Production management device, production management system, production management method, program, and storage medium

Abstract

To provide a production management device capable of preparing a plan with less deviation from actual production, a production management system, a production management method, a program, and a storage medium.SOLUTION: A production management device is configured to: acquire a first short-term plan generated based on a first long-term plan, the first long-term plan indicating a plan of production in a predetermined period, the first short-term plan indicating a plan of production in a first period shorter than the predetermined period; acquire first result data indicating actual result in work executed along a part of the first short-term plan; and acquire first prediction data by using the first result data, the first prediction data indicating a prediction of an actual result in work to be executed along another part of the first short-term plan. The production management device is configured to: correct the first short-term plan based on the first prediction data; acquire, using second result data indicating an actual result in work in a first period, second prediction data indicating a prediction of an actual result in production in the predetermined period; and prepare a second long-term plan in the predetermined period, using the second prediction data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] An embodiment of the present invention relates to a production management device, a production management system, a production management method, a program, and a storage medium. [Background technology]

[0002] Conventionally, production plans are created using a production scheduler. However, there is a demand for technology that can create plans that have a smaller deviation from actual production. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 6-231135 Summary of the Invention [Problem to be solved by the invention]

[0004] The problem to be solved by the present invention is to provide a production management device, a production management system, a production management method, a program, and a storage medium that are capable of creating a plan that has a smaller deviation from actual production. [Means for solving the problem]

[0005] A production management device according to an embodiment acquires a first short-term plan that is created based on a first long-term plan that indicates a production plan for a predetermined period, and that indicates a production plan for a first period that is shorter than the predetermined period. The production management device further acquires first performance data that indicates the performance of work performed in accordance with a portion of the first short-term plan. The production management device further uses the first performance data to acquire first forecast data that indicates a prediction of the performance of the work performed in accordance with another portion of the first short-term plan. The production management device further modifies the first short-term plan based on the first forecast data. The production management device further uses second performance data that indicates the performance of the work in the first period to acquire second forecast data that indicates a prediction of the production performance for the predetermined period. The production management device further uses the second forecast data to create a second long-term plan for the predetermined period. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a schematic diagram showing the configuration of a production management system according to an embodiment. [Figure 2] 2(a) and 2(b) are tables illustrating examples of production master data. [Figure 3] 3(a) to 3(d) are tables showing examples of manufacturing master data. [Figure 4] Figure 4(a) is an example of a long-term plan, and Figure 4(b) is an example of a short-term plan. [Figure 5] Fig. 5(a) is a schematic diagram showing the state of work, Fig. 5(b) is an image corresponding to Fig. 5(a), and Fig. 5(c) is a schematic diagram showing an example of the classification result. [Figure 6] 6(a) is a schematic diagram showing time-series detection data obtained by a detector, and FIG. 6(b) is a schematic diagram showing template data. [Figure 7] 7(a) is a schematic diagram showing the actual results for a part of the short-term plan, and FIG. 7(b) is a schematic diagram showing the forecast for another part of the short-term plan. [Figure 8]Fig. 8(a) is a table showing a pre-created short-term plan, and Fig. 8(b) is a table showing a revised short-term plan. [Figure 9] 9(a) is a schematic diagram showing the actual results for a part of the revised short-term plan, and FIG. 9(b) is a schematic diagram showing the forecast for another part of the revised short-term plan. [Figure 10] Figure 10(a) is a table showing the revised short-term plan, and Figure 10(b) is a table showing the further revised short-term plan. [Figure 11] Fig. 11(a) is a schematic diagram showing actual results for a part of a predetermined period, and Fig. 11(b) is a schematic diagram showing forecasts for another part of the predetermined period. [Figure 12] 12(a) and 12(b) are tables showing examples of updated manufacturing master data. [Figure 13] 1 is a flowchart showing a production management method according to an embodiment. [Figure 14] 4 is a flowchart showing specific processing by the production management device according to the embodiment. [Figure 15] 4 is a flowchart showing specific processing by the production management device according to the embodiment. [Figure 16] FIG. 2 is a schematic diagram showing a hardware configuration. DETAILED DESCRIPTION OF THE INVENTION

[0007] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the present specification and the drawings, elements similar to those already described are designated by the same reference numerals, and detailed descriptions thereof will be omitted where appropriate.

[0008] The production management system according to the embodiment is used to manage or support the production of products. The production management system modifies or creates a production plan based on data obtained during the execution of production-related tasks. The production plan includes a short-term plan and a long-term plan.

[0009] FIG. 1 is a schematic diagram showing the configuration of a production management system according to an embodiment. As shown in FIG. 1, the production management system 1 according to the embodiment includes a production management device 10, a storage device 20, an imaging device 30, and a detector 40.

[0010] The imaging device 30 is installed at a production site and captures images of workers or items handled during work. For example, the imaging device 30 repeatedly captures still images and stores the image data in the storage device 20. The imaging device 30 may also capture video. In this case, still images are repeatedly extracted from the video.

[0011] The detector 40 detects signals generated by the worker's actions. For example, the detector 40 includes one or more sensors selected from a torque sensor, an acceleration sensor, and an angular velocity sensor, and is provided on a tool such as a digital torque wrench or a digital caliper. The detector 40 detects signals generated when the worker uses the tool. The detector 40 stores the obtained time-series detection data in the storage device 20.

[0012] The detector 40 may be an acceleration sensor or an angular velocity sensor attached to the worker's hand or foot. The detector 40 detects the acceleration or angular velocity of a part of the worker's body. Multiple detectors 40 may be attached to the worker's body. The detector 40 stores the obtained time-series detection data in the storage device 20.

[0013] The storage device 20 stores image data and detection data as well as performance data from past productions, production master data relating to various production elements, and manufacturing master data relating to various manufacturing elements.

[0014] 2(a) and 2(b) are tables illustrating examples of production master data. The production master data 100A and 100B shown in Figures 2(a) and 2(b) include a process column 101, an operation column 102, a lead time column 103, and an available equipment column 104. A product is produced through multiple processes. A character string (name or ID) for identifying each process is registered in the process column 101. Each process includes one or more tasks. A character string for identifying each task is registered in the operation column 102. The lead time column 103 registers the time required from the start to the end of one production task. Hereinafter, lead time will be simply referred to as "LT." In the illustrated example, for each task, the "number of devices that can be assembled in one hour" is registered as LT. The available equipment column 104 registers the equipment that can be used for the task.

[0015] 3(a) to 3(d) are tables showing examples of manufacturing master data. The manufacturing master data includes individual master data and equipment operation master data for each worker. FIGS. 3(a) to 3(c) are examples of individual master data 110A to 110C for workers X to Z. The individual master data 110A to 110C include a worker column 111, a task column 112, a skill level column 113, a lead time column 114, and a yield column 115. The worker column 111 registers a character string for identifying each worker. The task column 112 registers a character string for identifying each task. The skill level column 113 registers the worker's skill level (proficiency) for each task. The lead time column 114 registers the worker's LT for each task. The yield column 115 registers the worker's yield for each task.

[0016] The LT registered in the production master data is related to the LT registered in the manufacturing master data. In the manufacturing master data, the LT for each task is registered for each worker. In the production master data, the average LT for each task performed by one or more workers is registered. If the LT of any worker is improved in the manufacturing master data, the LT in the production master data can also be improved.

[0017] 3(d) is an example of the equipment operation master data 120. The equipment operation master data 120 includes an equipment column 121 and a stoppage rate column 122. A character string for identifying each piece of equipment is registered in the equipment column 121. A temporary outage rate for each piece of equipment is registered in the outage rate column 122. A "temporary outage" refers to an operation outage of several minutes to several tens of minutes. Temporary outages occur due to minor equipment trouble, the raw materials used not having arrived at the equipment, etc.

[0018] The production management device 10 creates a long-term plan using various data. A long-term plan is a production plan for a longer period than a short-term plan, which will be described later. A long-term period is, for example, several weeks to several months. A long-term plan may also be called a "production schedule" or a "master schedule." As an example, a long-term plan specifies the number of products of each type to be produced over a period of several days to one week over a period of two to three months, a schedule for each product from the start of production to the completion of production, and the like.

[0019] The production management device 10 creates a short-term plan based on the long-term plan. A short-term plan indicates a production plan for a shorter period than the long-term plan described above. A short-term period is, for example, one day. A short-term plan may also be called an "input plan" or a "short schedule plan." As an example, a short-term plan specifies the types of products to be produced in one day, the number of products, the tasks to be performed, the start time of each task, the workers who will perform each task, etc. Below, we will explain an example in which a production plan for one day is specified by a short-term plan.

[0020] The production management device 10 creates long-term and short-term plans using a commonly available scheduler. Available schedulers include FLEXSCHE (registered trademark), Asprova (registered trademark), and JoyScheduler (registered trademark). In creating long-term and short-term plans, in addition to the production master data and manufacturing master data described above, process master data, resource master data, product configuration master data, work schedule master data, and the like are referenced.

[0021] The process master data includes the name of each process, the order of processes, and the standard LT for each process. The LT for the process master data is the same as the LT for the production master data. The resource master data includes the names of the equipment used in the process, the number of units of each piece of equipment, the names of the workers who use each piece of equipment, and the number of workers. The product structure master data includes the raw materials used, processed products in the middle of production, assembled products in the middle of production, and finished products, and defines the flow until the product is completed. The work schedule master data includes the working hours, overtime hours, and working days of each worker. The master data used to create the plan is stored in advance in the storage device 20.

[0022] Figure 4(a) is an example of a long-term plan, and Figure 4(b) is an example of a short-term plan. FIG. 4(a) shows the results of extracting only plans for which work will begin on "February 1st" from a long-term plan for the production of machine model A over several months. The long-term plan 130 shown in FIG. 4(a) indicates that parts for the machine will be received on "February 1st" and that 12 machines will be shipped by February 5th. FIG. 4(b) shows a portion of a short-term plan created based on the plan in FIG. 4(a). The short-term plan for "February 2nd" is shown in FIG. 4(b). This short-term plan 140 includes plans for the number of parts or work-in-progress to be input to the work site, the time of each task, the workers who will perform each task, the equipment to be used, and so on. Regarding the example tasks, "transport" refers to transporting parts to the work area, and "input" refers to using parts to produce a product.

[0023] The work for one day is carried out according to a short-term plan created in advance. After the work starts, the imaging device 30 acquires image data, and the detector 40 acquires detection data. Data may be continuously acquired by the imaging device 30 and the detector 40 even before the work starts. The production management device 10 acquires image data and detection data. The production management device 10 uses one or both of the image data and the detection data to calculate performance data that indicates the performance of the work that has been performed. The calculated performance data includes the LT of the work. A specific method for calculating performance data from image data or detection data will be described below.

[0024] The production management device 10 identifies the items to be worked on from the image data. The identification determines the type of item, the number of items of each type, and so on. The items are the objects of work and can be parts, work-in-progress items, finished products, etc. For example, a single part and a combination of parts are identified as different types of items. When a part is attached to a work-in-progress item, the work-in-progress item with the part attached is identified as a different type of item from the work-in-progress item without the part attached.

[0025] To identify an item, an identification model is used to identify the item in the image. The identification model preferably includes a neural network. To improve the accuracy of identification, the identification model more preferably includes a convolutional neural network (CNN). The identification model is trained in advance so that the number of items appearing in the image for each type is output in response to input image data. Image data and training data are used for training. The training data teaches the positions of the items appearing in the image, the types of items, the number of items of each type, etc.

[0026] The production management device 10 inputs image data into a classification model and acquires the type and number of items shown in the image. The production management device 10 stores the classification results in the storage device 20, linking them to the time the image was captured. Changes in the type and number of items correspond to the progress of the work. For example, the production management device 10 estimates, as performance data, the LT of a single task, the progress of the work, the number of times the work has been performed, and so on, based on changes in the number of each type of item.

[0027] Fig. 5(a) is a schematic diagram showing the state of work, Fig. 5(b) is an image corresponding to Fig. 5(a), and Fig. 5(c) is a schematic diagram showing an example of the classification result. In the example shown in FIG. 5(a), worker W is assembling a part 151 to a work-in-progress 152. FIG. 5(b) shows image data 160 obtained by capturing an image of the work shown in FIG. 5(a) with the imaging device 30. Upon acquiring the image data 160, the production management device 10 inputs the image data 160 into an identification model. The identification model outputs an identification result 161 corresponding to the part 151 and an identification result 162 corresponding to the work-in-progress 152, as shown in FIG. 5(c), for example. The production management device 10 identifies the items shown in the image based on the output result from the identification model.

[0028] For the task of assembling parts 151 to work-in-progress 152, the task can be estimated to be complete when the number of parts 151 decreases and the number of finished products in which parts 151 are assembled to work-in-progress 152 increases. When the same task is repeated, the increased number of finished products corresponds to the number of times the task is performed. The pace at which the number of finished products increases corresponds to LT. The difference between the decreased number of parts 151 and the increased number of finished products corresponds to the number of defective products. The production management device 10 stores these performance data estimated based on the identification results in the storage device 20.

[0029] In addition to the image data, the production management device 10 estimates the work being performed by the worker, the LT of the work, etc., by template matching using the detection data. For example, the detector 40 includes at least one selected from a torque sensor, an acceleration sensor, and an angular velocity sensor, and is incorporated into a tool (wrench or caliper). When the tool is used in the work, the detector 40 detects a signal that is different from when the tool is not being used. The detector 40 continuously detects the signal. This allows time-series detection data to be obtained.

[0030] The production management device 10 refers to a pre-set work standard. The work standard includes the tasks to be performed, the order of the tasks, and the standard time for each task. The production management device 10 extracts a portion of the time-series detected data. The length of the extracted data may be fixed or may be set based on the standard time. Here, the portion of data extracted from the entire time-series data is called "partial data."

[0031] The production management device 10 compares the partial data with pre-prepared template data. Template data is prepared for each task registered in the work standard. The more similar the waveform of the partial data and the waveform of the template data, the more likely it is that the worker is performing the task corresponding to that template data. The production management device 10 calculates the similarity between the waveform of the partial data and the waveform of each template data. The similarity is calculated using Dynamic Time Warping (DTW) or the like. The production management device 10 extracts the combination of partial data and template data that yields the greatest similarity. If the similarity of that combination exceeds a preset threshold, the production management device 10 estimates that the task corresponding to the template data is being performed.

[0032] The production management device 10 may extract portions of the detected data while varying the extraction start time. The production management device 10 compares each of a plurality of partial data sets with different start times with template data. The work being performed is estimated based on the similarity between each partial data set and the template data.

[0033] 6(a) is a schematic diagram showing time-series detection data obtained by a detector, and FIG. 6(b) is a schematic diagram showing template data. FIG. 6(a) shows detection data 200 from a detector 40 built into a wrench. In this case, a large signal is detected as a bolt is tightened. The number of times a large signal is detected corresponds to the number of times the bolt is tightened and the number of bolts. The magnitude of the signal corresponds to the tightening strength. The interval between large signals corresponds to the tightening timing. In the example of FIG. 6(a), a worker is performing task W2 after task W1. In task W2, two bolts are tightened. The worker tightens each bolt three times. Therefore, three peaks 201 to 203 are detected when one bolt is tightened.

[0034] The production management device 10 extracts data for a time range 205 from the detection data 200. The production management device 10 compares the partial data 210 with template data for tasks that may be performed after task W1. FIG. 6B shows an example of template data 220 corresponding to task W2. The template data 220 includes a waveform obtained when one bolt is tightened. A high degree of similarity is obtained between the partial data 210 and the template data 220. As a result, the production management device 10 estimates that the worker is performing task W2. Furthermore, the production management device 10 counts the number of bolts tightened by matching partial data 212, which comes after the partial data 210, with the template data. For example, the number of bolts to be tightened in task W2 is registered in the work standard. The production management device 10 can estimate the progress of task W2 by comparing the counted number of bolts with the number of bolts registered in the work standard.

[0035] The production management device 10 estimates the LT based on the estimation results of the work. The LT estimation method is arbitrary. For example, the time from the most recently estimated work to the next estimated work may be estimated as the LT of one work. Template data for estimating the start and end of one work may be prepared, and the LT may be estimated from the results of matching using these template data. Template data corresponding to an entire work may be prepared, and template matching may be performed while varying the period for extracting partial data. In this case, the length (time) of the partial data that obtains the greatest similarity is estimated as the lead time. When a specific work is repeated, the average LT of one work may be calculated by dividing the time until the work is performed multiple times by the number of times the work is performed.

[0036] If a worker only repeatedly performs a specific task, template data to be compared with the detected data may be specified. For example, if a worker only repeatedly performs task W2, the production management device 10 compares only the partial data with the template data 220. The production management device 10 repeatedly extracts data and matches the partial data with the template data 220. From the results, the production management device 10 can estimate the progress of one task W2, the number of times task W2 has been performed, the LT for task W2, and the like.

[0037] When the detector 40 is an acceleration sensor or angular velocity sensor attached to the worker, the task being performed and LT are estimated in the same manner as described above. Multiple detectors 40 may be attached to the worker. In this case, template data is prepared for each part of the worker's body. The production management device 10 compares the partial data obtained from each detection data with each template data, and estimates that the task corresponding to the template data with the highest similarity is being performed.

[0038] The time series data may be acquired from image data. The production management device 10 detects the posture of the worker in the image. The posture detection detects the worker's skeleton. The production management device 10 calculates the position of a specific part (for example, the head) in the image. The production management device 10 continuously acquires images or acquires video. The production management device 10 calculates the position of the specific part from multiple images that are consecutive in time. This allows time series data to be obtained that indicates continuous changes in the position of the specific part. Using this time series data, the work being performed and its lead time may be estimated, similar to the method described above.

[0039] Different data may be used for estimation for each task. For example, for a task performed by a certain worker, the LT, task progress, and task count may be estimated from changes in the number of each type of item captured in an image. For a different task performed by a different worker, the LT, task progress, and task count may be estimated by matching at least a portion of the detection data with template data. Alternatively, for a single task, the LT, task progress, and task count may be estimated by combining changes in the number of each type of item captured in an image with template matching.

[0040] While production work is being carried out according to the short-term plan, the production management device 10 repeatedly identifies items using image data and performs template matching using the detection data. As a result, the production management device 10 obtains performance data for each worker. The performance data includes the LT, number of tasks, etc. for the part of the short-term plan that has been executed.

[0041] The production management device 10 uses the obtained performance data for each worker to predict the performance of another part of the short-term plan. As an example, the short-term plan specifies the work schedule for each worker for one day. The production management device 10 estimates the LT for a certain worker's morning work from image data or detection data obtained in the morning. The production management device 10 uses the estimated LT to predict the LT for that worker's afternoon work that day.

[0042] The production management device 10 uses a first prediction model to predict performance. The first prediction model preferably includes a neural network. To improve the accuracy of prediction, the first prediction model more preferably includes a recurrent neural network (RNN). The first prediction model is trained in advance so as to output a performance prediction in response to input data. For the training, performance data obtained from past work is used. Use A part of the performance data is used as input data, and another part of the performance data is used as teaching data to be predicted.

[0043] In addition to the performance data, the production management device 10 may input other data that may affect the LT into the first prediction model. For example, the production management device 10 may input environmental data indicating the environment of the work site, biological data of the worker, and the like into the prediction model. The environmental data includes one or more selected from temperature, humidity, and atmospheric pressure. The biological data includes one or more selected from body temperature, pulse rate, blood pressure, body movement, cardiac potential, sweat rate, transcutaneous arterial oxygen saturation, and respiratory rate. The biological data can be acquired by a wearable sensor attached to the worker.

[0044] 7(a) is a schematic diagram showing the actual results for a part of the short-term plan, and FIG. 7(b) is a schematic diagram showing the forecast for another part of the short-term plan. In Figures 7(a) and 7(b), the horizontal axis represents time. The vertical axis represents LT. In Figure 7(b), the solid line represents the estimated LT for work that has been performed according to a part of the short-term plan. The dashed line represents the predicted LT for work that will be performed in the future according to another part of the short-term plan. As shown in Figures 7(a) and 7(b), the production management device 10 predicts the LT using the estimated performance data and the prediction model.

[0045] The production management device 10 uses the predicted LT to revise the short-term plan. First, the production management device 10 compares the predicted LT with the short-term plan. The short-term plan specifies the number of tasks to be performed. If the predicted LT is longer than the standard, it may not be possible to perform the specified number of tasks, and the number of tasks must be reduced. If the predicted LT is shorter than the standard, it is possible to perform more tasks.

[0046] Fig. 8(a) is a table showing a pre-created short-term plan, and Fig. 8(b) is a table showing a revised short-term plan. In the example of FIG. 8(a), worker X and worker Y are scheduled to assemble two machines of model A each in the morning, the first half of the afternoon, and the second half of the afternoon. For example, FIGS. 7(a) and 7(b) show the actual performance of worker X and its predicted performance. As shown in FIGS. 7(a) and 7(b), if a reduction in the LT of worker X is predicted, worker X will be able to assemble more machines thereafter. Based on the LT prediction results, the production management device 10 increases the number of machines that worker X will assemble in the afternoon, as shown in FIGS. 8(a) and 8(b).

[0047] When the short-term plan is revised, the production management device 10 may send a notification to a preset terminal device. For example, the production management device 10 sends the revised number of input units to a terminal device carried by a delivery worker. Sending at least a part of the revised short-term plan makes it easier for the worker to perform work in accordance with the revised short-term plan.

[0048] For example, a wearable terminal device worn by a worker notifies the worker of the revision of the short-term plan by sound, light, or vibration. The terminal device may be a smartphone, tablet, or smart glasses equipped with a display function. In this case, the terminal device displays the revised short-term plan or the details of the revision of the short-term plan to the worker.

[0049] 9(a) is a schematic diagram showing the actual results for a part of the revised short-term plan, and FIG. 9(b) is a schematic diagram showing the forecast for another part of the revised short-term plan. Figure 10(a) is a table showing the revised short-term plan, and Figure 10(b) is a table showing the further revised short-term plan. 9(a) and 9(b), the horizontal axis represents time. The vertical axis represents LT. In FIG. 9(b), the solid line represents the estimated LT for work performed along a portion of the revised short-term plan. The dashed line represents the predicted LT for work to be performed in the future along another portion of the revised short-term plan. The revised short-term plan may be further revised based on subsequently obtained performance data.

[0050] FIG. 9(a) shows the LT when worker X performs work in the first half of the afternoon in accordance with the revised short-term plan. The production management device 10 predicts the LT for work in the second half of the afternoon, as shown in FIG. 9(b), based on the results of work in the morning and the first half of the afternoon. In the illustrated example, the LT is not shortened compared to the prediction shown in FIG. 7(b). Based on the prediction results, the production management device 10 reduces the number of devices that worker X assembles, as shown in FIGS. 10(a) and 10(b). In this way, the production management device 10 may repeatedly revise the short-term plan using image data or detection data acquired in real time during work execution.

[0051] When a day's work according to the short-term plan is completed, the production management device 10 acquires performance data indicating the performance of that day's work. This performance data includes the LT, the number of tasks to be performed, etc., similar to the performance data for part of the short-term plan described above. Performance data is acquired for each worker. The production management device 10 uses the acquired performance data and previous performance data to acquire long-term forecast data for each worker. This forecast data indicates a forecast of the performance of work over a predetermined period (several weeks to several months). For example, the forecast data includes the LT for each day within the predetermined period, the number of tasks to be performed, etc.

[0052] The production management device 10 uses a second prediction model to predict actual results. The second prediction model is a model for predicting actual results over a longer period of time than the first prediction model. The second prediction model preferably includes a neural network. To improve the accuracy of prediction, the second prediction model more preferably includes an RNN. The second prediction model is trained in advance so as to output a prediction of actual results in response to input data. Long-term past performance data is used for training. A portion of the performance data is used as input data, and another portion of the performance data is used as teaching data to be predicted. As with the first prediction model, environmental data, biological data, etc. may be input to the second prediction model.

[0053] The production management device 10 updates the production master data and manufacturing master data based on the forecast data output from the second forecast model. First, the production management device 10 updates the LT of the manufacturing master data for each worker based on the forecast data for each worker. From the LT of the updated manufacturing master data, the production management device 10 updates the LT of the production master data.

[0054] Fig. 11(a) is a schematic diagram showing actual results for a part of a predetermined period, and Fig. 11(b) is a schematic diagram showing forecasts for another part of the predetermined period. In Figures 11(a) and 11(b), the horizontal axis represents time. The vertical axis represents LT. When work for "February 2nd" is performed according to the short-term plans shown in Figures 4(b), 8(b), and 10(b), the actual results of the work for "February 2nd" are obtained. The production management device 10 references the actual data for "February 2nd" and the earlier actual data shown in Figure 11(a). Using this actual data, the production management device 10 predicts the actual results for the future period from "February 3rd" onwards, as shown in Figure 11(b).

[0055] 12(a) and 12(b) are tables showing examples of updated manufacturing master data. For example, Figures 11(a) and 11(b) show the actual performance and prediction of worker X. As shown in Figures 11(a) and 11(b), when a reduction in the LT of worker X is predicted in the long term, the production management device 10 updates the LT of the manufacturing master data related to worker X as shown in Figure 12(a). In response to the update of the manufacturing master data, the production management device 10 updates the LT of the work involving worker X in the production master data as shown in Figure 12(b).

[0056] The production management device 10 creates a new long-term plan using the updated production master data. The scheduler can be used to create the long-term plan, as described above. The production management device 10 creates a short-term plan for the next day based on the new long-term plan and the updated production master data.

[0057] Thereafter, the above-mentioned process is repeated. That is, on the next day, production work is carried out in accordance with the new short-term plan. The actual results of work carried out in accordance with part of the short-term plan are used to predict future results. The short-term plan is revised based on the predicted results. Furthermore, at the end of the next day, a new long-term plan and a new short-term plan are created using the actual results of the work for the following day.

[0058] In the above example, the LT and the number of times an operation is performed are mainly used as the actual results. In addition to this example, the yield may also be used as the actual results. For example, the production management device 10 tallies the number of defective products generated in operations performed according to part of the short-term plan. The occurrence of defective products is determined based on input to a specific terminal device, the identification of the number of items in the defective product storage area, etc. The production management device 10 predicts the number of defective products in operations performed according to another part of the short-term plan from the tallied number of defective products. A prediction model different from the LT prediction is used to predict the number of defective products. The production management device 10 modifies the short-term plan based on the predicted number of defective products. The production management device 10 also tallies the number of defective products generated in one day's operations and uses this tallied number to predict the number of defective products for a specified period. The manufacturing master data and production master data are updated based on the predicted number of defective products, and new long-term and short-term plans are created.

[0059] The number of defective products may be expressed in other corresponding terms, such as the number of non-defective products, the rate of occurrence of defective products, or the yield rate. The production management device 10 may use both the number of defective products and the LT to revise the short-term plan, update each master data, etc.

[0060] FIG. 13 is a flowchart showing a production management method according to an embodiment. In the production management method PM shown in FIG. 13, first, the production management device 10 creates a long-term plan (first long-term plan) indicating a production plan for a predetermined period of time and a short-term plan (first short-term plan) indicating a production plan for a first period of time (Step S1). The long-term plan and short-term plan are created based on various master data. Production-related work is carried out in accordance with part of the short-term plan. The production management device 10 acquires first performance data for the work (Step S2). The production management device 10 uses the first performance data to acquire first forecast data (Step S3). The first forecast data includes a forecast of performance for another part of the work in the short-term plan that will be executed subsequently. The production management device 10 modifies the short-term plan based on the first forecast data (Step S4). Steps S2 to S4 may be repeated a predetermined number of times. The production management device 10 acquires second performance data indicating the performance of the work in the first period of time (Step S5). The production management device 10 uses the second performance data and past performance data to obtain second forecast data indicating a forecast of production performance over a predetermined period (step S6). The production management device 10 updates the production master data based on the second forecast data (step S7). The production management device 10 updates the production master data based on the updated production master data (step S8). The production management device 10 determines whether a termination condition for the process is met (step S9). The termination condition may be receipt of a stop instruction from the user, execution of the process a predetermined number of times, etc. If the termination condition is not met, step S1 is executed again.

[0061] For example, by executing step S1 again, a new long-term plan (second long-term plan) and a short-term plan (second short-term plan) indicating a production plan for a second period following the first period are created using the updated production master data and manufacturing master data. Third actual result data indicating the actual results of work performed in accordance with part of the new short-term plan is acquired. Using this third actual result data, third forecast data indicating a forecast of the actual results of work performed in accordance with another part of the new short-term plan is acquired. Based on this third forecast data, the new second short-term plan is revised. In this way, the revision of the short-term plan, the creation of a new long-term plan and short-term plan, etc. are repeated using the acquired actual results and the forecast based on those actual results.

[0062] 14 and 15 are flowcharts showing specific processing by the production management device according to the embodiment. An example of a specific method for estimating actual results in step S2 shown in FIG. 13 will be described with reference to FIGS. 14 and 15. First, the production management device 10 acquires data of length 2t from the detection data (step S21). "t" is a preset value. t may be set based on the standard work time registered in the work standard. The production management device 10 analyzes the acquired data (step S22). The production management device 10 calculates various data related to actual results from the analysis results (step S23). The production management device 10 determines whether the termination condition is met (step S24). If the termination condition is not met, step S21 is executed again.

[0063] FIG. 15 illustrates an example of a specific process in the analysis of step S22. In this example, the analysis is performed using detection data acquired from the detector 40. First, the production management device 10 divides the detection data into pieces of 2t length (step S22-1). For example, in the provisional division, the detection data is divided equally into pieces of a preset length. This results in multiple partial data. The production management device 10 reads unprocessed partial data from the multiple partial data (step S22-2). The production management device 10 reads unprocessed template data from the multiple template data, the similarity of which with the read partial data has not yet been calculated (step S22-3). The production management device 10 executes DTW, which associates template data with partial data using dynamic programming (step S22-4). The production management device 10 determines the average similarity of the obtained shortest paths as the similarity between the partial data and the template data (step S22-5).

[0064] The production management device 10 determines whether the obtained similarity is the largest among the similarities obtained for the partial data loaded immediately before in step S22-2. Then, the production management device 10 determines whether the obtained similarity exceeds a preset threshold (step S22-6). If the obtained similarity is the largest and exceeds the threshold, the production management device 10 estimates that the task corresponding to the template data was performed during the period of that partial data. The production management device 10 counts the action indicated by the partial data as the number of tasks for the estimated task (step S22-7). If, in step S22-6, the obtained similarity is not the largest or does not exceed the threshold, the production management device 10 determines whether there is unprocessed template data for which the similarity to the partial data loaded immediately before in step S22-2 has not yet been calculated (step S22-8).

[0065] If unprocessed template data exists, step S22-3 is executed again, and the unprocessed template data is read. If unprocessed template data does not exist, or if step S22-7 is executed, production management device 10 determines whether unprocessed partial data exists (step S22-9). If unprocessed partial data exists, step S22-2 is executed again, and the unprocessed partial data is read. If unprocessed partial data does not exist, production management device 10 ends step S22.

[0066] The advantages of the embodiment will be described. In production, long-term and short-term plans are generally created using a production scheduler. Scheduling using a production scheduler can improve production efficiency. In particular, a production scheduler can create a plan that takes into account not only the LT of the work but also the LT of transporting goods. Therefore, if the created plan can be executed, just-in-time production becomes possible.

[0067] However, there are many cases where discrepancies occur between plans and actual results due to factors such as short-term changes in workers' concentration, differences in workers' proficiency, and long-term changes in workers' proficiency. Furthermore, master data such as LT and yield, which are necessary for creating plans, is not frequently maintained. This data can deviate from actual values, preventing the production scheduler from creating accurate plans. Whenever a discrepancy occurs between the plan and actual results, the person in charge of planning adjusts the plan to reduce the discrepancy. However, this process requires a lot of man-hours.

[0068] To address this issue, the production management device 10 according to the embodiment uses the results of work performed according to a part of a short-term plan to predict the results of work performed according to another part of the short-term plan. For example, LT is affected by the worker's concentration. Even if the worker's concentration changes throughout the day, the results of some work can be used to predict the results of subsequent work. The production management device 10 then modifies the short-term plan based on the predicted results. By modifying the short-term plan, the discrepancy between the short-term plan and actual production can be reduced.

[0069] The production management system 10 also uses past work results to predict production results for a given period. The production management system 10 uses the predictions to create new long-term and short-term plans. This reduces the discrepancy between the long-term plan and actual production. The short-term plan based on the new long-term plan is further revised using data from when the short-term plan was executed.

[0070] In this way, by repeatedly revising the short-term plan, creating a new long-term plan, and creating a new short-term plan, it is possible to reduce the deviation between the plan and actual production. In particular, by analyzing and estimating work using image data, detection data, etc., it is possible to correct the short-term plan in real time. It is also possible to repeatedly correct the short-term plan. According to the embodiment, it is possible to create a plan that has a smaller deviation from actual production. This makes it possible to achieve even more efficient production than before.

[0071] Furthermore, the production management device 10 updates the master data based on long-term performance predictions. Because the master data is automatically updated, there is no need for manual updating of the master data. This reduces the burden of manual maintenance of the master data.

[0072] FIG. 16 is a schematic diagram showing a hardware configuration. The production management device 10 includes, for example, the hardware configuration shown in Fig. 16. The computer 90 shown in Fig. 16 includes a CPU 91, a ROM 92, a RAM 93, a storage device 94, an input interface 95, an output interface 96, and a communication interface 97. The functions of the production management device 10 may be realized by one computer 90, or may be realized by multiple computers 90 working together.

[0073] The ROM 92 stores programs that control the operation of the computer. The ROM 92 stores programs necessary for the computer to execute each of the above-mentioned processes. The RAM 93 functions as a storage area in which the programs stored in the ROM 92 are expanded.

[0074] The CPU 91 includes a processing circuit. The CPU 91 uses a RAM 93 as a work memory and executes a program stored in at least one of a ROM 92 and a storage device 94. During program execution, the CPU 91 controls each component via a system bus 98 and executes various processes.

[0075] The storage device 94 stores data necessary for executing the program and data obtained by executing the program.

[0076] 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.

[0077] The output interface (I / F) 96 connects the computer 90 and the output device 96a. The output I / F 96 is, for example, a video output interface such as a Digital Visual Interface (DVI) or a High-Definition Multimedia Interface (HDMI (registered trademark)). The CPU 91 can transmit data to the output device 96a via the output I / F 96 and cause the output device 96a to display an image.

[0078] The communication interface (I / F) 97 connects the computer 90 to a server 97a external to 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.

[0079] The computer 90 may communicate with a terminal device 97b via the communication I / F 97. The terminal device 97b is, for example, a smartphone, a tablet, smart glasses, or a wearable terminal carried by the worker.

[0080] The storage device 94 includes one or more selected from a hard disk drive (HDD) and a solid state drive (SSD). The input device 95a includes one or more selected from a mouse, a keyboard, a microphone (voice input), and a touchpad. The output device 96a includes one or more selected from a monitor, a projector, a speaker, and a printer. A device having the functions of both the input device 95a and the output device 96a, such as a touch panel, may also be used. The storage device 94 may also be used as the storage device 20.

[0081] The various data processing operations described above may be recorded as a computer-executable program on a magnetic disk (such as a flexible disk or hard disk), an optical disk (such as a CD-ROM, CD-R, CD-RW, DVD-ROM, DVD±R, or DVD±RW), a semiconductor memory, or other non-transitory computer-readable storage medium.

[0082] For example, information recorded on a recording medium can be read by a computer (or an embedded system). The recording medium may have any recording format (storage format). For example, a computer reads a program from the recording medium and causes a CPU to execute instructions written in the program based on the program. The computer may acquire (or read) the program via a network.

[0083] According to the embodiments described above, a production management device, a production management system, a production management method, a program, and a storage medium are provided that are capable of creating a plan that has a smaller deviation from actual production.

[0084] Although several embodiments of the present invention have been described above, these embodiments are presented by way of example only and are not intended to limit the scope of the invention. These novel embodiments can be embodied in various other forms, and various omissions, substitutions, modifications, etc. can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as set forth in the claims. Furthermore, the above-described embodiments can be implemented in combination with each other. [Explanation of symbols]

[0085] 1: Production management system 10: Production control device 20: Storage device 30: Imaging device 40: Detector 90: Computer 91:CPU 92:ROM 93:RAM 94:Storage device 95: Input interface 95a: Input device 96: Output interface 96a: Output device 97: Communication interface 97a:Server 97b: Terminal equipment 98: System bus 100A, 100B: Production master data 110A~110C: Individual master data 120: Equipment operation master data 130: Long-term planning 140: Short-term planning 151: Parts 152: Work in progress 160: Image data 161,162: Identification results 200:Detection data 201~203: Peak 205: Time span 210,212: Partial data 220: Template data W: Worker

Claims

1. acquiring a first short-term plan that is created based on a first long-term plan that indicates a production plan for a predetermined period, the first short-term plan indicating a production plan for a first period that is shorter than the predetermined period; acquiring first performance data indicating performance of work carried out in accordance with a portion of the first short-term plan; using the first actual result data to obtain first forecast data indicating a forecast of actual results for the work to be executed in accordance with another part of the first short-term plan; modifying the first short-term plan based on the first forecast data; obtaining second forecast data indicating a forecast of production results for the predetermined period using second result data indicating results of the work for the first period; A production management device that uses the second forecast data to create a second long-term plan for the specified period.

2. 2. The production management device according to claim 1, further comprising: a second short-term plan based on the second long-term plan, the second short-term plan indicating a production plan for a second period that is later than the first period and shorter than the predetermined period.

3. acquiring third performance data indicating performance of the work carried out in accordance with a part of the second short-term plan; using the third actual result data to obtain third forecast data indicating a forecast of actual results for the work to be executed in accordance with another part of the second short-term plan; 3. The production management device according to claim 2, wherein the second short-term plan is revised based on the third forecast data.

4. Further, another performance data showing the performance of the work carried out in accordance with the part of the revised first short-term plan is acquired; using the different performance data to obtain different forecast data indicative of a forecast of performance in the work to be performed according to another portion of the modified first short-term plan; 4. The production management device according to claim 1, further modifying the modified first short-term plan based on the other forecast data.

5. the first performance data includes a lead time for the work performed according to the part of the first short-term plan; Repeatedly acquiring image data depicting the work; Identifying the type and number of items shown in each of the plurality of image data; 5. The production management device according to claim 1, wherein the lead time is calculated using changes in the type and number of the items.

6. the first performance data includes a lead time for the work performed according to the part of the first short-term plan; acquiring time-series detection data indicating signals generated by the actions of a worker performing the work; 5. The production management device according to claim 1, wherein the lead time is calculated based on a result of comparing at least a part of the detection data with template data.

7. 7. The production management device according to claim 1, wherein the second performance data includes a lead time for the operation in the first period.

8. updating master data using the second forecast data; 8. The production management device according to claim 1, wherein the second long-term plan is created by scheduling based on the updated master data.

9. 9. The production management device according to claim 1, wherein the first prediction data is acquired by inputting the first performance data and environmental data indicating a production environment into a prediction model including a neural network.

10. acquiring a short-term plan that is created based on a long-term plan that indicates a production plan for a predetermined period, the short-term plan indicating a production plan for a first period that is shorter than the predetermined period; Obtaining past lead times for work performed in accordance with a portion of the short-term plan; using the past lead times to predict future lead times for the operations performed according to another portion of the short-term plan; modifying the short-term plan based on the future lead time; predicting a lead time for the work in the predetermined period using the lead time for the work executed in accordance with the modified short-term plan; A production management device that creates a new long-term plan for the predetermined period using the predicted lead time for the predetermined period.

11. A production management device according to any one of claims 1 to 10; an imaging device that captures an image of the work; a detector for detecting a signal generated by the action of a worker performing the task; A production management system equipped with the above.

12. A computer comprising: acquiring a first short-term plan that is created based on a first long-term plan that indicates a production plan for a predetermined period, the first short-term plan indicating a production plan for a first period that is shorter than the predetermined period; acquiring first performance data indicating performance of work carried out in accordance with a portion of the first short-term plan; using the first actual result data to obtain first forecast data indicating a forecast of actual results for the work to be executed in accordance with another part of the first short-term plan; modifying the first short-term plan based on the first forecast data; obtaining second forecast data indicating a forecast of production results for the predetermined period using second result data indicating results of the work for the first period; creating a second long-term plan for the predetermined period using the second forecast data; Production management methods.

13. A program for causing a computer to execute the production management method according to claim 12.

14. A storage medium storing the program according to claim 13.

Images