrate. At this time, the component mounting line mounts the component on the substrate based on the production data. The production data includes identification information of each component mounted on the substrate and a mounting order of the components. In addition, the production data sometimes includes component data of each component mounted on the substrate. The component data includes information indicating the shape of the mounted component and the like and operation parameters of the component mounting apparatus that processes the component. The operation parameters include, for example, a suction speed and a mounting load of a mounting head included in the component mounting apparatus.

For example, in the mounting substrate manufacturing system of patent document 1, the control parameters (or the machine parameters) corresponding to the operation parameters are corrected based on the results of the component mounting work. This enables the component data to be corrected appropriately and efficiently.

Prior art documents

Patent document

Patent document 1: JP-A2019-4129

Disclosure of Invention

Problems to be solved by the invention

However, the mounting substrate manufacturing system of patent document 1 has a problem that it is sometimes difficult to set appropriate operation parameters.

Accordingly, the present disclosure provides a production data generation device and the like capable of setting appropriate operation parameters.

Means for solving the problems

A production data generation device according to an aspect of the present disclosure includes: a model selection unit that selects at least 1 learning model from a plurality of different learning models that represent relationships between operating conditions of a component mounting apparatus for mounting components on a substrate and the components, respectively; a parameter estimation unit configured to estimate an operation parameter, which is an operation condition of a component mounting apparatus for mounting a component to be mounted on a substrate, based on the at least 1 learning model selected and component information on the component to be mounted on the substrate; and a data generation unit that generates production data including the component information and the operation parameter.

These general and specific aspects can be realized by a system, a method, an integrated circuit, a computer program, or a computer-readable recording medium such as a CD-ROM, or any combination of a system, a method, an integrated circuit, a computer program, and a recording medium. Further, the recording medium may be a non-transitory recording medium.

Effects of the invention

The production data generation device of the present disclosure can set appropriate operation parameters.

In addition, further advantages and effects in one aspect of the present disclosure will be apparent from the description and the accompanying drawings. The advantages and/or effects are provided by the features described in the several embodiments and the description and drawings, respectively, but not necessarily all of them need to be provided to obtain 1 or more of the same features.

Drawings

Fig. 1 is a diagram showing an example of the configuration of a production system in embodiment 1.

Fig. 2 is a diagram showing an example of the structure of the component mounting apparatus according to embodiment 1.

Fig. 3 is a view partially showing an example of a cross section a-a in fig. 2.

Fig. 4 is a block diagram showing the functional configurations of the production data generation apparatus and the component mounting line in embodiment 1.

Fig. 5 is a diagram showing an example of a component library in embodiment 1.

Fig. 6 is a diagram showing an example of production data in embodiment 1.

Fig. 7A is a diagram showing an example of a plurality of learning models managed in units of time held by the learning model holding unit in embodiment 1.

Fig. 7B is a diagram showing another example of a plurality of learning models managed in units of time held by the learning model holding unit in embodiment 1.

Fig. 8 is a diagram showing an example of a plurality of learning models managed in units of production facilities held by the learning model holding unit in embodiment 1.

Fig. 9A is a diagram showing an example of a plurality of learning models managed in units of production types held by the learning model holding unit in embodiment 1.

Fig. 9B is a diagram showing an example of a plurality of learning models managed in units of production types and production facilities held by the learning model holding unit in embodiment 1.

Fig. 10A is a diagram for explaining an outline of the operation parameter estimation processing in embodiment 1.

Fig. 10B is a diagram for explaining an outline of the learning process of the operation parameter model in embodiment 1.

Fig. 11 is a diagram showing an example of the overall processing in embodiment 1.

Fig. 12 is a diagram showing another example of the overall processing in embodiment 1.

Fig. 13 is a flowchart showing a processing operation of the production data generating apparatus according to embodiment 1.

Fig. 14 is a diagram showing an example of the configuration of the production system in embodiment 2.

Fig. 15 is a block diagram showing the functional configurations of the production management apparatus, the component mounting line, and the processing apparatus in embodiment 2.

Fig. 16 is a diagram showing an example of the overall processing in embodiment 2.

Fig. 17A is a diagram showing an example of screening information generated based on the inspection result of the mounting substrate in embodiment 2.

Fig. 17B is a diagram showing an example of screening information generated based on the actual mounting result of the component mounting line in embodiment 2.

Fig. 18A is a diagram showing an example of filtering information generated by selecting a component in embodiment 2.

Fig. 18B is a diagram showing an example of screening information generated by substrate selection in embodiment 2.

Fig. 19 is a flowchart showing a processing operation of the production management apparatus according to embodiment 2.

Detailed Description

In order to solve the above problem, a production data generation device according to an aspect of the present disclosure includes: a model selection unit that selects at least 1 learning model from a plurality of different learning models that represent relationships between operating conditions of a component mounting apparatus for mounting components on a substrate and the components, respectively; a parameter estimation unit configured to estimate an operation parameter, which is an operation condition of a component mounting apparatus for mounting a mounting target component on a substrate, based on the at least 1 learning model selected and component information on the mounting target component mounted on the substrate; and a data generation unit that generates production data including the component information and the operation parameter. For example, the part information may indicate at least 1 of a size, a shape, an appearance, a category, and a supply manner for supplying the part corresponding to the part information. Further, the operation parameter may be a parameter related to at least 1 of transfer, recognition, suction, and mounting of the component by the component mounting device.

Thus, since at least 1 learning model is selected from a plurality of different learning models and used for estimation of the operation parameter, it is possible to improve the possibility of estimating an appropriate operation parameter for the mounting target component. Therefore, appropriate operation parameters can be set. Further, when the component data having the operation parameters and the component information is included in the production data and the production data is used for mounting the component on the substrate by the component mounting apparatus, the mounting substrate with good quality can be produced. That is, the quality of the mounting substrate can be improved.

The operation parameter may be not only 1 parameter but also a set of a plurality of parameters. In this case, when the plurality of learning models are selected by the model selecting unit, the parameter estimating unit may estimate the plurality of parameters included in the operation parameter from the selected plurality of learning models.

Further, the production data generation device may further include: a data acquisition unit that acquires actual performance production data that includes part information relating to a mounted part and actual performance part data of an operation parameter used in mounting the mounted part and that is used by a part mounting device; and a learning unit that performs learning using the actual performance component data as teaching data to update the relationship represented by a learning model corresponding to the acquired actual performance production data among the plurality of learning models.

The operating parameters of the actual performance part data included in the actual performance production data are used in the mounting of the mounted parts, and at this time, correction and the like are performed. That is, the operation parameters are corrected so that a mounting substrate of better quality is produced. Therefore, by using the actual performance part data having the operation parameters as teaching data in learning of the learning model, the learning model can be further optimized. As a result, when the learning model is selected by the model selection unit, the estimation accuracy of the operation parameter can be improved.

Further, the plurality of learning models may be associated with different periods, and the learning unit may learn the learning model associated with the period during which the actual performance production data is acquired.

For example, 1 learning model out of the plurality of learning models is associated with the entire period (for example, the entire period from the past to the present), and the remaining at least 1 learning model is associated with each of the different ages. The different generations are, for example, 1990, 2000, 2010, and the like. Thus, a learning model corresponding to the entire period or an arbitrary age is selected from these learning models and used for estimation of the operation parameter. Therefore, the appropriate operation parameter corresponding to the period can be estimated for the component to be mounted.

Further, the plurality of learning models may be associated with different production facilities, and the learning unit may learn the learning model associated with the production facility including the component mounting apparatus using the actual performance production data.

For example, the production facility may be a component mounting apparatus, may be 1 component mounting line including the component mounting apparatus, or may be a facility including a plurality of component mounting lines. In this case, for example, 1 learning model out of the plurality of learning models is associated with a production facility including all component mounting lines arranged in a plant, and the remaining at least 1 learning model is associated with a different component mounting line. Thus, a learning model corresponding to all or any of the component mounting lines is selected from these learning models and used for estimation of the operation parameters. Therefore, the appropriate operation parameters corresponding to the production facility can be estimated for the component to be mounted.

Further, the plurality of learning models may be associated with different types of mounting boards, and the learning unit may learn the learning model corresponding to the type of mounting board produced using the actual performance production data.

For example, the type of the mounting substrate is a mass production type or a trial production type. In this case, for example, 1 learning model out of the plurality of learning models is associated with the mass production type, and the remaining 1 learning model is associated with the trial production type. Thus, a learning model corresponding to the mass production type or the trial production type is selected from these learning models and used for estimation of the operation parameters. Therefore, the appropriate operation parameter according to the type of the mounting substrate can be estimated for the mounting target component.

The embodiments are described below in detail with reference to the accompanying drawings.

The embodiments described below are all general or specific examples. The numerical values, shapes, materials, constituent elements, arrangement positions and connection modes of the constituent elements, steps, order of the steps, and the like shown in the following embodiments are examples, and the gist thereof is not intended to limit the present disclosure. In the following description, among the components in the embodiments, components not described in the independent claims indicating the highest concept are described as arbitrary components.

The drawings are schematic and are not necessarily strictly illustrated. In the drawings, the same constituent elements are denoted by the same reference numerals.

(embodiment mode 1)

[ production System ]

Fig. 1 is a diagram showing an example of the configuration of the production system in the present embodiment.

The production system 1 in the present embodiment includes 3 component mounting lines L1 to L3 and a production data generation device 100.

Each of the component mounting lines L1 to L3 is an example of a production facility of a mounting substrate, and the mounting substrate is produced by performing a solder printing operation, a component mounting operation, a reflow operation, and the like on a substrate carried in from the upstream side, and the produced mounting substrate is carried out to the downstream side.

The production data generation device 100 generates and outputs production data for producing the mounting substrates for the component mounting lines L1 to L3, respectively. The production data generation apparatus 100 can communicate with these component mounting lines L1 to L3 wirelessly or by wire. The wireless may be Wi-Fi (registered trademark), Bluetooth (registered trademark), ZigBee, or specific low power wireless.

The component mounting line L1 includes a line management device 200, a board supply device M1, a board delivery device M2, a solder printing device M3, component mounting devices M4 and M5, a reflow device M6, and a board collection device M7. The devices other than the line management device 200 included in the component mounting line L1 are connected in series by arranging the substrate supply device M1, the substrate delivery device M2, the solder printing device M3, the component mounting devices M4 and M5, the reflow device M6, and the substrate collection device M7 in this order. Each device other than the line management device 200 is hereinafter referred to as a working device. The component mounting line L1 may not include all of the above-described working devices as long as it includes the substrate supply device M1, at least 1 component mounting device, and the substrate recovery device M7. The component mounting line L1 may include, in addition to the above-described working devices, a solder applying device that applies solder to a substrate, a component inserting machine that mounts a radial component or an axial component to a substrate, and the like.

The line management device 200 acquires the production data generated by the production data generation device 100 from the production data generation device 100, and causes each of the working devices included in the component mounting line L1 to execute production of the mounting substrate based on the production data.

The substrate supply device M1 supplies the substrates used in the mounting substrates produced in the component mounting line L1 to the solder printing device M3 via the substrate delivery device M2. The solder printing apparatus M3 performs the solder printing operation described above. That is, the solder printing apparatus M3 prints solder on the substrate delivered from the substrate delivery apparatus M2 by screen printing.

The component mounting apparatuses M4 and M5 each perform the above-described component mounting operation of mounting at least 1 component on the substrate. The component mounting line L1 includes 2 stage component mounting devices M4 and M5, but the number of the devices is not limited to 2, and may be 1, or 3 or more. It can be said that the mounting substrate is substantially produced by the component mounting work performed by these component mounting apparatuses M4 and M5.

The reflow apparatus M6 performs the above-described reflow operation. That is, the reflow apparatus M6 heats the component-mounted substrate carried in from the component mounting apparatuses M4 and M5, hardens the solder on the substrate, and bonds the electrode portions of the substrate and the component. Specifically, the reflow apparatus M6 melts and solidifies the solder for component bonding by performing heating following a given heating curve. Thereby, the component is joined to the substrate by solder bonding. The substrate collection apparatus M7 collects the substrate subjected to the solder bonding from the reflow apparatus M6.

The component mounting lines L2 and L3 also have the same configuration as the component mounting line L1. In the present embodiment, the component mounting lines L1 to L3 have the same configuration, but may have different configurations. Further, in the present embodiment, the component mounting lines L1 to L3 include the wire management device 200, but the wire management device 200 may be independently provided from the component mounting lines L1 to L3, or may be incorporated into the component mounting lines L1 to L3.

[ component mounting device ]

Fig. 2 is a diagram showing an example of the structure of the component mounting apparatus M4. In the present embodiment, the component mounting apparatus M5 also has the same configuration as the component mounting apparatus M4. In this embodiment, the conveying direction of the substrate B is referred to as an X-axis direction, and a direction perpendicular to the X-axis direction is referred to as a Y-axis direction. The X-axis direction and the Y-axis direction are directions along a horizontal plane. Further, a direction perpendicular to the X-axis direction and the Y-axis direction is referred to as a Z-axis direction. The X-axis direction positive side and the negative side are the downstream side and the upstream side in the transport direction of the substrate B, respectively, and the Y-axis direction positive side and the negative side are the rear side (or the depth side) and the front side (or the near side) in the front-rear direction, respectively. The positive side and the negative side in the Z-axis direction are the upper side and the lower side in the up-down direction, respectively. An upper surface of the component mounting apparatus M4 is shown in fig. 2.

The component mounting device M4 includes a base 4, a substrate conveyance mechanism 5, 2 component supply units 6, 2X-axis beams 9, a Y-axis beam 8, 2 mounting heads 10, 2 component recognition cameras 11, and 2 substrate recognition cameras 12.

The substrate transport mechanism 5 includes 2 guide rails along the X-axis direction, and is disposed at the center of the base 4. The substrate transport mechanism 5 transports the substrate B carried in from the upstream side, and positions and holds the substrate B at a position for performing component mounting work.

The 2 component supply units 6 are arranged to sandwich the substrate transport mechanism 5 in the Y-axis direction. A plurality of feeders 7 are arranged in parallel in the X-axis direction in each component supply unit 6. The feeder 7 pitch-feeds the component carrier tape containing the components in the carrier tape feeding direction, thereby supplying the components to a position where the mounting head 10 takes out the components (hereinafter referred to as a component taking-out position).

Further, a tray feeder, a tube feeder, a bulk feeder, or the like may be disposed in the component supply unit 6. The tray feeder supplies the components from a tray in which the components are stored. The tube feeder supplies the component from a tubular housing in which the component is housed. The bulk feeder supplies components from a bulk case in which the components are stored.

The Y-axis beam 8 is arranged along the Y-axis direction at one end (right side in fig. 2) in the X-axis direction of the upper surface of the base 4. The 2X-axis beams 9 are coupled to the Y-axis beam 8 so as to be movable in the Y-axis direction in a state along the X-axis direction.

The mounting head 10 is movably fitted to each of the 2X-axis beams 9 in the X-axis direction. The mounting head 10 includes a plurality of suction modules 10a which can be raised and lowered while sucking and holding the components. Suction nozzles 10b are provided at the respective front ends of the suction modules 10a (see fig. 3).

The 2 mounting heads 10 are moved in the X-axis direction and the Y-axis direction by driving the Y-axis beam 8 and the X-axis beam 9, respectively. Thereby, the 2 mounting heads 10 respectively suck and take out the component suction nozzles 10B from the component taking-out positions of the feeders 7 arranged in the component supply sections 6 corresponding to the mounting heads 10, and mount the component suction nozzles on the mounting points (or mounting positions) of the boards B positioned in the board conveying mechanism 5.

The 2 component recognition cameras 11 are respectively disposed between one of the 2 component supply units 6 and the substrate transport mechanism 5. The component recognition camera 11 picks up an image of the component when the mounting head 10, which has taken out the component from the component supply part 6, moves above the component recognition camera 11. That is, the component recognizing camera 11 recognizes the holding posture of the component held by the mounting head 10 by imaging the component.

The substrate recognition camera 12 is mounted on the tray 9a on which the mounting head 10 is mounted. Thus, the substrate recognition camera 12 moves integrally with the mounting head 10. The substrate recognition camera 12 moves above the substrate B positioned on the substrate transport mechanism 5 in accordance with the movement of the mounting head 10, and recognizes the position of the substrate B by imaging a substrate mark (not shown) provided on the substrate B. In mounting of the component onto the substrate B by the mounting head 10, the mounting position is corrected based on the recognition result of the component by the component recognition camera 11 and the recognition result of the position of the substrate B by the substrate recognition camera 12.

Fig. 3 is a view partially showing an example of a cross section a-a in fig. 2. The component mounting device M4 has a function of mounting the component P on the substrate B.

As shown in fig. 3, the component supply unit 6 includes: a feeder base 13 a; a plurality of feeders 7 mounted on the feeder base 13 a; and a carriage 13 for supporting the feeder base 13 a.

The carriage 13 is configured to be detachably attached to the component mounting devices M4 and M5, and further includes a cassette holder 15. The magazine 15 is configured to hold a plurality of component reels C. The component reel C receives the component carrier tape 14 in a wound state. The component reels C are held at the upper holding position Hu or the lower holding position Hd of the cassette holder 15. The parts carrier tape 14 pulled out from the parts reel C held by the magazine 15 is mounted on the feeder 7. The feeder 7 may be disposed on a feeder base 13a provided on the base 4 without using the carriage 13. The component reel C may be held by the carriage 13 instead of the magazine 15.

In the present embodiment, as described above, the component mounting apparatuses M4 and M5 have the same configuration, but may have different configurations.

[ functional Structure of production data Generation apparatus and component mounting line ]

Fig. 4 is a block diagram showing the functional configurations of the production data generation apparatus 100 and the component mounting lines L1 to L3.

The production data generation device 100 includes a control unit 101, a data generation unit 102, a model selection unit 103, a learning unit 104, a parameter estimation unit 105, a display unit 106, an input/output unit 107, a data acquisition unit 108, a production data holding unit DB1, a learning model holding unit DB2, and a component library holding unit DB 3.

The model selecting unit 103 selects at least 1 learning model from the plurality of learning models held in the learning model holding unit DB 2.

The learning model holding unit DB2 holds the plurality of learning models. These learning models are different models from each other, and each of the learning models represents a relationship between an operation condition of the component mounting apparatus M4 or M5 for mounting the component P on the board B and the component P.

The parameter estimation unit 105 estimates an operation parameter, which is an operation condition of the component mounting device M4 or M5. That is, the parameter estimation unit 105 estimates the operation parameters for mounting the mounting target component P on the board B based on the at least 1 learning model selected by the model selection unit 103 and the component information on the mounting target component P mounted on the board B.

The data generation unit 102 generates production data including the component data having the component information and the operation parameters. Here, the production data indicates, for example, the mounting order of at least 1 component P mounted on the substrate B and the position where these components P are mounted on the substrate B (i.e., the mounting position described above), and includes the component data of each of the at least 1 component P. Further, the component data of each component P is held in the component library holding part DB 3. That is, the component library holding part DB3 holds a component library including component data of each of the plurality of types of components P. Therefore, if the component data of the component P mounted on the substrate B is included in the component library, the data generating unit 102 selects the component data of the component P from the component library, and generates production data including the selected component data. On the other hand, if the component data of the component P mounted on the substrate B is not included in the component library, the data generation unit 102 generates production data including component data including the component information of the component P and the operation parameters estimated as described above.

The data generating unit 102 generates and outputs such production data for the component mounting lines L1 to L3, respectively, and stores the production data in the production data holding unit DB 1.

The data acquisition unit 108 acquires actual performance production data including component information on the mounted component P and actual performance component data of the operation parameters used for mounting the mounted component P, which is used by the component mounting device M4 or M5.

The actual performance production data is, for example, data obtained by correcting or adjusting the production data generated by the data generation unit 102. That is, the component mounting apparatuses M4 and M5 included in the component mounting lines L1 to L3 mount the component P on the substrate B based on the production data, but a defective mounting substrate may be produced by the mounting. In such a case, in each of the component mounting lines L1 to L3, correction or adjustment of component data included in production data is performed in order to reduce the frequency of occurrence of defective products. Actual performance production data, including actual performance component data, is generated by such corrections or adjustments. The component mounting apparatuses M4 and M5 of the component mounting lines L1 to L3 mount the components P on the substrate B using the actual performance production data. The data obtaining unit 108 obtains the actual performance production data thus generated from the component mounting lines L1 to L3, respectively.

The learning unit 104 generates or updates a learning model by machine learning. In addition, the machine learning will be hereinafter referred to simply as learning. For example, the learning unit 104 generates a learning model by learning, and stores the generated learning model in the learning model holding unit DB 2. The learning unit 104 selects 1 learning model from the plurality of learning models held in the learning model holding unit DB2, and updates the selected learning model by learning. The actual performance production data acquired by the data acquisition unit 108 and used by each of the component mounting lines L1 to L3 is used for the learning by the learning unit 104.

That is, the learning unit 104 updates the relationship indicated by the learning model corresponding to the actual performance production data acquired by the data acquisition unit 108 among the plurality of learning models held in the learning model holding unit DB 2. In this case, the learning unit 104 updates the actual performance component data included in the actual performance production data by learning using the actual performance component data as teaching data. The learning model may be, for example, a neural network, a decision tree, or another model.

The display unit 106 displays the production data held in the production data holding unit DB1, the component library held in the component library holding unit DB3, and the like. Specific examples of the display portion 106 include, but are not limited to, a liquid crystal display, a plasma display, an organic EL (Electro-Luminescence) display, and the like.

The input/output unit 107 receives input data based on an operation of an operator of the production system 1, for example, and outputs the input data to the control unit 101. Such an input/output unit 107 includes, for example, a keyboard, a touch sensor, a touch pad, a mouse, and the like. The input/output unit 107 outputs data to and inputs data from the component mounting lines L1 to L3 and L1 to L3. The production data generated by the data generation unit 102 can be output to the component mounting lines L1 to L3 via the input/output unit 107. The input/output unit 107 may acquire the component information based on an operation by the operator and output the component information to the parameter estimation unit 105.

The control unit 101 controls each component other than the control unit 101 included in the production data generation apparatus 100. For example, the control unit 101 controls each component based on input data of the operator received by the input/output unit 107, and the like.

The production data holding part DB1, the learning model holding part DB2, and the component library holding part DB3 are recording media for holding production data, learning models, and component libraries. Such a recording medium is, for example, a hard disk, a ROM (Read Only Memory), a ram (random Access Memory), a semiconductor Memory, or the like. Such a recording medium may be volatile or nonvolatile.

The component mounting line L1 includes a work control unit 211, an input/output unit 212, a display unit 213, a work mechanism 214, and a production data holding unit DB 4. Further, each component other than the working mechanism 214 included in the component mounting line L1 may be provided in the line management device 200, or may be provided in an arbitrary working device different from the line management device 200.

The input/output unit 212 receives input data based on an operation of an operator of the production system 1, for example, and outputs the input data to the job control unit 211, similarly to the input/output unit 107 of the production data generation apparatus 100. Such an input/output unit 212 may include, for example, a keyboard, a touch sensor, a touch pad, a mouse, and the like. The input/output unit 212 outputs data to the production data generation device 100 and inputs data from the production data generation device 100. For example, the input/output unit 212 acquires production data from the production data generating apparatus 100 and stores the production data in the production data storage DB 4.

The display unit 213 displays the production data and the like held in the production data holding unit DB 4. Specific examples of the display portion 213 include, but are not limited to, a liquid crystal display, a plasma display, an organic EL display, and the like.

The working mechanism 214 is constituted by the mounting head 10 for producing the mounting substrate, the feeder 7, and the like.

The work control section 211 controls each component other than the work control section 211 included in the component mounting line L1. For example, the work control unit 211 controls each component based on input data of the operator received by the input/output unit 212. For example, the job control unit 211 causes the job mechanism 214 to execute at least 1 job among the solder printing job, the component mounting job, and the reflow job based on the production data held in the production data holding unit DB 4. The job control unit 211 corrects or adjusts the production data held in the production data holding unit DB4 in accordance with the input data of the operator received by the input/output unit 212. Thereby, the actual performance production data is generated. The job control unit 211 controls the input/output unit 212 to output the actual result production data from the input/output unit 212 to the production data generation apparatus 100.

The production data holding part DB4 is a recording medium for holding production data. Such a recording medium is, for example, a hard disk, RAM, ROM, semiconductor memory, or the like. Such a recording medium may be volatile or nonvolatile.

[ component library ]

Fig. 5 is a diagram showing an example of a component library.

The component library is composed of a plurality of component data Dc. Each of the plurality of part data Dc is data of 1 type of part P, and is associated with a part code for identifying the type of the part P. Such component data Dc includes component information d relating to the component P and an operation parameter M that is an operation condition of the component mounting device M4 or M5 for mounting the component P on the board B. In addition, an image, a numerical value, a term, or the like is shown in a blank part of each item in the component data Dc shown in fig. 5.

The part information d includes, for example, a shape diagram d1, size data d2, and part parameters d3 of the part P.

The shape map d1 illustrates the outline of the part P corresponding to the part data Dc. The size data d2 numerically represents information on the size of the component P, that is, the outer shape size, the number of leads, the lead pitch, the lead length, the lead width, the component height, and the like.

The component parameter d3 is attribute information for the component P. Such a part parameter d3 includes a part attribute d31, which is information on the part P itself, and carrier tape information d32, which is information on the part carrier tape 14 for supplying the part P by the feeder 7. The component attribute d31 represents, for example, the polarity, polarity flag, flag position, component type, and shape type of the component P. The carrier tape information d32 includes, for example, a carrier tape material of the component carrier tape 14, a carrier tape width indicating a width dimension of the component carrier tape 14, a carrier tape pitch indicating a carrier tape carrier pitch of the component carrier tape 14 of the feeder 7, and information on the color and material of the component carrier tape 14.

As described above, the component information d in the present embodiment indicates at least 1 of the size, shape, appearance, category, and supply method for supplying the component P corresponding to the component information d. The supply method corresponds to, for example, carrier tape information d 32.

The operation parameter M is a device parameter that defines an operation mode when the component P is mounted on the board B by the component mounting device M4 or M5. In the example shown here, the operation parameter M includes model information M1 indicating the type of the component mounting device M4 or M5, and nozzle setting information M2 indicating the type of the suction nozzle 10b used. The motion parameter m includes a speed parameter m3, identification information m4, gap information m5, suction information m6, mounting information m7, and the like.

The speed parameter m3 includes a lifting speed when the suction nozzle 10b performs a suction operation on the component P, a mounting speed when the mounting head 10 transfers the component P, and a carrier tape transfer speed when the feeder 7 transfers the component carrier 14. The identification information m4 is a parameter that specifies the manner of component identification. Specifically, the identification information m4 includes a camera type indicating the type of the component recognition camera 11 used, an illumination pattern indicating the illumination mode at the time of image pickup by the component recognition camera 11, and an identification speed indicating the moving speed of the mounting head 10 at the time of image pickup. The gap information m5 includes a suction gap when the component P is sucked by the suction nozzle 10B and a mounting gap when the sucked component P is mounted on the board B.

The suction information m6 includes a suction position shift and a suction angle indicating a shift amount of the suction nozzle 10b in sucking the component P. The mounting information m7 indicates the pressing load when the component P sucked by the suction nozzle 10B is mounted on the board B as the mounting load.

As described above, the operation parameter M in the present embodiment is a parameter related to at least 1 of the transfer, recognition, suction, and mounting of the component P by the component mounting device M4 or M5.

Each of the part information d and the operation parameter m included in the part data Dc in fig. 5 is an example, and may represent information other than the information shown in fig. 5, may represent the information shown in fig. 5 together with other information, or may represent only a part of the information shown in fig. 5. The number of pieces of information included in each of the part information d and the operation parameter m may be 1 or more.

In the present embodiment, when generating production data, the data generator 102 selects the component data Dc corresponding to the component P mounted on the substrate B from the component library held in the component library holding unit DB3, and generates production data including the component data Dc.

Further, if component data Dc corresponding to the component P mounted on the substrate B does not exist in the component library, the data generation unit 102 generates production data using the component data Dc not included in the component library. For example, the data generation unit 102 generates production data using the part data Dc having the part information d acquired by the input/output unit 107 and the operation parameter m estimated by the parameter estimation unit 105 for the part information d. The component information d acquired by the input/output unit 107 may be, for example, information acquired from CAD (Computer Aided Design) information relating to the component P mounted on the board B, or information input by an operation of an operator.

In addition, a default operation parameter m may be set for the component data Dc of the component library. When a default operation parameter m is set for the part data Dc selected from the part library, the data generation unit 102 may cause the parameter estimation unit 105 to estimate the operation parameter m corresponding to the part information d included in the part data Dc. When the operation parameter m is estimated by the parameter estimation unit 105, the data generation unit 102 replaces the default operation parameter m included in the part data Dc with the operation parameter m estimated by the parameter estimation unit 105. Then, the data generation unit 102 generates production data using the part data Dc subjected to the replacement of the operation parameter m.

All the information (i.e., parameters) included in the operation parameters m of the component data Dc may be defaults, or only some of the parameters may be defaults. When only a part of the parameters is the default, the parameter estimation unit 105 may estimate parameters that are substitutes for the default part of the parameters. The data generation unit 102 replaces the part of the operational parameters m included in the part data Dc with the parameters estimated by the parameter estimation unit 105. Then, the data generation unit 102 generates production data using the part data Dc subjected to the replacement of the part of the parameters.

[ production data ]

Fig. 6 is a diagram showing an example of the production data Dp.

In the production data Dp, for example, the component names and component codes of the respective plurality of components P to be mounted on the substrate B are arranged in the mounting order of the plurality of components P. In addition, the part code of the part P is a code for specifying the part data Dc of the part P from the part library. Further, the production data Dp indicates, for each of the plurality of components P, the assembly coordinates of the component P, the assembly angle, the identification information of the feeder 7, and the identification information of the mounting head 10 or the suction nozzle 10 b. The mounting coordinates of the component P are positions in the substrate B where the component P is mounted or mounted, and are also referred to as mounting points, mounting positions, or mounting positions. The mounting angle of the component P is an angle at which the suction nozzle 10B sucking the component P rotates about the central axis of the suction nozzle 10B as a rotation axis in order to mount the component P on the substrate B. The identification information of the feeder 7 corresponding to the component P is information for identifying the feeder 7 supplied with the component P. The identification information of the mounting head 10 corresponding to the component P is information for identifying the mounting head 10 used for mounting the component P on the substrate B.

For example, the production data Dp indicates, for the component P initially mounted on the board B, the component name "a component" of the component P, the component code "C001", the mounting coordinates "x 1, y 1", the mounting angle "θ 1", the identification information "F2" of the parts feeder 7, and the identification information "H3" of the mounting head 10.

The production data Dp in the present embodiment includes the part data Dc for each of the plurality of parts P mounted on the substrate B. For example, the production data Dp contains the part data Dc that establishes correspondence with the part code "C001" that the part P of the part name "a part" has.

[ learning model ]

Fig. 7A and 7B are diagrams illustrating an example of a plurality of learning models managed in units of time held by the learning model holding unit DB 2. The learning model in the present embodiment is also referred to as an operation parameter model hereinafter.

For example, as shown in fig. 7A, a plurality of operation parameter models Pm11 to Pm14, which are a plurality of learning models held in the learning model holding unit DB2, are managed in units of time. Specifically, the action parameter model Pm11 is generated by learning using actual performance production data used from 1990 to 1999. Similarly, the operating parameter model Pm12 is generated by learning using actual performance production data used from 2000 to 2009, and the operating parameter model Pm13 is generated by learning using actual performance production data used from 2010 to so far. Further, the operation parameter model Pm14 is generated by learning using actual performance production data used up to now from 1990.

Further, the plurality of operation parameter models Pm21 to Pm25, which are the plurality of learning models held in the learning model holding unit DB2, may be managed in units of time as shown in fig. 7B, or may be managed in time series.

For example, the action parameter model Pm21 is generated by learning using actual performance production data used on day 1, 7 months in 2019. The action parameter model Pm22 is generated by learning using the action parameter model Pm21 and actual performance production data used on day 7, month 2 of 2019. That is, the operation parameter model Pm22 is generated by learning using actual performance production data used between 7 months 1 day and 2 days in 2019.

Similarly, the action parameter model Pm23 is generated by learning using the action parameter model Pm22 and actual performance production data used on day 7, month 3 in 2019. That is, the operation parameter model Pm23 is generated by learning using actual performance production data used between 7 months 1 day and 3 days in 2019. The action parameter model Pm24 is generated by learning using the action parameter model Pm22 and actual performance production data used on 7, 4 and 2019. That is, the operation parameter model Pm24 is generated by learning using actual performance production data used between 7 months and 1 to 2 days in 2019 and used on 4 days. Therefore, the actual performance production data used on day 7, month 3 in 2019 is not reflected in the action parameter model Pm 24.

The action parameter model Pm25 is generated by learning using the action parameter model Pm24 and actual performance production data used on day 7/month 5 in 2019. That is, the operation parameter model Pm25 is generated by learning using actual performance production data used between 7 months 1 day and 2 days and between 4 days and 5 days in 2019. Therefore, the actual performance production data used on day 7, month 3 in 2019 is not reflected in the operating parameter model Pm25, similarly to the operating parameter model Pm 24.

As described above, in the present embodiment, a plurality of learning models (i.e., operation parameter models) are associated with different periods. In other words, the plurality of operation parameter models are managed in units of time. In this case, when learning is performed using the actual performance part data included in the actual performance production data as teaching data, the learning unit 104 learns a learning model corresponding to a period during which the actual performance production data is acquired.

For example, in the example shown in fig. 7A, when the data acquisition unit 108 of the production data generation apparatus 100 acquires actual performance production data in 2011, the learning unit 104 learns the operation parameter models Pm13 and Pm14 corresponding to 2011. In the example shown in fig. 7B, when the data acquisition unit 108 acquires actual performance production data on day 7/month 3 in 2019, the learning unit 104 learns the operating parameter model Pm22 or Pm23 corresponding to the period during which the actual performance production data is acquired.

Fig. 8 is a diagram showing an example of a plurality of learning models managed in units of production facilities held by the learning model holding unit DB 2.

For example, as shown in fig. 8, a plurality of operation parameter models Pm31 to Pm34, which are a plurality of learning models held in the learning model holding unit DB2, can be managed for each production facility. Specifically, the operating parameter model Pm31 is generated by learning using actual performance production data used in the component mounting line L1. Similarly, the operating parameter model Pm32 is generated by learning using actual performance production data used in the component mounting line L2, and the operating parameter model Pm33 is generated by learning using actual performance production data used in the component mounting line L3. The operation parameter model Pm34 is generated by learning using actual performance production data used in each of all the component mounting lines L1 to L3.

As described above, in the present embodiment, a plurality of learning models (i.e., operation parameter models) are associated with different production facilities. In other words, the plurality of operation parameter models are managed in units of production facilities. The production facility may be a component mounting line as described above, or may be a collection of a plurality of component mounting lines. The production facility may be 1 or more component mounting apparatuses, a floor on which a plurality of component mounting apparatuses or component mounting lines are disposed, or a factory. In this case, when learning is performed using the actual performance component data included in the actual performance production data as teaching data, the learning unit 104 learns a learning model corresponding to a production facility including the component mounting apparatus M4 or M5 using the actual performance production data.

For example, in the example shown in fig. 8, when the data acquisition unit 108 of the production data generation apparatus 100 acquires actual performance production data from the component mounting line L2, the learning unit 104 learns the operation parameter models Pm32 and Pm34 corresponding to the component mounting line L2.

Fig. 9A is a diagram showing an example of a plurality of learning models managed in units of production types held by the learning model holding unit DB 2.

For example, as shown in fig. 9A, a plurality of operation parameter models Pm41 to Pm44, which are a plurality of learning models held in the learning model holding unit DB2, can be managed for each production type. The production types include, for example, a trial production type and a mass production type. The trial type is a type of mounting substrate produced as a trial product, and the mass production type is a type of mounting substrate produced as a mass product. In the trial production type, an operation parameter that places more importance on quality than in the mass production type tends to be set, and in the mass production type, an operation parameter that places more importance on productivity than in the trial production type tends to be set. Therefore, in the trial production type and the mass production type, since the set operation parameters are different even for the same mounting board, the estimation accuracy is further improved so that the learning is performed for each production type. Specifically, the operation parameter model Pm41 is generated by learning actual performance production data used for production of the mounting substrate of the trial type T1. The operation parameter model Pm42 is generated by learning using actual performance production data used for producing a mounting board of a prototype type T2 different from the prototype type T1. The operation parameter model Pm43 is generated by learning using actual performance production data used in the production of the mass production type mounting substrate. The operation parameter model Pm44 is generated by learning using actual performance production data used for production of each of the mounting boards of all production types.

Fig. 9B is a diagram showing an example of a plurality of learning models managed in units of production types and production facilities held by the learning model holding unit DB 2.

For example, as shown in fig. 9B, a plurality of operation parameter models Pm51 to Pm54, which are a plurality of learning models held in the learning model holding unit DB2, can be managed for each combination of production type and production facility. In addition, in order to manage the parts for each production type, items for setting the production type may be provided in the parts data Dc.

Specifically, the operation parameter model Pm51 is generated by learning actual performance production data used for producing the mounting substrate of the trial type T1 by using the component mounting line L1. The operation parameter model Pm52 is generated by learning actual performance production data used for producing the mounting substrate of the trial type T2 by using the component mounting line L2. The operating parameter model Pm53 is generated by learning actual performance production data used for the production of the mass-production type mounting substrate by the component mounting line L3. The operation parameter model Pm54 is generated by learning actual performance production data used for producing the mounting boards of all production types by all the component mounting lines L1 to L3.

As described above, in the present embodiment, the plurality of learning models (i.e., operation parameter models) are associated with different types of production of the mounting boards. In other words, a plurality of learning models are managed in units of production types. In this case, the learning unit 104 learns a learning model corresponding to the type of the mounting board produced using the actual performance production data when performing learning using the actual performance component data included in the actual performance production data as teaching data.

For example, in the example shown in fig. 9A, when the data acquisition unit 108 of the production data generation apparatus 100 acquires actual performance production data of the trial type T1, the learning unit 104 learns the operation parameter models Pm41 and Pm44 corresponding to the trial type T1. In the example shown in fig. 9B, when the data acquisition unit 108 acquires actual performance production data of the trial type T2 from the component mounting line L2, the learning unit 104 learns the operation parameter models Pm52 and Pm54 corresponding to the trial type T2 and the component mounting line L2.

[ outline and flow of processing ]

Fig. 10A is a diagram for explaining an outline of the estimation process of the operating parameter m in the present embodiment.

The parameter estimation unit 105 acquires the component information d of the component P from the input/output unit 107, for example. The model selecting unit 103 selects, for example, 1 operating parameter model Pm from the plurality of operating parameter models Pm held in the learning model holding unit DB 2. Each of the plurality of operation parameter models Pm may be any one of operation parameter models Pm11 to Pm14, Pm21 to Pm25, Pm31 to Pm34, Pm41 to Pm44, and Pm51 to Pm54 shown in fig. 7A to 9B. The parameter estimation unit 105 estimates an operation parameter M, which is an operation condition of the component mounting apparatus M4 or M5 for mounting the component P indicated by the component information d on the board B, using the acquired component information d and the selected operation parameter model Pm. Then, the parameter estimation unit 105 outputs the part data Dc including the estimated operation parameter m and the part information d.

For example, when the plurality of operating parameter models Pm are managed in units of time as shown in fig. 7A, the model selecting unit 103 may select 1 operating parameter model Pm according to the manufacturing timing of the component P indicated by the component information d. For example, if the manufacturing time is 1990, the model selection unit 103 may select the operation parameter model Pm11 shown in fig. 7A. If the manufacturing time is unknown, the model selection unit 103 may select the operating parameter model Pm14 shown in fig. 7A. This makes it possible to select an appropriate operating parameter model Pm for estimating the operating parameter m for the component P.

In the case where the plurality of operating parameter models Pm are managed in time series as shown in fig. 7B, the model selection unit 103 may select 1 operating parameter model Pm updated on the latest date. For example, the model selection unit 103 may select the operating parameter model Pm25 shown in fig. 7B. In addition, when mounting boards using components similar to the component P are mass-produced in 2019, 7, 3, the model selection unit 103 may select the operation parameter model Pm23 shown in fig. 7B. This makes it possible to select an appropriate operating parameter model Pm for estimating the operating parameter m for the component P.

In the case where a plurality of operation parameter models Pm are managed on a production facility basis as shown in fig. 8, the model selection unit 103 may select 1 operation parameter model Pm corresponding to a production facility in which production of a mounting board using a component P is performed. For example, in the case where the production facility in which the mounted substrate using the component P is produced is the component mounting line L2, the model selection unit 103 may select the operation parameter model Pm32 shown in fig. 8. In addition, when the manufacturing facility that manufactures the mounting boards using the components P is not only the component mounting line L2, the model selection unit 103 may select the operation parameter model Pm34 shown in fig. 8. This makes it possible to select an appropriate operating parameter model Pm for estimating the operating parameter m for the component P.

In the case where the plurality of operating parameter models Pm are managed on a production type basis as shown in fig. 9A, the model selection unit 103 may select 1 operating parameter model Pm that corresponds to the production type of the mounting substrate produced using the component P. For example, in the case where the production type of the mounting substrate produced using the component P is a mass production type, the model selection unit 103 may select the operating parameter model Pm43 shown in fig. 9A. In addition, when the type of production of the mounting substrate produced using the component P is not only a mass production type, the model selection unit 103 may select the operating parameter model Pm44 shown in fig. 9A. This makes it possible to select an appropriate operating parameter model Pm for estimating the operating parameter m for the component P.

In the present embodiment, the model selection unit 103 selects 1 operating parameter model Pm, but the number is not limited to 1, and a plurality of operating parameter models Pm for estimating different operating conditions may be selected. For example, as shown in fig. 5, the motion parameter m includes different parameters such as a speed parameter m3 and identification information m 4. Therefore, the model selecting unit 103 can select, for example, the motion parameter model Pm for estimating the speed parameter m3 and the motion parameter model Pm for estimating the identification information m 4. In this case, the parameter estimation unit 105 may estimate the speed parameter m3 using the component information d and the operation parameter model Pm for the speed parameter m3, and estimate the identification information m4 using the component information d and the operation parameter model Pm for the identification information m 4.

The model selection unit 103 may automatically select the operation parameter model Pm as described above, or may perform the selection in accordance with the operation of the input/output unit 107 by the operator.

Fig. 10B is a diagram for explaining an outline of the learning process of the operation parameter model Pm in the present embodiment.

The learning unit 104 acquires actual performance production data from any one of the component mounting lines L1 to L3, for example, via the data acquisition unit 108. The actual performance production data includes the actual performance part data Dcu as described above. That is, the learning unit 104 acquires the actual performance part data Dcu. The actual performance component data Dcu is component data Dc used for mounting the component P on the substrate B by the component mounting apparatus M4 or M5, and is component data Dc subjected to correction or the like by the use thereof. For example, the actual performance unit data Dcu includes the operation parameter mu as the corrected operation parameter m, and the adsorption speed as the operation condition is corrected from V1 to V2 in the operation parameter mu.

Next, the learning unit 104 selects an operation parameter model Pm corresponding to the actual performance component data Dcu from the plurality of operation parameter models Pm held in the learning model holding unit DB 2. For example, as shown in fig. 7A and 7B, the learning unit 104 selects the operation parameter model Pm corresponding to a period during which the actual performance production data including the actual performance component data Dcu is acquired. Alternatively, as shown in fig. 8, the learning unit 104 selects the operation parameter model Pm corresponding to the production facility including the component mounting apparatus M4 or M5 using the actual performance production data including the actual performance component data Dcu. Alternatively, as shown in fig. 9A and 9B, the learning unit 104 selects the operation parameter model Pm corresponding to the production type of the mounting substrate produced using the actual performance production data including the actual performance component data Dcu.

Then, the learning unit 104 updates the selected operation parameter model Pm by learning using the acquired actual performance component data Dcu as teaching data. That is, the relationship between the component information d represented by the operating parameter model Pm and the operating condition is updated. Thereby, the learned operation parameter model Pmu is generated. The learning unit 104 replaces the operation parameter model Pm selected and held in the learning model holding unit DB2 as described above with the learned operation parameter model Pmu. Thus, the learned operation parameter model Pmu is stored as a new operation parameter model Pm in the learning model holding unit DB 2.

Fig. 11 is a diagram showing an example of the overall processing in the present embodiment. In the example shown in fig. 11, the plurality of operation parameter models Pm held in the learning model holding part DB2 are managed in units of time or in units of production type.

The parameter estimation unit 105 estimates an operating parameter m of the component P using the operating parameter model Pm selected by the model selection unit 103, and generates component data Dc including the component information d of the component P and the operating parameter m, as in the example shown in fig. 10A. Then, the data generation part 102 generates the production data Dp including the component data Dc, and outputs the production data Dp to, for example, the component mounting line L1 via the input-output part 107. In addition, in the example shown in fig. 11, the production data Dp is output to the component mounting line L1, but may be output to another component mounting line L2 or L3.

When the component mounting apparatuses M4 and M5 included in the component mounting line L1 acquire the production data Dp from the input/output unit 107 of the production data generation apparatus 100, at least 1 component P is mounted on the substrate B based on the production data Dp, thereby producing a mounted substrate. At this time, in the component mounting line L1, for example, the component data Dc included in the production data Dp is corrected so that the incidence of defects in the mounting substrate is reduced. As a specific example, the adsorption speed V1 included in the operation parameter m of the part data Dc is corrected to V2. As a result, actual performance production data including the actual performance component data Dcu having the operation parameter mu is generated. The actual performance part data Dcu is stored as new part data Dc in the part library storage DB 3. Specifically, the data acquisition unit 108 of the production data generation apparatus 100 acquires actual performance production data from the component mounting line L1, and stores actual performance component data Dcu included in the actual performance production data in the component library storage DB3 as new component data Dc. In addition, the correction of the part data Dc in the part mounting line L1 is not unnecessary, and in the case where there is no correction, the part mounting line L1 generates actual performance production data including the part data Dc acquired from the production data generating apparatus 100 as the actual performance part data Dcu.

When the actual performance production data is acquired by the data acquisition unit 108, the learning unit 104 selects the operation parameter model Pm corresponding to the actual performance component data Dcu included in the actual performance production data from the learning model holding unit DB2, as in the example shown in fig. 10B. Then, the learning unit 104 performs learning on the selected operation parameter model Pm using the actual performance component data Dcu, and stores the learned operation parameter model Pmu in the learning model holding unit DB 2.

Fig. 12 is a diagram showing another example of the overall processing in the present embodiment. In the example shown in fig. 12, the plurality of operation parameter models Pm held in the learning model holding portion DB2 are managed in units of production facilities.

Similarly to the example shown in fig. 10A, the parameter estimation unit 105 estimates an operating parameter m of the component P using the operating parameter model Pm selected by the model selection unit 103 for each production facility, and generates component data Dc including the component information d of the component P and the operating parameter m.

For example, the parameter estimation unit 105 estimates the operating parameters m based on the operating parameter model Pm for the component mounting line L1, that is, the operating parameter model Pm31 shown in fig. 8, and generates the component data Dc. Then, the data generation unit 102 generates production data Dp including the component data Dc, and outputs the production data Dp to, for example, the component mounting line L1 via the input/output unit 107. Further, the parameter estimation unit 105 estimates the operation parameter m based on the operation parameter model Pm for the component mounting line L2, that is, the operation parameter model Pm32 shown in fig. 8, and generates the component data Dc. Then, the data generation unit 102 generates production data Dp including the component data Dc, and outputs the production data Dp to, for example, the component mounting line L2 via the input/output unit 107. Further, the parameter estimation unit 105 estimates the operation parameter m based on the operation parameter model Pm for the component mounting line L3, that is, the operation parameter model Pm33 shown in fig. 8, and generates the component data Dc. Then, the data generation unit 102 generates production data Dp including the component data Dc, and outputs the production data Dp to, for example, the component mounting line L3 via the input/output unit 107.

Alternatively, the parameter estimation unit 105 estimates the operation parameter m based on the operation parameter model Pm for the component mounting lines L1 to L3, that is, the operation parameter model Pm34 shown in fig. 8, and generates the component data Dc. Then, the data generator 102 generates production data Dp including the component data Dc, and outputs the production data Dp to, for example, the component mounting lines L1 to L3 via the input/output unit 107.

In each of the component mounting lines L1 to L3, when the component mounting apparatuses M4 and M5 acquire the production data Dp from the input/output unit 107 of the production data generation apparatus 100, at least 1 component P is mounted on the substrate B based on the production data Dp. Thereby, a mounting substrate is produced. At this time, in each of the component mounting lines L1 to L3, for example, the component data Dc included in the production data Dp is corrected so that the occurrence rate of defects in the mounting substrate is reduced. As a result, actual performance production data including the actual performance component data Dcu is generated. These actual performance part data Dcu are stored in the part library storage DB3 as new part data Dc. Specifically, the data acquisition unit 108 of the production data generation apparatus 100 acquires actual performance production data from the component mounting lines L1 to L3, respectively, and stores the actual performance component data Dcu included in the actual performance production data in the component library holding unit DB3 as new component data Dc. In addition, the correction of the component data Dc in each of the component mounting lines L1 to L3 is not unnecessary. When no correction is made, each of the component mounting lines L1 to L3 generates actual performance production data including the component data Dc acquired from the production data generation apparatus 100 as the actual performance component data Dcu.

When the actual results production data of the component mounting line L1 is acquired by the data acquisition unit 108, the learning unit 104 selects the operation parameter model Pm corresponding to the actual results component data Dcu included in the actual results production data from the learning model holding unit DB2, as in the example shown in fig. 10B. Specifically, the learning unit 104 selects an operating parameter model Pm for the component mounting line L1, that is, an operating parameter model Pm31 shown in fig. 8. Then, the learning unit 104 performs learning on the selected operation parameter model Pm using the actual performance component data Dcu of the component mounting line L1. The actual performance component data Dcu is the component data Dc acquired from the component mounting line L1 by the data acquisition unit 108 and stored in the component library storage unit DB3 as described above. As a result, the learning unit 104 updates the selected operating parameter model Pm for the component mounting line L1 stored in the learning model holding unit DB2 to the learned operating parameter model Pmu for the component mounting line L1.

The learning unit 104 updates the operation parameter model Pm on each of the component mounting lines L2 and L3 in the same manner as the component mounting line L1. That is, the learning unit 104 updates the operation parameter model Pm for the component mounting line L2 stored in the learning model holding unit DB2 to the learned operation parameter model Pmu for the component mounting line L2. Further, the learning unit 104 updates the operating parameter model Pm for the component mounting line L3 stored in the learning model holding unit DB2 to the learned operating parameter model Pmu for the component mounting line L3.

Note that, when the data acquisition unit 108 acquires actual performance production data of any one of the component mounting lines L1 to L3, the learning unit 104 may select the operation parameter model Pm for all of the component mounting lines L1 to L3, that is, the operation parameter model Pm34 shown in fig. 8. In this case, the learning unit 104 performs learning on the selected operation parameter model Pm using the actual performance component data Dcu of any one of the component mounting lines L1 to L3. The actual performance component data Dcu is the component data Dc that is acquired from any one of the component mounting lines L1 to L3 by the data acquisition unit 108 and stored in the component library storage DB3, as described above. As a result, the learning unit 104 updates the operation parameter model Pm for the selected component mounting lines L1 to L3 stored in the learning model holding unit DB2 to the learned operation parameter model Pmu for the component mounting lines L1 to L3.

The data generation unit 102 in the present embodiment may import the production data Dp from a production facility such as another factory other than the factory having the production system 1, or may export the production data Dp to a production facility such as another factory.

Fig. 13 is a flowchart showing the processing operation of the production data generating apparatus 100 according to the present embodiment.

The input/output unit 107 of the production data generation apparatus 100 receives the component information d (step S11). The component information d may be generated and received by an operation of the input/output unit 107 by an operator, or may be selected from a plurality of component information d and received. The input/output unit 107 may receive the part information d by selecting the part data Dc having the default operating parameter m from among the plurality of part data Dc included in the part library, and extracting the part information d from the part data Dc. As shown in fig. 5, the part information d includes, for example, size data d2 and part attributes d 31.

Next, the model selecting unit 103 selects at least 1 operating parameter model Pm from the plurality of operating parameter models Pm held in the learning model holding unit DB2 (step S12).

Next, the parameter estimation unit 105 estimates the operation parameter m based on at least 1 operation parameter model Pm selected in step S12 and the component information d received in step S11 (step S13). The operation parameter M is an operation condition of the component mounting device M4 or M5 for mounting the component P determined based on the component information d onto the substrate B. Then, the parameter estimation unit 105 generates the part data Dc having the part information d and the operation parameter m (step S14).

Next, the data generation part 102 generates production data Dp including the part data Dc generated in step S14 (step S15). Then, the data generation unit 102 outputs the production data Dp to the component mounting lines L1 to L3, respectively. That is, the component mounting lines L1 to L3 each download the production data Dp from the data generation section 102, and start the production of the mounting substrate using the production data Dp (step S16).

Then, the learning unit 104 performs relearning of the operation parameter model Pm using the part data Dc (i.e., the actual result part data Dcu) included in the production data Dp used in each of the part mounting lines L1 to L3 as teaching data (step S17). The operation parameter model Pm to be relearned is, for example, an operation parameter model Pm corresponding to a period during which the used production data Dp (i.e., actual performance production data) is acquired.

As described above, in the production data generation device 100 according to the present embodiment, at least 1 operating parameter model Pm is selected from the plurality of operating parameter models Pm. Then, based on the selected at least 1 operating parameter model Pm and the component information d of the mounting target component P, an operating parameter m for mounting the mounting target component P on the substrate B is estimated.

Thus, since at least 1 operating parameter model Pm is selected from the plurality of operating parameter models Pm and used for estimation of the operating parameter m, the possibility of estimating the appropriate operating parameter m for the mounting target component P can be improved. Therefore, the appropriate operation parameter m can be set. Since the component data Dc having the operation parameters M and the component information d is included in the production data Dp, a mounting substrate with good quality can be produced when the production data Dp is used for mounting the component P on the substrate B by the component mounting apparatus M4 or M5. That is, the quality of the mounting substrate can be improved.

In addition, the production data generating apparatus 100 according to the present embodiment acquires actual performance production data including the actual performance component data Dcu, which is used by the component mounting apparatus M4 or M5. Then, the actual performance component data Dcu is used as teaching data to learn, thereby updating the operation parameter model Pm corresponding to the acquired actual performance production data among the plurality of operation parameter models Pm.

The operation parameters mu of the actual performance part data Dcu included in the actual performance production data are used in the mounting of the mounted part P, and are corrected or the like at this time. That is, the operation parameter mu is corrected so that a mounting substrate of better quality is produced. Therefore, by using the actual performance unit data Dcu having the operation parameters mu as teaching data in learning the operation parameter model Pm, the operation parameter model Pm can be further optimized. As a result, when the model selection unit 103 selects the operating parameter model Pm, the accuracy of estimating the operating parameter m can be improved.

In the production data generation device 100 according to the present embodiment, the plurality of operation parameter models Pm are associated with different periods, respectively, and the operation parameter model Pm corresponding to the period during which the actual performance production data is acquired is learned.

For example, as shown in fig. 7A, 1 motion parameter model Pm14 out of the motion parameter models Pm11 to Pml4 corresponds to the entire period (for example, the entire period from 1990 to the present). The remaining operation parameter models Pm11 to Pm13 correspond to different ages. The different generations are, for example, 1990, 2000, 2010, and the like. Thus, the operation parameter model Pm associated with the entire period or any one of the years is selected from the operation parameter models Pm11 to Pm14 and used for estimation of the operation parameter m. Therefore, the appropriate operation parameter m according to the period can be estimated for the mounting target component P.

In the production data generation apparatus 100 according to the present embodiment, as shown in fig. 8, the operation parameter models Pm31 to Pm34 are associated with different production facilities. Then, the operation parameter model Pm corresponding to the production facility including the component mounting apparatus M4 or M5 using the actual performance production data is learned.

Thus, the operation parameter model Pm associated with all or any one of the component mounting lines is selected from the operation parameter models Pm31 to Pm34 and used for estimation of the operation parameter m. Therefore, the appropriate operation parameter m according to the production facility can be estimated for the mounting target component P.

In the production data generating apparatus 100 according to the present embodiment, as shown in fig. 9A, the operation parameter models Pm41 to Pm44 are associated with different types of mounting boards, respectively. Then, the operation parameter model Pm corresponding to the type of the mounting substrate produced using the actual performance production data is learned.

Thus, the operation parameter model Pm associated with, for example, the mass production type or the trial production type is selected from the operation parameter models Pm41 to Pm44 and used for estimation of the operation parameter m. Therefore, the appropriate operation parameter m according to the type of the mounting substrate can be estimated for the mounting target component P.

As described above, in the present embodiment, the operation parameter model Pm specialized for the period, the type of the production equipment or the type of the mounting board, and the like can be used, and as a result, the operation parameter m suitable for the period, the type of the production equipment or the type of the mounting board can be estimated.

(modification of embodiment 1)

In the above embodiment, as shown in fig. 7A to 9B, the plurality of operation parameter models Pm are managed in units of time, production facility, or production type. However, the management method is not limited to this, and the plurality of operation parameter models Pm may be managed in other units. In the example shown in fig. 9B, the plurality of operation parameter models Pm are managed in units of combinations of production facilities and production types, but the combinations are not limited to these, and may be any combinations.

In the example shown in fig. 7B in the above embodiment, the model selection unit 103 selects 1 operation parameter model Pm updated on the latest date. Here, when the occurrence rate of defects in the mounting substrate produced by the production data Dp including the operation parameter m estimated based on the operation parameter model Pm is high, the model selection unit 103 may newly select the previously selected operation parameter model Pm as the operation parameter model Pm updated on the latest date. In the examples shown in fig. 7A, 8, 9A, and 9B, the model selection unit 103 may reselect the operation parameter model Pm according to the failure occurrence rate, for example. The reselection may be performed randomly or following a predetermined order.

The input/output unit 107 of the production data generating apparatus 100 according to the above embodiment may derive the at least 1 operating parameter model Pm held in the learning model holding unit DB2 to a facility other than the facility having the production system 1. The facility may be a factory or a floor. Further, the input/output unit 107 may introduce at least 1 operation parameter model Pm from another facility and store it in the learning model holding unit DB 2. This makes it possible to further optimize the operation parameter model Pm. The input/output unit 107 may draw in and derive the production data Dp held in the production data holding unit DB1, or may draw in and derive the component data Dc held in the component library holding unit DB 3.

The learning unit 104 of the production data generating apparatus 100 according to the above embodiment performs learning of the operation parameter model Pm corresponding to the actual achievement production data acquired by the data acquiring unit 108 among the plurality of operation parameter models Pm held in the learning model holding unit DB 2. However, the learning unit 104 may switch the operation parameter model Pm to be learned by an operation of the operator received by the input/output unit 107. Thus, the operation parameter model Pm specified by the operator is learned.

Further, the operation parameter m estimated by the parameter estimation unit 105 included in the component data Dc of the component library may be associated with the identification information of the operation parameter model Pm used for estimating the operation parameter m and the date and time at which the estimation is performed. This enables the operation parameter m to be appropriately managed.

The parameter estimation unit 105 may estimate the operation parameter m using only a part of the information, instead of using all the information included in the component information d shown in fig. 5. For example, the input/output unit 107 may receive a part of information used for estimation of the operation parameter m from among the component information d in accordance with the operation of the operator. When such partial information is received, the parameter estimation unit 105 estimates the operation parameter m using only the received partial information. Further, the parameter estimation unit 105 may estimate only a part of the parameters, instead of all the parameters included in the operation parameters m shown in fig. 5. For example, the input/output unit 107 may receive designation of a part of parameters to be estimated among the operation parameters m shown in fig. 5 in response to an operation by the operator. When such a partial parameter is specified, the parameter estimation unit 105 estimates only the specified partial parameter among the motion parameters m. The parameter estimation unit 105 may analyze all pieces of information included in the part information d as principal components and estimate the motion parameter m according to the analysis result.

(embodiment mode 2)

In the present embodiment, a filtering (filtering) is performed for the operation parameter mu included in the actual performance production data output from each of the component mounting lines L1 to L3.

[ production System ]

Fig. 14 is a diagram showing an example of the configuration of the production system in the present embodiment.

The production system 2 in the present embodiment includes 3 component mounting lines L1 to L3, a production management device 100a, a

data management device

300, and 3 inspection devices 401 to 403. That is, the production system 2 in the present embodiment includes: component mounting devices M4 and M5 that produce mounting substrates by mounting components P on the substrates B; and processing devices such as a data management device 300 and inspection devices 401 to 403 for performing processing related to the production of the mounting substrate.

Note that, of the components in the present embodiment, the same components as those in embodiment 1 are denoted by the same reference numerals as those in embodiment 1, and detailed description thereof is omitted.

The 3 component mounting lines L1 to L3 are the same as the 3 component mounting lines L1 to L3 of the production system 1 in embodiment 1.

The production management apparatus 100a manages production of the mounting substrate in the production system 2. Specifically, the production management device 100a has the same function as the production data generation device 100 in embodiment 1, and further has a function of screening the operation parameter mu included in the actual performance production data.

The data management device 300 is connected to the production management device 100a and the component mounting lines L1 to L3, respectively, and manages the production data Dp of the component mounting lines L1 to L3, respectively. The production data Dp may be actual performance production data used in each of the component mounting lines L1 to L3. The data management device 300 in the present embodiment generates filtering information used for filtering by the production management device 100a, and outputs the filtering information to the production management device 100 a.

The inspection devices 401 to 403 respectively inspect the mounting substrates produced by the component mounting lines L1 to 3. That is, the inspection device 401 inspects the mounted substrate of the component mounting line L1, the inspection device 402 inspects the mounted substrate of the component mounting line L2, and the inspection device 403 inspects the mounted substrate of the component mounting line L3. The inspection devices 401 to 403 in the present embodiment are connected to the production management device 100a, respectively, generate the screening information based on the inspection result of the mounted board, and output the screening information to the production management device 100 a.

The data management device 300 and the inspection devices 401 to 403 in the present embodiment are processing devices that perform processing related to the production of the mounting substrate.

[ functional structures of production management apparatus, component mounting line, and processing apparatus ]

Fig. 15 is a block diagram showing the functional configurations of the production management apparatus 100a, the component mounting lines L1 to L3, and the processing apparatus. In the present embodiment, as shown in fig. 15, the processing device 500 is configured by the data management device 300 and the inspection devices 401 to 403.

The production management device 100a includes a control unit 101, a data generation unit 102, a model selection unit 103, a learning unit 104, a parameter estimation unit 105, a display unit 106, an input/output unit 107, a data acquisition unit 108, a production data holding unit DB1, a learning model holding unit DB2, and a component library holding unit DB3, as in the production data generation device 100 according to embodiment 1. Further, the production management apparatus 100a includes: and a screening unit 109 for screening the operation parameter mu included in the actual performance production data.

Specifically, the data acquisition unit 108 of the production management device 100a according to the present embodiment acquires actual performance production data, which is production data Dp used for producing the mounted boards by the component mounting devices M4 and M5, from the component mounting lines L1 to L3, respectively. The actual performance production data includes, for at least 1 type of component P, an operation parameter mu that is an operation condition of the component mounting device M4 or M5 for mounting the component P on the substrate B. Further, the data acquisition unit 108 acquires filtering information from the processing device 500.

The screening unit 109 selects 1 or more operation parameters mu by screening at least 1 operation parameter mu included in the acquired actual performance production data using the screening information obtained from the processing device 500.

The learning unit 104 generates or updates the operation parameter model Pm, which is a learning model held in the learning model holding unit DB2, by learning using the selected 1 or more operation parameters mu as teaching data. The operation parameter model Pm represents the relationship between the operation condition of the component mounting apparatus M4 or M5 for mounting the component P on the substrate B and the component P. In the learning, more specifically, the actual performance part data Dcu including the selected 1 or more operation parameters mu is used as teaching data for each of the selected 1 or more operation parameters mu.

Further, the parameter estimation unit 105 in the present embodiment estimates the operation parameter M, which is the operation condition of the component mounting device M4 or M5 for mounting the yet-to-be-mounted mounting target component P on the board, as in embodiment 1. The estimation of the operating parameter m is performed based on the operating parameter model Pm held in the learning model holding unit DB2 and the component information d on the component P to be mounted on the board B.

The processing device 500 includes inspection devices 401 to 403 and a data management device 300.

The inspection apparatus 401 includes an inspection control unit 411, an input/output unit 412, a display unit 413, an inspection means 414, and an inspection data holding unit DB 5.

The input/output unit 412 receives input data based on an operation of an operator of the production system 2, for example, and outputs the input data to the inspection control unit 411. Such an input/output unit 412 may include, for example, a keyboard, a touch sensor, a touch pad, a mouse, and the like. The input/output unit 412 outputs data to the production management device 100a and inputs data from the production management device 100 a.

The inspection means 414 is configured by a means including, for example, a camera for inspecting the mounting substrate, and stores inspection data indicating the inspection result in the inspection data holding portion DB 5.

The inspection data holding DB5 is a recording medium for holding inspection data. Such a recording medium is, for example, a hard disk, a RAM, a ROM, a semiconductor memory, or the like. Such a recording medium may be volatile or nonvolatile.

The display unit 413 displays the inspection data and the like held in the inspection data holding unit DB 5. Specific examples of the display portion 413 include, but are not limited to, a liquid crystal display, a plasma display, an organic EL display, and the like.

The inspection control unit 411 controls the input/output unit 412, the display unit 413, the inspection mechanism 414, and the inspection data holding unit DB5, respectively. For example, the inspection control unit 411 causes the inspection mechanism 414 to start the inspection of the mounted board in response to the operation of the operator received by the input/output unit 412. The inspection control unit 411 in the present embodiment generates screening information and outputs the screening information to the data acquisition unit 108 of the production management apparatus 100a via the input/output unit 412.

The inspection apparatuses 402 and 403 also have the same configuration as the inspection apparatus 401.

The data management device 300 includes a data control unit 311, an input/output unit 312, a display unit 313, and a data holding unit DB 6.

The input/output unit 312 receives input data based on an operation of an operator of the production system 2, for example, and outputs the input data to the data control unit 311. Such an input/output unit 312 may include, for example, a keyboard, a touch sensor, a touch pad, a mouse, and the like. The input/output unit 312 outputs data to the production management apparatus 100a and the component mounting lines L1 to L3, and inputs data from the production management apparatus 100a and the component mounting lines L1 to L3.

The data holding portion DB6 is a recording medium for holding data. For example, the data is screening information. Such a recording medium may be a hard disk, RAM, ROM, semiconductor memory, or the like, and may be volatile or nonvolatile.

The display unit 313 displays the data and the like held in the data holding unit DB 6. Specific examples of the display portion 313 include, but are not limited to, a liquid crystal display, a plasma display, an organic EL display, and the like.

The data control unit 311 controls the input/output unit 312, the display unit 313, and the data holding unit DB6, respectively. The data control unit 311 in the present embodiment may generate screening information in the same manner as the inspection control unit 411 and output the screening information to the data acquisition unit 108 of the production management apparatus 100a via the input/output unit 312.

For example, the data control unit 311 in the present embodiment may generate substrate identification information for identifying the substrate B as the screening information. In this case, the plurality of actual performance production data Dpu corresponding to the plurality of different types of mounting boards are screened by the screening information. Therefore, the data management device 300 can be said to manage a plurality of actual performance production data Dpu corresponding to a plurality of different types of mounting boards. Alternatively, the data control unit 311 may generate 1 or more pieces of component identification information for identifying the type of the component P as the screening information.

[ outline of treatment ]

Fig. 16 is a diagram showing an example of the overall processing in the present embodiment.

In the present embodiment, as in embodiment 1, at least 1 piece of production data Dp is generated, and actual performance production data Dpu is output from each of the component mounting lines L1 to L3 based on the at least 1 piece of production data Dp.

The filtering unit 109 of the production management device 100a filters at least 1 of the operation parameters mu included in the actual result production data Dpu. At this time, the filtering unit 109 acquires the filtering information Df from the processing device 500, and performs filtering based on the filtering information Df to select 1 or more operation parameters mu. Then, the screening unit 109 stores the actual performance component data Dcu including the selected operation parameter mu in the component library holding unit DB3 as new component data Dc for each of the selected 1 or more operation parameters mu.

[ screening information ]

Fig. 17A is a diagram showing an example of screening information Df generated based on the inspection result of the mounting substrate.

For example, the inspection control units 411 of the inspection apparatuses 401 to 403 included in the processing apparatus 500 generate the screening information Df shown in fig. 17A and output the screening information Df to the screening unit 109.

That is, the inspection control unit 411 generates information indicating the quality index of each of at least 1 type of component P mounted on the mounting board as the screening information Df, by the inspection of the mounting board by the inspection mechanism 414. The quality index indicated by the screening information Df is also referred to as an installation quality index, and for example, the quality index indicates a larger value as the installation state of the component P corresponding to the quality index is better.

More specifically, when the inspection mechanism 414 includes a camera, the inspection control unit 411 calculates an installation quality index indicating a positional deviation of the mounted component P based on an image of the mounting board captured by the camera. The positional deviation of the component P is a difference between the mounting position of the component P in the substrate B represented by the image and the assembly coordinate (or mounting position) of the component P represented by the production data Dp. For example, the inspection controller 411 calculates a numerical value closer to 1 as the positional deviation of the component P is smaller, and conversely, calculates a numerical value closer to 0 as the positional deviation of the component P is larger, as the mounting quality index. That is, the mounting quality index can be normalized to a value in the range of 0 to 1. In addition, the mounting quality index may also be referred to as a score or an evaluation value.

By calculating the mounting quality index in this manner, the inspection control unit 411 generates screening information Df indicating the mounting quality index of each of the plurality of types of components P as shown in fig. 17A. The screening information Df represents the mounting quality index for each part name and part code of the part P. For example, the screening information Df shows "0.95" as the mounting quality index of the component P of the kind specified by the component name "component a" and the component code "C001".

When the screening information Df shown in fig. 17A is acquired, the screening unit 109 of the production management apparatus 100a performs screening using the screening information Df. That is, the screening unit 109 selects 1 or more operation parameters mu corresponding to the types of the components P having the mounting quality index of not less than the threshold value by the screening. For example, the screening unit 109 selects 1 or more operation parameters mu corresponding to the type of the component P whose mounting quality index is equal to or greater than the threshold value "0.85". In the example shown in fig. 17A, the screening unit 109 selects the operation parameter mu corresponding to the part P having the part name "part a" and the part code "C001" and the operation parameter mu corresponding to the part P having the part name "part G" and the part code "C034". That is, the screening unit 109 selects the actual performance part data Dcu of the part code "C001" and the actual performance part data Dcu of the part code "C034" from the plurality of actual performance production data Dpu, respectively.

As described above, in the present embodiment, the operation parameter mu corresponding to the type of the component P having a large mounting quality index is selected by screening. Thus, 1 or more operation parameters mu corresponding to the types of components P in good mounting states are selected by screening and used for learning, and operation parameters mu corresponding to the types of components P in poor mounting states are not used for learning. Therefore, the operating parameter model Pm for estimating the appropriate operating parameter m for achieving a good mounting state can be generated.

Fig. 17B is a diagram showing an example of the screening information Df generated based on the actual mounting results of the component mounting lines L1 to L3.

The data control unit 311 of the data management device 300 included in the processing device 500 may generate the filtering information Df shown in fig. 17B and output the filtering information Df to the filtering unit 109.

That is, the data control unit 311 acquires information indicating the operating conditions of the component mounting devices M4 and M5 included in the component mounting lines L1 to L3 via the input/output unit 312, respectively. The data control unit 311 generates information indicating the actual performance index of each of at least 1 component as the screening information based on the information indicating the operation state. The mounting actual performance index is an index relating to an error that occurs in the component mounting apparatuses M4 and M5 with respect to the component P due to the operation of the actual performance production data Dpu by the component mounting apparatuses M4 and M5, and for example, a smaller value is shown as the number of errors is smaller. In addition, the installation actual performance index may also be referred to as a score or an evaluation value.

More specifically, the mounting actual performance index is an index relating to errors such as the suction omission of the components P, the dropping of the components P, and the supply omission from the parts feeders 7 to the mounting head 10, which are generated by the component mounting devices M4 and M5. For example, the data control unit 311 represents the installation actual performance index as a percentage. That is, the data control unit 311 calculates a numerical value closer to 0% as the number of errors is smaller, and on the other hand, calculates a numerical value closer to 100% as the number of errors is larger, as the actual installation performance index.

By calculating the actual performance index of the mounting as described above, the data control unit 311 generates the screening information Df indicating the actual performance index of the mounting of each of the plurality of types of parts P as shown in fig. 17B. The screening information Df represents the installation performance index for each part P by the part name and the part code. For example, the screening information Df indicates "0.5%" as the mounting quality index of the component P of the type specified by the component name "component a" and the component code "C001".

When the screening information Df shown in fig. 17B is acquired, the screening unit 109 of the production management apparatus 100a performs screening using the screening information Df. That is, the screening unit 109 selects 1 or more operation parameters mu corresponding to the types of components P whose installation actual performance indexes are equal to or less than the threshold value by the screening. For example, the screening unit 109 selects 1 or more operation parameters mu corresponding to the type of the component P whose installation actual performance index is equal to or less than the threshold value "1%". In the example shown in fig. 17B, the screening unit 109 selects the operation parameter mu corresponding to the component P having the component name "component a" and the component code "C001", and the operation parameter mu corresponding to the component P having the component name "component B" and the component code "C102". That is, the screening unit 109 selects the actual performance part data Dcu of the part code "C001" and the actual performance part data Dcu of the part code "C102" from the plurality of actual performance production data Dpu.

As described above, in the present embodiment, the operation parameters mu corresponding to the types of the components P having the small mounting actual performance indexes are selected by screening. Thus, 1 or more operation parameters mu corresponding to the types of the components P having few errors in the component mounting apparatus M4 or M5 are selected by screening and used for learning, and the operation parameters mu corresponding to the types of the components P having many errors are not used for learning. Therefore, the operating parameter model Pm for estimating the appropriate operating parameter m for reducing the occurrence of the error can be generated.

Fig. 18A is a diagram showing an example of the filtering information Df generated by the selection of the component P.

The data control unit 311 of the data management device 300 included in the processing device 500 may generate the filtering information Df shown in (b) in accordance with the operation result of the operator shown in (a) of fig. 18A, and output the filtering information Df to the filtering unit 109.

For example, the data control unit 311 displays the component selection screen shown in (a) of fig. 18A on the display unit 313. The part selection screen shows the part name, the part code, and at least a part of the part information d (for example, the outer dimensions and the number of leads) of each part P processed by the production system 2. The operator inputs the learning label to the desired component P by operating the input/output unit 312 while viewing the component selection screen. For example, in a mounting substrate produced by mounting of a component P, in the case where the quality of the mounted state of the component P is good, the operator inputs a learning flag to the component P. Alternatively, in the case where the part P used in the past is an exceptional special part, the operator does not input the learning flag to the part P. When the operation parameter mu of the component P included in the actual performance production data Dpu is set in another factory, the operator does not input the learning flag to the component P. In the example shown in (a) of fig. 18A, the operator inputs learning flags for each part P of the part names "part a", "part B", "part D", and "part F". Then, the operator further operates the input/output unit 312 to select a decision button shown on the component selection screen. As a result, the data control unit 311 generates the filtering information Df shown in (b) of fig. 18A in accordance with the learning flag input to the component selection screen.

The filtering information Df shows, for each learning label input by the operator, the part name, the part code, and the like of the part P corresponding to the learning label as the part identification information of the part P. For example, the filtering information Df represents, as part identification information of each of the 4 parts P, a part name "part a" and a part code "C001", a part name "part B" and a part code "C002", a part name "part D" and a part code "C003", and a part name "part F" and a part code "C005". In this manner, the data management device 300 outputs the filtering information Df including 1 or more pieces of component identification information for identifying the types of the components P, respectively.

When the screening information Df shown in fig. 18A (b) is acquired, the screening unit 109 of the production management apparatus 100a performs screening using the screening information Df. That is, the screening unit 109 selects the operation parameter mu corresponding to the type of the component P identified by the component identification information for each of the 1 or more pieces of component identification information indicated by the screening information Df during the screening. In the example shown in fig. 18A (b), the filtering unit 109 selects the actual performance part data Dcu of the part code "C001", the actual performance part data Dcu of the part code "C002", the actual performance part data Dcu of the part code "C003", and the actual performance part data Dcu of the part code "C005" from the plurality of actual performance production data Dpu.

As described above, in the present embodiment, the operation parameters mu corresponding to the type of the component P designated by the operation of the operator are selected by the screening. Thus, 1 or more operation parameters mu corresponding to the type of component P identified based on the component identification information specified by the operator are selected by filtering and used for learning, and the operation parameters mu corresponding to the types of other components P are not used for learning. Therefore, the operating parameter model Pm for estimating the appropriate operating parameter mu for the specific component P can be generated.

Fig. 18B is a diagram showing an example of the screening information Df generated by the selection of the substrate B.

The data control unit 311 of the data management device 300 included in the processing device 500 may generate the filtering information Df shown in (B) in accordance with the operation result of the operator shown in (a) of fig. 18B, and output the filtering information Df to the filtering unit 109.

For example, the data control unit 311 displays the substrate selection screen shown in (a) of fig. 18B on the display unit 313. The substrate selection screen shows the substrate name, the substrate code, the auxiliary information, and the like of each substrate B processed by the production system 2. The operator inputs the learning mark to the desired board B by operating the input/output unit 312 while viewing the board selection screen. For example, the operator inputs a learning flag for each of the substrate names "a substrate", "B substrate", "D substrate", and "F substrate" of the substrates B. Then, the operator further operates the input/output unit 312 to select a decision button shown on the substrate selection screen. As a result, the data control unit 311 generates the filtering information Df shown in (B) of fig. 18B in accordance with the learning flag input to the board selection screen.

The screening information Df indicates, for each learning mark input by the operator, the substrate name, the substrate code, and the like of the substrate B corresponding to the learning mark, as the substrate identification information of the substrate B. For example, the screening information Df represents the substrate name "a substrate" and the substrate code "B001", the substrate name "B substrate" and the substrate code "B002", the substrate name "D substrate" and the substrate code "B004", and the substrate name "F substrate" and the substrate code "B006", as the substrate identification information of each of the 4 substrates B. In this manner, the data management device 300 outputs the screening information Df including 1 or more pieces of substrate identification information for identifying the type of each substrate B.

When the screening information Df shown in fig. 18B (B) is acquired, the screening unit 109 of the production management apparatus 100a performs screening using the screening information Df. That is, when the data acquiring unit 108 acquires a real performance production data group including a plurality of real performance production data Dpu, the screening unit 109 selects 1 or more operation parameters mu from at least 1 operation parameter mu included in the real performance production data group in the screening. These selected 1 or more operation parameters mu correspond to the types of the components P mounted on the substrates B of the types identified by the substrate identification information included in the screening information Df, respectively.

In the example shown in fig. 18B (B), the screening unit 109 selects actual performance component data Dcu corresponding to the types of components P mounted on the respective substrates B of the substrate codes "B001", "B002", "B004", and "B006" from the actual performance production data group. In addition, the production data Dp and the actual performance production data Dpu may show the board code of the board B used in the production of the mounting board. In this case, the screening unit 109 selects the actual performance production data Dpu indicating the board codes "B001", "B002", "B004", and "B006" from the actual performance production data group, and extracts the actual performance part data Dcu from the selected actual performance production data Dpu.

As described above, in the present embodiment, the operation parameter mu corresponding to the type of the component P mounted on the board B designated by the operator is selected by the screening. That is, 1 or more operation parameters mu corresponding to the type of the component P mounted on the board B designated by the operator are selected by screening and used for learning, and the operation parameters mu corresponding to the type of the component P mounted on the other board B are not used for learning. Therefore, the operation parameter model Pm for estimating the appropriate operation parameter mu for the specific substrate B can be generated.

[ treatment procedure ]

Fig. 19 is a flowchart showing a processing operation of the production management apparatus 100a in the present embodiment.

The data acquisition unit 108 of the production management device 100a acquires actual performance production data Dpu from the component mounting lines L1 to L3 (step S21). Further, the data acquisition unit 108 acquires the filtering information Df from the processing device 500 (step S22).

Next, the filtering unit 109 filters the operation parameters mu included in the actual performance production data Dpu acquired in step S21, using the filtering information Df acquired in step S22 (step S23). Thus, the operation parameter mu used for learning is selected from the actual performance production data Dpu.

Next, the learning unit 104 generates or updates the operation parameter model Pm by learning using the operation parameter mu selected by the filtering in step S23 (step S24). In this learning, the selected operation parameter mu and the part information d included in the actual performance part data Dcu together with the operation parameter mu are used as teaching data. In addition, in updating the operating parameter model Pm, the operating parameter model Pm corresponding to the actual performance production data Dpu that is held in the learning model holding unit DB2 is updated.

When the component P with an undetermined operating parameter m is selected by the input/output unit 107, the parameter estimation unit 105 estimates the operating parameter m of the selected component P using the operating parameter model Pm generated or updated in step S24 (step S25).

As described above, the production management device 100a according to the present embodiment acquires the actual performance production data Dpu, and performs screening for at least 1 operation parameter mu included in the acquired actual performance production data Dpu. That is, 1 or more operation parameters mu are selected from the actual performance production data Dpu using the filtering information Df obtained from the processing device 500. Then, the operation parameter model Pm is generated or updated by learning using the selected 1 or more operation parameters mu as teaching data.

Thus, 1 or more of the operation parameters mu selected by the filtering are used for learning, and the unselected operation parameters mu are not used for learning, so that the operation parameter model Pm can be optimized. As a result, by using the operating parameter model Pm, it is possible to estimate an appropriate operating parameter mu and set production data Dp to be used in the component mounting apparatus M4 or M5 later. Therefore, a mounting substrate with good quality can be produced. That is, the quality of the mounting substrate can be improved.

That is, in the present embodiment, the operation parameter mu used as teaching data in learning can be controlled, and learning intended by the user can be performed.

In the production management apparatus 100a according to the present embodiment, the operation parameter m for mounting the component P to be mounted on the substrate B is estimated based on the generated or updated operation parameter model Pm and the component information d. This allows the appropriate operating parameter m to be estimated and set for the component P to be mounted.

(modification of embodiment 2)

In the above embodiment, as shown in fig. 18A and 18B, the sort based on the specified component P or board B is performed, but the sort based on the product series of the mounting board may be performed. Further, a screen based on the date when the actual performance production data Dpu was obtained may be performed. For example, only the operation parameters mu included in the actual performance production data Dpu acquired on the latest date may be selected by filtering. Further, screening based on the designated component mounting line may be performed. For example, when the component mounting line L1 is designated, only the operation parameters mu included in the actual performance production data Dpu acquired from the component mounting line L1 can be selected by filtering.

In the example shown in fig. 17A and 17B, the screening information Df indicates an installation quality index or an installation actual performance index, but these are examples and may indicate other indices. In addition, the indices may be labeled with PPM (parts per million).

In the present embodiment, at least 1 operating parameter model Pm may be selected from a plurality of operating parameter models Pm as in embodiment 1. That is, only 1 operation parameter model Pm may be held in the learning model holding unit DB 2.

(other modification example)

The production data generation device, the production management device, and the like according to one or more embodiments have been described above based on the embodiments and modifications thereof, but the present disclosure is not limited to these embodiments and modifications. As long as the present disclosure is not deviated from the gist, a mode in which various modifications that occur to those skilled in the art are implemented to each embodiment or its modified examples, and a mode in which components in each embodiment and each modified example are combined and constructed may be included in the scope of the present disclosure.

In the above embodiments and modifications, each component may be implemented by dedicated hardware or by executing a software program suitable for each component. Each component can be realized by reading and executing a software program recorded in a recording medium such as a hard disk or a semiconductor memory by a program execution Unit such as a CPU (Central Processing Unit) or a processor. Here, software for realizing the devices and the like according to the above embodiments and modifications thereof is a program for causing a computer to execute each step included in the flowcharts shown in fig. 13 and 19.

The following cases are also included in the present disclosure.

(1) The devices are specifically computer systems composed of a microprocessor, a ROM, a RAM, a hard disk assembly, a display assembly, a keyboard, a mouse and the like. And storing the computer program in the RAM or the hard disk component. The microprocessor operates in accordance with the computer program, whereby each device achieves its function. Here, the computer program is configured by combining a plurality of command codes indicating instructions for a computer in order to achieve a predetermined function.

(2) A part or all of the components constituting each of the devices may be constituted by 1 system LSI (Large Scale Integration). The system LSI is a super-multifunctional LSI manufactured by integrating a plurality of components on 1 chip, and specifically is a computer system including a microprocessor, a ROM, a RAM, and the like. A computer program is stored in the RAM. The microprocessor operates in accordance with the computer program, whereby the system LSI achieves its functions.

(3) Some or all of the components constituting each of the devices may be constituted by an IC card or a single module that can be attached to and detached from each of the devices. The IC card or the module is a computer system constituted by a microprocessor, ROM, RAM, and the like. The IC card or the module may contain the above-described ultra-multifunctional LSI. The IC card or the module is caused to perform its function by the microprocessor operating in accordance with the computer program. The IC card or the module may have tamper resistance.

(4) The present disclosure may be the method shown above. The methods may be implemented as a computer program that is realized by a computer, or may be a digital signal that is configured by the computer program.

The present disclosure may be configured such that the computer program or the digital signal is recorded on a computer-readable recording medium such as a flexible disk, a hard disk, a CD-ROM, an MO, a DVD-ROM, a DVD-RAM, a BD (Blu-ray (registered trademark) Disc), a semiconductor memory, or the like. The digital signal may be recorded on such a recording medium.

Further, the present disclosure may be configured to transmit the computer program or the digital signal via an electric communication line, a wireless or wired communication line, a network typified by the internet, data broadcasting, or the like.

The present disclosure may be a computer system including a microprocessor and a memory, the memory storing the computer program, and the microprocessor operating in accordance with the computer program.

The program or the digital signal may be recorded in the recording medium and transferred, or may be transferred via the network or the like, and may be executed by another independent computer system.

(5) The above embodiment and the above modification may be combined.

Industrial applicability

The present disclosure can be utilized in a system for producing a mounting substrate by mounting a component on a substrate, or the like.

Description of reference numerals

1. 2 production system

7 feeder

10 mounting head

10a adsorption component

10b suction nozzle

11 parts identification camera

12 base plate identification camera

14-part carrier tape

100 production data generating device

100a production management device

101 control unit

102 data generating part

103 model selection unit

104 learning unit

105 parameter estimation unit

106. 213, 313, 413 display unit

107. 212, 312, 412 input/output unit

108 data acquisition unit

109 screening section

200 line management device

211 work control unit

214 operating mechanism

300 data management device

311 data control unit

401-403 inspection device

411 inspection control part

414 inspection mechanism

d part information

DB1, DB4 production data holder

DB2 learning model holding part

DB3 parts library holding part

DB5 inspection data holding part

DB6 data holding unit

Dc part data

Dcu actual performance part data

Dp production data

Dpu actual performance production data

L1-L3 parts mounting line

m, mu motion parameters

M4, M5 parts installation device.

Claims

1. A production data generation device is provided with:

a model selection unit that selects at least 1 learning model from a plurality of different learning models that represent relationships between operating conditions of a component mounting apparatus for mounting components on a substrate and the components, respectively;

a parameter estimation unit configured to estimate an operation parameter, which is an operation condition of a component mounting apparatus for mounting a mounting target component on a substrate, based on the at least 1 learning model selected and component information on the mounting target component mounted on the substrate; and

and a data generation unit that generates production data including the component information and the operation parameter.

2. The production data generation apparatus according to claim 1,

the production data generation device further includes:

a data acquisition unit that acquires actual performance production data that includes part information relating to a mounted part and actual performance part data of an operation parameter used in mounting the mounted part and that is used by a part mounting device; and

a learning unit configured to update the relationship represented by a learning model corresponding to the acquired actual performance production data among the plurality of learning models by learning using the actual performance component data as teaching data.

3. The production data generation apparatus according to claim 1 or 2,

the part information indicates at least 1 of a size, a shape, an appearance, a category, and a supply manner for supplying the part corresponding to the part information.

4. The production data generation apparatus according to any one of claims 1 to 3,

the operation parameter is a parameter related to at least 1 of transfer, recognition, suction, and mounting of the component by the component mounting apparatus.

5. The production data generation apparatus according to claim 2,

the plurality of learning models respectively correspond to mutually different periods,

the learning unit learns a learning model corresponding to a period during which the actual performance production data is acquired.

6. The production data generation apparatus according to claim 2 or 5,

the plurality of learning models respectively correspond to different production apparatuses,

the learning unit learns a learning model corresponding to a production facility including a component mounting apparatus using the actual performance production data.

7. The production data generation apparatus according to any one of claims 2, 5, and 6,

the plurality of learning models are respectively associated with mutually different types of mounting substrates,

the learning unit learns a learning model corresponding to a type of a mounting board produced using the actual performance production data.

8. A production data generating method, wherein,

selecting at least 1 learning model from a plurality of different learning models representing the relationship between the operation conditions of a component mounting apparatus for mounting components on a substrate and the components,

estimating an operation parameter which is an operation condition of a component mounting apparatus for mounting a mounting target component to a substrate, based on the selected at least 1 learning model and component information on the mounting target component mounted to the substrate,

generating production data comprising component data having the component information and the action parameters.

9. The production data generating method according to claim 8,

in the production data generating method, further,

acquiring actual performance production data including component information on a mounted component and actual performance component data including operation parameters used in mounting the mounted component and used by a component mounting apparatus,

updating the relationship represented by a learning model corresponding to the acquired actual performance production data among the plurality of learning models by learning using the actual performance component data as teaching data.

10. The production data generation method according to claim 8 or 9,

11. The production data generation method according to any one of claims 8 to 10,

12. The production data generating method according to claim 9,

in the learning, a learning model corresponding to a period during which the actual performance production data is acquired is learned.

13. The production data generation method according to claim 9 or 12,

the plurality of learning models respectively correspond to mutually different production apparatuses,

in the learning, a learning model corresponding to a production facility including a component mounting apparatus using the actual performance production data is learned.

14. The production data generation method according to any one of claims 9, 12, and 13,

in the learning, a learning model corresponding to a type of a mounting substrate produced using the actual performance production data is learned.

15. A program for causing a computer to execute the production data generation method according to any one of claims 8 to 14.