Substrate data estimation device and substrate data estimation method

Abstract

To provide a substrate data estimation device and a substrate data estimation method capable of estimating substrate data to be used for producing a mounting substrate from imperfect substrate data.SOLUTION: A substrate data estimation method for estimating substrate data to be used for producing a mounting substrate with a component mounting device includes: a learning step (ST2) of generating a learning model 19 on the basis of substrate data of a mounting substrate with a record that the mounting substrate was produced in the past (learning data 18); and a substrate data estimating step (ST3) of using the generated learning model 19 to estimate substrate data which may be used for the production (estimation substrate data 20) from imperfect substrate data (a production data library 15 or CAD data 17) of a mounting substrate to be produced.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The present invention relates to a board data estimation device and a board data estimation method for estimating board data used in the production of mounted boards by a component mounting device. [Background technology]

[0002] The component mounting device mounts components on a board to produce a mounted board, based on component information related to the components, such as the type of nozzle that picks up the components, the pickup conditions, and the imaging conditions for imaging the components with a camera, as well as board data including the mounting coordinates of the components, etc. Patent Document 1 discloses a method for simulating the mounting time required to mount components on a board, based on information (component library, mounting point data, etc.) used in the production of a mounted board by the component mounting device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2009-147018 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in conventional technologies including Patent Document 1, in order to simulate mounting time, etc., completed board data that can be used for production is required, and a simulation cannot be performed until the board data is completed. Therefore, there is room for further improvement in order to perform a simulation from an early stage of formulating a production plan.

[0005] SUMMARY OF THE PRESENT DISCLOSURE An object of the present invention is to provide a board data estimation device and a board data estimation method that are capable of estimating board data used in the production of mounted boards from incomplete board data. [Means for solving the problem]

[0006] The board data estimation device of the present invention is a board data estimation device that estimates board data used in the production of a mounted board by a component mounting device, and includes a learning unit that generates a learning model based on board data of a mounted board that has been produced in the past, and a board data estimation unit that uses the generated learning model to estimate board data that can be used in production from incomplete board data of a mounted board to be produced in the future. The board data includes mounting coordinates of components to be mounted on the mounting board and component information of the components to be mounted at the mounting coordinates, and the board data estimation unit estimates at least one of the mounting coordinates and the component information of the board data that can be used in the production. .

[0007] The board data estimation method of the present invention is a board data estimation method for estimating board data used in the production of a mounted board by a component mounting device, and includes a learning step of generating a learning model based on board data of a mounted board that has been produced in the past, and a board data estimation step of estimating board data that can be used in production from incomplete board data of a mounted board to be produced in the future, using the generated learning model. The board data includes mounting coordinates of components to be mounted on the mounting board and component information of the components to be mounted at the mounting coordinates, and in the board data estimation step, at least one of the mounting coordinates and the component information of the board data that can be used in the production is estimated. . Effect of the Invention

[0008] According to the present invention, it is possible to estimate board data to be used in producing a mounted board from incomplete board data. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a configuration explanatory diagram of a component mounting system according to an embodiment of the present invention; [Diagram 2] FIG. 1A is a diagram showing an example of a board on which components are mounted in a component mounting system according to an embodiment of the present invention; FIG. 1B is a diagram showing an example of a board on which components are mounted; [Diagram 3] FIG. 1 is a block diagram showing a configuration of a processing system of a management computer (board data estimation device) according to an embodiment of the present invention. [Figure 4] FIG. 1 is a diagram illustrating the configuration of production data used in a component mounting system according to an embodiment of the present invention; [Diagram 5] FIG. 1 is a diagram illustrating the configuration of component data used in a component mounting system according to an embodiment of the present invention; [Figure 6] FIG. 1 is an explanatory diagram of a substrate data estimation method according to an embodiment of the present invention; [Figure 7] FIG. 1A is a diagram showing an example of incomplete substrate data in a substrate data estimation method according to an embodiment of the present invention; FIG. 1B is a diagram showing an example of estimated substrate data; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] An embodiment of the present invention will be described with reference to the drawings. The configurations, shapes, etc. described below are examples for the purpose of explanation, and can be changed as appropriate according to the specifications of the component mounting system, component mounting line, management computer, component mounting device, etc. In the following, the same reference numerals are used for corresponding elements in all drawings, and duplicated explanations will be omitted.

[0011] First, the configuration of component mounting system 1 will be described with reference to Fig. 1. Component mounting system 1 has a function of mounting components on a board to produce a mounted board. In this embodiment, a configuration is adopted in which multiple (here, three) component mounting lines 4 are connected to a management computer 3 via a communication network 2. Work on each component mounting line 4 is managed by the management computer 3. Note that the number of component mounting lines 4 is not limited to three, and may be one, two, or four or more.

[0012] The management computer 3 has a function of creating data and parameters necessary for the operation of the production equipment of each component mounting line 4, and transmitting them to each production equipment. In addition, the management computer 3 has a function of simulating the productivity of mounted boards in the component mounting line 4 and formulating a production plan based on the data and parameters used in the production equipment of the component mounting line 4.

[0013] 1, component mounting line 4 is configured by connecting board supply device M1, board transfer device M2, solder printing device M3, component mounting devices M4 and M5, reflow device M6, and board removal device M7. Board B supplied by board supply device M1 is carried into solder printing device M3 via board transfer device M2, where a solder printing operation is performed in which solder for component joining is screen-printed onto lands L formed on board B (see FIG. 2(a)).

[0014] The board B after solder printing is transferred to component mounting devices M4 and M5 in sequence, where a component mounting operation is performed to mount components D on the board B after solder printing. The component mounting devices M4 and M5 take out the components D supplied by the feeder with a nozzle of the mounting head by vacuum suction, take an image of the state of the components D held by the nozzle with a component recognition camera, and mount the components at the mounting position P on the board B at a specified mounting angle (see FIG. 2(b)). The board B after component mounting is carried into the reflow device M6, where it is heated according to a specified heating profile to melt and solidify the solder for component joining. As a result, the components D are solder-bonded to the board, and a mounted board with the components D mounted on the board B is completed, and is collected by the board collection device M7.

[0015] Next, the configuration of the information processing system of the management computer 3 will be described with reference to Fig. 3. Here, among the multiple functions of the management computer 3, the configuration related to the function of estimating board data to be used in component mounting work (production of mounted boards) by component mounting devices M4 and M5 will be described. That is, the management computer 3 (board data estimation device) estimates board data that can be used for production from incomplete board data of mounted boards to be produced in the future and CAD data of board B, based on board data that has a track record of past production on the component mounting line 4.

[0016] The management computer 3 includes a processing unit 10, a storage unit 14 as a storage device, an input unit 21, a display unit 22, and a communication unit 23. The processing unit 10 is a data processing device such as a CPU, and includes a learning data creation unit 11, a learning unit 12, and a board data estimation unit 13 as internal processing units. The management computer 3 does not need to be configured as a single computer, and may be configured as a plurality of devices. For example, all or part of the storage unit and processing unit may be provided in a cloud via a server.

[0017] The input unit 21 is an input device such as a keyboard, a touch panel, a mouse, etc., and is used when inputting operation commands and data. The display unit 22 is a display device such as a liquid crystal panel, and in addition to displaying various data stored in the memory unit 14, displays various information such as an operation screen and an input screen for operation by the input unit 21. The communication unit 23 is a communication interface, and transmits and receives data to and from the production equipment (component mounting devices M4, M5) constituting the component mounting line 4 via the communication network 2.

[0018] 2, storage unit 14 stores production data library 15, component library 16, CAD data 17, learning data 18, learning model 19, estimated board data 20, etc. In production data library 15, production data used in the production of mounted boards by component mounting devices M4, M5 equipped in multiple component mounting lines 4 is stored for each production model name of the mounted board.

[0019] 4, an example of the production data 30 contained in the production data library 15 will be described. The production data library 15 includes production data 30 that has been produced in the past on multiple component mounting lines 4, as well as production data 30 that will be used in future production. Each of the multiple production data 30 contained in the production data library 15 specifies board data BD and equipment condition data 35 required to produce a mounted board of one production model name.

[0020] In the board data BD, the component name 31 of the component D to be mounted on the mounting board of the production model name, the code 32 which is a component code for associating the component with component data in the component library 16, the mounting coordinates 33 indicating the mounting position P of the component on the mounting board, and the mounting angle 34 indicating the mounting angle are defined for each component name 31 to be mounted. In this way, the board data BD includes the mounting coordinates 33 of the component D to be mounted on the mounting board, and the component information of the component D to be mounted at the mounting coordinates 33 (information included in the component data associated by the component code).

[0021] 4, the equipment condition data 35 specifies model data indicating the type of component mounting device M4, M5, supply position 36 indicating the position where the component is supplied, feeder 37 indicating the feeder used to supply the component, mounting head 38 indicating the mounting head that performs the component mounting work to mount the component, nozzle 39 indicating the nozzle used to hold the component, etc. In the example shown here, the equipment condition data 35 is included in the production data 30, but the equipment condition data 35 may be provided in the form of a separate file.

[0022] 3, a plurality of pieces of component data are stored in the component library 16, each of which associates a type of component D with operation parameters for precisely controlling various operations for mounting the component in the component mounting devices M4 and M5. The component data are associated with the board data BD included in the production data 30 by a component code.

[0023] An example of component data 40 (component information) included in the component library 16 will now be described with reference to Fig. 5. The component data 40 is associated with the production data 30 (board data BD, equipment condition data 35) by a component code 41 included in the component data 40 and a code 32 included in the production data 30. The component data 40 is composed of a shape diagram 42, size data 43, component parameters 44, and operation parameters 47. Images, numerical values, terminology, etc. are entered in the blank spaces of each item. The shape diagram 42 illustrates the external shape of the target component D. The size data 43 indicates size information of the component, i.e., external dimensions, number of leads, lead pitch, lead length, lead width, component height, etc., as numerical data.

[0024] The part parameters 44 are attribute information about the part, and include part attribute information 45, which is information about the part itself, and tape information 46, which is information about the carrier tape for feeding the part by a feeder. The part attribute information 45 indicates the polarity, polarity mark, mark position, part type, shape type, and price information of the part. The part type includes the type of the part D, such as resistor, capacitance, inductance, LSI, LED chip, and characteristic values. The tape information 46 includes the tape material of the carrier tape, the tape width indicating the width dimension of the carrier tape, the feed interval indicating the tape feed pitch, and color and material information, which is information related to the characteristics when the carrier tape is the subject of image recognition.

[0025] 5, the operation parameters 47 are machine parameters that define the operation mode when the component is the target of the component mounting work by the component mounting devices M4 and M5, that is, the mounting conditions under which the component mounting devices M4 and M5 mount the component D on the board B. In the example shown here, the operation parameters 47 include a model 47a that indicates the type of the component mounting devices M4 and M5, and a nozzle setting 47b that indicates the type of nozzle to be used. Furthermore, the operation parameters 47 include a speed parameter 47c, recognition 47d, gap 47e, suction 47f, and placement 47g.

[0026] The speed parameters 47c include the pickup speed when the nozzle picks up the component D, the mounting speed when the mounting head transports the component D, and the tape feed speed when the feeder feeds the carrier tape. The recognition parameters 47d are parameters that define the manner of component recognition, and include the camera type that indicates the type of component recognition camera to be used, the illumination mode that indicates the illumination form when capturing an image, and the recognition speed that is the nozzle movement speed when capturing an image.

[0027] 5, gap 47e includes a suction gap when component D is picked up by the nozzle, and a mounting gap when the held component D is mounted on the board B. Suction 47f specifies a suction position offset indicating an offset amount when component D is picked up by the nozzle, and a suction angle. Placement 47g specifies a pressure load when component D held by the nozzle is placed on the board B.

[0028] In this way, the component data 40 (component information) includes mounting conditions (operation parameters 47) for the component mounting devices M4, M5 to mount the components D on the mounting board. The component data 40 is also associated with the board data BD of the production data 30 by the component code 41. In this example, the board data BD and the component data 40 are provided as separate files and are associated with each other by the component code 41, but the format of the data provided is not limited to this. For example, the board data BD and the component data 40 (component information) may be provided in a file format that combines them.

[0029] 3, CAD data 17 includes the position of land L for producing board B (printed circuit board) on which component D is mounted, mounting position P, and the component name of component D to be mounted at mounting position P. Learning data creation unit 11 creates learning data 18 that associates board data BD of a mounting board that has been produced in the past with component data 40 of component D mounted on that mounting board, based on production data library 15 and component library 16. The created learning data 18 is stored in storage unit 14.

[0030] The learning unit 12 uses proven board data BD and component data 40 included in the learning data 18 as teacher data to generate a learning model 19 that estimates board data BD that can be used for production from incomplete board data BD (to be described later) by a learning algorithm using machine learning or the like. As the learning algorithm, a neural network (including deep learning using a multi-layered neural network), genetic programming, a decision tree, a Bayesian network, a support vector machine (SVM), or the like can be used. The generated learning model 19 is stored in the storage unit 14.

[0031] 3, the board data estimation unit 13 estimates (creates) board data BD (hereinafter referred to as “estimated board data”) that can be used in production from the incomplete board data BD of the mounting board to be produced, using the generated learning model 19. The created estimated board data 20 is stored in the storage unit 14.

[0032] Next, a board data estimation method for estimating board data BD used in the production of a mounted board by component mounting devices M4 and M5 from incomplete board data BD will be described with reference to Fig. 6. First, the learning data creation unit 11 creates learning data 18 by associating board data BD of a mounted board that has been produced in the past, which is included in the production data library 15, with component data 40 included in the component library 16 (ST1: learning data creation step). Next, the learning unit 12 generates a learning model 19 based on the board data BD of a mounted board that has been produced in the past, which is included in the learning data 18, and the component data 40 (ST2: learning step).

[0033] Next, the board data estimation unit 13 uses the generated learning model 19 to estimate board data BD and component data 40 that can be used for production from the incomplete board data BD of the mounted board to be produced, which is included in the production data library 15 and the CAD data 17 (ST3: board data estimation step). That is, in the board data estimation step (ST3), at least one of the mounting coordinates 33 of the board data BD that can be used for production, component information (component data 40) of the component D to be mounted on the mounting coordinates 33, and the mounting conditions (operation parameters 47 of the component data 40) under which the component mounting devices M4 and M5 mount the components D on the mounted board is estimated. The estimated board data BD is stored in the storage unit 14 as estimated board data 20.

[0034] 7, the board data estimation step (ST3) in which the board data estimation unit 13 estimates missing mounting coordinates 33 and component information based on the board data BD of an incomplete board B99 that is missing mounting coordinates 33 (mounting position P) and component information (component data 40) for at least a portion of a mounted board to be produced in the future, which is included in the production data library 15 and the CAD data 17. In Fig. 7(a) and Fig. 7(b), the board data BD of the board B99 includes the position of the land L in the left-side sufficient area Ba, the mounting position P, and component information of the component D to be mounted. However, the board data BD of the board B99 does not include the position of the land L in the right-side missing area Bb, the mounting position P, and component information of the component D to be mounted.

[0035] For example, at the stage where the detailed functions and layout of the circuit to be placed in the missing area Bb of the board B99 have not been determined, such incomplete board data BD is created. The board data estimation unit 13 uses the learning model 19 to estimate the position of the land La in the missing area Bb, the mounting position Pa, and the component Da to be mounted based on the tendency of mounted boards that have been produced on the component mounting line 4, the board data BD of a mounted board that has been produced with similar functions to the board B99, the arrangement of the land L similar to the full area Ba, and the component information of the component D to be mounted in the full area Ba. FIG. 7(c) shows the information of the full area Ba included in the board data BD of the board B99 and the information of the missing area Bb estimated by the board data estimation unit 13.

[0036] Next, referring to FIG. 2(a), the board data estimation step (ST3) will be described in which the board data estimation unit 13 estimates missing component information based on incomplete board data BD that is missing all of the component information (component data 40) of a mounting board to be produced in the future, which is included in the production data library 15 and the CAD data 17.

[0037] For example, incomplete board data BD like this is created at a stage where CAD data 17 contains information on the position of land L, mounting position P (mounting coordinates 33), and the name of the component to be mounted at mounting position P of a mounting board to be produced, but component information (component data 40) for the corresponding component D has not yet been created. Board data estimation unit 13 estimates the external dimensions, number of leads, lead pitch, etc. of size data 43 of component data 40 based on the position of land L and the number of lands L in the incomplete board data BD, the arrangement (layout) of similar lands L included in board data BD of a proven mounting board, the arrangement of component D, etc., and creates estimated board data 20 including component information.

[0038] As described above, the management computer 3 of this embodiment includes a learning unit 12 that generates a learning model 19 based on the board data BD of a mounted board that has been produced in the past, and a board data estimation unit 13 that uses the generated learning model 19 to estimate board data BD that can be used for production from incomplete board data BD of a mounted board to be produced in the future, and is a board data estimation device that estimates board data BD to be used in the production of a mounted board by component mounting devices M4 and M5. This makes it possible to estimate board data BD to be used in the production of a mounted board from incomplete board data BD. By using the estimated board data 20 estimated in this way, feedback to board design, simulation of productivity of mounted boards, and production planning can be performed at an early stage of production preparation. [Industrial Applicability]

[0039] The board data estimation device and board data estimation method of the present invention have the effect of being able to estimate board data used in the production of mounted boards from incomplete board data, and are useful in the field of mounting components on boards. [Explanation of symbols]

[0040] 3. Management computer (PCB data estimation device) 40 Parts data (parts information) BD board data M4, M5 component mounting equipment

Claims

1. A board data estimation device that estimates board data used in the production of a mounted board by a component mounting device, comprising: A learning unit that generates a learning model based on board data of mounted boards that have been produced in the past; a board data estimation unit that estimates board data that can be used for production from incomplete board data of a mounting board to be produced using the generated learning model, The board data includes mounting coordinates of components to be mounted on the mounting board and component information of the components to be mounted at the mounting coordinates, The board data estimation unit estimates at least one of the mounting coordinates and the component information of the board data that can be used for the production.

2. the incomplete board data is missing the mounting coordinates and the component information of at least a part of an area of ​​the mounting board to be produced, The board data estimating device according to claim 1 , wherein the board data estimating unit estimates the missing mounting coordinates and the missing component information.

3. The incomplete board data is missing all of the component information of the mounting board to be produced, The board data estimating device according to claim 1 , wherein the board data estimating unit predicts the missing component information.

4. the component information includes mounting conditions under which the component mounting device mounts components on a mounting board; The board data estimating device according to claim 1 , wherein the board data estimating unit also estimates the mounting conditions.

5. A board data estimation method for estimating board data used in production of a mounted board by a component mounting device, comprising: A learning process for generating a learning model based on board data of mounted boards that have been produced in the past; A board data estimation step of estimating board data that can be used for production from incomplete board data of a mounted board to be produced, using the generated learning model; The board data includes mounting coordinates of components to be mounted on the mounting board and component information of the components to be mounted at the mounting coordinates, A board data estimating method, wherein in the board data estimating step, at least one of the mounting coordinates and the component information of the board data that can be used for the production is estimated.

6. the incomplete board data is missing the mounting coordinates and the component information of at least a part of an area of ​​the mounting board to be produced, The board data estimating method according to claim 5 , wherein in the board data estimating step, the missing mounting coordinates and the missing component information are estimated.

7. The incomplete board data is missing all of the component information of the mounting board to be produced, The board data estimating method according to claim 5 , wherein in the board data estimating step, the missing component information is estimated.

8. the component information includes mounting conditions under which the component mounting device mounts components on a mounting board; 8. The board data estimating method according to claim 5, wherein the mounting conditions are also predicted in the board data estimating step.

Images