WO2021111851A1

WO2021111851A1 - Production data generation device, production data generation method, and program

Info

Publication number: WO2021111851A1
Application number: PCT/JP2020/042631
Authority: WO
Inventors: 栄滋志垣; 山崎　琢也; 敬明横井; 維里岩田; 隕林譚; 太一清水
Original assignee: パナソニックＩｐマネジメント株式会社
Priority date: 2019-12-02
Filing date: 2020-11-16
Publication date: 2021-06-10
Also published as: JPWO2021111851A1; CN114747307A; DE112020005919T5

Abstract

Provided is a production data generation device capable of setting appropriate operating parameters. The production data generation device (100) comprises: a model selection unit (103) which selects at least one operation parameter model (Pm) from among a plurality of operation parameter models (Pm) that are different from each other; a parameter estimation unit (105) which, on the basis of at least one selected operation parameter model (Pm), and component information (d) regarding a mounting target component (P) mounted on a board (B), estimates operation parameters (m) that are the operation conditions of a component mounting device (M4) or (M5) for mounting the mounting target component (P) on the board (B); and a data generation unit (102) which generates production data (Dp) including component data (Dc) having the component information (d) and operation parameters (m).

Description

Production data generator, production data generation method, and program

This disclosure relates to an apparatus, a method, a program, etc. for generating production data for producing a mounting board.

A component mounting line that includes at least one component mounting device produces a mounting board by mounting components on the board. At this time, the component mounting line mounts the component on the board based on the production data. The production data includes identification information of each component mounted on the board and the mounting order of those components. In addition, the production data may include component data for each component mounted on the board. The component data includes information indicating the shape of the component to be mounted and operating parameters of the component mounting device that handles the component. The operating parameters include, for example, the suction speed of the mounting head or the mounting load of the component mounting device.

For example, in the mounting board manufacturing system of Patent Document 1, the control parameters (or machine parameters) corresponding to the operating parameters are modified based on the results of the component mounting work. As a result, the component data can be corrected appropriately and efficiently.

Japanese Unexamined Patent Publication No. 2019-4129

However, the mounting board manufacturing system of Patent Document 1 has a problem that it may be difficult to set appropriate operating parameters.

Therefore, the present disclosure provides a production data generator or the like capable of setting appropriate operating parameters.

The production data generation device according to one aspect of the present disclosure is at least one from a plurality of different learning models showing the relationship between the operating conditions of the component mounting device for mounting the component on the substrate and the component. A component for mounting the mounting target component on the board based on a model selection unit that selects one learning model, the selected at least one learning model, and component information regarding the mounting target component mounted on the board. It includes a parameter estimation unit that estimates operation parameters that are operating conditions of the mounting apparatus, and a data generation unit that generates production data including the component information and component data having the operation parameters.

It should be noted that these comprehensive or specific embodiments may be realized in a recording medium such as a system, method, integrated circuit, computer program or computer-readable CD-ROM, and the system, method, integrated circuit, computer program. And any combination of recording media may be realized. Further, the recording medium may be a non-temporary recording medium.

The production data generator of the present disclosure can set appropriate operating parameters.

Further advantages and effects in one aspect of the present disclosure will be clarified from the specification and drawings. Such advantages and / or effects are provided by some embodiments and features described herein and drawings, respectively, but not all are provided to obtain one or more identical features. No need.

FIG. 1 is a diagram showing an example of the configuration of the production system according to the first embodiment. FIG. 2 is a diagram showing an example of the configuration of the component mounting device according to the first embodiment. FIG. 3 is a diagram partially showing an example of the AA cross section in FIG. FIG. 4 is a block diagram showing each functional configuration of the production data generation device and the component mounting line according to the first embodiment. FIG. 5 is a diagram showing an example of a component library according to the first embodiment. FIG. 6 is a diagram showing an example of production data according to the first embodiment. FIG. 7A is a diagram showing an example of a plurality of learning models held in the learning model holding unit according to the first embodiment and managed in units of time. FIG. 7B is a diagram showing another example of a plurality of learning models held by the learning model holding unit according to the first embodiment and managed in units of time. FIG. 8 is a diagram showing an example of a plurality of learning models held by the learning model holding unit according to the first embodiment and managed in units of production equipment. FIG. 9A is a diagram showing an example of a plurality of learning models held in the learning model holding unit according to the first embodiment and managed in production type units. FIG. 9B is a diagram showing an example of a plurality of learning models held by the learning model holding unit according to the first embodiment and managed in the production type unit and the production equipment unit. FIG. 10A is a diagram for explaining an outline of the operation parameter estimation process according to the first embodiment. FIG. 10B is a diagram for explaining an outline of the learning process of the operation parameter model according to the first embodiment. FIG. 11 is a diagram showing an example of the overall processing according to the first embodiment. FIG. 12 is a diagram showing another example of the overall processing according to the first embodiment. FIG. 13 is a flowchart showing the processing operation of the production data generator according to the first embodiment. FIG. 14 is a diagram showing an example of the configuration of the production system according to the second embodiment. FIG. 15 is a block diagram showing the functional configurations of the production control device, the component mounting line, and the processing device according to the second embodiment. FIG. 16 is a diagram showing an example of the overall processing according to the second embodiment. FIG. 17A is a diagram showing an example of filtering information generated based on the inspection result of the mounting substrate in the second embodiment. FIG. 17B is a diagram showing an example of filtering information generated based on the mounting results of the component mounting line in the second embodiment. FIG. 18A is a diagram showing an example of filtering information generated by selection of parts in the second embodiment. FIG. 18B is a diagram showing an example of filtering information generated by selecting a substrate in the second embodiment. FIG. 19 is a flowchart showing the processing operation of the production control device according to the second embodiment.

In order to solve the above-mentioned problems, the production data generation devices according to one aspect of the present disclosure show the relationship between the operating conditions of the component mounting device for mounting the components on the substrate and the components. The mounting target is based on a model selection unit that selects at least one learning model from a plurality of different learning models, the selected at least one learning model, and component information about the mounting target component to be mounted on the board. It includes a parameter estimation unit that estimates operating parameters that are operating conditions of a component mounting device for mounting components on a board, and a data generation unit that generates production data including the component information and component data having the operating parameters. .. For example, the component information may indicate at least one of the dimensions, shape, appearance, type, and supply form for supplying the component corresponding to the component information. Further, the operation parameter may be a parameter relating to at least one of transfer, recognition, suction, and mounting of the component by the component mounting device.

As a result, at least one learning model is selected from a plurality of learning models that are different from each other and used for estimating the operation parameters, so that the possibility that an appropriate operation parameter is estimated for the mounting target component can be increased. Therefore, appropriate operating parameters can be set. Further, when the component data having such operation parameters and 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 device, a high quality mounting board is produced. be able to. That is, the quality of the mounting board can be improved.

The operation parameter may be a set of a plurality of parameters as well as one parameter. In this case, when a plurality of learning models are selected by the model selection unit, the parameter estimation unit may estimate a plurality of parameters included in the operation parameters from the selected learning models.

In addition, the production data generator further includes actual production data used by the component mounting device, including component information relating to the mounted component and actual component data having operating parameters used to mount the mounted component. The relationship is updated by the data acquisition unit that acquires the data and the learning model corresponding to the acquired actual production data among the plurality of learning models, by learning using the actual component data as the teacher data. It may be provided with a learning unit to perform.

The operating parameters of the actual parts data included in the actual production data are used for mounting the mounted parts, and corrections are made at that time. That is, its operating parameters have been modified to produce better quality mounting boards. Therefore, by using the actual component data having such an operation parameter as the teacher data for learning 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 operating parameters can be improved.

Further, each of the plurality of learning models is associated with different periods, and the learning unit may perform learning on the learning model corresponding to the period in which the actual production data is acquired.

For example, one of the learning models is associated with the entire period (eg, the entire period from the past to the present), and each of the remaining at least one learning model is associated with a different age group. .. The different ages are, for example, the 1990s, 2000s, 2010s, and the like. As a result, a learning model associated with the entire period or any age is selected from those learning models and used for estimating the operation parameters. Therefore, it is possible to estimate an appropriate operating parameter according to the period for the component to be mounted.

Further, each of the plurality of learning models is associated with different production equipment, and the learning unit learns the learning model corresponding to the production equipment including the component mounting device using the actual production data. May be good.

For example, the production equipment may be a component mounting device, one component mounting line including the component mounting device, or equipment including a plurality of component mounting lines. In this case, for example, one of the plurality of learning models is associated with the production equipment including all the component mounting lines arranged in the factory, and each of the remaining at least one learning model is different from each other. It is associated with the component mounting line. As a result, from those learning models, all the component mounting lines or the learning models associated with any of the component mounting lines are selected and used for estimating the operation parameters. Therefore, it is possible to estimate appropriate operating parameters according to the production equipment for the parts to be mounted.

Further, each of the plurality of learning models is associated with a different type of mounting board, and the learning unit learns from the learning model corresponding to the type of mounting board produced by using the actual production data. May be done.

For example, the type of mounting board is a mass production type or a prototype type. In this case, for example, one of the plurality of learning models is associated with the mass production type, and the remaining one learning model is associated with the prototype type. As a result, the learning model associated with the mass production type or the prototype type is selected from those learning models and used for estimating the operation parameters. Therefore, it is possible to estimate appropriate operating parameters according to the type of mounting board for the mounting target component.

Hereinafter, the embodiment will be specifically described with reference to the drawings.

Note that all of the embodiments described below show comprehensive or specific examples. Numerical values, shapes, materials, components, arrangement positions and connection forms of components, steps, order of steps, etc. shown in the following embodiments are examples, and are not intended to limit the present disclosure. Further, among the components in the following embodiments, the components not described in the independent claims indicating the highest level concept are described as arbitrary components.

In addition, each figure is a schematic view and is not necessarily exactly illustrated. Further, in each figure, the same components are designated by the same reference numerals.

(Embodiment 1)
[Production system]
FIG. 1 is a diagram showing an example of a configuration of a production system according to the present embodiment.

The production system 1 in the present embodiment includes three 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 mounting board production facility, and a mounting board is produced by performing solder printing work, component mounting work, reflow work, etc. on the board carried in from the upstream side. Then, the produced mounting board is carried out to the downstream side.

The production data generation device 100 generates and outputs production data for producing a mounting board for each of the component mounting lines L1 to L3. The production data generation device 100 may communicate with those component mounting lines L1 to L3 via wireless or wired. The radio may be Wi-Fi®, Bluetooth®, ZigBee, or a specified low power radio.

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 recovery device M7. .. Each device other than the line management device 200 included in the component mounting line L1 includes a board supply device M1, a board delivery device M2, a solder printing device M3, a component mounting devices M4 and M5, a reflow device M6, and a board recovery device M7. They are arranged in order and connected in series. Each device other than these line management devices 200 is hereinafter referred to as a work device. The component mounting line L1 may not include all the above-mentioned working devices as long as it includes the board supply device M1, at least one component mounting device, and the board recovery device M7. Further, the component mounting line L1 may include, in addition to the above-mentioned working device, a solder coating device for applying solder to the substrate, a component insertion machine for mounting radial components or axial components on the 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 produces the mounting board based on the production data by each work device included in the component mounting line L1. To execute.

The board supply device M1 supplies the board used for the mounting board produced on the component mounting line L1 to the solder printing device M3 via the board delivery device M2. The solder printing apparatus M3 performs the above-mentioned solder printing operation. That is, the solder printing device M3 screen-prints the solder on the board delivered from the board delivery device M2.

Each of the component mounting devices M4 and M5 executes the above-mentioned component mounting operation for mounting at least one component on the board. The component mounting line L1 includes two component mounting devices M4 and M5, but the number of the component mounting devices M4 and M5 is not limited to two, and may be one or three or more. Further, it can be said that the mounting board is substantially produced by the component mounting work by these component mounting devices M4 and M5.

The reflow device M6 performs the above-mentioned reflow work. That is, the reflow device M6 heats the substrate on which the component is mounted, which is carried in from the component mounting devices M4 and M5, cures the solder on the substrate, and joins the electrode portion of the substrate and the component. Specifically, the reflow device M6 melts and solidifies the solder for joining parts by heating according to a predetermined heating profile. As a result, the components are soldered to the substrate. The substrate recovery device M7 recovers the solder-bonded substrate from the reflow device M6.

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

[Parts mounting device]
FIG. 2 is a diagram showing an example of the configuration of the component mounting device M4. In the present embodiment, the component mounting device M5 also has the same configuration as the component mounting device M4. In the present embodiment, the transport direction of the substrate B is referred to as the X-axis direction, and the direction perpendicular to the X-axis direction is referred to as the Y-axis direction. The X-axis direction and the Y-axis direction are directions along the horizontal plane. Further, the direction perpendicular to the X-axis direction and the Y-axis direction is referred to as a Z-axis direction. The plus side and minus side in the X-axis direction are the downstream side and the upstream side in the transport direction of the substrate B, respectively, and the plus side and the minus side in the Y-axis direction are the rear side (or the back side) and the front side (or the back side) in the front-rear direction, respectively. Or the front side). The positive side and the negative side in the Z-axis direction are the upper side and the lower side in the vertical direction, respectively. In FIG. 2, the upper surface of the component mounting device M4 is shown.

The component mounting device M4 includes a base 4, a board transfer mechanism 5, two component supply units 6, two X-axis beams 9, a Y-axis beam 8, two mounting heads 10, and two component recognitions. A camera 11 and two substrate recognition cameras 12 are provided.

The board transfer mechanism 5 is provided with two rails along the X-axis direction, and is arranged in the center of the base 4. The board transfer mechanism 5 transports the board B carried in from the upstream side, and positions and holds the board B at a position for executing the component mounting operation.

The two component supply units 6 are arranged so as to sandwich the substrate transfer mechanism 5 in the Y-axis direction. A plurality of feeders 7 are arranged in parallel along the X-axis direction in each component supply unit 6. The feeder 7 supplies the component to a position where the component is taken out by the mounting head 10 (hereinafter, referred to as a component take-out position) by pitch-feeding the component tape containing the component in the tape feeding direction.

A tray feeder, a stick feeder, a bulk feeder, or the like may be arranged in the parts supply unit 6. The tray feeder supplies the parts from the tray containing the parts. The stick feeder supplies the parts from a stick case containing the parts. The bulk feeder supplies the parts from a bulk case containing the parts.

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

The mounting head 10 is mounted on each of the two X-axis beams 9 so as to be movable in the X-axis direction. The mounting head 10 includes a plurality of suction units 10a that can move up and down while sucking and holding parts. A suction nozzle 10b is provided at each tip of the suction unit 10a (see FIG. 3).

Each of the two mounting heads 10 moves in the X-axis direction and the Y-axis direction by driving the Y-axis beam 8 and the X-axis beam 9. As a result, each of the two mounting heads 10 sucks and takes out the parts from the parts taking-out position of the feeder 7 arranged in the parts supply unit 6 corresponding to the mounting heads 10 by the suction nozzle 10b, and causes the substrate transfer mechanism 5 to take out the parts. It is mounted at the mounting point (or mounting position) of the positioned board B.

Each of the two component recognition cameras 11 is arranged between one of the two component supply units 6 and the board transfer mechanism 5. The component recognition camera 11 takes an image of the component when the mounting head 10 that has taken out the component from the component supply unit 6 moves above the component recognition camera 11. That is, the component recognition camera 11 recognizes the holding posture of the component by taking an image of the component held by the mounting head 10.

The board recognition camera 12 is attached to the plate 9a to which the mounting head 10 is attached. Therefore, the board recognition camera 12 moves integrally with the mounting head 10. Such a board recognition camera 12 moves above the board B positioned by the board transfer mechanism 5 as the mounting head 10 moves, and images a board mark (not shown) provided on the board B. Recognizes the position of the substrate B. In the mounting of the component on the board B by the mounting head 10, the mounting position is corrected based on the component recognition result by the component recognition camera 11 and the position recognition result of the board B by the board recognition camera 12.

FIG. 3 is a diagram partially showing an example of the AA cross section in FIG. The component mounting device M4 has a function of mounting the component P on the substrate B.

As shown in FIG. 3, the parts supply unit 6 includes a feeder base 13a, a plurality of feeders 7 mounted on the feeder base 13a, and a carriage 13 that supports the feeder base 13a.

The dolly 13 is detachably configured with respect to the component mounting devices M4 and M5, and further includes a cassette holder 15. The cassette holder 15 is configured to be able to hold a plurality of component reels C. The component reel C stores the component tape 14 in a wound state. Each of the plurality of component reels C is held at the upper holding position Hu or the lower holding position Hd of the cassette holder 15. The component tape 14 pulled out from the component reel C held by the cassette holder 15 is attached to the feeder 7. The feeder 7 may be arranged on the feeder base 13a provided on the base 4 without using the carriage 13. Further, the dolly 13 may hold the component reel C instead of the cassette holder 15.

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

[Functional configuration of production data generator and component mounting line]
FIG. 4 is a block diagram showing each functional configuration of the production data generation device 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, and a production data holding unit DB1. It includes a learning model holding unit DB2 and a parts library holding unit DB3.

The model selection unit 103 selects at least one learning model from a plurality of learning models held in the learning model holding unit DB2.

The learning model holding unit DB2 holds the above-mentioned plurality of learning models. Each of these plurality of learning models is a different model from each other, and shows the relationship between the operating conditions of the component mounting device M4 or M5 for mounting the component P on the substrate B and the component P.

The parameter estimation unit 105 estimates the operating parameters that are the operating conditions of the component mounting device M4 or M5. That is, the parameter estimation unit 105 sets the mounting target component P on the board B based on at least one learning model selected by the model selection unit 103 and component information regarding the mounting target component P mounted on the board B. Estimate the operating parameters to implement.

The data generation unit 102 generates production data including the component data having the above-mentioned component information and operation parameters. Here, the production data indicates, for example, the mounting order of at least one component P mounted on the board B and the position where the component P is mounted on the board B (that is, the above-mentioned mounting position), and the production data thereof. Each component data of at least one component P is included. Further, the component data of each component P is held in the component library holding unit DB3. That is, the parts library holding unit DB3 holds a parts library including the parts data of each of the plurality of types of parts P. Therefore, if the component data of the component P mounted on the board B is included in the component library, the data generation unit 102 selects the component data of the component P from the component library and selects the selected component data. Generate production data that includes. On the other hand, if the component data of the component P mounted on the board B is not included in the component library, the data generation unit 102 obtains the component information of the component P and the operation parameters estimated as described above. Generate production data including parts data to have.

The data generation unit 102 generates and outputs such production data for each of the component mounting lines L1 to L3, and stores the production data in the production data holding unit DB1.

The data acquisition unit 108 includes actual production data used by the component mounting apparatus M4 or M5, including actual component data having component information regarding the mounted component P and operating parameters used for mounting the mounted component P. To get.

The actual production data is, for example, data that has been modified or tuned with respect to the production data generated by the data generation unit 102. That is, the component mounting devices M4 or M5 included in each of the component mounting lines L1 to L3 mount the component P on the board B based on the production data, but the mounting may produce a defective mounting board. .. In such a case, in each of the component mounting lines L1 to L3, the component data included in the production data is corrected or tuned so that the frequency of defective products is reduced. By such modification or tuning, actual production data including actual part data is generated. Each of the component mounting devices M4 or M5 of the component mounting lines L1 to L3 mounts the component P on the substrate B using the actual production data. The data acquisition unit 108 acquires the actual production data thus generated from each of the component mounting lines L1 to L3.

The learning unit 104 generates or updates a learning model by machine learning. Note that machine learning is simply referred to as learning below. For example, the learning unit 104 generates a learning model by learning, and stores the generated learning model in the learning model holding unit DB2. Further, the learning unit 104 selects one learning model from a plurality of learning models held in the learning model holding unit DB2, and updates the selected learning model by learning. For such learning by the learning unit 104, the actual production data used in each of the component mounting lines L1 to L3 and acquired by the data acquisition unit 108 is used.

That is, the learning unit 104 updates the relationship indicated by the learning model corresponding to the actual production data acquired by the data acquisition unit 108 among the plurality of learning models held in the learning model holding unit DB2. At this time, the learning unit 104 updates the actual component data included in the actual production data by learning using the actual component data as teacher 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 and the parts library held in the parts library holding unit DB3. Specific examples of the display unit 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, for example, input data based on an operation by an operator of the production system 1, 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. Further, the input / output unit 107 outputs data to the component mounting lines L1 to L3 and inputs data from the component mounting lines L1 to L3. The production data generated by the data generation unit 102 may be output to the component mounting lines L1 to L3 via the input / output unit 107. Further, the input / output unit 107 may acquire the above-mentioned component information based on the operation by the operator and output it 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 device 100. For example, the control unit 101 controls each component based on the input data of the operator received by the input / output unit 107.

The production data holding unit DB1, the learning model holding unit DB2, and the parts library holding unit DB3 are recording media for holding the production data, the learning model, and the parts library. For example, such a recording medium is a hard disk, a ROM (ReadOnlyMemory), a RAM (RandomAccessMemory), a semiconductor memory, or the like. In addition, such a recording medium may be volatile or non-volatile.

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 DB4. Each component other than the work mechanism 214 included in the component mounting line L1 may be provided in the line management device 200, or may be provided in any work device different from the line management device 200. ..

Like the input / output unit 107 of the production data generation device 100, the input / output unit 212 receives input data based on, for example, an operation by an operator of the production system 1, and outputs the input data to the work control unit 211. Such an input / output unit 212 may include, for example, a keyboard, a touch sensor, a touch pad, a mouse, or the like. Further, 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 generation device 100 and stores the production data in the production data holding unit DB4.

The display unit 213 displays the production data and the like held in the production data holding unit DB4. Specific examples of the display unit 213 are, but are not limited to, a liquid crystal display, a plasma display, an organic EL display, and the like.

The work mechanism 214 includes a mechanism such as a mounting head 10 and a feeder 7 for producing a mounting board.

The work control unit 211 controls each component other than the work control unit 211 included in the component mounting line L1. For example, the work control unit 211 controls each component based on the input data of the operator received by the input / output unit 212. For example, the work control unit 211 causes the work mechanism 214 to perform at least one of the above-mentioned solder printing work, component mounting work, and reflow work based on the production data held in the production data holding unit DB4. .. Further, the work control unit 211 corrects or tunes the production data held in the production data holding unit DB 4 according to the input data of the operator received by the input / output unit 212. As a result, the above-mentioned actual production data is generated. By controlling the input / output unit 212, the work control unit 211 causes the input / output unit 212 to output the actual production data to the production data generation device 100.

The production data holding unit DB4 is a recording medium for holding production data. For example, such a recording medium may be a hard disk, RAM, ROM, semiconductor memory, or the like. In addition, such a recording medium may be volatile or non-volatile.

[Parts library]
FIG. 5 is a diagram showing an example of a parts library.

The parts library consists of a plurality of parts data DCs. Each of the plurality of component data Dc is data of one type of component P, and is associated with a component code for identifying the type of the component P. Such component data Dc has component information d relating to component P and an operating parameter m which is an operating condition of the component mounting device M4 or M5 for mounting the component P on the substrate B. An image, a numerical value, a term, or the like is shown in a blank portion of each item in the component data Dc shown in FIG.

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

The shape diagram d1 illustrates the outer shape of the component P corresponding to the component data Dc. The size data d2 numerically indicates information on the size of the component P, that is, external dimensions, number of leads, lead pitch, lead length, lead width, component height, and the like.

The component parameter d3 is attribute information about the component P. Such a component parameter d3 includes a component attribute d31 which is information about the component P itself, and tape information d32 which is information about a component tape 14 for supplying the component P by the feeder 7. The component attribute d31 indicates, for example, the polarity, polarity mark, mark position, component type, and shape type of the component P. The tape information d32 includes, for example, the tape material of the component tape 14, the tape width indicating the width dimension of the component tape 14, the feed interval indicating the tape feed pitch of the component tape 14 by the feeder 7, and the color and material of the component tape 14. Contains information about.

As described above, the component information d in the present embodiment is the dimension, shape, appearance, type of the component P corresponding to the component information d, and at least one of the supply modes for supplying the component P. Shown. The supply form corresponds to, for example, tape information d32.

The operation parameter m is a machine parameter that defines an operation mode when the component mounting device M4 or M5 mounts the component P on the substrate B. 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. Further, the operation parameter m includes a speed parameter m3, recognition information m4, gap information m5, suction information m6, mounting information m7, and the like.

The speed parameter m3 includes an ascending / descending speed when the component P is sucked by the suction nozzle 10b, a mounting speed when the component P is transferred by the mounting head 10, and a tape feeding speed when the component tape 14 is fed by the feeder 7. including. The recognition information m4 is a parameter that defines the mode of component recognition. Specifically, the recognition information m4 includes a camera type indicating the type of the component recognition camera 11 to be used, an illumination mode indicating the illumination mode at the time of imaging by the component recognition camera 11, and movement of the mounting head 10 at the time of imaging. Includes recognition speed, which indicates speed. 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 substrate B.

The suction information m6 includes a suction position offset indicating an offset amount when the component P is sucked by the suction nozzle 10b, and a suction angle. The mounting information m7 indicates a pressing load when the component P sucked by the suction nozzle 10b is mounted on the substrate B as a mounting load.

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

The component information d and the operation parameter m included in the component data Dc in FIG. 5 are examples, and may indicate information other than the information shown in FIG. 5, and the information shown in FIG. 5 and others. The information may be shown together with the above information, or only a part of the information shown in FIG. 5 may be shown. Further, the number of information included in each of the component information d and the operation parameter m may be one or a plurality.

In the present embodiment, when the data generation unit 102 generates the production data, the data generation unit 102 selects the component data Dc corresponding to the component P mounted on the board B from the component library held in the component library holding unit DB3. , Generate production data including the part data Dc.

Further, if the component data Dc corresponding to the component P mounted on the board B is not 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 uses the component data Dc having the component information d acquired by the input / output unit 107 and the operation parameter m estimated by the parameter estimation unit 105 with respect to the component information d. To generate. The component information d acquired by the input / output unit 107 may be, for example, information acquired from CAD (Computer Aided Design) information regarding the component P mounted on the board B, and is input by an operator's operation. It may be information.

In addition, the default operating parameter m may be set in the component data Dc of the component library. If the default operating parameter m is set in the component data Dc selected from the component library, the data generation unit 102 causes the parameter estimation unit 105 to input the operating parameter m corresponding to the component information d included in the component data Dc to the parameter estimation unit 105. It may be estimated. 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 component 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 component data Dc in which the operation parameter m has been replaced.

Note that all the information (that is, parameters) included in the operation parameter m of the component data Dc may be the default, or only some parameters may be the default. If only some of the parameters are the default, the parameter estimation unit 105 may estimate a parameter that replaces some of the default parameters. The data generation unit 102 replaces some of the parameters of the operation parameters m included in the component data Dc with the parameters estimated by the parameter estimation unit 105. Then, the data generation unit 102 generates production data using the component data Dc in which some of the parameters have been replaced.

[Production data]
FIG. 6 is a diagram showing an example of production data Dp.

In the production data Dp, for example, the component names and component codes of the plurality of components P mounted on the board B are arranged in the mounting order of the plurality of components P. The component code of the component P is a code for specifying the component data Dc of the component P from the component library. Further, the production data Dp indicates, for each of the plurality of parts P, the mounting coordinates of the parts P, the mounting angle, the identification information of the feeder 7, and the identification information of the mounting head 10 or the suction nozzle 10b. The mounting coordinates of the component P are positions on the board B on which the component P is mounted or mounted, and are also referred to as a mounting point, a mounting position, or a mounting position. The mounting angle of the component P is an angle at which the suction nozzle 10b that sucks the component P rotates around 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 that supplies 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, in the production data Dp, for the component P that is first mounted on the substrate B, the component name "A component", the component code "C001", the mounting coordinates "x1, y1", and the mounting angle "θ1" of the component P, The identification information “F2” of the feeder 7 and the identification information “H3” of the mounting head 10 are shown.

Further, the production data Dp in the present embodiment includes the component data Dc of each of the plurality of components P mounted on the substrate B. For example, the production data Dp includes the part data Dc associated with the part code “C001” possessed by the part P having the part name “A part”.

[Learning model]
7A and 7B are diagrams showing an example of a plurality of learning models held in the learning model holding unit DB2 and managed in units of time. The learning model in this embodiment is also hereinafter referred to as an operation parameter model.

For example, each of the plurality of operation parameter models Pm11 to Pm14, which are the plurality of learning models held in the learning model holding unit DB2, is managed in units of time as shown in FIG. 7A. Specifically, the operation parameter model Pm11 is generated by learning using the actual production data used between 1990 and 1999. Similarly, the motion parameter model Pm12 is generated by learning using the performance production data used between 2000 and 2009, and the motion parameter model Pm13 is the performance production used between 2010 and the present. It is generated by learning using data. Further, the operation parameter model Pm14 is generated by learning using the actual production data used from 1990 to the present.

Further, each of the plurality of operation parameter models Pm21 to Pm25, which are the plurality of learning models held in the learning model holding unit DB2, is managed in time units as shown in FIG. 7B, and further, in chronological order. It may be managed.

For example, the operation parameter model Pm21 is generated by learning using the actual production data used on July 1, 2019. The operation parameter model Pm22 is generated by learning using the operation parameter model Pm21 and the actual production data used on July 2, 2019. That is, the operation parameter model Pm22 is generated by learning using the actual production data used between July 1st and 2nd, 2019.

Similarly, the operation parameter model Pm23 is generated by learning using the operation parameter model Pm22 and the actual production data used on July 3, 2019. That is, the operation parameter model Pm23 is generated by learning using the actual production data used between July 1st and 3rd, 2019. The operation parameter model Pm24 is generated by learning using the operation parameter model Pm22 and the actual production data used on July 4, 2019. That is, the operation parameter model Pm24 is generated by learning using the actual production data used between July 1st and 2nd and 4th of July 2019. Therefore, the operating parameter model Pm24 does not reflect the actual production data used on July 3, 2019.

The operation parameter model Pm25 is generated by learning using the operation parameter model Pm24 and the actual production data used on July 5, 2019. That is, the operation parameter model Pm25 is generated by learning using the actual production data used between July 1st and 2nd and 4th to 5th, 2019. Therefore, the operation parameter model Pm25 does not reflect the actual production data used on July 3, 2019, as in the operation parameter model Pm24.

As described above, in the present embodiment, each of the plurality of learning models (that is, the operation parameter model) is associated with different periods. In other words, multiple operating parameter models are managed on an hourly basis. In this case, when the learning unit 104 performs learning using the actual component data included in the actual production data as teacher data, the learning unit 104 learns on the learning model corresponding to the period in which the actual production data is acquired.

For example, in the example shown in FIG. 7A, when the data acquisition unit 108 of the production data generation device 100 acquires the actual production data in 2011, the learning unit 104 refers to the operation parameter models Pm13 and Pm14 corresponding to the 2011. Do learning. Further, in the example shown in FIG. 7B, when the data acquisition unit 108 acquires the actual production data on July 3, 2019, the learning unit 104 uses the operation parameter model Pm22 or the operation parameter model Pm22 corresponding to the period in which the actual production data is acquired. Learn for Pm23.

FIG. 8 is a diagram showing an example of a plurality of learning models held in the learning model holding unit DB2 and managed in units of production equipment.

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

As described above, in the present embodiment, each of the plurality of learning models (that is, the operation parameter model) is associated with different production facilities. In other words, multiple operating parameter models are managed on a production facility basis. As described above, the production equipment may be a component mounting line or a set of a plurality of component mounting lines. Further, the production equipment may be one or more component mounting devices, a floor on which a plurality of component mounting devices or component mounting lines are arranged, or a factory. In this case, when the learning unit 104 performs learning using the actual component data included in the actual production data as teacher data, the learning model corresponding to the production equipment including the component mounting device M4 or M5 using the actual production data. Learn for.

For example, in the example shown in FIG. 8, when the data acquisition unit 108 of the production data generation device 100 acquires the actual production data from the component mounting line L2, the learning unit 104 has the operation parameter model Pm32 and the operation parameter model Pm32 corresponding to the component mounting line L2. Learn for Pm34.

FIG. 9A is a diagram showing an example of a plurality of learning models held in the learning model holding unit DB2 and managed for each production type.

For example, each of the plurality of operation parameter models Pm41 to Pm44, which are the plurality of learning models held in the learning model holding unit DB2, may be managed for each production type as shown in FIG. 9A. Production types include, for example, prototype types and mass production types. The prototype type is a type of mounting board produced as a prototype, and the mass production type is a type of mounting board produced as a mass-produced product. In the prototype type, operating parameters that emphasize quality are set as compared with the mass production type, and in the mass production type, operating parameters that emphasize productivity tend to be set as compared with the prototype type. Therefore, since the operation parameters set are different between the prototype type and the mass production type even if they are the same mounting board, the estimation accuracy is improved by learning for each production type. Specifically, the operation parameter model Pm41 is generated by learning using the actual production data used in the production of the prototype type T1 mounting board. The operation parameter model Pm42 is generated by learning using the actual production data used for producing the mounting board of the prototype type T2 different from the prototype type T1. The operation parameter model Pm43 is generated by learning using the actual production data used in the production of the mass production type mounting board. Further, the operation parameter model Pm44 is generated by learning using the actual production data used for each production of the mounting boards of all production types.

FIG. 9B is a diagram showing an example of a plurality of learning models held in the learning model holding unit DB2 and managed in the production type unit and the production equipment unit.

For example, as shown in FIG. 9B, each of the plurality of operation parameter models Pm51 to Pm54, which are the plurality of learning models held in the learning model holding unit DB2, is managed for each combination of production type and production equipment. May be good. In addition, in order to manage each production type, an item for setting the production type may be provided in the part data Dc.

Specifically, the operation parameter model Pm51 is generated by learning using the actual production data used for the production of the prototype type T1 mounting board by the component mounting line L1. The operation parameter model Pm52 is generated by learning using the actual production data used in the production of the prototype type T2 mounting board by the component mounting line L2. The operation parameter model Pm53 is generated by learning using the actual production data used for the production of the mass production type mounting board by the component mounting line L3. Further, the operation parameter model Pm54 is generated by learning using the actual production data used for the production of the mounting boards of all production types by all the component mounting lines L1 to L3.

As described above, in the present embodiment, each of the plurality of learning models (that is, the operation parameter model) is associated with different production types of the mounting board. In other words, multiple learning models are managed on a production type basis. In this case, when the learning unit 104 performs learning using the actual component data included in the actual production data as teacher data, the learning unit 104 refers to the learning model corresponding to the type of the mounting board produced using the actual production data. To learn.

For example, in the example shown in FIG. 9A, when the data acquisition unit 108 of the production data generation device 100 acquires the actual production data of the prototype type T1, the learning unit 104 applies the operation parameter models Pm41 and Pm44 corresponding to the prototype type T1. Learn for it. Further, in the example shown in FIG. 9B, when the data acquisition unit 108 acquires the actual production data of the prototype type T2 from the component mounting line L2, the learning unit 104 receives the operation parameter model corresponding to the prototype type T2 and the component mounting line L2. Learning is performed for Pm52 and Pm54.

[Outline and flow of processing]
FIG. 10A is a diagram for explaining an outline of the estimation process of the operation parameter m in the present embodiment.

The parameter estimation unit 105 acquires the component information d of the component P from, for example, the input / output unit 107. Further, the model selection unit 103 selects, for example, one operation parameter model Pm from a plurality of operation parameter models Pm held in the learning model holding unit DB2. Each of the plurality of operation parameter models Pm may be any of the operation parameter models Pm11 to Pm14, Pm21 to Pm25, Pm31 to Pm34, Pm41 to Pm44, and Pm51 to Pm54 shown in FIGS. 7A to 9B. .. The parameter estimation unit 105 uses the acquired component information d and the selected operation parameter model Pm to mount the component P indicated by the component information d on the substrate B, or the component mounting device M4 or M5. The operating parameter m, which is the operating condition of, is estimated. Then, the parameter estimation unit 105 outputs the component data Dc including the estimated operation parameter m and the component information d.

For example, when a plurality of operation parameter models Pm are managed in units of time as shown in FIG. 7A, the model selection unit 103 uses one operation parameter model Pm according to the manufacturing time of the component P indicated by the component information d. May be selected. For example, if the manufacturing time is in the 1990s, 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 operation parameter model Pm14 shown in FIG. 7A. Thereby, an appropriate operation parameter model Pm for estimating the operation parameter m for the component P can be selected.

Further, when a plurality of operation parameter models Pm are managed in chronological order as shown in FIG. 7B, the model selection unit 103 may select one operation parameter model Pm updated on the latest date. Good. For example, the model selection unit 103 may select the operation parameter model Pm25 shown in FIG. 7B. Further, when many mounting boards using components similar to the component P are produced on July 3, 2019, the model selection unit 103 may select the operation parameter model Pm23 shown in FIG. 7B. Good. Thereby, an appropriate operation parameter model Pm for estimating the operation parameter m for the component P can be selected.

Further, when a plurality of operation parameter models Pm are managed in units of production equipment as shown in FIG. 8, the model selection unit 103 is associated with the production equipment that produces the mounting board using the component P. One operating parameter model Pm may be selected. For example, when the production facility that produces the mounting board using the component P is the component mounting line L2, the model selection unit 103 may select the operation parameter model Pm32 shown in FIG. Further, when the production equipment for producing the mounting board using the component P is not limited to the component mounting line L2, the model selection unit 103 may select the operation parameter model Pm34 shown in FIG. Thereby, an appropriate operation parameter model Pm for estimating the operation parameter m for the component P can be selected.

Further, when a plurality of operation parameter models Pm are managed in production type units as shown in FIG. 9A, the model selection unit 103 is associated with the production type of the mounting board produced by using the component P. One operating parameter model Pm may be selected. For example, when the production type of the mounting board produced by using the component P is a mass production type, the model selection unit 103 may select the operation parameter model Pm43 shown in FIG. 9A. Further, when the production type of the mounting board produced by using the component P is not limited to the mass production type, the model selection unit 103 may select the operation parameter model Pm44 shown in FIG. 9A. Thereby, an appropriate operation parameter model Pm for estimating the operation parameter m for the component P can be selected.

In the present embodiment, the model selection unit 103 selects one operation parameter model Pm, but is not limited to one, and selects a plurality of operation parameter models Pm for estimating different operation conditions. May be good. For example, as shown in FIG. 5, the operation parameter m includes different parameters such as the speed parameter m3 and the recognition information m4. Therefore, the model selection unit 103 may select, for example, an operation parameter model Pm for estimating the speed parameter m3 and an operation parameter model Pm for estimating the recognition information m4. In this case, the parameter estimation unit 105 estimates the speed parameter m3 by using the component information d and the operation parameter model Pm for the speed parameter m3, and uses the component information d and the operation parameter model Pm for the recognition information m4. The recognition information m4 may be estimated.

Further, the model selection unit 103 may automatically select the operation parameter model Pm as described above, or may perform the selection according to the operation of the operator to the input / output unit 107.

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

The learning unit 104 acquires actual production data from any of the component mounting lines L1 to L3 via, for example, the data acquisition unit 108. As described above, the actual production data includes the actual part data Dcu. That is, the learning unit 104 acquires the actual component data Dcu. The actual component data Dcu is the component data Dc used for mounting the component P on the substrate B by the component mounting device M4 or M5, and is the component data Dc modified by the use thereof. For example, this actual component data Dcu includes an operation parameter mu as a modified operation parameter m, and in the operation parameter mu, the suction speed, which is an operation condition, is modified from V1 to V2.

Next, the learning unit 104 selects the operation parameter model Pm corresponding to the actual component data Dcu from the plurality of operation parameter models Pm held in the learning model holding unit DB2. For example, as shown in FIGS. 7A and 7B, the learning unit 104 selects the operation parameter model Pm corresponding to the period in which the actual production data including the actual 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 equipment including the component mounting device M4 or M5 using the actual production data including the actual component data Dcu. Alternatively, as shown in FIGS. 9A and 9B, the learning unit 104 selects the operation parameter model Pm corresponding to the production type of the mounting board produced using the actual production data including the actual component data Dcu.

Then, the learning unit 104 updates the selected operation parameter model Pm by learning using the acquired actual component data Dcu as teacher data. That is, the relationship between the component information d indicated by the operating parameter model Pm and the operating conditions is updated. As a result, the operation parameter model Pmu after learning is generated. The learning unit 104 replaces the operation parameter model Pm selected as described above and held in the learning model holding unit DB2 with the operation parameter model Pmu after learning. As a result, the trained operation parameter model Pmu is stored in the learning model holding unit DB2 as a new operation parameter model Pm.

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

Similar to the example shown in FIG. 10A, the parameter estimation unit 105 estimates the operation parameter m of the component P using the operation parameter model Pm selected by the model selection unit 103, and the component information d of the component P and its operation parameters. The component data Dc including m is generated. Then, the data generation unit 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 unit 107. 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 devices 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 device 100, at least one component P is mounted on the substrate B based on the production data Dp. By doing so, the mounting board is produced. At this time, in the component mounting line L1, the component data Dc included in the production data Dp is modified so that, for example, the defect occurrence rate of the mounting board is reduced. As a specific example, the adsorption rate V1 included in the operation parameter m of the component data Dc is corrected to V2. As a result, the actual production data including the actual component data Dcu having the operation parameter mu is generated. The actual component data Dcu is stored in the component library holding unit DB3 as new component data Dc. Specifically, the data acquisition unit 108 of the production data generation device 100 acquires the actual production data from the component mounting line L1, and the actual component data Dcu included in the actual production data is used as a new component data Dc in the component library. It is stored in the holding unit DB3. Note that the component data Dc in the component mounting line L1 is not always modified, and if there is no modification, the component mounting line L1 includes the component data Dc acquired from the production data generator 100 as the actual component data Dcu. Generate actual production data.

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

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

Similar to the example shown in FIG. 10A, the parameter estimation unit 105 estimates the operation parameter m of the component P using the operation parameter model Pm selected by the model selection unit 103 for each production facility, and the component of the component P. The component data Dc including the information d and its operation parameter m is generated.

For example, the parameter estimation unit 105 estimates the operation parameter m based on the operation parameter model Pm for the component mounting line L1, that is, the operation parameter model Pm31 shown in FIG. 8, and generates the component data Dc. Then, the data generation unit 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 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 the 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 the 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 generation unit 102 generates the 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 devices M4 and M5 acquire the production data Dp from the input / output unit 107 of the production data generation device 100, at least one component P is mounted on the substrate based on the production data Dp. Implement in B. As a result, the mounting board is produced. At this time, in each of the component mounting lines L1 to L3, the component data Dc included in the production data Dp is modified so that, for example, the defect occurrence rate of the mounting board is reduced. As a result, actual production data including actual component data Dcu is generated. The actual component data Dcu is stored in the component library holding unit DB3 as new component data Dc. Specifically, the data acquisition unit 108 of the production data generation device 100 acquires the actual production data from each of the component mounting lines L1 to L3, and the actual component data Dcu included in the actual production data is used as a new component. It is stored as data Dc in the parts library holding unit DB3. It should be noted that the component data Dc in each of the component mounting lines L1 to L3 is not always modified. If there is no modification, each of the component mounting lines L1 to L3 generates actual production data including the component data Dc acquired from the production data generation device 100 as the actual component data Dcu.

When the data acquisition unit 108 acquires the actual production data of the component mounting line L1, the learning unit 104 has an operation parameter model corresponding to the actual component data Dcu included in the actual production data, as in the example shown in FIG. 10B. Pm is selected from the learning model holding unit DB2. Specifically, the learning unit 104 selects the operation parameter model Pm for the component mounting line L1, that is, the operation parameter model Pm31 shown in FIG. Then, the learning unit 104 learns the selected operation parameter model Pm by using the actual component data Dcu of the component mounting line L1. The actual 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 holding unit DB3 as described above. As a result, the learning unit 104 updates the operation parameter model Pm for the selected component mounting line L1 stored in the learning model holding unit DB2 to the learned operation parameter model Pmu for the component mounting line L1.

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

Further, when the data acquisition unit 108 acquires the actual production data of any of the component mounting lines L1 to L3, the learning unit 104 has an operation parameter model Pm for all the component mounting lines L1 to L3, that is, FIG. The operation parameter model Pm34 shown in the above may be selected. In this case, the learning unit 104 learns the selected operation parameter model Pm by using the actual component data Dcu according to any of the component mounting lines L1 to L3. The actual component data Dcu is component data Dc acquired from any of the component mounting lines L1 to L3 by the data acquisition unit 108 and stored in the component library holding unit DB3 as described above. As a result, the learning unit 104 uses the operation parameter model Pm for the selected component mounting lines L1 to L3 stored in the learning model holding unit DB2, and the learned operation parameter model Pmu for the component mounting lines L1 to L3. Update to.

The data generation unit 102 in the present embodiment may import the production data Dp from the production equipment of a factory other than the factory having the production system 1, and the production data Dp may be imported into the production equipment of the other factory. May be exported.

FIG. 13 is a flowchart showing the processing operation of the production data generation device 100 according to the present embodiment.

The input / output unit 107 of the production data generation device 100 receives the component information d (step S11). This component information d may be generated and accepted by an operation by the input / output unit 107 by the operator, or may be accepted by being selected from a plurality of component information d. Further, the input / output unit 107 selects the component data Dc having the default operation parameter m from the plurality of component data Dc included in the component library, and extracts the component information d from the component data Dc to extract the component information d. Information d may be accepted. As shown in FIG. 5, the component information d includes, for example, size data d2 and component attribute d31.

Next, the model selection unit 103 selects at least one operation parameter model Pm from the plurality of operation parameter model 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 one operation parameter model Pm selected in step S12 and the component information d received in step S11 (step S13). This operating parameter m is an operating condition of the component mounting device M4 or M5 for mounting the component P specified by the component information d on the substrate B. Then, the parameter estimation unit 105 generates the component data Dc having the component information d and the operation parameter m (step S14).

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

Then, the learning unit 104 relearns the operation parameter model Pm using the component data Dc (that is, the actual component data Dcu) included in the production data Dp used in each of the component mounting lines L1 to L3 as the teacher data. (Step S17). The operation parameter model Pm to be relearned is, for example, an operation parameter model Pm corresponding to a period in which the used production data Dp (that is, actual production data) is acquired.

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

As a result, at least one operation parameter model Pm is selected from the plurality of operation parameter models Pm and used for estimating the operation parameter m, so that there is a possibility that an appropriate operation parameter m can be estimated for the mounting target component P. Can be enhanced. Therefore, an appropriate operation parameter m can be set. Further, when the component data Dc having such an operation parameter m and the component information d is included in the production data Dp and the production data Dp is used for mounting the component P on the substrate B by the component mounting device M4 or M5. Can produce high quality mounting boards. That is, the quality of the mounting board can be improved.

Further, in the production data generation device 100 in the present embodiment, the actual production data including the actual component data Dcu used by the component mounting apparatus M4 or M5 is acquired. Then, among the plurality of operation parameter models Pm, the operation parameter model Pm corresponding to the acquired actual production data is updated by learning using the actual component data Dcu as the teacher data.

The operation parameter mu of the actual component data Dcu included in the actual production data is used for mounting the mounted component P, and at that time, corrections and the like are performed. That is, the operating parameter mu has been modified so that a better quality mounting board is produced. Therefore, by using the actual component data Dcu having such an operation parameter mu as teacher data for learning the operation parameter model Pm, it is possible to further optimize the operation parameter model Pm. As a result, when the operation parameter model Pm is selected by the model selection unit 103, the estimation accuracy of the operation parameter m can be improved.

Further, in the production data generation device 100 of the present embodiment, each of the plurality of operation parameter models Pm is associated with different periods, and the learning is performed on the operation parameter model Pm corresponding to the period in which the actual production data is acquired. It is done against.

For example, as shown in FIG. 7A, one of the operation parameter models Pm11 to Pm14, the operation parameter model Pm14, is associated with the entire period (for example, the entire period from 1990 to the present). The remaining operation parameter models Pm11 to Pm13 are associated with different age groups. The different ages are, for example, the 1990s, 2000s, 2010s, and the like. As a result, the operation parameter model Pm associated with the entire period or any age is selected from the operation parameter models Pm11 to Pm14 and used for estimating the operation parameter m. Therefore, it is possible to estimate an appropriate operation parameter m according to the period for the mounting target component P.

Further, in the production data generation device 100 according to the present embodiment, as shown in FIG. 8, each of the operation parameter models Pm31 to Pm34 is associated with different production facilities. Then, the learning is performed on the operation parameter model Pm corresponding to the production equipment including the component mounting device M4 or M5 using the actual production data.

As a result, the operation parameter model Pm associated with all the component mounting lines or any of the component mounting lines is selected from the operation parameter models Pm31 to Pm34 and used for estimating the operation parameter m. Therefore, it is possible to estimate an appropriate operation parameter m according to the production equipment for the mounting target component P.

Further, in the production data generation device 100 according to the present embodiment, as shown in FIG. 9A, the operation parameter models Pm41 to Pm44 are associated with different mounting board types. Then, the learning is performed on the operation parameter model Pm corresponding to the type of the mounting board produced using the actual production data.

Thereby, for example, the operation parameter model Pm associated with the mass production type or the prototype type is selected from the operation parameter models Pm41 to Pm44 and used for estimating the operation parameter m. Therefore, it is possible to estimate an appropriate operation parameter m according to the type of the mounting board for the mounting target component P.

Thus, in this embodiment, the operating parameter model Pm specialized for the period, the type of production equipment or mounting board, etc. can be used, and as a result, for that period, the type of production equipment or mounting board, etc. An appropriate operating parameter m can be estimated.

(Modified Example of Embodiment 1)
In the above embodiment, as shown in FIGS. 7A to 9B, a plurality of operation parameter models Pm are managed in units of time, production equipment, or production type. However, the mode of management is not limited to these, and a plurality of operation parameter models Pm may be managed in other units. Further, in the example shown in FIG. 9B, a plurality of operation parameter models Pm are managed in units of combinations of production equipment and production type, but the combinations are not limited to this, and any combination can be used. There may be.

Further, in the example shown in FIG. 7B in the above embodiment, the model selection unit 103 selects one operation parameter model Pm updated on the latest date. Here, when the defect occurrence rate of the mounting board 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 performs the operation selected earlier. The parameter model Pm may be reselected to the operating parameter model Pm updated before the latest date. Further, even in the examples shown in FIGS. 7A, 8, 9A and 9B, the model selection unit 103 may reselect the operation parameter model Pm according to, for example, the defect occurrence rate. The reselection may be performed randomly or according to a predetermined procedure.

Further, the input / output unit 107 of the production data generation device 100 in the above embodiment transfers at least one operation parameter model Pm held in the learning model holding unit DB2 to a facility other than the facility having the production system 1. You may export it. The facility may be a factory or a floor. Further, the input / output unit 107 may import at least one operation parameter model Pm from another facility and store it in the learning model holding unit DB2. As a result, the operation parameter model Pm can be further optimized. Further, the input / output unit 107 may import and export the production data Dp held in the production data holding unit DB1 and import and export the parts data Dc held in the parts library holding unit DB3. You may.

Further, the learning unit 104 of the production data generation device 100 in the above embodiment corresponds to the actual production data acquired by the data acquisition unit 108 among the plurality of operation parameter model Pm held in the learning model holding unit DB2. Learning for the motion parameter model Pm to be performed. However, the learning unit 104 may switch the operation parameter model Pm to be learned by the operation of the operator received by the input / output unit 107. As a result, 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 includes the identification information of the operation parameter model Pm used for estimating the operation parameter m and its estimation. It may be associated with the date and time. Thereby, the operation parameter m can be appropriately managed.

Further, the parameter estimation unit 105 may estimate the operation parameter m using only a part of the information without using all the information included in the component information d shown in FIG. For example, the input / output unit 107 may accept a part of the component information d that is used for estimating the operation parameter m according to the operation by the operator. When such a part of the information is received, the parameter estimation unit 105 estimates the operation parameter m using only the received part of the information. Further, the parameter estimation unit 105 may estimate only a part of the parameters without estimating all the parameters included in the operation parameter m shown in FIG. For example, the input / output unit 107 may accept the designation of some parameters to be estimated among the operation parameters m shown in FIG. 5 according to the operation by the operator. When such a part of the parameters is specified, the parameter estimation unit 105 estimates only the specified part of the operation parameters m. Further, the parameter estimation unit 105 may perform principal component analysis on all the information included in the component information d and estimate the operation parameter m according to the analysis result.

(Embodiment 2)
In the present embodiment, filtering is performed on the operation parameter mu included in the actual 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 according to the present embodiment.

The production system 2 in the present embodiment includes three component mounting lines L1 to L3, a production control device 100a, a data management device 300, and three inspection devices 401 to 403. That is, the production system 2 in the present embodiment is the component mounting devices M4 and M5 that produce the mounting board by mounting the component P on the board B, and the data management device 300 or the data management device 300 that performs processing related to the production of the mounting board. It has a processing device such as inspection devices 401 to 403.

Of the components of the present embodiment, the same components as those of the first embodiment are designated by the same reference numerals as those of the first embodiment, and detailed description thereof will be omitted.

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

The production control device 100a manages the production of the mounting board in the production system 2. Specifically, the production control device 100a has the same function as the production data generation device 100 in the first embodiment, and further has a function of filtering the operation parameter mu included in the actual production data.

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

The inspection devices 401 to 403 inspect the mounting boards produced by the component mounting lines L1 to L3, respectively. That is, the inspection device 401 inspects the mounting board of the component mounting line L1, the inspection device 402 inspects the mounting board of the component mounting line L2, and the inspection device 403 inspects the mounting board of the component mounting line L3. Further, each of the inspection devices 401 to 403 in the present embodiment is connected to the production control device 100a, generates the above-mentioned filtering information based on the inspection result of the mounting board thereof, and transfers the filtering information to the production control device 100a. Output.

Note that each of the data management device 300 and the inspection devices 401 to 403 in the present embodiment is a processing device that performs processing related to the production of the mounting board.

[Functional configuration of production control equipment, component mounting line, and processing equipment]
FIG. 15 is a block diagram showing the functional configurations of the production control device 100a, the component mounting lines L1 to L3, and the processing device. In the present embodiment, as shown in FIG. 15, the processing device 500 is composed of the data management device 300 and the inspection devices 401 to 403.

The production management device 100a is the same as the production data generation device 100 of the first embodiment, that is, the control unit 101, the data generation unit 102, the model selection unit 103, the learning unit 104, the parameter estimation unit 105, the display unit 106, and the input / output unit. It includes 107, a data acquisition unit 108, a production data holding unit DB1, a learning model holding unit DB2, and a parts library holding unit DB3. Further, the production control device 100a includes a filtering unit 109 that filters the operation parameter mu included in the actual production data.

Specifically, the data acquisition unit 108 of the production control device 100a in the present embodiment inputs the production data Dp used for the production of the mounting board by the component mounting device M4 or M5, that is, the actual production data, to the component mounting line L1. Obtained from each of ~ L3. This actual production data includes, for each of at least one type of component P, an operating parameter mu which is an operating 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 filtering unit 109 selects one or more operation parameter mu by filtering the at least one operation parameter mu included in the acquired actual production data using the filtering 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 one or more selected operation parameter mu as teacher data. This operation parameter model Pm shows the relationship between the operating conditions of the component mounting device M4 or M5 for mounting the component P on the substrate B and the component P. In the above-mentioned learning, specifically, for each of the selected one or more operation parameters mu, the actual component data Dcu including the operation parameter mu is used as the teacher data.

Further, the parameter estimation unit 105 in the present embodiment, as in the first embodiment, has an operating parameter m which is an operating condition of the component mounting device M4 or M5 for mounting the mounting target component P which has not been mounted yet on the substrate. To estimate. The estimation of the operation parameter m is performed based on the operation parameter model Pm held in the learning model holding unit DB2 and the component information d regarding the mounting target component P mounted on the substrate B.

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

The inspection device 401 includes an inspection control unit 411, an input / output unit 412, a display unit 413, an inspection mechanism 414, and an inspection data holding unit DB5.

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

The inspection mechanism 414 includes a mechanism including, for example, a camera for inspecting the mounting board, and stores inspection data indicating the inspection result in the inspection data holding unit DB5.

The inspection data holding unit DB5 is a recording medium for holding the inspection data. For example, such a recording medium may be a hard disk, RAM, ROM, semiconductor memory, or the like. In addition, such a recording medium may be volatile or non-volatile.

The display unit 413 displays the inspection data and the like held in the inspection data holding unit DB5. Specific examples of the display unit 413 are, 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 each of the input / output unit 412, the display unit 413, the inspection mechanism 414, and the inspection data holding unit DB5. For example, the inspection control unit 411 causes the inspection mechanism 414 to start the inspection of the mounting board in response to the operation by the operator received by the input / output unit 412. Further, the inspection control unit 411 according to the present embodiment generates filtering information and outputs the filtering information to the data acquisition unit 108 of the production control device 100a via the input / output unit 412.

The

inspection devices

402 and 403 also have the same configuration as the above-mentioned inspection device 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 DB6.

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

The data holding unit DB6 is a recording medium for holding data. For example, the data is filtering information. Further, such a recording medium may be a hard disk, RAM, ROM, a semiconductor memory, or the like, and may be volatile or non-volatile.

The display unit 313 displays the data and the like held in the data holding unit DB6. Specific examples of the display unit 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 each of the input / output unit 312, the display unit 313, and the data holding unit DB6. Further, the data control unit 311 in the present embodiment may generate filtering information and output it to the data acquisition unit 108 of the production control device 100a via the input / output unit 312, similarly to the inspection control unit 411 described above. Good.

For example, the data control unit 311 in the present embodiment may generate substrate identification information for identifying the substrate B as filtering information. In this case, a plurality of actual production data Dpu corresponding to a plurality of different types of mounting boards are filtered by the filtering information. Therefore, it can be said that the data management device 300 is a device that manages a plurality of actual production data Dpu corresponding to a plurality of different types of mounting boards. Alternatively, the data control unit 311 may generate one or more component identification information for identifying the type of the component P as filtering information.

[Outline of processing]
FIG. 16 is a diagram showing an example of the overall processing in the present embodiment.

In the present embodiment, as in the first embodiment, at least one production data Dp is generated, and based on the at least one production data Dp, the actual production data Dpu is output from each of the component mounting lines L1 to L3. Will be done.

The filtering unit 109 of the production control device 100a filters at least one operation parameter mu included in the actual 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 one or more operation parameters mu. Then, the filtering unit 109 stores the actual component data Dcu including the operation parameter mu for each of the selected one or more operation parameters mu in the component library holding unit DB3 as new component data Dc.

[Filtering information]
FIG. 17A is a diagram showing an example of filtering information Df generated based on the inspection result of the mounting substrate.

For example, each inspection control unit 411 of the inspection devices 401 to 403 included in the processing device 500 generates the filtering information Df shown in FIG. 17A and outputs it to the filtering unit 109.

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

More specifically, when the inspection mechanism 414 includes a camera, the inspection control unit 411 indicates the mounting quality indicating the misalignment of the mounted component P based on the image of the mounting board obtained by imaging with the camera. Calculate the index. The misalignment of the component P is the difference between the mounting position of the component P on the substrate B indicated by the image and the mounting coordinates (or mounting position) of the component P indicated by the production data Dp. For example, the inspection control unit 411 calculates a numerical value closer to 1 as the displacement of the component P is smaller, and conversely, calculates a numerical value closer to 0 as the displacement of the component P is larger as the mounting quality index. .. That is, the mounting quality index may be normalized as a numerical value in the range of 0 to 1. The mounting quality index may be referred to as a score or an evaluation value.

By calculating the mounting quality index in this way, the inspection control unit 411 generates filtering information Df indicating the mounting quality index of each of the plurality of types of components P, as shown in FIG. 17A. This filtering information Df indicates a mounting quality index for each part name and part code of the part P. For example, the filtering information Df indicates "0.95" as the mounting quality index of the type of component P specified by the component name "A component" and the component code "C001".

When the filtering unit 109 of the production control device 100a acquires the filtering information Df shown in FIG. 17A, the filtering unit 109 performs filtering using the filtering information Df. That is, the filtering unit 109 selects one or more operation parameters mu corresponding to the type of the component P whose mounting quality index is equal to or higher than the threshold value by the filtering. For example, the filtering unit 109 selects one or more operation parameters mu corresponding to the type of component P having a mounting quality index of the threshold value “0.85” or more. In the example shown in FIG. 17A, the filtering unit 109 has an operation parameter mu corresponding to the component P having the component name “A component” and the component code “C001”, and the component P having the component name “G component” and the component code “C034”. Select the operation parameter mu corresponding to. That is, the filtering unit 109 selects the actual part data Dcu of the part code "C001" and the actual part data Dcu of the part code "C034" from each of the plurality of actual production data Dpu.

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 filtering. As a result, one or more operation parameter mu corresponding to the type of component P having a good mounting state is selected by filtering and used for learning, and the operation parameter mu corresponding to the type of component P having a bad mounting state is used for learning. Not used. Therefore, it is possible to generate an operation parameter model Pm for estimating an appropriate operation parameter m for realizing a good mounting state.

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

Further, 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 it to the filtering unit 109.

That is, the data control unit 311 acquires information indicating the operating status of the component mounting devices M4 and M5 included in the component mounting line from each of the component mounting lines L1 to L3 via the input / output unit 312. The data control unit 311 generates information indicating the mounting performance index of each of at least one type of component as filtering information based on the information indicating the operating status. The mounting performance index is an index relating to an error that occurs in the component mounting devices M4 and M5 with respect to the component P due to the operation based on the actual production data Dpu by the component mounting devices M4 and M5. Shown. The implementation performance index may be referred to as a score or an evaluation value.

More specifically, the mounting performance index is an index related to errors such as a suction error of the component P caused by the component mounting devices M4 and M5, a drop of the component P, or a supply error from the feeder 7 to the mounting head 10. is there. For example, the data control unit 311 indicates the implementation performance index as a percentage. That is, the data control unit 311 calculates a numerical value closer to 0% as the mounting performance index as the number of errors decreases, and conversely, calculates a numerical value closer to 100% as the mounting performance index as the number of errors increases.

By calculating the mounting performance index in this way, the data control unit 311 generates filtering information Df indicating the mounting performance index of each of the plurality of types of components P, as shown in FIG. 17B. This filtering information Df indicates the mounting performance index for each part name and part code of the part P. For example, the filtering information Df indicates "0.5%" as the mounting quality index of the type of component P specified by the component name "A component" and the component code "C001".

When the filtering unit 109 of the production control device 100a acquires the filtering information Df shown in FIG. 17B, the filtering unit 109 performs filtering using the filtering information Df. That is, the filtering unit 109 selects one or more operation parameters mu corresponding to the type of the component P whose mounting performance index is equal to or less than the threshold value by the filtering. For example, the filtering unit 109 selects one or more operation parameters mu corresponding to the type of the component P whose mounting performance index is the threshold value “1%” or less. In the example shown in FIG. 17B, the filtering unit 109 has an operation parameter mu corresponding to the component P having the component name “A component” and the component code “C001”, and the component P having the component name “B component” and the component code “C102”. Select the operation parameter mu corresponding to. That is, the filtering unit 109 selects the actual part data Dcu of the part code "C001" and the actual part data Dcu of the part code "C102" from the plurality of actual production data Dpu.

As described above, in the present embodiment, the operation parameter mu corresponding to the type of the component P having a small mounting performance index is selected by filtering. As a result, one or more operation parameters mu corresponding to the type of component P having few errors in the component mounting device M4 or M5 are selected by filtering and used for learning, and correspond to the type of component P having many errors. The operation parameter mu is not used for learning. Therefore, it is possible to generate an operation parameter model Pm for estimating an appropriate operation parameter m for reducing the occurrence of an error.

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 generates the filtering information Df shown in (b) according to the operation result by the operator shown in (a) of FIG. 18A and outputs it to the filtering unit 109. You may.

For example, the data control unit 311 displays the component selection screen shown in FIG. 18A (a) on the display unit 313. On this component selection screen, a component name, a component code, and at least a part (for example, external dimensions and number of leads) of the component information d of each component P handled in the production system 2 are shown. The operator inputs the learning flag to the desired component P by operating the input / output unit 312 while looking at the component selection screen. For example, in the mounting board produced by mounting the component P, when the mounting state of the component P is good, the operator inputs a learning flag to the component P. Alternatively, if the part P used in the past is an exceptional special part, the operator does not input the learning flag for the part P. Further, when the operation parameter mu of the component P included in the actual production data Dpu is set in another factory, the operator does not input the learning flag for the component P. In the example shown in FIG. 18A (a), the operator inputs a learning flag for each component P of the component names “A component”, “B component”, “D component”, and “F component”. Then, the operator further operates the input / output unit 312 to select the decision button displayed on the component selection screen. As a result, the data control unit 311 generates the filtering information Df shown in FIG. 18A (b) according to the learning flag input to the component selection screen.

The filtering information Df indicates, for each learning flag input by the operator, the part name and the part code of the part P corresponding to the learning flag as the part identification information of the part P. For example, the filtering information Df contains the part name "A part" and the part code "C001", the part name "B part" and the part code "C002", and the part name "C002" as the part identification information of each of the four parts P. "D part" and part code "C003", and part name "F part" and part code "C005" are shown. In this way, the data management device 300 outputs the filtering information Df including one or more component identification information for identifying the type of the component P, respectively.

When the filtering unit 109 of the production control device 100a acquires the filtering information Df shown in FIG. 18A (b), the filtering unit 109 performs filtering using the filtering information Df. That is, in the filtering, the filtering 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 one or more component identification information indicated by the filtering information Df. In the example shown in FIG. 18A (b), the filtering unit 109 uses the actual production data Dpu of the plurality of actual production data Dpu to obtain the actual component data Dcu of the component code “C001”, the actual component data Dcu of the component code “C002”, and the component code. The actual part data Dcu of "C003" and the actual part data Dcu of the part code "C005" are selected.

As described above, in the present embodiment, the operation parameter mu corresponding to the type of the component P specified by the operation by the operator is selected by the filtering. As a result, one or more operation parameters mu corresponding to the type of the part P identified by the part identification information specified by the operator are selected by filtering and used for learning, and the operation parameters corresponding to the other types of the part P are used. mu is not used for learning. Therefore, it is possible to generate an operation parameter model Pm for estimating an appropriate operation parameter mu for a specific component P.

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

The data control unit 311 of the data management device 300 included in the processing device 500 generates the filtering information Df shown in (b) according to the operation result by the operator shown in (a) of FIG. 18B and outputs it to the filtering unit 109. You may.

For example, the data control unit 311 displays the board selection screen shown in FIG. 18B (a) on the display unit 313. On this board selection screen, a board name, a board code, auxiliary information, and the like of each board B handled by the production system 2 are shown. The operator inputs the learning flag to the desired board B by operating the input / output unit 312 while looking at the board selection screen. For example, the operator inputs a learning flag for each board B of the board names "A board", "B board", "D board", and "F board". Then, the operator further operates the input / output unit 312 to select the decision button displayed on the board selection screen. As a result, the data control unit 311 generates the filtering information Df shown in FIG. 18B (b) according to the learning flag input to the board selection screen.

The filtering information Df indicates, for each learning flag input by the operator, the board name and board code of the board B corresponding to the learning flag as board identification information of the board B. For example, the filtering information Df contains the substrate name "A substrate" and the substrate code "B001", the substrate name "B substrate" and the substrate code "B002", and the substrate name "B002" as the substrate identification information of each of the four substrates B. The "D board" and the board code "B004", and the board name "F board" and the board code "B006" are shown. In this way, the data management device 300 outputs the filtering information Df including one or more board identification information for identifying the type of the board B, respectively.

When the filtering unit 109 of the production control device 100a acquires the filtering information Df shown in FIG. 18B (b), the filtering unit 109 performs filtering using the filtering information Df. That is, when the actual production data group composed of a plurality of actual production data Dpu is acquired by the data acquisition unit 108, the filtering unit 109 starts from at least one operation parameter mu included in the actual production data group in the filtering. Select one or more operating parameters mu. Each of the one or more selected operation parameters mu corresponds to the type of component P mounted on the type of substrate B identified by the substrate identification information included in the filtering information Df.

In the example shown in FIG. 18B (b), the filtering unit 109 is a component P mounted on each board B of the board codes “B001”, “B002”, “B004” and “B006” from the actual production data group. Select the actual part data Dcu corresponding to the type of. The production data Dp and the actual production data Dpu may indicate the substrate code of the substrate B used in the production of the mounting substrate. In this case, the filtering unit 109 selects the actual production data Dpu indicating each of the board codes "B001", "B002", "B004", and "B006" from the actual production data group, and those selected actual production. The actual component data Dcu is extracted from the 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 specified by the operator is selected by the filtering. That is, one or more operation parameters mu corresponding to the type of the component P mounted on the board B specified by the operator are selected by filtering and used for learning, and the type of the component P mounted on the other board B is selected. The corresponding motion parameter mu is not used for learning. Therefore, it is possible to generate an operation parameter model Pm for estimating an appropriate operation parameter mu for a specific substrate B.

[Processing flow]
FIG. 19 is a flowchart showing a processing operation of the production control device 100a according to the present embodiment.

The data acquisition unit 108 of the production control device 100a acquires the actual 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 uses the filtering information Df acquired in step S22 to filter each operation parameter mu included in the actual production data Dpu acquired in step S21 (step S23). As a result, the operation parameter mu used for learning is selected from the actual 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 component information d included in the actual component data Dcu together with the operation parameter mu are used as teacher data. Further, in the update of the operation parameter model Pm, the operation parameter model Pm corresponding to the actual production data Dpu held in the learning model holding unit DB2 is updated.

Then, when the component P whose operation parameter m is undecided is selected by the input / output unit 107, the parameter estimation unit 105 generates or updates the operation parameter m of the selected component P in step S24. Estimate using the parameter model Pm (step S25).

As described above, in the production control device 100a in the present embodiment, the actual production data Dpu is acquired, and at least one operation parameter mu included in the acquired actual production data Dpu is filtered. That is, one or more operation parameters mu are selected from the actual production data Dpu by using the filtering information Df obtained from the processing device 500. Then, the operation parameter model Pm is generated or updated by learning using one or more selected operation parameters mu as teacher data.

As a result, one or more operation parameter mu selected by filtering is used for learning, and the operation parameter mu not selected is not used for learning, so that the operation parameter model Pm can be optimized. As a result, by using this operation parameter model Pm, an appropriate operation parameter mu can be estimated and then set in the production data Dp used in the component mounting apparatus M4 or M5. Therefore, it is possible to produce a high quality mounting board. That is, the quality of the mounting board can be improved.

That is, in the present embodiment, it is possible to control the operation parameter mu used as teacher data in learning, and it is possible to perform learning intended by the user.

Further, in the production control device 100a according to the present embodiment, the operation parameter m for mounting the mounting target component P on the substrate B is estimated based on the generated or updated operation parameter model Pm and the component information d. To. Thereby, an appropriate operation parameter m can be estimated and set for the mounting target component P.

(Modified Example of Embodiment 2)
In the above embodiment, as shown in FIGS. 18A and 18B, filtering is performed based on the specified type of component P or the type of substrate B, but filtering based on the product series of the mounting substrate may be performed. .. Further, filtering may be performed based on the date when the actual production data Dpu is acquired. For example, only the operation parameter mu included in the actual production data Dpu acquired on the latest date may be selected by filtering. In addition, filtering based on the specified component mounting line may be performed. For example, when the component mounting line L1 is specified, only the operation parameter mu included in the actual production data Dpu acquired from the component mounting line L1 may be selected by filtering.

Further, in the examples shown in FIGS. 17A and 17B, the filtering information Df indicates a mounting quality index or a mounting performance index, but these are examples and may indicate other indexes. In addition, these indices may be expressed in PPM (parts per million).

Further, in the present embodiment, it is not necessary to select at least one operation parameter model Pm from the plurality of operation parameter models Pm as in the first embodiment. That is, only one operation parameter model Pm may be held in the learning model holding unit DB2.

(Other variants)
The production data generation device, the production control device, and the like according to one or more aspects have been described above based on the embodiments and variations thereof, but the present disclosure is limited to these embodiments and variations thereof. It is not something that is done. As long as the gist of the present disclosure is not deviated, various modifications that can be conceived by those skilled in the art are applied to each embodiment or a modification thereof, and a form constructed by combining the components of each embodiment and each modification is also available. It may be included within the scope of the present disclosure.

In each of the above embodiments and modifications thereof, each component may be configured by dedicated hardware or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU (Central Processing Unit) or a processor reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory. Here, the software that realizes the devices of each of the above-described embodiments and modifications thereof is a program that causes a computer to execute each step included in the flowchart shown in FIG. 13 or FIG.

The following cases are also included in this disclosure.

(1) Each of the above devices is specifically a computer system composed of a microprocessor, a ROM, a RAM, a hard disk unit, a display unit, a keyboard, a mouse, and the like. A computer program is stored in the RAM or the hard disk unit. When the microprocessor operates according to the computer program, each device achieves its function. Here, a computer program is configured by combining a plurality of instruction codes indicating instructions to a computer in order to achieve a predetermined function.

(2) A part or all of the components constituting each of the above devices may be composed of one system LSI (Large Scale Integration: large-scale integrated circuit). A system LSI is an ultra-multifunctional LSI manufactured by integrating a plurality of components on a single 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. When the microprocessor operates according to the computer program, the system LSI achieves its function.

(3) Some or all of the components constituting each of the above devices may be composed of an IC card or a single module that can be attached to and detached from each device. The IC card or the module is a computer system composed of a microprocessor, a ROM, a RAM, and the like. The IC card or the module may include the above-mentioned super multifunctional LSI. When the microprocessor operates according to a computer program, the IC card or the module achieves its function. This IC card or this module may have tamper resistance.

(4) The present disclosure may be the method shown above. Further, it may be a computer program that realizes these methods by a computer, or it may be a digital signal composed of the computer program.

Further, the present disclosure discloses a recording medium in which the computer program or the digital signal can be read by a computer, for example, a flexible disk, a hard disk, a CD-ROM, an MO, a DVD, a DVD-ROM, a DVD-RAM, a BD (Blu-ray It may be recorded on a registered trademark) Disc), a semiconductor memory, or the like. Further, it may be the digital signal recorded on these recording media.

Further, in the present disclosure, the computer program or the digital signal may be transmitted via a telecommunication line, a wireless or wired communication line, a network typified by the Internet, data broadcasting, or the like.

Further, the present disclosure is a computer system including a microprocessor and a memory, and the memory may store the computer program, and the microprocessor may operate according to the computer program.

Further, it is carried out by another independent computer system by recording and transferring the program or the digital signal on the recording medium, or by transferring the program or the digital signal via the network or the like. May be.

(5) The above-described embodiment and the above-mentioned modification may be combined with each other.

This disclosure can be used in a system for producing a mounting board by mounting a component on a board.

1, 2 Production system 7 Feeder 10 Mounting head

10a Suction unit

10b Suction nozzle 11 Parts recognition camera 12 Board recognition camera 14 Parts tape 100 Production data generation device 100a Production control device 101 Control unit 102 Data generation unit 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 Filtering unit 200 Line management device 211 Work control unit 214 Work mechanism 300 Data management device 311 Data control unit 401 ~ 403 Inspection device 411 Inspection control unit 414 Inspection mechanism d Part information DB1, DB4 Production data holding unit DB2 Learning model holding unit DB3 Parts library holding unit DB5 Inspection data holding unit DB6 Data holding unit Dc Parts data Dcu Actual parts data Dp Production data Dpu Actual production data L1 to L3 Parts mounting line m, mu Operation parameters M4, M5 Parts mounting device

Claims

A model selection unit that selects at least one learning model from a plurality of learning models that are different from each other and show the relationship between the operating conditions of the component mounting device for mounting the component on the board and the component.
Based on the selected at least one learning model and the component information about the mounting target component mounted on the board, the operating parameters which are the operating conditions of the component mounting device for mounting the mounting target component on the board are estimated. Parameter estimation unit and
It includes a data generation unit that generates production data including the component information and component data having the operation parameters.
Production data generator.
The production data generator further
A data acquisition unit that acquires actual production data used by the component mounting device, including actual component data having component information related to the mounted component and operating parameters used for mounting the mounted component.
Among the plurality of learning models, the learning unit includes a learning unit that updates the relationship indicated by the learning model corresponding to the acquired actual production data by learning using the actual component data as teacher data.
The production data generator according to claim 1.
The part information indicates at least one of the dimensions, shape, appearance, type, and supply form for supplying the part corresponding to the part information.
The production data generator according to claim 1 or 2.
The operating parameter is a parameter relating to at least one of transfer, recognition, suction, and mounting of a component by the component mounting device.
The production data generator according to any one of claims 1 to 3.
Each of the plurality of learning models is associated with different periods from each other.
The learning unit learns from the learning model corresponding to the period in which the actual production data is acquired.
The production data generator according to claim 2.
Each of the plurality of learning models is associated with different production facilities.
The learning unit learns a learning model corresponding to a production facility including a component mounting device using the actual production data.
The production data generator according to claim 2 or 5.
Each of the plurality of learning models is associated with a different type of mounting board, and is associated with each other.
The learning unit learns a learning model corresponding to the type of mounting board produced by using the actual production data.
The production data generator according to claim 2, 5 or 6.
At least one learning model is selected from a plurality of learning models that are different from each other and show the relationship between the operating conditions of the component mounting device for mounting the component on the board and the component.
Based on the selected at least one learning model and the component information about the mounting target component mounted on the board, the operating parameters which are the operating conditions of the component mounting device for mounting the mounting target component on the board are estimated. And
Generate production data including the component information and component data having the operating parameters.
Production data generation method.
In the production data generation method, further
Acquire the actual production data used by the component mounting device, including the actual component data having the component information regarding the mounted component and the operating parameters used for mounting the mounted component.
Among the plurality of learning models, the relationship indicated by the learning model corresponding to the acquired actual production data is updated by learning using the actual component data as teacher data.
The production data generation method according to claim 8.
The part information indicates at least one of the dimensions, shape, appearance, type, and supply form for supplying the part corresponding to the part information.
The production data generation method according to claim 8 or 9.
The operating parameter is a parameter relating to at least one of transfer, recognition, suction, and mounting of a component by the component mounting device.
The production data generation method according to any one of claims 8 to 10.
Each of the plurality of learning models is associated with different periods from each other.
In the learning, learning is performed on the learning model corresponding to the period in which the actual production data is acquired.
The production data generation method according to claim 9.
Each of the plurality of learning models is associated with different production facilities.
In the learning, learning is performed on a learning model corresponding to a production facility including a component mounting device using the actual production data.
The production data generation method according to claim 9 or 12.
Each of the plurality of learning models is associated with a different type of mounting board, and is associated with each other.
In the learning, training is performed on a learning model corresponding to the type of mounting board produced using the actual production data.
The production data generation method according to claim 9, 12 or 13.
A program that causes a computer to execute the production data generation method according to any one of claims 8 to 14.