Processing method, generation apparatus, processing system, program, and storage medium

Abstract

To provide a processing method capable of generating effective countermeasures by improving defects, a generation device, a processing system, a program, and a storage medium.SOLUTION: According to an embodiment, a processing method makes a computer refer to an individual model that shows countermeasures to a cause of a defective mode in a product. Further, the processing method makes the computer generate an integrated model by rearranging and connecting a plurality of individual models in accordance with a plurality of weights respectively set in a plurality of causes about each of the plurality of defective modes.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] Embodiments of the present invention relate to a processing method, a generating apparatus, a processing system, a program, and a storage medium. [Background technology]

[0002] Generally, when a defect occurs, countermeasures are implemented. Ideally, these countermeasures should be more effective in improving the defect. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-87110 [Overview of the project] [Problems that the invention aims to solve]

[0004] The problem that this invention aims to solve is to provide a processing method, a generating apparatus, a processing system, a program, and a storage medium that can generate effective countermeasures by improving defects. [Means for solving the problem]

[0005] The processing method according to the embodiment causes a computer to refer to individual models that indicate countermeasures for the causes of failure modes in a product. Furthermore, the processing method causes the computer to generate an integrated model by rearranging and connecting the multiple individual models according to a plurality of weights set for each of the plurality of causes for each of the plurality of failure modes. [Brief explanation of the drawing]

[0006] [Figure 1] This is a flowchart showing the processing method according to the embodiment. [Figure 2] This is an example of data stored in the first database. [Figure 3]This is an example of data stored in the second database. [Figure 4] This is an example of a generated integrated model. [Figure 5] This is an example of data stored in the third database. [Figure 6] This is an example of data stored in the third database. [Figure 7] This is an example of data stored in the third database. [Figure 8] This is an example of data stored in the third database. [Figure 9] This is an example of data stored in the third database. [Figure 10] This is an example of data stored in the third database. [Figure 11] This is an example of data stored in the third database. [Figure 12] This is an example of data stored in the third database. [Figure 13] This is an example of data stored in the third database. [Figure 14] This is an example of data stored in the third database. [Figure 15] This is an example of data stored in the third database. [Figure 16] This is an example of data stored in the third database. [Figure 17] This is an example of data stored in the third database. [Figure 18] This is an example of data stored in the third database. [Figure 19] This is an example of data available for the processing method according to the embodiment. [Figure 20] This is an example of data available for the processing method according to the embodiment. [Figure 21] This is an example of data available for the processing method according to the embodiment. [Figure 22] This is an example of data available for the processing method according to the embodiment. [Figure 23] This is a schematic diagram illustrating an integrated model. [Figure 24] This is a schematic diagram illustrating an integrated model. [Figure 25] This is a schematic diagram showing a processing system according to an embodiment. [Figure 26] This is a schematic diagram showing the manufacturing line for mounted circuit boards. [Figure 27] This is a schematic diagram showing the processing system according to the embodiment. [Figure 28] This is an example of output from the generation device according to the embodiment. [Figure 29] This is an example of output from the generation device according to the embodiment. [Figure 30] This is an example of output from the generation device according to the embodiment. [Figure 31] This is an example of output from the generation device according to the embodiment. [Figure 32] This is an example of output from the generation device according to the embodiment. [Figure 33] This is an example of output from the generation device according to the embodiment. [Figure 34] This is an example of output from the generation device according to the embodiment. [Figure 35] This is a schematic diagram showing the hardware configuration. [Modes for carrying out the invention]

[0007] The embodiments of the present invention will be described below with reference to the drawings. In this specification and in the drawings, elements similar to those already described are denoted by the same reference numerals, and detailed descriptions will be omitted as appropriate.

[0008] Figure 1 is a flowchart illustrating the processing method according to the embodiment. Figure 2 is an example of data stored in the first database. Figure 3 is an example of data stored in the second database. Figure 4 is an example of the generated integrated model. This embodiment relates to a processing method for generating a model for improving a product. As shown in Figure 1, the processing method M1 includes steps S1 to S7.

[0009] First, the system references the first and second databases (step S1). The first database stores the failure modes that may occur in the product, the causes of the failure modes, and the weights of the causes. The second database stores the causes and individual models that indicate the countermeasures for those causes.

[0010] As shown in Figure 2, the first database 100 stores multiple failure modes 110, and one or more causes 120 are associated with each failure mode 110. Each cause 120 is also assigned a weight 130. A failure mode 110 is a classification of a type of defect (malfunction, failure, failure, malfunction, etc.) that may occur in a product. A cause 120 indicates the cause of a failure mode 110. One or more causes 120 are associated with each failure mode 110. The weight 130 indicates the importance of the cause 120. In this example, a larger weight indicates a higher importance of the cause 120. For example, a larger weight 130 indicates a higher probability that the cause 120 is the cause of the failure mode 110. Alternatively, a larger weight 130 indicates that resolving the cause 120 will contribute significantly to improving the failure mode 110.

[0011] A common cause 120 can be assigned to different failure modes 110. In the example in Figure 2, the same "print misalignment" causes 121 and 122 are associated with the "bridge" failure mode 111 and the "misalignment" failure mode 112. Even in this case, the weight 131 of cause 121 and the weight 132 of cause 122 can be different from each other. This is because the impact of each cause 120 on the failure mode 110 can differ for each failure mode 110. The same applies to "mount misalignment".

[0012] As shown in Figure 3, the second database 200 stores multiple causes 210 and multiple individual models 220. Cause 210 is associated with cause 120 and indicates the cause of the malfunction mode 110. Individual models 220 indicate countermeasures for cause 210. One individual model 220 is associated with one cause 210. Individual models 220 may be executed by a human. At least a portion of an individual model 220 may be written in a programming language and executed automatically by a computer.

[0013] Multiple causes 120 with the same content in the first database 100 are linked to a single cause 210. For example, in Figure 2, causes 121 and 122 of "print misalignment" are both linked to cause 211. The individual model 221 linked to cause 211 is a countermeasure for causes 121 and 122.

[0014] Each individual model 220 includes a decision 220a, a process 220b, an exit terminal 220c, and a return terminal 220d. Decision 220a is a step to determine whether cause 210 has occurred. In the example shown in Figure 3, the first step of each individual model 220 is the decision step. Before decision 220a, one or more other steps selected from processes, preparations, inputs / outputs, displays, etc., may be executed. The first step may be the first step executed in the integrated model, which is the main routine. If decision 220a determines that cause 211 has occurred, the process 220b step is executed. The exit terminal 220c indicates the termination of that individual model 220 and the integrated model. When process 220b is executed, the individual model 220 and the integrated model terminate. If decision 220a does not determine that cause 211 has occurred, the process proceeds to the return terminal 220d, and the first step of another individual model 220 is executed. If the return terminal 220d is not connected to another individual model 220, the integrated model terminates.

[0015] Next, for each failure mode in the first database, the individual models stored in the second database are sorted and connected to each other according to the weights set for each cause (step S2). This generates an integrated model.

[0016] In the example shown in Figure 2, for the "bridge" failure mode 111, the weight of "excessive print volume" is greater than the weight of "mismounting". The weight of "mismounting" is greater than the weight of "mismounting". As shown in Figure 4, depending on the weight, the individual model for "mismounting" is ranked higher than the individual model for "mismounting". The individual model for "excessive print volume" is ranked higher than the individual model for "mismounting". The return terminals and the first step are connected between the individual models to generate an integrated model 250 for improving the failure mode.

[0017] Next, it is determined whether a defect has occurred in the product (Step S3). For example, the product is inspected during or after the production process. Based on the inspection results, the product quality data is entered into a designated database or terminal device. If a defect is found during the inspection, that information is included in the quality data.

[0018] If the quality data contains information indicating that a defect has occurred, the integrated model generated for the defect mode to which the defect is classified is executed (step S4). For example, if the quality data contains information indicating the occurrence of a "bridge," the integrated model corresponding to the bridge is extracted from the multiple integrated models generated. The extracted integrated model shown in Figure 4 is then executed.

[0019] The integrated model may be executed by a human. At least a portion of the integrated model may be written in a programming language and executed automatically by a computer. When the integrated model is executed, confirmation data regarding the cause is collected. For example, when the integrated model shown in Figure 4 is executed, the computer first outputs a command to the output device to check whether the printed volume of solder paste is too large. The computer receives confirmation data indicating the result of a human check. The confirmation data may be collected automatically by an inspection device. For example, if confirmation data indicating that the printed volume is too large is input, the computer outputs a command to check for wear or damage to the squeegee. The computer also outputs a command to input that confirmation data and accepts the input of the confirmation data.

[0020] Furthermore, the processing in a single individual model may be described in one program file, or it may be divided and described in multiple program files. Similarly, the processing in an integrated model may be described in one program file, or it may be divided and described in multiple program files. The execution entity may differ for each program file.

[0021] The verification data obtained from the execution of the integrated model is recorded in the third database (step S5). The third database stores information about the target product, such as the number of occurrences of each cause and the configuration of the product's production line.

[0022] The cause weights stored in the first database are set based on the data stored in the third database. When the data stored in the third database is updated, the weights in the first database may change. When the weights change, the order of the individual models included in the integrated model may change. Therefore, it is determined whether the integrated model needs to be updated when the weights change (step S6).

[0023] If the integrated model needs to be updated, the weights are updated (step S7). Then, step S1 is executed again. That is, a new integrated model is generated according to the updated weights.

[0024] Figures 5 to 18 show examples of data stored in the third database. The weights of the first database vary according to the score based on the data stored in the third database. Table 310, shown in Figure 5, includes failure mode 311, countermeasure ID 312, countermeasure 313, and count 314. Failure mode 311 corresponds to failure mode 110 in the first database. Countermeasure 313 indicates an individual model for the cause. Countermeasure ID 312 is a character used to identify each countermeasure 313. Note that if each countermeasure 313 can be identified by the combination of the name of failure mode 311 and the name of the countermeasure 313, the countermeasure ID 312 may be omitted. The count 314 indicates the number of times the failure mode occurred was resolved by countermeasure 313. In other words, the count 314 indicates the number of occurrences of the cause corresponding to countermeasure 313. The more a countermeasure 313 resolves a failure mode 311, the more effective that countermeasure 313 is. For example, the more cases there are (314), the higher the score for countermeasure 313 will be set, and the weight of the cause 120 associated with countermeasure 313 will be set higher. The number of cases (314) may also be used as the score.

[0025] Figure 6 is Table 320, which shows scores according to the presence or absence of an inspection machine. Table 320 includes the type of inspection machine 321, the score 322, and the score 323. Score 322 shows the score when an inspection machine is provided. Score 323 shows the score when an inspection machine is not provided. In processes where an inspection machine is provided, defects are more easily detected. By detecting defects, the impact on subsequent processes can be reduced. Therefore, as shown in Figure 6, the score may change depending on the presence or absence of an inspection machine in each process. Specifically, when an inspection machine is provided, the score is set lower than when an inspection machine is not provided.

[0026] Based on the data shown in Figures 5 and 6, the table 330 shown in Figure 7 may be generated. Table 330 includes failure mode 331, countermeasure ID 332, countermeasure 333, number of cases 334, process 335, inspection machine score 336, and overall score 337. Failure mode 331, countermeasure ID 332, countermeasure 333, and number of cases 334 correspond to failure mode 311, countermeasure ID 312, countermeasure 313, and number of cases 314 in Table 310, respectively. Process 335 indicates the process in which failure mode 331 may occur. The inspection machine score 336 is a score depending on whether or not an inspection machine is provided in the process, and is based on Table 320 shown in Figure 6. The overall score 337 is a combined score based on the number of cases 334 and the inspection machine score 336. In this example, the overall score 337 is calculated by multiplying the number of cases 334 and the inspection machine score 336.

[0027] The correspondence between failure modes and processes, and between processes and inspection machines, may be stored in tables 310 and 320 shown in Figures 5 and 6, or they may be stored in separate tables.

[0028] The number of cases, 334, may be adjusted depending on when the corresponding cause occurred. For example, let's call the score based on the number of cases, Sc, and the total number of past occurrences, n. all n the number of occurrences in the most recent m months m When any coefficient is α (0 ≤ α ≤ 1), the score Sc is expressed by the following formula. Sc = α × n m / n all +(1-α)×(n all -n m ) / n all For example, to increase the influence of the most recent m months on the weighting, it is set to 0.5 < α ≤ 1. To decrease the influence of the most recent m months on the weighting, it is set to 0 ≤ α < 0.5. When α = 0.5, there is no weighting based on the period. The overall score 337 is set based on the score Sc, which is based on the adjusted number of cases 334, and the inspection machine score 336.

[0029] A season may be considered as the time period. Let Sc be the score based on the number of cases 334, and n be the total number of all past occurrences all , the number of occurrences in spring (March-May) be n Spring , the number of cases in summer (June-August) be n Summer , the number of occurrences in autumn (September-November) be n Autumn , the number of occurrences in winter (December-February) be n Winter , and arbitrary coefficients be α1 to α4, the score Sc is expressed by the following formula. Each of the coefficients α1 to α4 is 0 or more and 1 or less, and is set such that the sum of α1 to α4 is 1. Sc=(α1×n Spring +α2×n Summer +α3×n Autumn +α4×n Winter ) / 4×n all For example, when the occurrence of step S3 is in winter, if the influence of the number of winter occurrences on the weight is made larger than others, the coefficient α4 is set to be larger than the coefficients α1 to α3.

[0030] A table 340 shown in Figure 8 includes elapsed years 341 and scores 342 to 344. The elapsed years 341 indicate the number of years that have elapsed since the manufacturing apparatus provided in the production line was manufactured. In general, the older a manufacturing apparatus is, the more likely a defect will occur in its process. The higher the possibility of a defect occurring, the larger the score is set. The scores 342 to 344 indicate specific scores for each process. The correlation between manufacturing apparatuses and defects differs for each process. Therefore, a score is set for each combination of a process and elapsed years.

[0031] Table 351, shown in Figure 9(a), includes line operation 351a, score 351b, and 351c. Line operation 351a shows information about the operation method at each process or production line. Scores 351b and 351c show scores corresponding to the production method in each line operation method. Generally, in a dedicated line that produces only a specific product, the number of products produced is one, and there are no changes in manufacturing conditions due to setup changes. Therefore, there are few changes in state, and once a stable state is established, defects are unlikely to occur. Accordingly, the score is set low. On the other hand, in lines that produce multiple types of products in large quantities, or lines that produce many varieties in small quantities, defects are more likely to occur, and the proportion of defects to the overall product is high. Because of the significant impact on the production site, the score is set high.

[0032] Table 352, shown in Figure 9(b), includes the work method 352a, score 352b, and as score 352c for a given task. Generally, the more human intervention involved, the higher the probability of defects. Therefore, when human intervention is present, the score is set higher compared to when there is no human intervention.

[0033] Table 353 shown in Figure 9(c) includes scores 353a to 353e for each work method in the process of dividing the substrate. As shown in Figures 9(b) to 9(c), each score may be set according to the relationship between the specific operation method and the possibility of defects occurring, or the relationship between the operation method and the impact of defects. By setting the scores based on the production line configuration as shown in Figures 8 and 9(a) to 9(c), the weights can be set more appropriately.

[0034] Table 360, shown in Figure 10, includes scale 361 and scores 362-364. Scale 361 indicates the personnel size of the product production site. Scores 362-364 show the case-specific scores according to the scale. In Case 1, the smaller the personnel size, the higher the score. For example, smaller scales tend to have less accumulated know-how. Know-how can be enhanced by increasing the number of individual models executed. Based on this idea, the score is set as in Case 1. In Case 2, the smaller the personnel size, the lower the score. Smaller businesses may lack the manpower to execute individual models, and may only be required to execute the minimum necessary individual models. Based on this idea, the score is set as in Case 2. Considering both Cases 1 and 2, the score may also be set as in Case 3. Which case's score is used is determined before executing processing method M1.

[0035] Table 370, shown in Figure 11, includes skill levels 371, percentages 372, and multipliers 373. The data shown in Figure 10 may also be further considered in relation to the percentages of each skill level shown in Figure 11. Skill level 371 indicates the skill level (proficiency) of workers on the production floor. Percentage 372 indicates the ratio of workers at each skill level to the total number of workers. Multiplier 373 indicates the multiplier applied to the score in Table 360. Production sites with no skilled workers or an excessive number of beginners are more likely to experience defects. If the percentage of workers at any skill level falls outside the range specified by percentage 372, the score in Table 360 ​​is multiplied by the set multiplier 373.

[0036] Table 380, shown in Figure 12, includes elements 381, personnel 382, ​​and multipliers 383. Further consideration of process-specific elements, as shown in Figure 12, may be applied to the data shown in Figure 7 or Figure 10. Elements 381 represent equipment, processes, etc., in a process. Personnel 382 indicates the number of personnel involved in each element 381. Multipliers 383 represent the multiplier applied to the process score. Generally, a larger number of personnel suggests a higher likelihood of sufficient manpower to execute individual models. Therefore, the multiplier is set lower for larger personnel. If prioritizing defect improvement, the multiplier 383 may be set to a value proportional to the number of personnel.

[0037] Table 390, shown in Figure 13, includes additional elements 391, score 392, and score 393. Additional element 391 indicates additional elements related to workers. In this example, additional element 391 includes a "certification system" regarding workers' skills and knowledge, workers managing multiple production lines, and daily personnel changes on production lines. In organizations with a certification system for workers, product quality is more easily ensured. Therefore, when a certification system exists, the score is set lower compared to when there is no certification system. When workers manage multiple production lines, defects are more likely to occur compared to when workers manage only one production line. Therefore, when workers manage multiple lines, the score is set higher compared to when they do not. Thus, the weights may be adjusted according to the additional elements related to workers.

[0038] Table 400, shown in Figure 14, includes process personnel 401, score 402, and score 403. Scores may be used based on both the number of personnel in the process or production line and whether or not they are working on multiple tasks. While having multiple people work on multiple tasks can reduce the number of personnel, having multiple people work on multiple tasks requires coordination among several workers, making it easier for omissions, errors, and duplication to occur, thus making management difficult. Taking these factors into consideration, Table 400 sets a score for each person depending on whether or not they are working on multiple tasks.

[0039] Table 410, shown in Figure 15, includes repair man-hours 411 and scores 412. Repair man-hours 411 indicate the man-hours required to repair a defect. Score 412 indicates the score assigned to each repair man-hour. It is desirable that the longer the man-hours required to repair a defect, the lower the frequency of that defect occurrence. Therefore, the longer the repair man-hours, the higher the score is set. For example, the man-hours required for repair are pre-registered for each cause registered in the first database. A score is set for the repair man-hours of each cause according to the registered repair man-hours.

[0040] Table 420, shown in Figure 16, includes unit price 421 and score 422. Unit price 421 indicates the unit price of the product's components. In the example in Figure 16, the unit prices are shown in a ranked order. For example, the unit price 421 is the unit price of a printed circuit board. Score 422 indicates the score assigned to each unit price 421. A higher unit price is desirable to indicate a lower frequency of defects in that product. Therefore, a higher unit price is assigned a higher score. For example, a list of components used in a product is prepared in advance. In the list, components associated with defect modes and components subject to score setting are specified in advance. An integrated model is generated for each component and each defect mode. Depending on the unit price of each component, the order of the individual models in the integrated model may differ.

[0041] A score may be set according to the difficulty of producing the product. Table 431 shown in Figure 17(a) includes board size 431a and score 431b. Board size 431a is the size of the printed circuit board or printed wiring board. The larger the board size, the greater the difficulty of production. Therefore, the larger the board size, the higher the score is set. Table 432 shown in Figure 17(b) includes component count 432a and score 432b. Component count 432a indicates the number of components provided on one board. The more components there are, the greater the difficulty of production. Therefore, the more components there are, the higher the score is set. Table 433 shown in Figure 17(c) includes mounting density 433a and score 433b. Mounting density 433a indicates the mounting density on one board. The higher the mounting density, the greater the difficulty of production. Therefore, the higher the mounting density, the higher the score is set. Table 434, shown in Figure 17(d), includes spacing 434a and score 434b. Spacing 434a indicates the average or minimum spacing between components on a single substrate. The narrower the spacing, the greater the difficulty of production. Therefore, the narrower the spacing, the higher the score is set. Table 435, shown in Figure 17(e), includes shape 435a and score 435b. Shape 435a indicates whether the shape of the substrate used is common or special. When a special-shaped substrate is used, the difficulty of production increases compared to when a common-shaped substrate is used. Therefore, when a special-shaped substrate is used, the score is set higher compared to when a common-shaped substrate is used.

[0042] A score may be set according to the specifications of the components included in the product. Table 441, shown in Figure 18(a), includes function 441a and score 441b. Function 441a indicates the function of the component. Higher-functioning components have a greater impact on product quality, so a higher score is assigned to them. Table 442, shown in Figure 18(b), includes price 442a and score 442b. Price 442a indicates the price of the component in question. It is desirable that the higher the price, the lower the frequency of defects related to that component. Therefore, a higher score is assigned to components with a higher price. Table 443, shown in Figure 18(c), includes area 443a and score 443b. Area 443a indicates the area of ​​the component in question. The smaller the area of ​​a component, the greater the difficulty of mounting that component. The difficulty decreases as the area increases, but beyond a certain area, the difficulty increases again. Therefore, a lower score is assigned to intermediate areas. Table 444, shown in Figure 18(d), includes height 444a and score 444b. Height 444a indicates the height dimension of the component in question. The taller the component, the greater the difficulty of mounting it. Therefore, the taller the component, the higher the score is set. Table 445, shown in Figure 18(e), includes electrode pitch 445a and score 445b. Electrode pitch 445a indicates the electrode pitch within the component in question. The narrower the pitch, the greater the difficulty of production. Therefore, the narrower the pitch, the higher the score is set. For example, score Sc0 according to the specifications of a component is determined by the following formula using score Sc1 set as score 441b, score Sc2 set as score 442b, score Sc3 set as score 443b, score Sc4 set as score 444b, and score Sc5 set as score 445b. Sc0 = Sc1 × Sc2 × (Sc3 + Sc4 + Sc5)

[0043] A score may be assigned to the product's production environment. For example, scores may be assigned to temperature, humidity, airflow, wind speed, presence or absence of an ionizer, and particle counter measurement results. Specifically, if a product is produced in a space with few particles, the likelihood of defects decreases compared to when it is produced in a space with many particles. Therefore, the score will be set lower.

[0044] Figures 19 to 22 show examples of data that can be used in the processing method according to this embodiment. The relationships between the production line and the equipment used therein, the relationships between products and processes on the production line, and the linking of data between the first and second databases can be found in the tables shown in Figures 19 to 22. The tables shown in Figures 19 to 22 may be stored in any of the first to third databases, or in a database other than these.

[0045] Table 450, shown in Figure 19, includes Type 451, Name 452, Machine ID 453, Manufacturer 454, Line 455, Year of Manufacture 456, and Elapsed Years 457. Type 451 indicates the type of equipment used in the line. Name 452 indicates the name of the equipment (common name on the line). Machine ID 453 is a character used to identify the equipment. Line 455 indicates the line on which the equipment is installed. Year of Manufacture 456 indicates the year the equipment was manufactured. The Year of Manufacture 456 may also include the month and day for greater detail. Elapsed Years 457 indicates the number of years that have passed since the equipment was manufactured. Using Table 450 shown in Figure 19, the elapsed years 341 and scores 342-344 in Table 340 shown in Figure 8 can be calculated. Alternatively, instead of Table 340 shown in Figure 8, a formula for calculating scores corresponding to the elapsed years may be stored in the third database.

[0046] Table 460, shown in Figure 20, includes product name 461, model number 462, board size 463, number of components 464, component spacing 465, and data 466-472 indicating the presence or absence of each process. Model number 462 is a string indicating the product model. Board size 463, number of components 464, and component spacing 465 correspond to board size 431a, number of components 432a, and spacing 434a shown in Figure 17. In data 466-472, "0" indicates that the indicated process does not exist in the production line for that product. "1" indicates that the indicated process exists in the production line for that product. Table 460, shown in Figure 20, can be used when deriving the scores for each table shown in Figures 17 and 18.

[0047] The table 500 shown in Figure 21 includes failure modes 501 and data 502-518. Failure mode 501 corresponds to failure mode 110 registered in the first database 100. Data 502-518 indicate the presence of a failure mode in each process. "0" indicates that the failure mode does not occur in the process indicated. "1" indicates that the failure mode may occur in the process indicated.

[0048] Table 520, shown in Figure 22, contains cause 521 and data 522-538. Cause 521 corresponds to cause 120 registered in the first database 100. Data 522-538 indicates the presence of causes related to a failure mode in each process. "0" indicates that the cause in the indicated process is not related to a failure mode. "1" indicates that the cause in the indicated process may be related to a failure mode.

[0049] Using tables 500 and 520 shown in Figures 21 and 22, the failure modes 110 and causes 120 stored in the first database 100 can be linked to the causes 210 and individual models 220 stored in the second database 200.

[0050] Additionally, tables showing the names of each product, the processes involved in each product, and the order of those processes may be used.

[0051] The weights of the first database are set based on at least one of the data from the third database described above. Specifically, the weights of the first database are determined using one or more selected from Group 1, which consists of scores based on the number of occurrences of each cause, the configuration of the production line, the size of the workforce at the production site, the repair man-hours for each defect mode, the price of the parts, the difficulty of producing the product, the types of parts included in the product, the production environment of the product, the age of the manufacturing equipment for the product, and the timing of the occurrence of each cause. By using one or more scores selected from Group 1, the weights can be set more appropriately. As a result, it becomes possible to generate an integrated model that is more effective in improving defects.

[0052] For example, a weighting model is pre-configured that outputs the weight of each cause in response to the input score of each data point. The scores of each data point stored in a third database are input to this model to obtain the weight of each cause. For example, the model may include a neural network. Multiple data points are input to multiple terminals in the input layer. Multiple cause weights are output from multiple terminals in the output layer.

[0053] The weights between each node of the neural network are initially set by the user or by predetermined rules. Each time the integrated model based on the weights from the weighted model is run, the user provides feedback on that integrated model. Alternatively, the system may automatically provide feedback based on the judgment results of a tester, neural network, etc. For example, the feedback may include countermeasures that actually improved the bad mode. The weighted model is learned based on the feedback so that the weight for those countermeasures is output as higher.

[0054] Alternatively, the neural network may be pre-trained through supervised learning. Multiple training datasets are used to train the neural network. Each training dataset includes input data and instructional data. The input data includes the score of each data point that is input to the input layer. The instructional data includes the weights of each cause corresponding to the input data. The neural network is trained so that the instructional data is output in response to the input data.

[0055] Figures 23 and 24 are schematic diagrams illustrating the integrated model. Note that the specific details of each individual model are omitted in Figures 23 and 24. In the integrated model shown in Figure 23, individual models A1 to A6 are arranged for a given failure mode. A1 ~W A6 This indicates the cause weights corresponding to individual models A1 to A6. The execution of each individual model may be determined based on its weight. For example, the threshold for the weights is set to 2. Only individual models with corresponding weights greater than 2 will be executed. When the integrated model is executed, individual models are executed in order from A1, but individual models A5 and A6, whose corresponding weights are 2 or less, will not be executed.

[0056] Alternatively, the integrated model may consist only of individual models whose corresponding weights exceed a threshold. In the integrated model shown in Figure 24, individual models A1 to A4 are listed. This integrated model does not include individual models A5 and A6. As a result, individual models A5 and A6, whose corresponding weights are 2 or less, are not executed. In both examples in Figure 23 and Figure 24, no verification data for individual models A5 and A6 is input while the integrated model is running.

[0057] By selecting individual models to execute based on their weight, only the most important individual models are executed. For example, the execution of individual models that are unlikely to improve a faulty mode is suppressed, reducing the burden of verification by operators when running the integrated model.

[0058] Furthermore, the number of individual models executed can be controlled by adjusting the scores related to the weights of all causes, as shown in tables 360-400 in Figures 10-14. For example, the higher the score in tables 360, 390, or 400, or the higher the multiplier in table 370 or 380, the uniformly higher the weight of each cause. This increases the number of individual models executed. For example, the scores related to the weights of causes are adjusted according to the manpower available to run the integrated model. Companies with multiple manufacturing sites can standardize the process within the company by not using table 360, or they can adjust the scores to match the capabilities of each site by using table 360.

[0059] The advantages of the embodiment will be explained. When a product malfunctions, corrective measures are typically implemented. When a person devises these measures, the content depends on their experience and knowledge, leading to inconsistencies in the solutions. One approach is to prepare a list of possible solutions in advance and implement them when a malfunction occurs. In this case, the order in which the solutions are implemented affects the time required for improvement. That is, the sooner effective solutions are implemented, the shorter the time it takes to resolve the malfunction. However, the order depends on the person's experience and knowledge, and determining the order can be burdensome. In particular, some products have multiple causes for a single malfunction mode. Furthermore, common causes may exist between different malfunction modes. Therefore, it is not easy for a person to appropriately determine the correct solutions for each malfunction mode.

[0060] In addressing these challenges, the processing method according to the embodiment first references individual models. These individual models are prepared in advance and represent countermeasures for the causes of failure modes in the product. Next, an integrated model is generated for each of the multiple failure modes. The integrated model is generated by rearranging and connecting the multiple individual models. At this time, the order of the multiple individual models is determined according to the multiple weights set for each of the multiple causes. These processes can be executed by a computer.

[0061] According to the embodiment, an integrated model is generated for each failure mode. Therefore, when any failure occurs, the appropriate integrated model corresponding to that failure mode can be executed. Furthermore, each integrated model is generated by rearranging multiple individual models according to weights indicating importance or effectiveness. Therefore, the order of the individual models does not depend on human knowledge, experience, etc. In addition, according to the generated integrated model, the individual models that are effective in improvement are executed more quickly, and the time to improvement can be shortened. Moreover, since the generation of multiple integrated models is performed by a computer, the burden on humans can be reduced.

[0062] According to the embodiment, an integrated model effective for improving defects can be automatically generated.

[0063] The embodiment is particularly effective for products produced through the substrate mounting process, and products produced through the resin molding process or die casting process. These processes are particularly prone to a wide variety of defects, and the causes of these defects are also diverse. Therefore, it is difficult for humans to determine countermeasures against defects. According to the embodiment, effective countermeasures can be automatically generated even for defects in products produced through such processes.

[0064] Figure 25 is a schematic diagram showing a processing system according to an embodiment. The processing method M1 shown in Figure 1 can be executed by the processing system 1 shown in Figure 25. The processing system 1 includes a generation device 10, a collection system 20, a first storage device 31, a second storage device 32, a third storage device 33, and an execution device 40.

[0065] The generation device 10 executes the flowchart shown in Figure 1 to generate an integrated model. The execution device 40 executes at least some of the steps in the integrated model. The generation device 10 and the execution device 40 are computers. The generation device 10 may also have the functionality of the execution device 40. The collection system 20 collects quality data. The collection system 20 includes inspection machines installed on each production line. For example, some of the functions of a Manufacturing Execution System (MES) can be used as the collection system 20. The first to third storage devices 31 to 33 store the first to third databases, respectively. The generation device 10, the collection system 20, the first to third storage devices 31 to 33, and the execution device 40 are connected to each other via wired communication, wireless communication, or the internet.

[0066] (Examples) Figure 26 is a schematic diagram showing a manufacturing line for a mounted circuit board. For example, as shown in Figure 26, the printed circuit board manufacturing line 600 includes a printing press 602, a printing inspection machine 604, a mounter 606, a mounting inspection machine 608, a reflow oven 610, and a visual inspection machine 612, and processes the circuit board 614a. The circuit board 614a is a PWB. The PWB circuit board 614a is fed into the manufacturing line 600, and a printed circuit board (PCB) circuit board 614b with electronic components mounted is manufactured.

[0067] The printer 602 prints solder paste onto the circuit board 614a. The print inspection machine 604 takes an image of the circuit board 614a with the solder paste printed on it. The print inspection machine 604 checks from the image whether the solder paste has been printed properly.

[0068] The mounter 606 mounts electronic components onto the substrate 614a. In the illustrated example, multiple mounters 606 each mount multiple electronic components onto a single substrate 614a. The mounting inspection machine 608 images the substrate 614a with the electronic components mounted on it. The mounting inspection machine 608 checks from the image whether the electronic components are properly mounted.

[0069] The reflow oven 610 heats the substrate 614a and melts the solder paste. As the temperature of the substrate 614a decreases, the solder paste solidifies, and the mounted electronic components are electrically connected to the solder. This manufactures the substrate 614b. The visual inspection machine 612 takes an image of the soldered substrate 614b. The visual inspection machine 612 checks from the image whether the electronic components are properly soldered.

[0070] Figure 27 is a schematic diagram showing the processing system according to the embodiment. For example, as shown in Figure 27, the processing system 1a is applied to the manufacturing line 600. The processing system 1a comprises a generation device 10, a collection system 20, and the first to fourth databases DB1 to DB4.

[0071] The manufacturing line 600 and processing equipment 620 function as a data collection system 20. Specifically, the printer 602, mounter 606, and reflow oven 610 store preset settings or processing conditions measured during processing in a fourth database DB4 via the network for processing the substrate 614a. For example, the printer 602 stores the amount of solder printed, printing pressure, temperature, and print head movement speed in the fourth database DB4. The reflow oven 610 stores the reflow temperature, pressure, etc. in the fourth database DB4.

[0072] The printing inspection machine 604, the mounting inspection machine 608, and the visual inspection machine 612 store identification data (ID) of the inspected substrate 614a or 614b, the time the inspection result was obtained, the ID of the inspection machine, inspection conditions, inspection results, and quality data based on the inspection results in the fourth database DB4 via the network. For example, the printing inspection machine 604 and the mounting inspection machine 608 each store in the fourth database DB4 the amount of deviation of solder and electronic components relative to the standard position, and inspection results based on the amount of deviation. The visual inspection machine 612 stores in the fourth database DB4 the amount of solder overflow from electronic components and inspection results based on the amount of overflow.

[0073] Furthermore, each inspection machine transmits the obtained data to a processing unit 620 provided in conjunction with the inspection machine. The processing unit 620 can display the received data on a monitor 621 (display device). An inspector 625 is assigned to each inspection machine. The inspector 625 can check the data obtained from the inspection machine on the monitor 621. If a defect in the substrate 614a or 614b is found from the data of the inspection machine, the inspector 625 may use the processing unit 620 to save the data related to the defect to the fourth database DB4.

[0074] The first database DB1 stores multiple failure modes and multiple causes. The second database DB2 stores multiple causes and multiple individual models. The generation device 10 accesses the first database DB1 and the second database DB2 and pre-generates an integrated model from the data in the first database DB1 and the second database DB2. The generation device 10 also accesses the fourth database DB4 and retrieves the data stored in the fourth database DB4. The generation device 10 links the retrieved data with each other as appropriate. For example, the generation device 10 links the obtained data for each inspection machine. The generation device 10 may also link the data obtained in the processing of each substrate 614a or 614b.

[0075] The generation device 10 determines whether the obtained data contains data indicating a defect in substrate 614a or 614b. If there is data indicating a defect in substrate 614a or 614b, the generation device 10 executes an integrated model corresponding to the defect mode indicated by that data. In other words, in the processing system 1a, the generation device 10 also functions as the execution device 40 shown in Figure 25.

[0076] For example, the processing unit 620 operates as a client, and the generation device 10 operates as a server on the network. When the integrated model is executed by the generation device 10, the countermeasures for each individual model are displayed on the monitor 621. The countermeasures are executed, for example, by an inspector 625. The countermeasures may also be executed by an engineer responsible for maintenance, etc. Here, we will describe an example in which the countermeasures are executed by an inspector 625. The inspector 625 inputs the results of the countermeasures into the processing unit 620. The processing unit 620 transmits the input data to the generation device 10.

[0077] The generation device 10 saves the data obtained during the execution of the integrated model to the third database DB3. The generation device 10 determines whether the integrated model needs to be updated if the weights of the first database DB1 change due to the saving of data to the third database DB3. If the integrated model needs to be updated, the generation device 10 generates a new integrated model.

[0078] Figure 28 shows an example of output from the processing apparatus according to the embodiment. Figures 29 to 34 show examples of output from the generation apparatus according to the embodiment. If the inspector detects a defect in substrate 614a or substrate 614b using the inspection machine, they input data into the user interface (UI) 700, for example, as shown in Figure 28. The UI 700 displays input fields 701a to 705a, icons 701b to 705b, and icon 706. The inspector inputs the data using the input device provided in the processing unit while checking the UI 700.

[0079] The product (circuit board) ID is entered in input field 701a. The inspector can display a list of product names by clicking icon 701b and select an ID from the list. Alternatively, the processing unit 620 may accept input from an ID reader connected to the processing unit 620. The reader may be a barcode reader, QR code (registered trademark) reader, color code reader, IC tag reader, etc.

[0080] Input field 702a is used to enter the IDs of equipment such as the printer 602, mounter 606, and reflow oven 610. The inspector can click icon 702b to display a list of equipment names and select an ID from the list. Alternatively, the processing unit 620 may accept a selection of a production line. For example, the inspector may select a production line ID to select all equipment IDs at once. The equipment IDs may also be automatically selected based on the product model number of the substrate 614a or 614b, by referring to a predetermined line or process chart.

[0081] The ID of the worker (inspector) is entered in input field 703a. The inspector can view a list of worker names by clicking icon 703b and can also select an ID from the list.

[0082] Input field 704a is where a code to identify the fault mode is entered. The inspector can click icon 704b to display a list of fault mode names and select a code from the list.

[0083] Input field 705a is used to input the location where a defect occurred on board 614a or 614b. The inspector can click icon 705b to display a list of locations and select a location from the list.

[0084] When data is entered into input fields 701a to 705a, the inspector clicks icon 706 to complete data registration. The generator 10 receives the registered data. The generator 10 executes the integrated model corresponding to the failure mode identified by the failure code.

[0085] The generation device 10 displays the UI 710 shown in Figure 29 on the monitor 621. The UI 710 displays the individual models 711a to 715a included in the executed integrated model as a countermeasure ranking. The countermeasure ranking is the order of the individual models included in the integrated model generated using weights. By clicking on any of the individual models 711a to 715a, the inspector can display the confirmation information 716 for that individual model. In the illustrated example, information about individual model 711a is displayed. For individual models that have already implemented countermeasures and are ranked highly in the countermeasure ranking, the registered confirmation results and countermeasures are displayed. If the integrated model has individual models arranged in series as shown in Figure 4, not all countermeasure rankings are displayed. Only individual models that have already implemented countermeasures and individual models that will be addressed in the future are displayed. As an example, suppose the individual model related to "insufficient solder printing volume" is set to a high position in the countermeasure ranking based on its weight. In this case, the data from the printing inspection machine 604 is referenced, and if there are no problems with the printing inspection results of the defective part, even if it is ranked higher in the weighting system, it is determined that it does not fall under "insufficient solder printing volume" and will not be displayed in the countermeasure ranking.

[0086] Furthermore, when the integrated model is executed, at least some of the individual models may be processed in parallel. If the individual models are processed in parallel, all countermeasure rankings are displayed, and countermeasures are reviewed or executed in order from the top-ranked individual models. Whether the processing of individual models within the integrated model is serial or parallel may be switched by software depending on the processing status of the integrated model. The switching may be performed automatically by the software or selected by the user. As criteria for switching modes, for example, the number of individual models currently running or the CPU and memory usage as indicators of the processing speed of the generation device 10 can be used. When the integrated model processes serially, countermeasures can be displayed quickly and executed early, while when it processes in parallel, all countermeasures can be displayed at once.

[0087] The content (countermeasures) displayed in confirmation information 716 is implemented. The confirmation items may display not only the name of the individual model but also the actual work performed. For example, if checking squeegee wear, the system may instruct the inspector to stop the printer, wipe off the squeegee paste, and visually check for deformation due to wear. The countermeasures are carried out, for example, by the inspector. The countermeasures may also be carried out by an engineer in charge of maintenance, etc. The inspector enters the results of the confirmation into input fields 716a to 716d and clicks icon 717 to register the data. The generation device 10 receives the registered confirmation data. The inspector carries out the countermeasures indicated by the individual model in the displayed order 711b to 715b until the cause of the defect is identified.

[0088] Monitor 621 may display a screen for narrowing down the displayed countermeasures (individual models). The generation device 10 displays the UI 720 shown in Figure 30 on Monitor 621. UI 720 displays input fields 721a to 727a, icons 722b to 727b, and icon 728.

[0089] Input field 721a is for entering a period. Once a period is entered, the system searches for products to which individual models were applied, the countermeasures taken for those products, the verification results of the implemented countermeasures, and the corrective actions taken during that period. The search results include cases where no countermeasures were taken, in which case the verification results and corrective actions may not be displayed. Input field 722a is for entering a product ID. Once a product ID is entered, the system searches for individual models that were previously valid for the product with that product ID. Similarly, input fields 723a to 726a can be used to enter product codes, equipment IDs, worker IDs, and locations, respectively. The system searches for individual models that were previously valid for the products related to the entered data. Inspectors can also click icons 722b to 726b to display a list of product, equipment, worker, and location names, and select an ID or code from the list.

[0090] Inspectors can also enter fault codes into input field 727a. When a fault code is entered, the integrated model corresponding to the fault mode identified by that fault code is displayed. Inspectors can also click icon 727b to display a list of fault mode names and select a code from the list.

[0091] Not all of the items shown in UI720 need to be entered. It is sufficient if one or more of the items are entered. After entering the search criteria, the inspector clicks icon 728. The generator 10 accepts the search criteria and displays the countermeasures (individual models) that match the search criteria on monitor 621.

[0092] Alternatively, when a period is entered in input field 721a, the generation device 10 may calculate the weight of each cause based on the quality data, verification data, etc., obtained during the entered period. The generation device 10 rearranges the individual models according to the calculated weights and generates a new integrated model. For example, by specifying a specific period in the most recent period, an integrated model effective for the failure mode that has occurred recently can be generated. It is also possible to apply the new integrated model to the results executed on past integrated models and display corrective action instructions again. By applying the new integrated model to past results, corrective actions that were not displayed in the past integrated model can be executed. In this case, the corrective action instructions and executed results from past integrated models and individual models are also stored as records.

[0093] As shown in Figure 30, an icon 729 may be displayed on the UI 720 to switch between the functions described above when a period is entered in the input field 721a. By clicking the icon 729, the user can switch between the functions that are used when a period is entered in the input field 721a. In other words, when a period is entered, the user can switch between a function that searches for products, countermeasures, etc. to which individual models are applied, and a function that generates an integrated model according to the period.

[0094] Once the cause of the defect is identified, the inspector inputs the results of the integrated model's execution into the generation device 10. As shown in Figure 31, the generation device 10 displays a UI 730 for inputting the results of the integrated model's execution on the monitor 621. The UI 730 displays input fields 731a to 734a, icons 731b to 734b, and icon 735.

[0095] Input field 731a is for entering the product ID. Input field 732a is for entering the code of the cause of the defect. Input field 733a is for entering the code of the countermeasure that was effective against the defect mode when the integrated model was run. Input field 734a is for entering notes about the effective countermeasure. Inspectors can also click icons 731b to 733b to display a list of product, cause, and defect mode names, and select an ID or code from the list. Inspectors can also click icon 734b to refer to previously entered notes.

[0096] The product ID, cause code, and corrective action code may be automatically entered by the generation device 10 based on the information presented in Figure 29. The inspector enters the necessary data and clicks icon 735. This sends the entered data to the generation device 10. The generation device 10 saves the received data to the third database DB3 as appropriate. It also updates the integrated model as needed.

[0097] As shown in Figure 32, the generation device 10 may display a UI 740 for editing or checking individual models. The UI 740 displays an input field 741, search results 742, an editing area 743, and icons 744. A period is entered in the input field 741. Malfunction modes that occurred during the entered period are searched for, and information regarding the cause of the malfunction mode is displayed in the search results 742.

[0098] The search result 742 displays the name of the individual model, the date the individual model was registered or updated, the number of occurrences indicating the number of cases for which corrective action instructions were issued by the individual model, and the status indicating the implementation status of the corrective action instructions. The individual model ID, the registrant of the individual model, and the code or name of the product to which the individual model is applied may also be displayed. The status may be displayed as, for example, "Not yet corrected" for individual models for which corrective action has not been taken, "In progress" for individual models for which corrective action is being taken, and "Corrected" for individual models for which corrective action has been completed. If all occurrences are not corrected, it may be displayed as "Not yet corrected," or if even one occurrence is not corrected, it may be displayed as "Not yet corrected." In addition, the number of occurrences for "Not yet corrected," "In progress," and "Corrected" may be displayed as a breakdown. The editing area 743 displays the name of the cause 743a, input fields 743b and 743c, icons 743d and 743e. Input field 743b is where the code of the individual model to be configured is entered. Input field 743c is where a memo about the individual model to be configured is entered.

[0099] The user can display a list of countermeasure names by clicking icon 743d, and can also select a countermeasure from the list. The code of the selected countermeasure is entered into input field 743b. In this case, the individual model containing the selected countermeasure can be viewed and edited in UI740. The user can also refer to previously entered notes by clicking icon 743e. The user may be an inspector, a production line manager, or a processing system administrator.

[0100] Once the individual model has been reviewed and edited, the user clicks icon 744. This registers the edited content in the second database, DB2.

[0101] As shown in Figure 33, the generator 10 may display a UI 750 for editing the scores of each element. The UI 750 displays input fields 751 and 752, an icon 753, a search result 754, an editing area 755, and an icon 756. A period is entered in input field 751. Once a period is entered, the score tables registered for the entered period are displayed as search results. The name of the score table may be directly specified in input field 752. The user enters data in input field 751 or 752 and then clicks the icon 753. The search result 754 corresponding to the entered data is displayed. The search result 754 displays the date, score code, score table name, and number of entries. The date indicates the day the score table was registered. The score code is a string used to identify each score table. The number of entries is the number of individual models that reference the score table.

[0102] For example, clicking on any of the data displayed in search result 754 will display data related to the selected score table in the score editing area 755. In the illustrated example, the editing area 755 displays the inspection machine type, score code, presence / absence, and score value included in the score table. The user can enter data in the input fields 755a or 755b for each row and edit the presence / absence conditions and score values ​​for each inspection machine type. Once editing is complete, the user clicks icon 756. Clicking icon 756 registers the edited score.

[0103] As shown in Figure 34, the generation device 10 may display a UI 760 for checking the integrated model. The display area 761 of the UI 760 displays the ranking of the individual models in any integrated model. Through the display area 761 of the UI 760, the user can check the order in which the individual models are arranged in any integrated model.

[0104] In display area 761, the user may be able to change the order of individual models. Once editing of the integrated model is complete, the user clicks icon 762. This registers the edited content.

[0105] A manufacturing line for PCBs is equipped with equipment manufactured by multiple companies, and each piece of equipment is assigned an engineer. For example, if a defect occurs, each engineer investigates the cause for their respective piece of equipment and implements countermeasures.

[0106] For example, for the printing press 602, the following are performed: cleaning and checking the condition of the metal mask, cleaning and checking the mounting condition of the squeegee, cleaning and checking the condition of the backup plate, cleaning the inside of the equipment, checking the temperature controller or air conditioner, and greasing the drive unit of the device. For the mounter 606, the following are performed: cleaning and checking the condition of the nozzles, maintenance of the head unit, cleaning and checking the condition of the feeder, cleaning the inside of the equipment, and greasing the drive unit of the device. For the reflow oven 610, the following are performed: removal and cleaning of flux inside the oven, adjustment and checking of the labyrinth height, cleaning and checking of various sensors such as the oxygen concentration meter, cleaning and checking of the reflow pallet, cleaning and checking of the fan, and checking of the temperature profile.

[0107] If each engineer were to investigate the cause of a defect and implement countermeasures for their respective piece of equipment, a significant amount of time would be spent in total. Traditionally, it has been difficult to implement optimal countermeasures for defects throughout the entire 600-unit manufacturing line.

[0108] To address this issue, processing system 1a generates an integrated model in which countermeasures for the manufacturing line 600 are ordered for each failure mode. When a failure occurs, countermeasures are executed sequentially according to the integrated model corresponding to that failure mode. For example, by executing countermeasures according to the integrated model, ineffective or unnecessary countermeasures are less likely to be implemented. This allows for earlier detection of the cause of the failure mode and faster recovery of the manufacturing line 600.

[0109] Figure 35 is a schematic diagram showing the hardware configuration. Each of the generating device 10 and the executing device 40 includes, for example, the configuration of the computer 90 shown in Figure 35. The computer 90 includes a CPU 91, ROM 92, RAM 93, storage device 94, input interface 95, output interface 96, and communication interface 97.

[0110] ROM92 stores programs that control the operation of computer 90. ROM92 contains the programs necessary for computer 90 to perform each of the processes described above. RAM93 functions as a memory area where the programs stored in ROM92 are loaded.

[0111] The CPU 91 includes processing circuits. The CPU 91 uses the RAM 93 as work memory and executes programs stored in at least one of the ROM 92 or the storage device 94. During program execution, the CPU 91 controls each component via the system bus 98 and performs various processes.

[0112] The memory device 94 stores data necessary for program execution and data obtained through program execution.

[0113] The input interface (I / F) 95 connects the computer 90 and the input device 95a. The input I / F 95 is, for example, a serial bus interface such as USB. The CPU 91 can read various data from the input device 95a via the input I / F 95.

[0114] The output interface (I / F) 96 connects the computer 90 to the output device 96a. The output I / F 96 is a video output interface such as a Digital Visual Interface (DVI) or a High-Definition Multimedia Interface (HDMI®). The CPU 91 can send data to the output device 96a via the output I / F 96 and display an image on the output device 96a.

[0115] The communication interface (I / F) 97 connects the computer 90 to a server 97a located outside the computer 90. The communication I / F 97 is, for example, a network card such as a LAN card. The CPU 91 can read various data from the server 97a via the communication I / F 97.

[0116] The storage device 94 includes one or more selected from Hard Disk Drives (HDDs) and Solid State Drives (SSDs). The input device 95a includes one or more selected from a mouse, keyboard, microphone (voice input), and touchpad. The output device 96a includes one or more selected from a monitor and a projector. Devices that have the functions of both input device 95a and output device 96a, such as a touch panel, may also be used.

[0117] The functions of the generation device 10 and the execution device 40 may be implemented by a single computer or by the cooperation of multiple computers. The processing of the various data described above may be recorded as a program that can be executed by a computer on a magnetic disk (flexible disk and hard disk, etc.), an optical disk (CD-ROM, CD-R, CD-RW, DVD-ROM, DVD±R, DVD±RW, etc.), a semiconductor memory, or another non-transitory computer-readable storage medium.

[0118] For example, information recorded on a recording medium can be read by a computer (or embedded system). The recording format (storage format) of the recording medium is arbitrary. For example, a computer reads a program from the recording medium and has the CPU execute the instructions written in the program based on this program. In a computer, program acquisition (or reading) may be performed via a network.

[0119] According to the embodiments described above, a processing method, a generating apparatus, a processing system, a program, and a storage medium are provided that can automatically generate an integrated model effective for improving defects.

[0120] Although several embodiments of the present invention have been illustrated above, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. Furthermore, the embodiments described above can be implemented in combination with each other. [Explanation of Symbols]

[0121] 1: Processing system, 10: Generator, 20: Collection system, 31: First memory device, 32: Second memory device, 33: Third memory device, 40: Execution device, 90: Computer, 100: First database, 200: Second database, 250: Integrated model, 600: Manufacturing line, 602: Printer, 604: Print inspection machine, 606: Mounter, 608: Assembly inspection machine, 610: Reflow oven, 612: Visual inspection machine, 614a, 614b: Substrate, 620: Processing device, 621: Monitor, 625: Inspector, DB1: First database, DB2: Second database, DB3: Third database, DB4: Fourth database, M1: Processing method

Claims

1. On the computer, A separate model that shows countermeasures for the cause of a failure mode in a product, which includes a determination step for determining whether the cause is occurring, a processing step that is executed when it is determined that the cause is occurring, an exit terminal indicating the end of the separate model and the integrated model, and a return terminal that proceeds when it is determined that the cause is not occurring, and refers to the separate model. For each of the multiple failure modes, the multiple individual models are rearranged according to the multiple weights set for each of the multiple causes, and the integrated model is generated by connecting the return terminal of one individual model to the first step of another individual model that is connected next to that individual model in the rearranged multiple individual models. Processing method.

2. To the aforementioned computer, To obtain quality data regarding the aforementioned product, If the quality data indicates the occurrence of any of the aforementioned failure modes, the integrated model corresponding to the occurrence of the failure mode is executed. The processing method according to claim 1.

3. The processing method according to claim 2, wherein the computer receives confirmation data relating to some of the multiple causes obtained when the integrated model is executed.

4. The processing method according to claim 3, wherein the computer updates the weights of at least some of the plurality of causes using the verification data.

5. The processing method according to claim 4, wherein the computer updates one or more of the integrated models in accordance with the update of the weights.

6. To the aforementioned computer, A user interface showing data relating to one of the aforementioned multiple individual models is displayed on the display device. The user interface allows the user to edit the data. The processing method according to any one of claims 1 to 5.

7. The processing method according to any one of claims 1 to 5, wherein when the integrated model is executed, the computer causes one or more of the rearranged individual models to be displayed on a display device.

8. The processing method according to any one of claims 2 to 5, wherein each of the integrated models is generated using two or more individual models corresponding to two or more of the causes whose weights are greater than a threshold among the plurality of causes.

9. The processing method according to any one of claims 2 to 5, wherein when the integrated model is executed, only one or more individual models corresponding to one or more of the causes whose weight is greater than a threshold are executed.

10. The processing method according to any one of claims 1 to 5, wherein the plurality of weights are determined using one or more selected from a first group consisting of a score based on the number of occurrences of each of the plurality of causes, a score based on the configuration of the production line of the product, a score based on the size of personnel involved in the production of the product, a score based on the repair man-hours for each of the plurality of failure modes, a score based on the price of the parts of the product, a score based on the difficulty of producing the product, a score based on the types of parts included in the product, a score based on the production environment of the product, a score based on the number of years elapsed since the production of the manufacturing equipment for the product, and a score based on the timing of occurrence of each of the plurality of causes.

11. The processing method according to claim 10, wherein the plurality of weights are obtained by inputting one or more selected from the first group into a neural network.

12. A separate model that shows countermeasures for the cause of a failure mode in a product, which includes a determination step for determining whether the cause is occurring, a processing step that is executed when it is determined that the cause is occurring, an exit terminal indicating the end of the separate model and the integrated model, and a return terminal to proceed to when it is determined that the cause is not occurring, For each of the multiple failure modes, the multiple individual models are rearranged according to the multiple weights set for each of the multiple causes, and the integrated model is generated by connecting the return terminal of one individual model to the first step of another individual model that is connected next to that individual model. generator.

13. The generating apparatus according to claim 12, A data collection system for collecting quality data related to the aforementioned product, A processing system equipped with [the following features].

14. A program that causes the computer to execute the processing method described in any one of claims 1 to 5.

15. A storage medium storing a program that causes the computer to execute the processing method described in any one of claims 1 to 5.

Images