Information processing method, information processing device, and program

Abstract

Provided is an information processing method with which it is possible to evaluate and update a production plan on the basis of an estimated result of a current production capacity relating to a production facility. According to the information processing method, which is used for updating the production plan for producing a product using the production facility, an information processing device: estimates the current production capacity relating to the production facility on the basis of actual production result data indicating an actual value of the production capacity of the production facility; evaluates the production plan on the basis of the estimated current production capacity; and updates the production plan on the basis of the result of the evaluation.

Description

Technical Field

[0001] The present disclosure relates to an information processing method, an information processing apparatus, and a program.

Background Art

[0002] Patent Document 1 discloses a production plan creation apparatus that creates a production plan for a manufacturing process composed of a plurality of work processes.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

[0004] However, in Patent Document 1, no consideration is given to estimating the current production capacity of production facilities and evaluating and updating the production plan based on the estimation result.

[0005] An object of the present disclosure is to provide an information processing method, an information processing apparatus, and a program capable of evaluating and updating a production plan based on an estimation result of the current production capacity of production facilities.

[0006] An information processing method according to one aspect of the present disclosure is an information processing method for updating a production plan for producing products using production equipment, wherein the information processing device estimates the current production capacity of the production equipment based on production performance data indicating the actual production capacity of the production equipment, evaluates the production plan based on the estimated current production capacity, and updates the production plan based on the results of the evaluation. An information processing device according to another aspect of the present disclosure is an information processing device for updating a production plan for producing products using production equipment, comprising: an estimation unit that estimates the current production capacity of the production equipment based on production performance data indicating the actual production capacity of the production equipment; an evaluation unit that evaluates the production plan based on the current production capacity estimated by the estimation unit; and an update unit that updates the production plan based on the results of the evaluation by the evaluation unit.

[0007] A program according to another aspect of the present disclosure causes an information processing device for updating a production plan for producing products using production equipment to execute a function that estimates the current production capacity of the production equipment based on production performance data indicating the actual production capacity of the production equipment, evaluates the production plan based on the current production capacity estimated by the estimation means, and updates the production plan based on the results of the evaluation by the evaluation means.

[0008] According to this disclosure, production plans can be evaluated and updated early based on the estimated current production capacity of production facilities, thereby reducing the risk of delivery delays and facilitating on-site response. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows the configuration of a production planning management device according to an embodiment of the present disclosure. [Figure 2] This is a simplified diagram showing production capacity information. [Figure 3] This diagram shows a simplified representation of the switching time information. [Figure 4] This is a diagram that shows order information in a simplified form. [Figure 5]This diagram shows production performance data in a simplified form. [Figure 6] This diagram shows a simplified representation of the actual switching data. [Figure 7] This diagram shows the current production capacity estimation process. [Figure 8] This figure shows the current process for estimating the switching time. [Figure 9] This is a simplified diagram showing production plan information. [Figure 10] This diagram shows a selection of jobs included in the production plan information. [Figure 11] This is a flowchart showing the processing flow executed by the information processing unit. [Figure 12] This diagram shows a simplified version of the simulation results for production planning information. [Figure 13] This diagram shows a simplified version of the process for updating production plan information. [Figure 14] This diagram shows a simplified version of the process for updating production plan information. [Figure 15] This diagram shows a simplified version of the process for updating production plan information. [Figure 16] This diagram shows a simplified version of the process for updating production plan information. [Modes for carrying out the invention]

[0010] (Knowledge that forms the basis of this disclosure) In production lines that use multiple production facilities to produce multiple types of products, a production plan is formulated to prevent delivery delays, and the operation of each production facility is managed according to that plan. For example, the production plan for the current month is formulated on the first working day of each month.

[0011] However, the production capacity (production volume per unit time) of each production facility fluctuates daily due to various factors, including mechanical problems. Therefore, if production does not proceed according to the production plan and a delay in delivery occurs, or if there is a high probability of such a delay, the production plan needs to be reviewed.

[0012] However, if the production plan is updated after or just before the delivery delay occurs, it will be difficult to respond on-site in the production line or the like, and there is a risk of inducing another mistake.

[0013] In order to solve such problems, the present inventors estimated the current production capacity based on production performance data indicating the actual values of the production capacity of production equipment, and evaluated the production plan based on the estimated current production capacity, and obtained the knowledge that the production plan can be updated at an early stage, and arrived at the present disclosure.

[0014] Next, embodiments of the present disclosure will be described.

[0015] (Embodiments of the Present Disclosure) Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. Elements having the same reference numerals in different drawings indicate the same or corresponding elements. In addition, the components, the arrangement positions of the components, the connection forms, the order of operations, etc., shown in the following embodiments are examples, and are not intended to limit the present disclosure. The present disclosure is limited only by the claims. Therefore, among the components in the following embodiments, the components not described in the independent claims indicating the highest concept of the present disclosure are not necessarily required to achieve the problems of the present disclosure, but are described as constituting a more preferable form.

[0016] FIG. 1 is a diagram showing the configuration of a production plan management device 1 according to an embodiment of the present disclosure. The production plan management device 1 includes an information processing unit 11, a storage unit 12, a communication unit 13, an input unit 14, and a display unit 15. The production plan management device 1 may be configured as a dedicated terminal or may be configured by a general-purpose personal computer or the like.

[0017] The information processing unit 11 is configured using a processor (information processing device) such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The storage unit 12 is configured using an HDD (Hard Disk Drive), SSD (Solid State Drive), or semiconductor memory. The communication unit 13 is configured using a communication module compatible with any communication standard such as Bluetooth (registered trademark) or Wi-Fi (registered trademark). The input unit 14 is configured using any input device such as a touch panel, mouse, or keyboard. The display unit 15 is configured using a liquid crystal display or an organic EL (Electroluminescence) display. The information processing unit 11 may also be implemented in an external terminal or server device capable of communicating with the production planning management device 1. External terminals include personal computers, smartphones, or tablet devices. Server devices include edge servers or cloud servers.

[0018] The memory unit 12 stores production capacity information 31, changeover time information 32, order information 33, production performance data 34, changeover performance data 35, capacity estimation model 36, changeover estimation model 37, and production planning information 38. The production capacity information 31, changeover time information 32, order information 33, production performance data 34, and changeover performance data 35 are input to the memory unit 12 from the communication unit 13 or the input unit 14, and the memory unit 12 holds this information and data.

[0019] Figure 2 is a simplified diagram of the production capacity information 31. The production capacity information 31 is a database containing multiple items such as production equipment, product type, and production capacity (units / day). The types of products that can be produced and the production capacity differ depending on the production equipment. For example, the production capacity when producing product type A using production equipment X is a maximum of 500 units per day.

[0020] Figure 3 is a simplified diagram of the transition time information 32. The transition time information 32 is a database containing multiple items: production equipment, product type before transition, product type after transition, and transition time (hours). The transition time is the time required to switch the product produced by a certain production equipment from one product type to another. The transition time differs depending on the production equipment, product type before transition, and product type after transition. For example, the transition time when switching the product produced by production equipment X from product type A to product type B is 5.0 hours.

[0021] Figure 4 is a simplified diagram of order information 33. Order information 33 is a database containing multiple items such as product type, quantity, and delivery date. For example, it indicates that 1000 units of product type A need to be delivered by April 5, 2022 (indicated as 2022-04-05).

[0022] Figure 5 is a simplified diagram of the production performance data 34. The production performance data 34 is a database containing multiple items such as production equipment, product type, production start date and time, production end date and time, and production quantity, and shows the actual production capacity of the production equipment. For example, it means that 100 units of product type A were produced by production equipment X between 8:00 AM on April 1, 2022 (indicated as 2022-04-01 08:00) and 6:00 PM on April 1, 2022 (indicated as 2022-04-01 18:00). The production performance data 34 includes updated actual values, which are the actual values ​​since the last update of the production plan information 38, and pre-update actual values, which are the actual values ​​before the last update of the production plan.

[0023] Figure 6 is a simplified diagram of the changeover performance data 35. The changeover performance data 35 is a database containing multiple items such as date and time, production equipment, product type before changeover, product type after changeover, and changeover time (hours), and shows the actual value of the changeover time. For example, on April 2, 2022 at 18:00 (indicated as 2022-04-02 18:00), a changeover operation was performed at production equipment X from product type A to product type B, and the changeover time at that time was 4.5 hours. The changeover performance data 35 includes the post-update actual value, which is the actual value since the last update of the production plan information 38, and the pre-update actual value, which is the actual value before the last update of the production plan.

[0024] Figure 7 shows the current production capacity estimation process using the capacity estimation model 36. The capacity estimation model 36 is an estimation model that uses, for example, Bayesian estimation, and machine learning is performed using production performance data 34. Based on the production performance data 34, the capacity estimation model 36 estimates the current production capacity for each production facility. The production performance data 34 includes updated performance values ​​and pre-update performance values, and when estimating the current estimated capacity by a weighted average of the two, the weight values ​​of the updated performance values ​​may be set higher than the weight values ​​of the pre-update performance values. Input data DI1 and DI2 are input to the capacity estimation model 36, and output data DO1 is output from the capacity estimation model 36. Input data DI1 represents the production facility, input data DI2 represents the product type, and output data DO1 represents the probability distribution of production capacity. The horizontal axis of output data DO1 is production capacity, and the vertical axis is probability density. In other words, the capacity estimation model 36 is a machine learning-prepared estimation model that uses production facilities and product types as explanatory variables and the probability distribution of production capacity as the dependent variable. As the estimation model algorithm, any algorithm capable of estimating the distribution of probability density for continuous values ​​can be used, such as random forests, neural networks, gradient boosting, or linear regression.

[0025] Figure 8 shows the current switching time estimation process using the switching estimation model 37. The switching estimation model 37 is an estimation model that uses, for example, Bayesian estimation, and machine learning is performed using switching performance data 35. Based on the switching performance data 35, the switching estimation model 37 estimates the current switching time for each production facility. The switching performance data 35 includes updated performance values ​​and pre-update performance values. Here, when estimating the current switching time by a weighted average of the two, the weight value of the updated performance value may be set higher than the weight value of the pre-update performance value. Input data DI1, DI3, and DI4 are input to the switching estimation model 37. Output data DO2 is output from the switching estimation model 37. Input data DI1 shows the production facility, input data DI3 shows the product type before switching, input data DI4 shows the product type after switching, and output data DO2 shows the probability distribution of switching time. In the output data DO2, the horizontal axis is switching time, and the vertical axis is probability density. In other words, the switching estimation model 37 is a machine learning-based estimation model that uses production equipment, product varieties before switching, and product varieties after switching as explanatory variables, and the probability distribution of switching time as the dependent variable. As the algorithm for the estimation model, any algorithm capable of estimating the distribution of probability density for continuous values ​​can be used, such as random forest, neural network, gradient boosting, or linear regression.

[0026] Figure 9 is a simplified diagram showing the current production plan information 38 that was last updated and stored in the memory unit 12. The production plan information 38 has an arrangement pattern P1 of multiple jobs J1 to J8 arranged in chronological order by product type for production by the production equipment. The horizontal axis represents time, and the vertical axis represents the classification of production equipment X to Z. The gap between two adjacent jobs on the horizontal axis is the switchover time. Production equipment X processes jobs J1 to J3 in order, production equipment Y processes jobs J4 to J6 in order, and production equipment Z processes jobs J7 and J8 in order. The length of each job J on the horizontal axis corresponds to the production time. At the end of each job J, the probability value of a delivery delay occurring for that job is indicated. For example, the probability of a delivery delay occurring for job J1 is 2%.

[0027] Figure 10 shows a selection of jobs J1 and J2 included in the production plan information 38. The production time required for job J1, the switchover time between jobs J1 and J2, and the production time required for job J2 are defined as probability distributions K1, K12, and K2, respectively. For example, for job J2, the integral of the portion of the probability distribution K2 located to the right of the rightmost edge of job J2 corresponds to the probability of a delivery delay occurring for job J2.

[0028] As shown in Figure 1, the information processing unit 11 includes an acquisition unit 21, an estimation unit 22, a prediction unit 23, an evaluation unit 24, an update unit 25, and an output unit 26, which are functions realized by the processor executing a program read from a non-volatile recording medium such as a computer-readable ROM (Read Only Memory). In other words, the above program is a program that causes the information processing unit 11, which is an information processing device installed in the production planning management device 1, to function as an acquisition unit 21, an estimation unit 22, a prediction unit 23, an evaluation unit 24, an update unit 25, and an output unit 26. Details of the processing content executed by each processing unit will be described later.

[0029] Figure 11 is a flowchart showing the processing flow executed by the information processing unit 11.

[0030] First, in step SP01, the acquisition unit 21 acquires production capacity information 31, changeover time information 32, order information 33, production performance data 34, and changeover performance data 35 by reading them from the storage unit 12.

[0031] Next, in step SP02, the estimation unit 22 uses the capacity estimation model 36 to estimate the current production capacity for each production facility based on the production performance data 34. The estimation unit 22 also uses the switchover estimation model 37 to estimate the current switchover time for each production facility based on the switchover performance data 35.

[0032] Next, in step SP03, the prediction unit 23 performs a simulation to evaluate the current production plan information 38 using the current production capacity and current changeover time estimated by the estimation unit 22. That is, the prediction unit 23 predicts the production time required for each job J and the changeover time between each adjacent job J by recalculating them using the current production capacity and current changeover time estimated by the estimation unit 22 for the current production plan information 38 shown in Figure 9. The prediction unit 23 also predicts the probability of delivery delays occurring for each job J by recalculating them.

[0033] Figure 12 is a simplified diagram showing the simulation results of production plan information 38 after step SP03. The probability of a delivery delay for job J3 increased from 5% at the time of the previous update (Figure 9) to 15% in the simulation results.

[0034] As shown in Figure 11, in step SP04, the evaluation unit 24 determines whether or not there is a risk of delivery delay in the simulation results. An acceptable value (e.g., 5%) is set for the probability of delivery delay, and the evaluation unit 24 determines that there is a risk of delivery delay if there are jobs J whose probability of delivery delay exceeds the acceptable value, and on the other hand, it determines that there is no risk of delivery delay if there are no jobs J whose probability of delivery delay exceeds the acceptable value.

[0035] If it is determined that there is no risk of delivery delay (Step SP04: NO), the process is terminated without updating the current production plan information 38.

[0036] If it is determined that there is a risk of delivery delay (Step SP04: YES), then in Step SP05, the update unit 25 updates the current production plan information 38.

[0037] Figures 13 to 16 show a simplified version of the update process for production plan information 38. Figure 13 shows how the update unit 25 extracts the portion of job J3 that exceeds the allowable value for the probability of delivery delay, creating a new job J9, and sequentially inserts it between other jobs J to change the sequence pattern P. Figure 14 shows the case where the new job J9 is inserted after job J6. Figure 15 shows the case where the new job J9 is inserted between jobs J4 and J5. Figure 16 shows the case where the new job J9 is inserted between jobs J7 and J8.

[0038] As shown in Figure 13, first, the update unit 25 extracts the excess portion of job J3 that exceeds the tolerance value for the probability of delivery delay, creating a new job J9. Next, the update unit 25 sequentially inserts the extracted excess portion of job J9 between other jobs J to change the sequence pattern P, and then re-executes the above simulation for each sequence pattern P.

[0039] As shown in Figure 14, when job J9 is inserted after job J6 as in the array pattern P2, the switching time between jobs J6 and J9 is very long, resulting in a probability of delivery delay for job J9 exceeding the acceptable value at 20%.

[0040] As shown in Figure 15, when job J9 is inserted between jobs J4 and J5 as in the array pattern P3, the probability of delivery delays for all jobs J1 to J9 is below the acceptable value.

[0041] As shown in Figure 16, when job J9 is inserted between jobs J7 and J8 as in the array pattern P4, the probability of a delivery delay for job J8 exceeds the acceptable value at 8%, while the probability of delivery delays for the other jobs J1-J7 and J9 is below the acceptable value.

[0042] In step SP05, the update unit 25 identifies an optimal arrangement pattern P3 for all jobs J1 to J9 in which the probability of delivery delays is below an acceptable value, and updates the production plan information 38 in accordance with this optimal arrangement pattern.

[0043] As shown in Figure 11, in step SP06, the output unit 26 outputs the updated production plan information 38 from the update unit 25. The output updated production plan information 38 is input to the display unit 15 and displayed on the display screen of the display unit 15.

[0044] If there is no sequence pattern P3 in which the probability of delivery delays for all jobs J1 to J9 is below an acceptable value, the update unit 25 identifies the sequence pattern P4 that minimizes the maximum probability of delivery delays for all jobs J1 to J9 as the optimal sequence pattern, and updates the production plan information 38 in accordance with that optimal sequence pattern.

[0045] In this case, in step SP06, the output unit 26 outputs the updated production plan information 38 from the update unit 25, along with an alert indicating that there are no sequence patterns for all jobs in which the probability of delivery delays is below an acceptable value. The output updated production plan information 38 and the alert are input to the display unit 15 and displayed on the display screen of the display unit 15.

[0046] According to the production planning management device 1 of this embodiment, the estimation unit 22 estimates the current production capacity of the production equipment, allowing the update unit 25 to evaluate and update the production plan early based on the estimation results. As a result, it becomes possible to reduce the risk of delivery delays and facilitate on-site response.

[0047] Furthermore, by having the estimation unit 22 further estimate the current changeover time for the production equipment, the evaluation unit 24 can evaluate the production plan based on the estimated results of both the current production capacity and the current changeover time, thereby improving the accuracy of the evaluation.

[0048] Furthermore, the evaluation unit 24 can perform a quantitative evaluation by evaluating the probability of delivery delays for each of the multiple jobs.

[0049] Furthermore, since the remaining jobs, excluding those immediately before and after the insertion of the excess portion, remain unchanged in their order, the number of changes to the production plan can be minimized. As a result, on-site responses to production plan updates can be made easier.

[0050] (Appearance) From the embodiments described above, the following aspects of the disclosure can be derived. Each aspect of the disclosure will now be described.

[0051] An information processing method according to a first aspect of this disclosure is an information processing method for updating a production plan for producing products using production equipment, wherein the information processing device estimates the current production capacity of the production equipment based on production performance data indicating the actual production capacity of the production equipment, evaluates the production plan based on the estimated current production capacity, and updates the production plan based on the evaluation result.

[0052] According to the first embodiment, by estimating the current production capacity of the production facilities, the production plan can be evaluated and updated early based on the estimation results, thereby reducing the risk of delivery delays and facilitating on-site response.

[0053] In the first aspect of the information processing method relating to the second aspect of this disclosure, it is preferable to use a machine learning-based estimation model in estimating the current production capacity, with the production equipment and the types of products as explanatory variables and the probability distribution of the production capacity as the dependent variable.

[0054] According to the second embodiment, the estimation accuracy can be improved by using a machine learning-based estimation model in estimating current production capacity. Furthermore, by making the target variable of the estimation model a probability distribution of production capacity, it becomes possible to evaluate the risk of delivery delays as a probability value.

[0055] In the third aspect of the present disclosure, the information processing method may, in the first or second aspect, include updated actual values, which are actual values ​​since the last update of the production plan, and pre-update actual values, which are actual values ​​prior to the last update of the production plan.

[0056] According to the third aspect, by including not only pre-update performance values ​​but also post-update performance values ​​in the production performance data, it becomes possible to perform estimations that take into account the situation since the last update of the production plan, and as a result, the estimation accuracy can be improved.

[0057] In the fourth aspect of the information processing method of this disclosure, in the third aspect, it is preferable to set the weight value of the updated actual value higher than the weight value of the pre-update actual value.

[0058] According to the fourth aspect, estimations can be made that place more emphasis on the situation after the previous update of the production plan than on the situation before the previous update, and as a result, estimation accuracy can be improved.

[0059] The information processing method according to the fifth aspect of this disclosure further estimates the current switching time for the production equipment based on switching performance data that shows the actual value of the switching time required to switch the product to be produced by the production equipment from one type to another, in any one of the first to fourth aspects, and in evaluating the production plan, evaluates the production plan based on the estimated current production capacity and the estimated current switching time.

[0060] According to the fifth aspect, by further estimating the current changeover time for production equipment, the production plan can be evaluated based on the estimated results of both the current production capacity and the current changeover time, thereby improving the accuracy of the evaluation.

[0061] In the sixth aspect of the information processing method of this disclosure, in the fifth aspect, it is preferable to use a machine learning-based estimation model in which the production equipment, the product varieties before the changeover, and the product varieties after the changeover are used as explanatory variables and the probability distribution of the changeover time is used as the dependent variable in estimating the current changeover time.

[0062] According to the sixth aspect, the estimation accuracy can be improved by using a machine learning-based estimation model in estimating the current switching time. Furthermore, by making the probability distribution of the switching time the dependent variable of the estimation model, it becomes possible to evaluate the risk of delivery delays as a probability value.

[0063] In the seventh aspect of this disclosure, the information processing method may, in the fifth or sixth aspect, include updated actual values, which are actual values ​​since the last update of the production plan, and pre-update actual values, which are actual values ​​prior to the last update of the production plan.

[0064] According to the seventh aspect, by including not only pre-update performance values ​​but also post-update performance values ​​in the production performance data, it becomes possible to perform estimations that take into account the situation since the last update of the production plan, and as a result, the estimation accuracy can be improved.

[0065] In the information processing method according to the eighth aspect of this disclosure, in the seventh aspect, it is preferable to set the weight value of the updated actual value higher than the weight value of the pre-update actual value.

[0066] According to the eighth aspect, estimations can be made that place more emphasis on the situation after the previous update of the production plan than on the situation before the previous update, and as a result, estimation accuracy can be improved.

[0067] In the information processing method according to the ninth aspect of this disclosure, in any one of the first to eighth aspects, in evaluating the production plan, it is preferable to perform a simulation of the probability distribution of production time based on the estimated current production capacity for each of the multiple jobs, in which the products to be produced by the production equipment are arranged in time series by type, and to evaluate the probability of delivery delays for each of the multiple jobs.

[0068] According to the ninth aspect, a quantitative evaluation can be performed by evaluating the probability of delivery delays for each of the multiple jobs.

[0069] In the tenth aspect of the present disclosure, the information processing method, in the ninth aspect, allows for updating the production plan by extracting the excess portion of a job from which the probability of delivery delays exceeds a tolerance value, sequentially inserting the extracted excess portion between other jobs, re-running the simulation, determining an optimal arrangement pattern in which the probability of delivery delays for all jobs is less than or equal to the tolerance value, or an arrangement pattern in which the maximum probability of delivery delays for all jobs is minimized, and updating the production plan in accordance with the optimal arrangement pattern.

[0070] According to the tenth embodiment, since the remaining jobs other than those before and after the insertion of the excess portion are not rearranged, the number of changes to the production plan can be minimized, and as a result, on-site responses to updates to the production plan can be made easier.

[0071] An information processing device according to an eleventh aspect of the present disclosure is an information processing device for updating a production plan for producing products using production equipment, comprising: an estimation unit that estimates the current production capacity of the production equipment based on production performance data indicating the actual production capacity of the production equipment; an evaluation unit that evaluates the production plan based on the current production capacity estimated by the estimation unit; and an update unit that updates the production plan based on the results of the evaluation by the evaluation unit.

[0072] According to the 11th aspect, by estimating the current production capacity of production facilities, the production plan can be evaluated and updated early based on the estimation results, thereby reducing the risk of delivery delays and facilitating on-site response.

[0073] A program according to a twelfth aspect of this disclosure is a program that causes an information processing device for updating a production plan for producing products using production equipment to execute a function that estimates the current production capacity of the production equipment based on production performance data indicating the actual production capacity of the production equipment, evaluates the production plan based on the current production capacity estimated by the estimation means, and updates the production plan based on the results of the evaluation by the evaluation means.

[0074] According to the 12th aspect, by estimating the current production capacity of production facilities, the production plan can be evaluated and updated early based on the estimation results, thereby reducing the risk of delivery delays and facilitating on-site response.

[0075] This disclosure can also be implemented as a program that causes a computer to execute each characteristic configuration included in such a method or apparatus, or as a system that operates using such a program. It goes without saying that such a computer program can be distributed via a computer-readable, non-temporary recording medium such as a CD-ROM, or via a communication network such as the Internet. [Industrial applicability]

[0076] This disclosure is particularly useful for application to production planning management systems that manage production plans for producing a wide variety of products using multiple production facilities. [Explanation of Symbols]

[0077] 1. Production planning and management system 11. Information Processing Department 22 Estimation part 23 Prediction Section 24 Evaluation Department 25 Update section 34 Production Performance Data 35 Switching Performance Data 36. Capability Estimation Models 37 Switching Estimation Model 38 Production Plan Information

Claims

1. An information processing method for updating a production plan for producing products using production equipment, wherein the information processing device is Based on production performance data showing the actual production capacity of the aforementioned production facility, the current production capacity of the aforementioned production facility is estimated. Based on the estimated current production capacity, the production plan is evaluated. Based on the evaluation results, the production plan will be updated. The aforementioned production performance data includes updated performance values, which are the actual values ​​since the last update of the production plan, and pre-update performance values, which are the actual values ​​prior to the last update of the production plan. An information processing method that sets the weight value of the updated actual value to be higher than the weight value of the pre-update actual value.

2. The information processing method according to claim 1, wherein in estimating the current production capacity, a machine learning-based estimation model is used in which the production equipment and the types of products are used as explanatory variables and the probability distribution of the production capacity is used as the dependent variable.

3. An information processing method for updating a production plan for producing products using production equipment, wherein the information processing device is Based on production performance data showing the actual production capacity of the aforementioned production facility, the current production capacity of the aforementioned production facility is estimated. Based on the actual changeover time data, which shows the actual changeover time required to switch the products produced by the aforementioned production equipment from one type to another, the current changeover time for the aforementioned production equipment is estimated. The production plan is evaluated based on the estimated current production capacity and the estimated current changeover time. Based on the evaluation results, the production plan will be updated. The aforementioned changeover performance data includes the updated performance value, which is the actual value since the last update of the production plan, and the pre-update performance value, which is the actual value before the last update of the production plan. An information processing method that sets the weight value of the updated actual value to be higher than the weight value of the pre-update actual value.

4. The information processing method according to claim 3, wherein in estimating the current switching time, a machine learning-based estimation model is used in which the production equipment, the product varieties before the switching, and the product varieties after the switching are used as explanatory variables, and the probability distribution of the switching time is used as the dependent variable.

5. In evaluating the aforementioned production plan, For each of the multiple jobs arranged in time series by product type for production by the aforementioned production equipment, a simulation of the probability distribution of production time is performed based on the estimated current production capacity. An information processing method according to any one of claims 1 to 4, which evaluates the probability of a delivery delay occurring for each of the aforementioned multiple jobs.

6. In updating the production plan, Of the jobs where the probability of delivery delay exceeds the acceptable value, the portion exceeding that acceptable value is extracted from the job. The extracted excess portion is sequentially inserted between other jobs, and the simulation is rerun. The optimal sequence pattern is determined to be the sequence pattern in which the probability of delivery delays occurring for all jobs is less than or equal to the tolerance value, or the sequence pattern in which the maximum probability of delivery delays occurring for all jobs is minimized. The information processing method according to claim 5, which updates the production plan in accordance with the aforementioned optimal arrangement pattern.

7. An information processing device for updating a production plan for producing products using production equipment, An estimation unit that estimates the current production capacity of the production equipment based on production performance data showing the actual production capacity of the production equipment, An evaluation unit that evaluates the production plan based on the current production capacity estimated by the estimation unit, An update unit updates the production plan based on the results of the evaluation by the evaluation unit, Equipped with, The aforementioned production performance data includes updated performance values, which are the actual values ​​since the last update of the production plan, and pre-update performance values, which are the actual values ​​prior to the last update of the production plan. The estimation unit sets the weight value of the updated actual value to be higher than the weight value of the pre-update actual value.

8. An information processing device for updating production plans for producing products using production equipment, Based on production performance data showing the actual production capacity of the aforementioned production facility, the current production capacity of the aforementioned production facility is estimated. Based on the estimated current production capacity, the production plan is evaluated. Based on the evaluation results, the production plan will be updated. The aforementioned production performance data includes updated performance values, which are the actual values ​​since the last update of the production plan, and pre-update performance values, which are the actual values ​​prior to the last update of the production plan. A program for executing a function that sets the weight value of the updated actual value to be higher than the weight value of the pre-update actual value.

Images