JP7531153B2 - Operation parameter creating device and operation parameter creating method - Google Patents

Description

The present invention relates to an operating parameter creation device and an operating parameter creation method that create operating parameters for a component mounting device to mount components on a board.

The component mounting device that mounts components on a board controls the component mounting operation based on operating parameters including many parameters related to component suction by the nozzle, component shape recognition, and component mounting on the board. Appropriate values for these operating parameters are set for each component. Patent Document 1 describes the calculation of parameters such as appropriate operating acceleration for the head based on the ratio between the input mass of the component and the area of the suction hole of the nozzle that picks up the component.

JP 2012-156200 A

However, while conventional technologies including Patent Document 1 can calculate generic operating parameters for a variety of components from a small amount of input information, when there is an important component that requires high mounting accuracy, there is no guarantee that optimal operating parameters will be created for this component, and there is room for further improvement in creating optimal operating parameters according to the priority of various components.

The present invention aims to provide an operating parameter creation device and an operating parameter creation method that can create optimal operating parameters according to the priority of parts.

The operational parameter creation device of the present invention is an operational parameter creation device that creates operational parameters for a component mounting device to mount a component on a board, and includes an information acquisition unit that acquires component information including component shape information, operational parameters, and a priority of the high mounting accuracy required for the component, a learning data creation unit that creates learning data based on the component information by weighting according to the priority of the high mounting accuracy required for the component , a learning unit that generates or updates a learning model based on the learning data, and an operational parameter creation unit that creates operational parameters from the component shape information using the generated or updated learning model.

The operating parameter creation method of the present invention is an operating parameter creation method for creating operating parameters for a component mounting device to mount a component on a board, and includes the steps of: acquiring component information including component shape information, operating parameters, and a priority of the high mounting accuracy required for the component; creating learning data based on the component information by weighting according to the priority of the high mounting accuracy required for the component ; generating or updating a learning model based on the learning data; and creating operating parameters from the component shape information using the generated or updated learning model.

The present invention makes it possible to create optimal operating parameters according to the priority of each part.

FIG. 1 is a configuration explanatory diagram of a component mounting system according to an embodiment of the present invention; FIG. 1 is a block diagram showing the configuration of a processing system of a management computer (operation parameter creation device) according to an embodiment of the present invention. 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; 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; FIG. 13 is a diagram showing an example of a priority input screen displayed on a management computer (operation parameter creation device) according to an embodiment of the present invention. FIG. 13 is a diagram showing an example of a weighting input screen displayed on a management computer (operation parameter creation device) according to an embodiment of the present invention. FIG. 1 is a flow diagram of an operation parameter creation method according to an embodiment of the present invention.

One embodiment of the present invention will be described with reference to the drawings. First, the configuration of component mounting system 1 will be described with reference to FIG. 1. Component mounting system 1 has the function of mounting components on a board to produce a mounted board. In this embodiment, multiple (here, three) component mounting lines 4 are connected to management computer 3 via communication network 2. Work on each component mounting line 4 is managed by 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.

The management computer 3 has the function of creating data and parameters necessary for the operation of the production equipment of each component mounting line 4 and sending it to each piece of production equipment. In addition, data such as the operation status and work history of each piece of production equipment is sent from each piece of production equipment to the management computer 3. In addition, the management computer 3 has the function of creating operating parameters, component data, production data, etc. used by the production equipment of the component mounting line 4. Note that the component mounting system 1 may be provided with a line management computer for each component mounting line 4, and data may be sent and received between the management computer 3 and each piece of production equipment via the line management computer.

In FIG. 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. Boards supplied by board supply device M1 are carried into solder printing device M3 via board transfer device M2, where solder printing work is performed to screen-print solder for joining components onto the boards.

After solder printing, the boards are handed over to component mounting devices M4 and M5 in sequence, where component mounting work is performed to mount components on the boards after solder printing. Component mounting devices M4 and M5 use a nozzle on the mounting head to pick up components supplied by the feeder by vacuum suction, capture an image of the component held by the nozzle with a component recognition camera, and mount the component at the mounting position on the board at a specified mounting angle. Component mounting devices M4 and M5 are equipped with multiple sensors to monitor operational mistakes and operational errors during component mounting work, such as the suction operation in which the nozzle picks up the component and the component recognition in which the component recognition camera captures and recognizes the removed component.

After the components are mounted on the board, it is carried into the reflow device M6, where it is heated according to a specified heating profile, causing the solder used to join the components to melt and solidify. This results in the components being solder-joined to the board, completing the mounting board with the components mounted on the board, which is then collected by the board collection device M7.

The configuration of the information processing system of the management computer 3 will now be described with reference to FIG. 2. Here, the configuration relating to the function of creating operating parameters used in component mounting work by component mounting devices M4 and M5 will be described, in addition to the multiple functions provided by the management computer 3. The management computer 3 (operation parameter creation device) creates operating parameters corresponding to new components based on component data, operating parameters, etc. that have a track record of being used in production on the component mounting line 4.

The management computer 3 includes a processing unit 10, a memory unit 17 which is a storage device, as well as an input unit 25, a display unit 26, and a communication unit 27. The processing unit 10 is a data processing device such as a CPU, and includes an input processing unit 11, an information acquisition unit 12, a data creation unit 13, a learning unit 14, a learning model evaluation unit 15, and an operation parameter creation unit 16 as internal processing units. Note that the management computer 3 does not need to be configured as a single computer, and may be configured as multiple devices. For example, all or part of the memory unit and processing unit may be provided in the cloud via a server.

The input unit 25 is an input device such as a keyboard, touch panel, or mouse, and is used when inputting operation commands and data. The display unit 26 is a display device such as a liquid crystal panel, and in addition to displaying various data stored in the memory unit 17, displays various information such as an operation screen and an input screen for operation by the input unit 25. The communication unit 27 is a communication interface, and transmits and receives data to and from the production equipment (component mounting devices M4, M5) that make up the component mounting line 4 via the communication network 2.

In FIG. 2, the storage unit 17 stores a production data library 18, a component library 19, priority data 20, a weighting table 21, learning data 22, a learning model 23, evaluation data 24, etc. In the production data library 18, production data used in the production of mounted boards by component mounting devices M4 and M5 is stored for each production model name of the mounted board.

Now, referring to FIG. 3, an example of production data 30 contained in production data library 18 will be described. Each of the multiple production data 30 contained in production data library 18 specifies the data necessary to produce a mounting board for one production model name. That is, the production data 30 specifies for each component to be mounted a "component name" 31 of the component to be mounted on the mounting board for that production model name, a "component n" 32 which is a component code for associating that component with component data in component library 19, "mounting coordinates" 33 which indicate the mounting position and mounting angle of that component on the mounting board, and a "mounting angle" 34.

In addition, the production data 30 specifies, for each component name, equipment condition data 35 that indicates the conditions of the equipment used to produce the mounted board, i.e., the setting state of component mounting devices M4 and M5. Note that in the example shown here, the production data 30 provided by the communication network 2 includes the equipment condition data 35, but it is also possible to provide only the equipment condition data 35 in the form of a separate file.

The equipment condition data 35 specifies model data indicating the type of component mounting device M4, M5, a "supply position" 36 indicating the position to which the component is supplied, a "feeder" 37 indicating the feeder used to supply the components, a "mounting head" 38 indicating the mounting head that performs the component mounting work to mount the component, and a "nozzle" 39 indicating the nozzle used to hold the component.

In FIG. 2, component library 19 stores multiple component data that associate the type of component with operating parameters for precisely controlling the various tasks of mounting the component in component mounting devices M4 and M5. The component data is associated with production data 30 by a component code. That is, even for components with the same component name, component library 19 stores different component data that correspond to the mounting position of the production model name of the mounting board to be produced. Note that if the operating parameters are the same even if the production model name and mounting position are different, common component data is used.

Now, referring to FIG. 4, an example of part data 40 included in the part library 19 will be described. The part data 40 is associated with the production data 30 by a "part code" 41 included in the part data 40 and a "part n" 32 included in the production data 30.

The part data 40 consists of a shape diagram 42, size data 43, part parameters 44, and operation parameters 47. Images, values, terms, etc. are entered in the blank spaces for each item. Note that the "values" used here are not limited to numerical data, but also include the selection results of options expressed quantitatively and qualitatively, such as yes/no, cheap/expensive, high/medium/low speed, etc. The shape diagram 42 illustrates the external shape of the target part. The size data 43 shows size information of the part, i.e., external dimensions, number of leads, lead pitch, lead length, lead width, part height, etc., as numerical data.

In FIG. 4, part parameters 44 are attribute information about the part, and include part information 45, which is information about the part itself, and tape information 46, which is information about the carrier tape for supplying the part by a feeder. Part information 45 indicates the polarity, polarity mark, mark position, part type, shape type, and price information of the part. Tape information 46 includes the tape material of the carrier tape, tape width indicating the width dimension of the carrier tape, feed interval indicating the tape feed pitch, and color/material information, which is information related to the characteristics when the carrier tape is the subject of image recognition.

The operation parameters 47 are machine parameters that stipulate the operation mode when the component is the target of component mounting work by the component mounting devices M4 and M5. In the example shown here, the operation parameters 47 include a model 47a indicating the type of the component mounting device M4 and M5, and a nozzle setting 47b indicating the type of nozzle to be used. In addition, the operation parameters 47 include a speed parameter 47c, recognition 47d, gap 47e, suction 47f, attachment 47g, etc.

In FIG. 4, the speed parameters 47c include the pickup speed when the nozzle picks up the components, the mounting speed when the mounting head transports the components, and the tape feed speed when the feeder feeds the carrier tape. In this embodiment, the pickup speed, mounting speed, and tape feed speed can be set as a percentage of the maximum speed between 100% and 20%. Recognition 47d is a parameter that specifies the mode of component recognition, and includes a camera type that indicates the type of component recognition camera used, an illumination mode that indicates the illumination form during imaging, and a recognition speed that is the nozzle movement speed during imaging. The recognition speed can be set to high speed, medium speed, or low speed. Note that the speed-related parameters may be numerical values (1 to 100%) or options (high speed, medium speed, low speed, etc.).

Gap 47e includes the suction gap when the nozzle picks up a component and the mounting gap when the held component is mounted on the board. Suction 47f specifies the suction position offset, which indicates the offset amount when the nozzle picks up a component, and the suction angle. Placement 47g specifies the pressure load when the component held by the nozzle is placed on the board.

In this way, the operation parameters 47 include nozzle parameters (nozzle settings 47b) related to the nozzle that picks up the component, pickup parameters related to pickup when the nozzle picks up the component (pickup speed, pickup gap, pickup 47f), recognition parameters (recognition 47d) for recognizing the shape of the component, and mounting parameters for mounting the component (mounting speed, mounting gap, placement 47g). Note that the component parameters 44 and operation parameters 47 shown in the component data 40 in Figure 4 are examples of the relevant items, and various parameters other than the items shown here are set as necessary.

For example, these include the suction hold time, which is the time the nozzle is in contact with the component when suctioning a component; the mounting hold time, which is the time the component is in contact with the board when mounting the component on the board; the component recognition count, which is the number of times the component is recognized by the recognition camera; suction check ON/OFF, which determines whether a check is performed to determine whether the component has been picked up; thickness variation tolerance, which sets the tolerance when measuring the component thickness; component suction status detection ON/OFF, which determines whether the component suction status is detected; simultaneous component suction/mounting ON/OFF, which determines whether components are picked up or mounted simultaneously; automatic component suction position learning ON/OFF, which determines whether the component suction position is automatically set; the component suction retry count, which determines whether a component is picked up again when suction has failed; and the recognition retry count, which determines whether a component is recognized again when it cannot be recognized.

In FIG. 2, priority data 20 is data that associates priorities with component names 31 of components to be mounted on a board. The priority of a component is set by a production manager based on criteria such as the mounting accuracy required when mounting on a board. Weighting table 21 is a data table that associates the priority of a component with weighting when generating a learning model (described below) and a criterion (target accuracy rate) when evaluating the generated learning model. The weighting and target accuracy rate are set by the production manager. The input processing unit 11 displays an input screen on the display unit 26 that allows the production manager to input various information for setting priority data 20 and weighting table 21 from the input unit 25.

Now, referring to FIG. 5, the priority input screen 50 displayed by the input processing unit 11 on the display unit 26 will be described. A "Priority" input frame 51, an "Undo" button 52, and a "Confirm" button 53 are displayed on the priority input screen 50. The "Priority" input frame 51 displays the part type and shape type for each part name 31, and the production manager operates the input unit 25 to input the priority. In this example, the priority is selected from the preset "Top Priority", "Priority", and "Standard" from a drop-down menu. The data displayed in the "Priority" input frame 51 can be changed by operating the scroll bar.

When the production manager operates the input unit 25 to operate the "Undo" button 52, the selected priority returns to its original state. When the production manager operates the input unit 25 to operate the "Decide" button 53, the input processing unit 11 stores the priority entered on the priority input screen 50 in the memory unit 17 as priority data 20. In this way, the input unit 25 accepts the input of part priorities. The input processing unit 11 is an information creation unit that creates part information including priorities based on the input part priorities.

Next, referring to FIG. 6, the weighting input screen 54 displayed by the input processing unit 11 on the display unit 26 will be described. A "weighting" input frame 55, an "Undo" button 56, and a "Confirm" button 57 are displayed on the weighting input screen 54. In the "weighting" input frame 55, the production manager operates the input unit 25 to input weighting and a target correct answer rate for each of the three priority levels: "highest priority," "priority," and "standard."

In this example, the weighting is "10" for "top priority", "2" for "priority", and "1" for "standard". The target accuracy rates are "95% or more" for "top priority", "80% or more" for "priority", and "60% or more" for "standard". The weighting is referred to when the data creation unit 13 creates the learning data 22. The target accuracy rates are referred to when the learning model evaluation unit 15 evaluates the learning model 23. Note that the weighting and the target accuracy rates are not limited to this example and may be changed as appropriate.

In FIG. 6, when the production manager operates the "Undo" button 56 using the input unit 25, the selected priority returns to its original state. When the production manager operates the "Confirm" button 57 using the input unit 25, the input processing unit 11 stores the weighting for each priority and the target correct answer rate entered into the weighting input screen 54 as a weighting table 21 in the memory unit 17. Note that although the priority in the priority data 20 and weighting table 21 described above is three levels, the priority is not limited to this and may be two levels or four or more levels.

In FIG. 2, the information acquisition unit 12 acquires part information from the storage unit 17 for the data creation unit 13 to create the learning data 22 and evaluation data 24. Specifically, the information acquisition unit 12 acquires part information including part shape information (size data 43, part parameters 44), proven operation parameters 47, and part priorities from proven production data 30 contained in the production data library 18, proven part data 40 contained in the part library 19, and priority data 20. Hereinafter, the proven operation parameters 47 are referred to as "proven operation parameters."

The data creation unit 13 creates learning data 22 based on the part information acquired by the information acquisition unit 12. Specifically, the data creation unit 13 extracts, from the part information, information on parts with priorities of "top priority" and "priority", and further information on a predetermined number of parts (e.g., 1,000 parts) randomly selected from among the parts with priority of "standard". Furthermore, the data creation unit 13 creates learning data 22 based on the weighting included in the weighting table 21 so that many parts with priorities of "top priority" and "priority" are included.

For example, in the case of the weighting table 21 shown in FIG. 6, the part information of a part with a priority of "highest priority" is duplicated ten times, and the part information of a part with a priority of "priority" is duplicated twice, and these are included in the learning data 22. In this way, the data creation unit 13 is a learning data creation unit that creates learning data 22 by weighting according to the priority of the part based on the part information. The created learning data 22 is stored in the memory unit 17.

In FIG. 2, the data creation unit 13 creates evaluation data 24 based on the part information acquired by the information acquisition unit 12. Specifically, the data creation unit 13 extracts part information on a predetermined number of parts randomly extracted from the parts with priority levels of "highest priority" and "priority" and from the parts with priority level of "standard" that were not selected as learning data 22. Note that the parts with priority level of "standard" extracted as learning data 22 may also be extracted as evaluation data 24. The created evaluation data 24 is stored in the memory unit 17.

The learning unit 14 uses the learning data 22 as teacher data to generate a learning model 23 that creates (estimates) operating parameters 47 from part shape information (size data 43, part parameters 44) by a learning algorithm using machine learning or the like. As the learning algorithm, a neural network (including deep learning using a multi-layer neural network), genetic programming, decision tree, Bayesian network, support vector machine (SVM), or the like may be used. The generated learning model 23 is stored in the memory unit 17. In this way, the learning unit 14 generates or updates the learning model 23 based on the learning data 22.

In FIG. 2, the motion parameter creation unit 16 creates (estimates) motion parameters 47 from part shape information using the learning model 23 generated or updated by the learning unit 14 stored in the memory unit 17. For example, the motion parameter creation unit 16 uses shape information of a new part as input information to create motion parameters 47 corresponding to that part. Hereinafter, the motion parameters 47 estimated by the motion parameter creation unit 16 using the learning model 23 are referred to as "estimated motion parameters."

In FIG. 2, the learning model evaluation unit 15 evaluates the learning model 23 generated by the learning unit 14 based on the evaluation data 24 and the target correct answer rate included in the weighting table 21. Specifically, the learning model evaluation unit 15 evaluates the learning model 23 by comparing the operation parameters 47 (estimated operation parameters) created by the operation parameter creation unit 16 using the learning model 23 from the part shape information included in the part information of the part included in the evaluation data 24 with the operation parameters 47 (actual operation parameters) included in the information of the part in the evaluation data 24.

For example, the learning model evaluation unit 15 compares each of the estimated and actual operating parameters of a certain part, searches for the parameter with the largest difference ratio (%), and calculates the difference ratio of that parameter from 100% to be the accuracy rate. Then, the learning model evaluation unit 15 determines that the criterion is met if the calculated accuracy rate is higher than the target accuracy rate corresponding to the priority of the part. In other words, a part with a "highest priority" priority is determined to meet the criterion if the accuracy rate is the target accuracy rate of "95% or more". Note that the learning model evaluation unit 15 may make a determination by comparing only specific parameters (for example, the speed parameter 47c and the gap 47e) rather than all parameters of the operation parameters 47.

The above-mentioned method of evaluating the learning model 23 is an example, and other evaluation methods may be used. For example, the number or ratio of operation parameters 47 with a correct answer rate of 80% or more among the operation parameters 47 to be compared may be used as a criterion for judgment. In this way, the learning model evaluation unit 15 evaluates the learning model 23 based on the priority of the part, depending on whether the comparison between the estimated operation parameters and the actual operation parameters meets a criterion (target correct answer rate) according to the priority of the part. If the estimated operation parameters do not meet the criterion, the data creation unit 13 (learning data creation unit) changes the weighting according to the priority of the part and recreates the learning data 22, and the learning unit 14 generates or updates the learning model 23 based on the recreated learning data 22.

For example, if the estimated operation parameters of a part with a priority of "highest priority" do not satisfy the criteria, the data creation unit 13 changes the weighting of that part from "10" to "15" and creates the learning data 22. Note that the weighting of all parts with a priority of "highest priority" may be changed uniformly. In this way, if the estimated operation parameters created from the learning model 23 do not satisfy a predetermined criterion, the weighting is changed and the learning model 23 is regenerated, and estimated operation parameters are created using the learning model 23 that satisfies the criterion, thereby creating optimal operation parameters 47 (estimated operation parameters) according to the priority of the part.

Next, following the flow of FIG. 7, an operation parameter creation method (operation parameter creation process) by the management computer 3, which is an operation parameter creation device that creates operation parameters 47 for component mounting devices M4 and M5 to mount components on a board, will be described. First, the production manager uses the priority input screen 50 (see FIG. 5) to input priorities for existing components (ST1: priority input process). The production manager inputs priorities such as "top priority" or "priority" for important components for which estimation of operation parameters 47 is essential. In this manner, the input of component priorities is accepted. The input priority for each component is stored in the memory unit 17 as priority data 20.

Next, the production manager uses the weighting input screen 54 (see FIG. 6) to input weights and target correct answer rates for each priority (ST2: weighting input process). The input weights and target correct answer rates are stored in the storage unit 17 as a weighting table 21. Note that if a default weighting table 21 is used, the weighting input process (ST2) is omitted.

When the priority, weighting, and target accuracy rate are set, the information acquisition unit 12 acquires part information including part shape information (size data 43, part parameters 44), proven operating parameters 47 (proven operating parameters), and part priority from the production data 30 contained in the production data library 18, the part data 40 contained in the part library 19, and the priority data 20 (ST3: information acquisition process). That is, part information is created based on the part priority input in the priority input process (ST1).

In FIG. 7, the data creation unit 13 then creates learning data 22 and evaluation data 24 based on the priority data 20, weighting table 21, and part information (ST4: learning data creation process). That is, the learning data 22 is created by weighting according to the priority of the parts. The created learning data 22 and evaluation data 24 are each stored in the memory unit 17. Next, the learning unit 14 generates a learning model 23 based on the learning data 22 (ST5: learning model generation process). The generated learning model 23 is stored in the memory unit 17.

Then, the learning model evaluation unit 15 evaluates the learning model 23 based on the evaluation data 24 and the target accuracy rate included in the weighting table 21 (ST6: learning model evaluation step). Specifically, the operation parameter creation unit 16 compares the estimated operation parameters created by using the learning model 23 from the part shape information included in the part information with the actual operation parameters included in the part information, and evaluates the learning model 23 based on whether the comparison satisfies a standard (target accuracy rate) according to the priority of the part.

In FIG. 7, if the comparison does not satisfy the criteria (No in ST7), the process returns to the learning data creation process (ST4), and the learning data 22 is recreated (ST4) by changing the weighting according to the priority of the parts, and a learning model 23 is generated or updated (ST5) based on the recreated learning data 22. If the comparison satisfies the criteria (Yes in ST7), that learning model 23 is selected (ST8: learning model selection process).

Then, using the determined learning model 23, operation parameters 47 (estimated operation parameters) for mounting the new component on the board using component mounting devices M4 and M5 are created from the shape information of the new component (size data 43, component parameters 44) (ST9: operation parameter creation process). This makes it possible to create optimal operation parameters 47 according to the priority of the components. When operation parameters 47 have been created for all new components (Yes in ST10), the operation parameter creation process ends.

As described above, the operation parameter creation device (management computer 3) of this embodiment includes an information acquisition unit 12 that acquires part information including part shape information (size data 43, part parameters 44), operation parameters 47 (actual operation parameters), and part priority, a learning data creation unit (data creation unit 13) that creates learning data 22 based on the part information, a learning unit 14 that generates or updates a learning model 23 based on the learning data 22, and an operation parameter creation unit 16 that creates operation parameters 47 (estimated operation parameters) from the part shape information using the generated or updated learning model 23. This makes it possible to create optimal operation parameters 47 according to the priority of the part.

The operating parameter creation device and operating parameter creation method of the present invention have the effect of being able to create optimal operating parameters according to the priority of the parts, and are useful in the field of mounting parts on a board.

3. Management computer (operation parameter creation device)
M4, M5 component mounting equipment

Claims (14)

An operation parameter creation device that creates operation parameters for a component mounting device to mount a component on a board,
an information acquisition unit that acquires information about a component, including shape information, operation parameters, and a priority level of a mounting accuracy required for the component;
a learning data creation unit that creates learning data by weighting the learning data in accordance with the priority of the required mounting accuracy of the component based on the information of the component;
A learning unit that generates or updates a learning model based on the learning data;
An operation parameter creation device comprising: an operation parameter creation unit that creates operation parameters from part shape information using the generated or updated learning model. an input unit that receives an input of a priority level of the required mounting accuracy of the component;
2. The operation parameter creating device according to claim 1, further comprising: an information creating section that creates information about the component based on the input priority of a level of mounting accuracy required for the component. 3. The operation parameter creation device according to claim 1, wherein the operation parameters include at least any of a nozzle parameter related to a nozzle that picks up the component, a pickup parameter related to pickup when picking up the component with the nozzle, a recognition parameter for recognizing a shape of the component, and a mounting parameter for mounting the component. An operation parameter creation device as described in any one of claims 1 to 3, further comprising a learning model evaluation unit that evaluates the learning model by comparing operation parameters created by the operation parameter creation unit using the learning model from part shape information included in the part information with operation parameters included in the part information. 5. The operation parameter generating device according to claim 4 , wherein the learning model evaluating unit evaluates the learning model based on a priority of a level of mounting accuracy required for the component. 5. The operation parameter creation device according to claim 4 , wherein the learning model evaluation unit evaluates the learning model based on whether the comparison of the operation parameters satisfies a criterion corresponding to a priority of a required mounting accuracy of the component. if said comparison of operating parameters does not meet said criteria;
the learning data creation unit recreates the learning data by changing a weighting according to a priority of a required mounting accuracy of the component;
The operation parameter generating device according to claim 6 , wherein the learning unit generates or updates a learning model based on the recreated learning data. 1. An operation parameter creation method for creating operation parameters for a component mounting device to mount a component on a board, comprising:
Acquire information about the part, including shape information, operation parameters, and a priority level of mounting accuracy required for the part;
creating learning data based on the information on the components and weighting the data in accordance with the priority of the required mounting accuracy of the components ;
Generate or update a learning model based on the learning data;
An operating parameter creation method comprising: creating operating parameters from part shape information using the generated or updated learning model. Accepting an input of a priority level of the required mounting accuracy of the component;
9. The operation parameter creating method according to claim 8 , further comprising creating information about the component based on an input priority of a level of mounting accuracy required for the component. 10. The operation parameter creating method according to claim 8, wherein the operation parameters include at least any of a nozzle parameter related to a nozzle that picks up the component, a pickup parameter related to pickup when picking up the component with the nozzle, a recognition parameter for recognizing a shape of the component, and a mounting parameter for mounting the component. The operation parameter creation method according to any one of claims 8 to 10, further comprising: evaluating the learning model by comparing operation parameters created using the learning model from part shape information included in the part information with operation parameters included in the part information. The operation parameter creation method according to claim 11 , further comprising the step of evaluating the learning model based on a priority of a level of mounting accuracy required for the component. 12. The operation parameter generating method according to claim 11 , further comprising the step of evaluating the learning model based on whether the comparison of the operation parameters satisfies a criterion corresponding to a priority of a level of mounting accuracy required for the component. if said comparison of operating parameters does not meet said criteria;
Recreating the learning data by changing the weighting according to the priority of the required mounting accuracy of the component;
The operation parameter generating method according to claim 13 , further comprising generating or updating a learning model based on the recreated learning data.

Images