Installation condition estimation device, learning device, and installation condition estimation method

Abstract

The present invention provides an installation condition estimation device, a learning device, and an installation condition estimation method. The installation condition can be estimated with high accuracy even with a small amount of information. The installation condition estimation system (100) estimates the installation condition of an installation device (200) for installing a component (P) on a substrate (B), and comprises: an information acquisition unit (108) for acquiring a value of at least one component parameter among component parameters related to the component (P), namely, first component information; and an estimation unit (105) for estimating the installation condition based on the first component information acquired by the information acquisition unit (108).

Description

Technical Field

[0001] The present disclosure relates to an apparatus, a method, a program, and a learning apparatus for estimating mounting conditions for mounting a component on a substrate by a mounting apparatus. Background Art

[0002] The mounting device for mounting components on the substrate selects a nozzle for adsorbing and holding the component based on mounting conditions corresponding to the size and weight of the component, and determines the speed until the component is mounted on the substrate. Generally, the mounting conditions correspond to the identification information of each component mounted on the substrate.

[0003] For example, in the technology described in Patent Document 1, the motion acceleration, which is one of the mounting conditions, is calculated based on information on the component and the type of the suction nozzle that sucks and holds the component.

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Publication No. 2012-156200

[0007] However, since only CAD data of the mounting substrate exists, only part of the component information required for calculating the mounting conditions may be acquired, or only part of the component information may be acquired at different timings. Summary of the invention

[0008] To this end, the present disclosure provides a mounting condition estimation device, a learning device, a mounting condition estimation system, a mounting condition estimation method, and a program that can estimate the mounting condition using only a portion of component information.

[0009] An installation condition estimation device involved in one scheme of the present disclosure estimates the installation conditions of an installation device used to install a component on a substrate, and the installation condition estimation device comprises: a component information acquisition unit, which acquires the value of at least one component parameter among component parameters that are parameters related to the component, namely, first component information; and an estimation unit, which estimates the installation conditions based on the first component information acquired by the component information acquisition unit.

[0010] A learning device according to another embodiment of the present disclosure learns a model for estimating installation conditions of an installation device for installing a component on a substrate, the learning device comprising: a learning component information acquisition unit that acquires component information, i.e., a value of a parameter related to the component; a learning installation condition acquisition unit that acquires installation conditions corresponding to the component information acquired by the learning component information acquisition unit; and a learning unit that learns the model based on the component information acquired by the learning component information acquisition unit and the installation conditions acquired by the learning installation condition acquisition unit, the learning component information acquisition unit acquires the value of at least one component parameter among the component parameters, i.e., first component information, and the values ​​of other component parameters, i.e., second component information, the learning unit learns the first model based on the first component information acquired by the learning component information acquisition unit and the installation conditions corresponding to the first component information, and learns the second model based on the first component information, the second component information, and the installation conditions corresponding to the first component information and the second component information acquired by the learning component information acquisition unit.

[0011] In addition, these general or specific solutions can be implemented by systems, methods, integrated circuits, computer programs, or computer-readable CD-ROMs or other recording media, or by any combination of systems, methods, integrated circuits, computer programs, and recording media. In addition, the recording medium can be a non-transitory recording medium.

[0012] Effects of the Invention

[0013] According to the mounting condition estimation device of the present disclosure, even when all the component information that can be obtained is not complete, the mounting conditions can be estimated to set the mounting device.

[0014] In addition, further advantages and effects in one aspect of the present disclosure will be clear from the specification and the drawings. The relevant advantages and / or effects are provided respectively by several embodiments and the features recorded in the specification and the drawings, but it is not necessary to provide all the relevant advantages and / or effects in order to obtain one or more of the same features. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a diagram showing an example of the structure of the mounting device in the embodiment.

[0016] Figure 2 It partially expresses Figure 1 Figure AA section in.

[0017] Figure 3 It is a block diagram showing the functional structure of the installation condition estimation system in the embodiment.

[0018] Figure 4This is a diagram showing an example of a mounting condition estimation screen.

[0019] Figure 5 This is a flowchart showing the flow of the installation condition estimation system according to the present embodiment when estimating installation conditions.

[0020] Figure 6 This is a diagram showing an example of a mounting condition estimation screen on which dimensional values ​​are displayed.

[0021] Figure 7 This is a diagram showing an example of a mounting condition estimation screen displaying mounting conditions estimated based on dimensional values.

[0022] Figure 8 This is a diagram showing an example of a mounting condition estimation screen displaying the values ​​of dimensions and weight.

[0023] Fig. 9 This is a diagram showing an example of a mounting condition estimation screen displaying mounting conditions estimated based on dimension and weight values.

[0024] Fig.10 This is a diagram showing an example of a mounting condition estimation screen displaying dimension values ​​and a top view image.

[0025] Fig.11 It is a flowchart showing the process flow of the mounting device and the mounting condition estimation system.

[0026] Fig.12 It is a block diagram showing the functional structure of the installation condition estimation device.

[0027] Fig.13 It is a block diagram showing the functional structure of the learning device.

[0028] Fig.14 This is a diagram showing an example of a database used for estimation by the estimation unit.

[0029] Description of Reference Numerals

[0030] 4 abutments

[0031] 5. Substrate transport mechanism

[0032] 6. Parts Supply Department

[0033] 7 Feeder

[0034] 8 Y-axis beam

[0035] 9 X-axis beam

[0036] 9a Plate

[0037] 10 Mounting head

[0038] 10a Adsorption components

[0039] 10b Suction nozzle

[0040] 11 Parts of the Camera

[0041] 12. Substrate recognition camera

[0042] 13 Cars

[0043] 13a Feeder base

[0044] 14 Component Carrier Tape

[0045] 15 Box rack

[0046] 100 Installation Condition Estimation System

[0047] 101 Control Department

[0048] 102 Data Generation Department

[0049] 103 Model Selection Department

[0050] 104 Learning Department

[0051] 105 Estimation Department

[0052] 106 Display

[0053] 107 Input and output unit

[0054] 108 Information Acquisition Department

[0055] 110 Installation condition estimation device

[0056] 120 Learning Devices

[0057] 200 Installation

[0058] 210 Installation condition estimation screen

[0059] 211 Parts information screen

[0060] 212 Installation conditions screen

[0061] 220 Database DETAILED DESCRIPTION

[0062] In order to solve the above-mentioned problems, a mounting condition estimation device involved in one scheme of the present disclosure estimates the mounting conditions of a mounting device for mounting a component on a substrate, and comprises: a component information acquisition unit that acquires the value of at least one component parameter among the component parameters related to the component, that is, first component information; and an estimation unit that estimates the mounting conditions based on the first component information acquired by the component information acquisition unit. For example, the parameters related to the component may include at least one of the size, shape, weight, appearance, category, surface condition of the component, and the provision form for providing the component. In addition, the mounting conditions may include at least one of the type of suction nozzle for adsorbing the component in the mounting device, the transfer, recognition, adsorption, and equipment of the component, and the component information acquisition unit may acquire the measurement data obtained by the mounting device when measuring the component as at least one of the first component information and the second component information.

[0063] Thus, even at a stage where all the component information that is used as input for estimating the installation condition is not complete, the installation condition can be estimated. Therefore, the installation condition can be set for the installation device at a stage where the amount of component information is small, and productivity can be improved. In addition, production simulation can be performed at a stage where the amount of component information is small.

[0064] In addition, the component information acquisition unit may acquire the value of other component parameters related to the component, namely, second component information, and the estimation unit may include: a first model learned based on the first component information and the installation condition; and a second model learned based on the first component information, the second component information and the installation condition, estimating the installation condition based on at least one of the first component information and the second component information acquired by the component information acquisition unit.

[0065] According to this, by estimating the mounting conditions using a model corresponding to the type of the acquired component information, it is possible to estimate the optimal mounting conditions according to the amount of information of the acquired component information.

[0066] In addition, the learning device learns a model for estimating the mounting conditions of the mounting device for mounting the component on the substrate, and includes: a learning component information acquisition unit that acquires component information, which is a value of a parameter related to the component; a learning mounting condition acquisition unit that acquires mounting conditions corresponding to the component information acquired by the learning component information acquisition unit; and a learning unit that learns the model based on the component information acquired by the learning component information acquisition unit and the mounting conditions acquired by the learning mounting condition acquisition unit, wherein the learning component information acquisition unit acquires the value of at least one component parameter among the component parameters, which is the first component information, and the values ​​of other component parameters, which is the second component information, and the learning unit learns the first model based on the first component information acquired by the learning component information acquisition unit and the mounting conditions corresponding to the first component information, and learns the second model based on the first component information, the second component information, and the mounting conditions corresponding to the first component information and the second component information acquired by the learning component information acquisition unit. The learning component information acquisition unit can acquire measurement data obtained by the mounting device measuring the component as at least one of the first component information and the second component information. The measurement data can include a defect rate when the component is mounted by the mounting device.

[0067] According to this, models corresponding to the types of component information can be prepared, and therefore, the optimal mounting conditions according to the amount of information of the acquired component information can be estimated.

[0068] The following embodiments are described with reference to the accompanying drawings. In addition, the embodiments described below all represent general or specific examples. The numerical values, shapes, materials, components, configuration positions of components, connection forms, steps, order of steps, etc. shown in the following embodiments are examples and do not limit the subject matter of the present disclosure. In addition, among the components in the following embodiments, the components that are not recorded in the independent claims representing the highest concept are described as arbitrary components.

[0069] In addition, each figure is a schematic diagram and is not necessarily a strict illustration. In addition, in each figure, the same reference numeral may be attached to the same component.

[0070] Figure 1: is a diagram showing an example of the structure of the mounting device 200. In the present embodiment, the conveying 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. Furthermore, the direction perpendicular to the X-axis direction and the Y-axis direction is referred to as the Z-axis direction. The positive side and the negative side in the X-axis direction are the downstream side and the upstream side in the conveying direction of the substrate B, respectively, and the positive side and the negative side in the Y-axis direction are the rear side (or the inner side) and the front side (or the front side) in the front-to-back direction, respectively. The positive side and the negative side in the Z-axis direction are the upper side and the lower side in the up-down direction, respectively. Figure 1 The upper surface of the mounting device 200 is shown in FIG.

[0071] The mounting device 200 includes a base 4 , a substrate conveying mechanism 5 , two component supplying units 6 , two X-axis beams 9 , a Y-axis beam 8 , two mounting heads 10 , two component recognition cameras 11 , and two substrate recognition cameras 12 .

[0072] The substrate conveying mechanism 5 includes two slide rails along the X-axis direction, and is disposed at the center of the base 4. The substrate conveying mechanism 5 conveys the substrate B carried in from the upstream side, and positions and holds the substrate B at a position for performing a component mounting operation.

[0073] The two component supplying sections 6 are arranged to sandwich the substrate conveying mechanism 5 in the Y-axis direction. A plurality of feeders 7 are arranged in parallel along the X-axis direction in each component supplying section 6. The feeders 7 feed the component carrier tape containing the components by pitch feeding in the carrier tape feeding direction, and supply the components to a position (hereinafter referred to as a component taking-out position) where the mounting head 10 takes out the components.

[0074] In addition, a tray feeder, a rod feeder, or a bulk feeder may be arranged in the component supplying section 6. A tray feeder supplies components from a tray storing components. A rod feeder supplies components from a rod container storing components. A bulk feeder supplies components from a bulk container storing components.

[0075] The Y-axis beam 8 is disposed on one side of the upper surface of the base 4 in the X-axis direction ( Figure 1 The end (on the right side in the middle) is arranged along the Y-axis direction. The two X-axis beams 9 are connected to the Y-axis beam 8 so as to be movable in the Y-axis direction while being along the X-axis direction.

[0076] The two X-axis beams 9 are each provided with a mounting head 10 that is movable in the X-axis direction. The mounting head 10 includes a plurality of suction components 10a that can be raised and lowered while holding the component by suction. A suction nozzle 10b (see FIG. 1 ) is provided at the front end of each suction component 10a. Figure 2 ).

[0077] The two mounting heads 10 are respectively moved in the X-axis direction and the Y-axis direction by driving the Y-axis beam 8 and the X-axis beam 9. Thus, the two mounting heads 10 respectively suck and take out the components from the component taking-out position of the feeder 7 of the component supply unit 6 corresponding to the mounting head 10 by the suction nozzle 10b, and mount them on the mounting point (or mounting position) of the substrate B positioned on the substrate conveying mechanism 5.

[0078] The two component recognition cameras 11 are respectively arranged between one of the two component supplying sections 6 and the substrate conveying mechanism 5. The component recognition cameras 11 capture images of the components when the mounting head 10 that takes out the components from the component supplying section 6 moves above the component recognition cameras 11. That is, the component recognition cameras 11 capture images of the components held by the mounting head 10 to recognize the components and the holding posture of the components.

[0079] The substrate recognition camera 12 is mounted on the plate 9a on which the mounting head 10 is mounted. Therefore, the substrate recognition camera 12 moves together with the mounting head 10. Such a substrate recognition camera 12 moves to the upper side of the substrate B positioned on the substrate conveying mechanism 5 along with the movement of the mounting head 10, and captures a substrate mark (not shown) provided on the substrate B to recognize the position of the substrate B. During the mounting of the component on the substrate B by the mounting head 10, the mounting position is corrected based on the recognition result of the component by the component recognition camera 11 and the recognition result of the position of the substrate B by the substrate recognition camera 12.

[0080] Figure 2 It partially expresses Figure 1 The mounting device 200 has a function of mounting a component P on a substrate B.

[0081] like Figure 2 As shown, the component 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.

[0082] The trolley 13 is configured to be freely detachable relative to the base 4, and further includes a cassette rack 15. The cassette rack 15 is configured to be able to hold a plurality of component reels C. The component reels C store the component carrier tape 14 in a wound state. The plurality of component reels C are respectively held at the upper holding position Hu or the lower holding position Hd of the cassette rack 15. The component carrier tape 14 pulled out from the component reel C held by the cassette rack 15 is equipped on the feeder 7. In addition, the feeder 7 may also be configured on a feeder base 13a provided on the base 4 instead of using the trolley 13.

[0083] Figure 31 is a block diagram showing the functional structure of the installation condition estimation system 100. The installation condition estimation system 100 is a system having both the function of an installation condition estimation device and the function of a learning device, and includes a control unit 101, a data generation unit 102, a model selection unit 103, a learning unit 104, an estimation unit 105, a display unit 106, an input / output unit 107, an information acquisition unit 108, an installation condition storage unit DB1, and a model storage unit DB2.

[0084] The model selection unit 103 selects an appropriate model corresponding to the type of component information (component parameter) obtained from a plurality of learned models including the first model and the second model stored in the model storage unit DB2. In the case of the present embodiment, it is explained that the component parameters include four parameters, namely, size, weight, friction coefficient, and defective rate obtained from the top view image, and the mounting condition estimation system 100 includes the first model to the eighth model corresponding to the combination of these parameters.

[0085] The model holding unit DB2 holds at least the first model and the second model. In the case of the present embodiment, the model holding unit DB2 holds eight models, namely the first model to the eighth model. These multiple learned models can be models of different types or models of the same type. Models (algorithms) can exemplify regression models such as linear regression, logistic regression, support vector machines, etc., tree models such as decision trees, random forests, neural networks, etc. For example, a model that can estimate appropriate installation conditions even when the number of input component parameters is small can be used as the first model, and a model that is suitable for situations where more types of component parameters are input than the first model can be used as the second model.

[0086] The information acquisition unit 108 is a processing unit that functions as a component information acquisition unit, a learning component information acquisition unit, and a learning mounting condition acquisition unit. When the information acquisition unit 108 functions as a component information acquisition unit, the information acquisition unit 108 acquires the value of at least one component parameter among the component parameters that are parameters related to the component P from CAD data, measurement values ​​measured in the mounting device 200, and the like, that is, first component information. Furthermore, there is also a case where the value of another component parameter related to the component P, that is, second component information, is acquired. The timing at which the information acquisition unit 108 acquires the first component information and the second component information may be the same, or the second component information may be acquired at a timing that lags behind the first component information.

[0087] When the information acquisition unit 108 functions as a learning component information acquisition unit, the information acquisition unit 108 acquires first component information and second component information related to the component P from the mounting data storage unit DB1 or the like. The information acquisition unit 108 outputs the acquired component information to the learning unit 104 .

[0088] When the information acquisition unit 108 functions as a learned mounting condition acquisition unit, the information acquisition unit 108 acquires mounting conditions corresponding to component information from the mounting data storage unit DB1 etc. The information acquisition unit 108 outputs the acquired mounting conditions to the learning unit 104 in association with the component information.

[0089] The input / output unit 107 receives input data based on, for example, an operator's operation, and outputs the input data to the control unit 101. Such an input / output unit 107 may include, for example, a keyboard, a touch sensor, a touch panel, or a mouse.

[0090] In addition, the input / output unit 107 also includes an interface for outputting data to and inputting data from the installation device 200. The installation data generated by the data generation unit 102 can be output to the installation device 200 via the input / output unit 107, and the actual performance of the installation conditions can be input from the installation device 200 or the installation simulator.

[0091] The estimation unit 105 estimates the mounting conditions of the mounting device 200. In the case of the present embodiment, the estimation unit 105 estimates the mounting conditions for mounting the component P on the substrate B based on the model selected by the model selection unit 103 and taking the component information related to the component P mounted on the substrate B as input. In addition, a specific estimation method by the estimation unit 105 will be described later.

[0092] The data generating unit 102 generates mounting data for mounting the components P on the substrate B using the mounting conditions estimated by the estimating unit 105, the mounting conditions adjusted by the operator, etc., the actual mounting conditions, etc. The mounting data includes, for example, the types of components P to be mounted on the substrate B, the mounting order, and the mounting positions of the components P on the substrate B.

[0093] The installation data may include component information corresponding to the component P. In the case of the present embodiment, the installation data is stored in the installation data storage unit DB1. The installation data is stored in a state where component information of each of a plurality of types of components P is associated with the installation conditions. Therefore, when installation data related to the same type of component P as the component P whose installation conditions are estimated by the estimation unit 105 is stored, the data generation unit 102 updates the installation data. On the other hand, when there is no installation data corresponding to the same type of component P, new data is added to the installation data.

[0094] There are cases where the mounting conditions included in the mounting data generated by the data generation unit 102 are corrected or adjusted based on the actual performance of the mounting conditions obtained from the mounting device 200. That is, the mounting device 200 mounts the component P on the substrate B based on the mounting conditions estimated by the estimation unit 105, but there are cases where a defective mounting substrate is produced due to the mounting. In such a case, the mounting device 200 corrects or adjusts the component data included in the mounting conditions so that the frequency of defective products is reduced. There are cases where the mounting data is updated by such correction or adjustment.

[0095] The learning unit 104 learns the model including the first model and the second model. In the case of the present embodiment, the learning unit 104 learns the model by supervised learning. The learning unit 104 uses the first component information acquired from the installation data or the like by the information acquisition unit functioning as the component information acquisition unit as input information, and uses the installation conditions corresponding to the first component information as supervised information to learn the first model. In addition, the learning unit 104 uses the first component information and the second component information as input information, and uses the installation conditions corresponding to the first component information and the second component information as supervised information to learn the second model.

[0096] Furthermore, when other models are stored in the model storage DB2, the learning unit 104 may perform learning using component information and mounting conditions corresponding to the model.

[0097] The control unit 101 controls each component other than the control unit 101 included in the mounting condition estimation system 100. For example, the control unit 101 controls each component based on input data of an operator received by the input / output unit 107, and the like.

[0098] The installation data storage unit DB1 and the model storage unit DB2 are recording media for storing installation conditions and models, respectively. For example, such recording media are hard disks, RAM (Read Only Memory), ROM (Random Access Memory), or semiconductor memories. In addition, such recording media may be volatile or non-volatile.

[0099] The display unit 106 displays the component information acquired by the information acquisition unit 108 and the mounting conditions which are the results estimated by the estimation unit 105. The type of the display unit 106 is not particularly limited, and a liquid crystal display can be exemplified, for example.

[0100] Figure 42 is a diagram showing an example of the installation condition estimation screen 210. The installation condition estimation screen 210 displayed on the display unit 106 includes a component information screen 211 for presenting component information and an installation condition screen 212 for presenting estimated installation conditions.

[0101] As parameters related to the component P, there are size, shape, weight, appearance, type, surface state, and provision form, etc., but in the case of this embodiment, all the component parameters related to the component P are length L, width W, height T, weight as the size, friction coefficient as the surface state, and top view image as the appearance. In addition, the top view image is used when estimating the type and type of the component by image matching, etc.

[0102] As installation parameters for installing the component P, there are the type of suction nozzle for suction, the transfer, recognition, suction, and equipment of the component, but in the case of this embodiment, all installation parameters related to the component P are the type of suction nozzle and the equipment conditions including the transfer and equipment of the component. In addition, the so-called equipment condition is a parameter indicating the speed state at which the component is transferred and equipped with respect to a predetermined specified value.

[0103] Next, a method of estimating the installation conditions will be described. Figure 5 It is a flowchart showing the process when the installation condition estimation system 100 involved in this embodiment estimates the installation conditions. The information acquisition unit 108 functions as a component information acquisition unit, and obtains component information related to the component P from CAD data, the input and output unit 107, etc. (S101). If the operator presses the estimate button in the installation condition estimation screen 210 displayed by the display unit 106 (S102 "Yes"), it is determined whether there is a value of the dimension of one of the component parameters (in the case of this embodiment, it is the first component information) (S103). In the case where there is no value of the dimension (S103 "No"), an error message is displayed (S104) and the processing is terminated. On the other hand, in the case where there is a value of the dimension (S103 "Yes"), it is determined whether there is only the value of the dimension in the component information or whether there are other values ​​(S105). When the component information obtained is as follows: Figure 6 If only the size is shown (S105 "Yes"), estimation is performed using the first model learned using the size value and the installation condition (S106), as shown in Figure 7 As shown in FIG. 1 , the installation condition as the estimation result is displayed on the display unit 106 ( S107 ).

[0104] Next, the acquired component information contains information other than size (S105 "No") and the value of weight other than the size value (in the case of the present embodiment, the second component information) (S108 "Yes") and if Figure 8When only the size and weight values ​​exist as shown (S109 "Yes"), estimation is performed by using the size and weight values ​​and the second model learned based on the installation conditions (S110), as shown in FIG. Fig. 9 As shown in FIG. 1 , the installation condition as the estimated result is displayed on the display unit 106 (S107). Here, the weight of the component P can be the result actually measured by the installation device 200. Alternatively, the weight of the component P measured by the operator input via the input / output unit 107 can be used. The type of nozzle as the estimated installation condition is different from the result estimated by the first model. That is, a more appropriate installation condition is estimated by the second model.

[0105] Next, if there is no weight value (S108 “No”) or friction coefficient value (the third component information in the present embodiment) other than the size value (S111 “No”), then the Fig. 9 The top view image shown in FIG. 1 is used to derive the defect rate, and the estimation is performed by using the third model learned by using the values ​​of the size and defect rate (the fourth component information in the present embodiment) and the mounting conditions (S112). Fig.10 As shown in FIG. 1 , the mounting condition as the estimation result is displayed on the display unit 106 (S107). Here, the top view image of the component P can be obtained, for example, by the substrate recognition camera 12 of the mounting device 200. The mounting condition as the estimation result based on the combination of component parameters this time, i.e., the equipment condition is reduced to 80%. It is considered that this is because the defective rate of the component P is reflected in the estimation result, and the mounting condition of the component P that is held by suction by the suction nozzle is transferred more slowly due to the high defective rate.

[0106] Next, when there is no weight value other than the dimension value (S108 "No"), there is a friction coefficient value (S111 "Yes"), and there is no component information other than the dimension and friction coefficient values ​​(S113 "Yes"), an estimation is performed using the fourth model learned using the dimension and friction coefficient values ​​and the installation conditions (S114), and the estimation result, i.e., the installation conditions, is displayed on the display unit 106 (S107).

[0107] Next, when there is no weight value other than the dimension value (S108 "No"), there is a friction coefficient value (S111 "Yes"), or there is component information other than the dimension and friction coefficient values ​​(S113 "No"), an estimation is performed using the fifth model learned using the dimension, friction coefficient, and defective rate values ​​and installation conditions (S115), and the estimation result, i.e., the installation conditions, is displayed on the display unit 106 (S107).

[0108] Next, when there is a weight value in addition to the dimension value (S108 "Yes") and there are values ​​other than the dimension and weight (S109 "No") and there is no friction coefficient value (S116 "No"), an estimation is performed using the sixth model learned using the dimension, weight and defective rate values ​​and the installation conditions (S118), and the installation conditions as the estimation results are displayed on the display unit 106 (S107).

[0109] Next, when there is a weight value in addition to the dimension value (S108 "Yes"), there are values ​​other than the dimension and weight (S109 "No"), there is a friction coefficient value (S116 "Yes"), or there are only dimension, weight, and friction coefficient values ​​(S117 "Yes"), an estimation is performed using the seventh model learned using the dimension, weight, and friction coefficient values ​​and installation conditions (S119), and the installation conditions as the estimation results are displayed on the display unit 106 (S107).

[0110] Next, when there is a weight value in addition to the dimension value (S108 "Yes"), there is a value other than the dimension and weight (S109 "No"), there is a friction coefficient value (S116 "Yes"), and there are values ​​other than the dimension, weight, and friction coefficient (S117 "No"), an estimation is performed using the eighth model learned using the dimension, weight, friction coefficient, and defective rate values ​​and the installation conditions (S120), and the installation conditions as the estimation results are displayed on the display unit 106 (S107).

[0111] Next, the flow of processing by the mounting apparatus 200 and the mounting condition estimation system 100 in production of a mounting substrate will be described. Fig.11 It is a flowchart showing the process flow of the mounting device and the mounting condition estimation system.

[0112] In the mounting device 200, production of the mounting substrate is started (S201). The mounting data generated based on the result estimated by the mounting condition estimation system 100 is used in the production of the mounting substrate. If a timing at which the component parameters can be measured occurs during the production of the plurality of components P being sequentially mounted on the substrate B (S202 "Yes"), the mounting device 200 performs measurement of the component P (S203). For example, in the case of measuring the weight of the component P, the identification mark (e.g., Figure 6 The component name AX) shown in the figure and the weight value are associated and output, and the information acquisition unit 108 of the mounting condition estimation system 100 functions as a component information acquisition unit to acquire the weight value (S204).

[0113] The installation condition estimation system 100, which has obtained the weight value as the component information, estimates the value including the weight for the component name AX, and resets the installation condition of the estimation result to the new installation data (S205). After that, the component name AX is installed with the new installation condition. The above process is repeated until the production is completed (S206 "No").

[0114] When the production of the mounting substrate is completed (S206: Yes), the mounting results are summarized (S207). The summary of the mounting results includes the collection of mounting conditions adjusted by the operator during production, the defective rate of each component P, etc.

[0115] The component information including the measured value and the defective rate is associated with the actual performance of the mounting condition and outputted, and the information acquisition unit 108 of the mounting condition estimation system 100 functions as a learned component information acquisition unit and a learned mounting condition acquisition unit to acquire the actual performance mounting information (S208).

[0116] The installation condition estimation system 100 updates the installation data stored in the installation data storage unit DB1 based on the new actual installation information (S209). In addition, the installation condition estimation system 100 relearns each model based on the new actual installation information (S210).

[0117] In addition, the present invention is not limited to the above-mentioned embodiments. For example, the constituent elements described in this specification may be arbitrarily combined, and other embodiments realized by removing some of the constituent elements may be used as embodiments of the present invention. In addition, for the above-mentioned embodiments, various modifications that can be thought of by those skilled in the art within the meaning of the words and phrases described in the scope of the claims without departing from the gist of the present invention are also included in the present invention.

[0118] For example, the installation condition estimation system 100 that performs machine learning of a model and estimates the installation condition is described as an example, but it can also be separated into Fig.12 The installation condition estimation device 110 for estimating the installation condition as shown in FIG. Fig.13 The learning device 120 performs machine learning of the model as shown. In this case, the information acquisition unit 108 of the mounting condition estimation device 110 functions as a component information acquisition unit. The information acquisition unit 108 of the learning device 120 functions as a learned component information acquisition unit and a learned mounting condition acquisition unit.

[0119] In addition, the installation condition estimation system 100 and the installation condition estimation device 110 are described as having a data generation unit 102 and an installation data holding unit DB1, but at least one of the installation condition estimation system 100 and the installation condition estimation device 110 may be included in the installation device 200 or other higher-level computers.

[0120] In addition, in the above-mentioned embodiment, the case where the installation condition is estimated based on the model obtained by machine learning is described, but the estimation unit 105 may also be as follows. Fig.14 As shown, the installation condition is estimated based on the database 220 in which the component information and the installation condition are associated for each component name. Specifically, for example, when the information acquisition unit 108 only obtains the value of the dimension for the component name AX, the estimation unit 105 may determine the value of the dimension with the highest similarity from the database 220, and estimate the installation condition associated with the determined value of the dimension as the installation condition of the component name AX. In addition, when the value of the weight of the component name AX is obtained by measurement, etc., the installation condition associated with the weight value with the highest similarity can be estimated as the installation condition of the component name AX from the installation conditions associated with the value of the dimension with a similarity of more than a first threshold value with respect to the value of the dimension. Furthermore, the installation condition of the component name AX may be estimated based on the similarity of the friction coefficient and the top view image.

[0121] In addition, as the measuring device provided in the mounting device 200, the component recognition camera 11, the substrate recognition camera 12, and the weight measuring device are exemplified, but other examples include a height sensor for measuring the height of the component P, a three-dimensional measuring device for measuring the three-dimensional shape of the component P, and the like. In addition, these measured values ​​can be used as one of the component information.

[0122] In addition, although the installation device 200 and the installation condition estimation system 100 are described in a one-to-one state, multiple installation devices 200 can be connected to each other so as to be communicable with respect to one installation condition estimation system 100. The so-called communicable connection also includes a connection via a public line such as the Internet. By collecting actual installation conditions from multiple installation devices 200, a database 220 rich in information can be constructed, or a machine learning model can be learned based on a large amount of information, and the estimation accuracy of the installation conditions can be improved.

[0123] Furthermore, a plurality of installation condition estimation devices 110 may be communicatively connected to one learning device 120 , and the plurality of installation condition estimation devices 110 may estimate the installation conditions using the same learned model or database 220 .

[0124] In addition, the following cases are also included in the present disclosure.

[0125] (1) Each of the above-mentioned devices is specifically a computer system including a microprocessor, ROM, RAM, hard disk assembly, display assembly, keyboard, mouse, etc. A computer program is stored in the RAM or hard disk assembly. Each device achieves its function by the microprocessor operating according to the computer program. Here, the computer program is composed of a combination of multiple command codes representing instructions to the computer in order to achieve a given function.

[0126] (2) Some or all of the components constituting each of the above-mentioned devices may include a system LSI (Large Scale Integration). A system LSI is a multifunctional LSI manufactured by integrating multiple components on a single chip, and specifically, is a computer system including a microprocessor, ROM, RAM, etc. A computer program is stored in the RAM. The microprocessor operates according to the computer program, and the system LSI achieves its function.

[0127] (3) A part or all of the components constituting each of the above-mentioned devices may include an IC card or a single module that can be detached from each device. The IC card or the module is a computer system including a microprocessor, ROM, RAM, etc. The IC card or the module may include the above-mentioned ultra-multifunctional LSI. The IC card or the module achieves its function by the microprocessor operating according to the computer program. The IC card or the module may be tamper-resistant.

[0128] (4) The present disclosure may be the methods described above. In addition, the present disclosure may be a computer program that implements the methods on a computer, or a digital signal including the computer program.

[0129] In addition, the present disclosure may be set as a scheme in which the computer program or the digital signal is recorded on a computer-readable recording medium such as a floppy disk, a hard disk, a CD-ROM, an MO, a DVD, a DVD-ROM, a DVD-RAM, a BD (Blu-ray (registered trademark) Disc), a semiconductor memory, etc. In addition, it may be set as the digital signal recorded on these recording media.

[0130] In addition, the present disclosure may be implemented as a mode in which the computer program or the digital signal is transmitted via a telecommunication line, a wireless or wired communication line, a network represented by the Internet, data broadcasting, or the like.

[0131] Furthermore, the present disclosure may be a computer system including a microprocessor and a memory, wherein the memory stores the computer program and the microprocessor operates according to the computer program.

[0132] Furthermore, the program or the digital signal may be recorded on the recording medium and transferred, or the program or the digital signal may be transferred via the network or the like, so that the program or the digital signal can be implemented by another independent computer system.

[0133] (5) The above-described embodiments and modifications may be combined.

[0134] Industrial Applicability

[0135] The present disclosure can be utilized in a system for producing a mounting substrate by mounting components on a substrate, and the like.

Claims

1. A mounting condition estimation device for estimating mounting conditions of a mounting device for mounting a component on a substrate, the mounting condition estimation device comprising: a component information acquisition unit that acquires first component information that is a value of at least one component parameter among component parameters related to the component; and an estimating unit that estimates a mounting condition based on the first component information acquired by the component information acquiring unit, The component information acquisition unit acquires the value of another component parameter related to the component, that is, second component information, The estimation unit includes: a first model learned based on first component information and mounting conditions; and a second model learned based on the first component information, the second component information, and mounting conditions, and the estimation unit estimates the mounting conditions based on the first component information and the second component information acquired by the component information acquisition unit.

2. The installation condition estimation device according to claim 1, wherein: The parameters related to the component include at least one of the size, shape, weight, appearance, type, surface state of the component and a provision form for providing the component.

3. The installation condition estimation device according to claim 1, wherein: The mounting conditions include at least one of information related to the type of a suction nozzle that sucks the component in the mounting device, and the transfer, recognition, suction, and equipment of the component.

4. The installation condition estimation device according to claim 1, wherein: The component information acquisition unit acquires measurement data obtained by measuring the component by the mounting device as at least one of first component information and second component information.

5. A learning device for learning a model for estimating mounting conditions of a mounting device for mounting a component on a substrate, the learning device comprising: a learning component information acquisition unit that acquires component information that is a value of a parameter related to the component; a learned installation condition acquisition unit that acquires an installation condition corresponding to the component information acquired by the learned component information acquisition unit; and a learning unit that causes a model to learn based on the component information acquired by the learning component information acquisition unit and the installation conditions acquired by the learning installation condition acquisition unit, The learned component information acquisition unit acquires a value of at least one component parameter among the component parameters, namely, first component information, and a value of another component parameter, namely, second component information. The learning unit learns the first model based on the first component information obtained by the learning component information acquisition unit and the installation conditions corresponding to the first component information, and learns the second model based on the first component information, the second component information, and the installation conditions corresponding to the first component information and the second component information obtained by the learning component information acquisition unit.

6. The learning device according to claim 5, wherein: The learned component information acquisition unit acquires measurement data obtained by measuring the component by the mounting device as at least one of the first component information and the second component information.

7. The learning device according to claim 6, wherein: The measurement data includes a defective rate when the component is mounted by the mounting device.

8. A system for estimating installation conditions, comprising: The installation condition estimation device according to claim 1 or 2; and The learning device according to any one of claims 5 to 7.

9. A method for estimating mounting conditions, comprising estimating mounting conditions of a mounting device for mounting a component on a substrate, The component information acquisition unit acquires first component information which is a value of at least one component parameter among component parameters related to the component. the estimating unit estimates the mounting condition based on the first component information acquired by the component information acquiring unit, The component information acquisition unit acquires the value of another component parameter related to the component, that is, second component information, The estimation unit includes: a first model learned based on first component information and mounting conditions; and a second model learned based on the first component information, the second component information, and mounting conditions, and the estimation unit estimates the mounting conditions based on the first component information and the second component information acquired by the component information acquisition unit.

Images