WO2022091571A1 - Dispositif de mise à jour de procédure de travail, procédé de mise à jour de procédure de travail, et programme - Google Patents

Dispositif de mise à jour de procédure de travail, procédé de mise à jour de procédure de travail, et programme Download PDF

Info

Publication number
WO2022091571A1
WO2022091571A1 PCT/JP2021/032074 JP2021032074W WO2022091571A1 WO 2022091571 A1 WO2022091571 A1 WO 2022091571A1 JP 2021032074 W JP2021032074 W JP 2021032074W WO 2022091571 A1 WO2022091571 A1 WO 2022091571A1
Authority
WO
WIPO (PCT)
Prior art keywords
work
time
procedure
fastest
actual
Prior art date
Application number
PCT/JP2021/032074
Other languages
English (en)
Japanese (ja)
Inventor
孝忠 長岡
Original Assignee
三菱電機株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 三菱電機株式会社 filed Critical 三菱電機株式会社
Priority to JP2022558891A priority Critical patent/JP7387025B2/ja
Publication of WO2022091571A1 publication Critical patent/WO2022091571A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Definitions

  • This disclosure relates to a work procedure update device, a work procedure update method, and a program.
  • setup work including parts replacement, mounting board changes, jig or tool replacements, and equipment program changes. Since the market needs in recent years require high-mix low-volume production, shortening the setup work time that occurs when switching production models on a daily basis has become a priority issue for factory reform.
  • Patent Document 1 There is a system that extracts such setup work and calculates the work time required for the setup work.
  • the setup work management system described in Patent Document 1 has a limit number of simultaneous work, which is the maximum number of workers who can efficiently perform setup work at the same time, and an allotted number of workers, which is the number of workers assigned to each setup work. And, based on, the time required for the setup work is calculated. It is explained that this makes it possible to appropriately manage the setup work that occurs corresponding to the component mounting line.
  • the setup work management system described in Patent Document 1 extracts the setup work generated by the setup change based on the mounting data and the production planning information. Then, the simultaneous work limit number of people is calculated based on the extracted setup work and the unit setup work information.
  • Patent Document 1 it is difficult to accurately predict the working time based on the number of people who can work at the same time.
  • the setup change is performed only a few times a day, and the timing of the setup work varies depending on the daily production situation, so it is difficult to specify the timing to analyze the work. For this reason, it was inefficient because it was necessary to assign a production engineer to the site to improve the setup work. That is, it is difficult to evaluate the actual setup work state and reflect it in the work procedure without lowering the production efficiency.
  • This disclosure has been made in view of the above circumstances, and is a work procedure updating device, a work procedure update method, and a work procedure update device capable of updating the fastest work time according to the actual work state to a feasible optimum work procedure.
  • the purpose is to provide a program.
  • the work procedure updating device of the present disclosure acquires the actual work time based on the actual work video of the work, and is the fastest when the actual work time is shorter than the fastest work time stored in the storage unit. It is equipped with the fastest work time update unit that updates the work time to the actual work time. Further, the work procedure update device uses a trained model in which the fastest work time and the appropriateness of work have been learned in advance, and extracts the optimum work procedure based on the updated fastest work time. It is provided with a unit and a work procedure update unit that updates the work procedure stored in the storage unit to the extracted optimum work procedure.
  • the fastest work time is updated based on the video of the work and the optimum work procedure at the fastest work time is extracted, the optimum work that can realize the fastest work time according to the actual work state can be realized. It will be possible to update to the procedure.
  • a block diagram showing a configuration example of a work procedure update system according to an embodiment of the present disclosure.
  • Flowchart of actual work video acquisition process Flowchart of fastest work time update process
  • Optimal work procedure Block diagram showing the learning device of the extraction unit
  • Optimal work procedure Block diagram showing the inference device of the extraction unit
  • Flow chart of inference processing Graph showing the fastest working time and the shortest actual working time
  • a table showing the optimal work procedure
  • a table showing the working time of the optimum work procedure A table showing the working time of the actual work procedure Table showing work improvement plans
  • FIG. 1 is a block diagram showing a configuration example of the work procedure update system 1 according to the embodiment of this disclosure.
  • the work procedure update system 1 is a system that generates and updates a work procedure when the work in the factory is executed at the fastest working time.
  • the work procedure update system 1 generates and updates the work procedure for the setup work that occurs when the production model is changed.
  • the setup work is a work that occurs when a model of a product produced in a factory is switched, and is, for example, replacement of parts, change of a mounting board, replacement of a jig or a tool, and change of a program of equipment.
  • the work procedure update system 1 updates the fastest work time and the optimum work procedure based on the photographing device 100 for photographing the worker performing the setup work and the work moving image photographed by the photographing device 100.
  • a work procedure updating device 200 is provided.
  • the photographing device 100 is an arbitrary photographing device that photographs the setup work of the field worker during the setup work period of the preset analysis target model and during the preset analysis target period.
  • a wearable device that can be attached to the worker's body and photographed is preferable in order to photograph the work contents of the operator at a close distance.
  • smart glasses or HoloLens® may be used.
  • it may be an action camera or a wearable camera mounted next to the worker's helmet.
  • the timing of shooting may be determined by the operation of the operator.
  • the shooting is started by pressing the shooting start button of the shooting device 100. Further, when the operator completes the setup work, the shooting is stopped by pressing the shooting end button of the shooting device 100. As a result, one cycle of setup work is photographed. If the model is not the model to be analyzed or the period is not the analysis target period, the photographing device 100 automatically or manually stops the photographing.
  • the photographing device 100 can be connected to the work procedure updating device 200 by any wired or wireless communication means.
  • the photographing device 100 transmits the captured moving image to the work procedure updating device 200 at an arbitrary timing.
  • the operation including the start or stop of photography of the photographing apparatus 100 may be controlled by the working procedure updating apparatus 200.
  • the work procedure updating device 200 stores a calculation processing unit 210 that executes a process of acquiring or generating various data based on a shooting moving image shot by the shooting device 100, and a data acquired or generated by the calculation processing unit 210. It includes a storage unit 220 and a display unit 230 that displays information acquired or generated by the arithmetic processing unit 210.
  • the arithmetic processing unit 210 is an arbitrary arithmetic processing unit, for example, a CPU (Central Processing Unit).
  • the arithmetic processing unit 210 acquires the actual work video included in the shot video by executing the program stored in the storage unit 220 and saves it in the storage unit 220, based on the actual work video acquisition unit 211 and the actual work time.
  • Fastest work time update unit 212 that updates the fastest work time
  • optimal work procedure extraction unit 213 that extracts the optimum work procedure by artificial intelligence (AI)
  • work procedure update unit 214 that updates the work procedure
  • optimum work It functions as a work time comparison unit 215 that compares the work time of the procedure with the actual work time
  • a work improvement plan output unit 216 that outputs a work improvement plan based on the comparison result of the work time.
  • the storage unit 220 is an arbitrary storage device, and is, for example, a flash memory, a non-volatile semiconductor memory including an EPROM (ErasableProgrammableReadOnlyMemory), or a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD ( Digital Versatile Disc).
  • EPROM ErasableProgrammableReadOnlyMemory
  • magnetic disk a magnetic disk
  • a flexible disk an optical disk
  • a compact disk a mini disk
  • DVD Digital Versatile Disc
  • the storage unit 220 has been learned to be used by the actual work database 221 containing the data related to the actual work, the fastest work time database 222 including the data of the fastest work time, and the optimum work procedure extraction unit 213. It has a learned model storage unit 223 for storing a model and a work procedure storage unit 224 for storing a work procedure.
  • the storage unit 220 also stores a program executed by the arithmetic processing unit 210.
  • the function of the arithmetic processing unit 210 and the contents of the storage unit 220 will be described in detail.
  • the actual work video acquisition unit 211 of the arithmetic processing unit 210 acquires the actual work video from the start of the work to the completion of the work for each series of setup work from the shot video shot by the shooting device 100.
  • FIG. 2 is a flowchart of the actual work video acquisition process.
  • the actual work moving image acquisition unit 211 first determines the setup work to be analyzed (step S101), and then determines the work period to be analyzed and the model of the product (step S102). After that, a moving image from the start to the completion of the work is acquired from the photographing device 100 (step S103), and the acquired actual work data is stored in the actual work database 221 of the storage unit 220.
  • the actual work video acquired in step S103 may be recorded by the shooting device 100 in advance before the start of a series of actual work video acquisition processes, or as a part of the actual work video acquisition process, the work procedure update device. It may be taken by the photographing apparatus 100 based on the control signal from 200. The operator may decide the timing of starting and stopping the shooting by the shooting device 100.
  • the shooting device 100 is a moving image shooting device including smart glasses or HoloLens
  • application software for controlling the moving image shooting device is installed in advance in the work procedure updating device 200 in order to acquire the actual work moving image in step S103. Keep it.
  • each moving image file is associated with the identification information of the worker, the work period, and the information of the product model, and is stored as a group.
  • the storage unit 220 of the work procedure update device 200 managed by the manufacturing department includes the actual work database 221.
  • the actual work database 221 is a local database or a cloud type database outside the work procedure update device 200. It may be.
  • the data recorded in the performance work database 221 may be compressed and stored.
  • old data may be automatically deleted to manage the storage capacity of the database.
  • the fastest work time update unit 212 calculates the actual work time per cycle of setup work based on the moving image data acquired from the actual work database 221 of the storage unit 220. More specifically, the fastest work time update unit 212 calculates the time from the start to the completion of the setup work as the actual work time of one cycle. If shooting starts when the work starts and shooting is completed when the work is completed, the shooting time is the actual work time. If the work start time and the shooting start time or the work completion time and the shooting completion time do not match, manual measurement may be performed. Alternatively, the actual working time may be calculated from the captured video image using any analysis software. As the analysis software, for example, Smart Logger (registered trademark), which is a work dynamic analysis system, can be used.
  • FIG. 3 is a flowchart of the fastest working time update process.
  • the fastest work time update unit 212 calculates the actual work time of the setup work of the model to be analyzed performed during one day, and the shortest actual work time is the shortest among them. Is extracted (step S201). The numerical value of the actual work time is continuously managed during the predetermined analysis period, and the fastest work time in the previous period and the shortest actual work time in one day, which are stored in the fastest work time database 222, are compared with each other. Is repeatedly executed (step S202).
  • step S203: Yes If there is a day when the shortest actual work time is shorter than the fastest work time (step S203: Yes), the fastest work time is updated to the shortest actual work time of the day (step S204, fastest work time update step). If multiple actual work times are shorter than the fastest work time during the analysis period, the shortest actual work time within the analysis period is set as the new fastest work time. On the other hand, when all the actual work times are equal to or longer than the fastest work time (step S203: No), the process ends without changing the fastest work time.
  • the optimum working procedure extraction unit 213, which will be described later, may extract the shortest working time of the working procedure with the least waste of operation.
  • the work procedure with the least waste of operation is the work procedure with the largest value-added time ratio indicating the added value per unit time derived based on a predetermined standard.
  • the fastest work time update unit 212 By using the fastest work time update unit 212, it is possible for the setup worker to shoot and analyze the work video at the conventional site and greatly reduce the indirect work time required for the fastest work time. For example, the effect of shortening the analysis time when using a smart logger is 1/10. Further, it is possible to use the fastest working time based on the actual value at the actual production site for the evaluation of the working efficiency instead of the fastest working time obtained from the conventional mathematical formula.
  • the fastest working time updated by the fastest working time updating unit 212 is stored in the fastest working time database 222 of the storage unit 220.
  • the fastest working time database 222 is included in the storage unit 220 of the working procedure updating device 200 managed by the manufacturing department, but the fastest working time database 222 is a local database outside the working procedure updating device 200 or. It may be a cloud-type database.
  • the optimum work procedure extraction unit 213 extracts the optimum work procedure based on the procedure work time corresponding to each work procedure among the updated fastest work time when the fastest work time update unit 212 updates the fastest work time. do. Extraction of the optimum work procedure is performed using artificial intelligence (AI).
  • AI artificial intelligence
  • the artificial intelligence that extracts the optimum work procedure is realized by the optimum work procedure extraction unit 213 of the arithmetic processing unit 210 and the learned model storage unit 223 of the storage unit 220.
  • the optimum work procedure extraction unit 213 includes a learning device 217 and an inference device 218 (see FIGS. 4A and 5A).
  • the configuration in which the learning device 217 and the inference device 218 are included in the work procedure updating device 200 is described.
  • the learning device 217 and the inference device 218 are used to learn the appropriateness of the setup work of the target product including the vacuum cleaner, the dehumidifier, and the dishwasher.
  • the form of the learning device 217 and the inference device 218 is arbitrary, and may be, for example, a device separate from the target product and connected to the target product via a network. Alternatively, it may be built in the target product. Further, the learning device 217 and the inference device 218 may exist on the cloud server together with the learned model storage unit 223.
  • FIG. 4A is a block diagram showing the learning device 217 of the optimum work procedure extraction unit 213, and FIG. 4B is a flowchart of the learning process.
  • the case of learning the setup work of the target product including the vacuum cleaner, the dehumidifier, and the dishwasher will be described.
  • the learning device 217 includes a data acquisition unit 2171 and a model generation unit 2172.
  • the data acquisition unit 2171 acquires the new fastest work time updated by the fastest work time update unit 212 and the appropriateness of the work as learning data.
  • the data of the fastest working time also includes the contents of each working procedure included in the series of setup work and the data of the procedure working time which is the time required for them.
  • the appropriateness of work is an index showing the ease of work or the small number of wastes of work, and the work with the least number of wastes of operations hidden in the work is optimized.
  • the appropriateness of the work may be set by the user, or may be automatically determined based on a predetermined standard.
  • the model generation unit 2172 learns the appropriateness of work based on the learning data including the information of the combination of the new fastest work time and the appropriateness of work acquired by the data acquisition unit 2171. That is, the model generation unit 2172 generates a trained model for inferring the appropriateness of the work from the new fastest work time and the appropriateness of the work related to the setup work of the target product.
  • the learning data in this learning process is data in which the new fastest working time and the appropriateness of the work are associated with each other.
  • the learning algorithm used by the model generation unit 2172 may be a conventional algorithm. For example, supervised learning, unsupervised learning or reinforcement learning can be used.
  • deep learning may be executed to learn the extraction of the feature amount itself, or machine learning may be executed according to genetic programming, functional logic programming, and a support vector machine.
  • the model generation unit 2172 learns the appropriateness of the work for the fastest working time by supervised learning according to the neural network model.
  • supervised learning refers to a method of learning a feature in the learning data by giving a set of input and result (label) data to the learning device, and inferring the result from the input.
  • a neural network is composed of an input layer having a plurality of neurons, an intermediate layer (hidden layer) having a plurality of neurons, and an output layer having a plurality of neurons.
  • the intermediate layer is one layer or two or more layers.
  • the model generation unit 2172 is supervised learning based on the learning data including the information of the combination of the new fastest work time and the appropriateness of the work acquired by the data acquisition unit 2171. , Learn the appropriateness of work for the fastest work time.
  • the model generation unit 2172 adjusts the weight W1 between the input layer intermediate layers and the weight W2 between the intermediate layer output layers, and outputs a result (output from the output layer when a new fastest working time is input to the input layer). Learning is performed by finding the weights W1 and W2 that can approach the appropriateness of the work that is the correct answer). For example, when the work speed calculated from the procedure work time included in the fastest work time is input to the input layer, an index showing less waste of operation is obtained in the intermediate layer, and the appropriateness of the work is shown in the output layer. It is output, and the weights W1 and W2 are determined by comparing this with the appropriateness of the work that is the correct answer.
  • the trained model storage unit 223 stores the trained model output by the model generation unit 2172.
  • the flow of the learning process (model generation step) is as shown in the flowchart of FIG. 4B.
  • the data acquisition unit 2171 of the learning device 217 acquires new data on the fastest working time and the appropriateness of the work (step S301).
  • the new fastest work time and the appropriateness of the work are acquired at the same time, but it is sufficient if the new fastest work time and the appropriateness of the work can be input in association with each other.
  • Data of appropriateness may be acquired at different timings.
  • the model generation unit 2172 performs learning processing based on the combination of the new fastest work time and the appropriateness of the work acquired by the data acquisition unit 2171 (step S302), and generates a trained model. Then, the generated trained model is stored in the trained model storage unit 223 (step S303).
  • FIG. 5A is a block diagram showing the inference device 218 of the optimum work procedure extraction unit 213, and FIG. 5B is a flowchart of the inference process.
  • the inference device 218 includes a data acquisition unit 2181 and an inference unit 2182.
  • the data acquisition unit 2181 acquires a new fastest work time updated by the fastest work time update unit 212 as input data.
  • the inference unit 2182 infers the appropriateness of the work for the fastest work time acquired by the data acquisition unit 2181 by using the trained model stored in the trained model storage unit 223. That is, the inference unit 2182 inputs the fastest work time into the trained model, and outputs the appropriateness of the work inferred from the new fastest work time and the procedure work time included in the new fastest work time.
  • the configuration for outputting the appropriateness of the work using the trained model generated by the model generation unit 2172 of the learning device 217 has been described, but the trained model is acquired from the outside of the work procedure updating device.
  • the appropriateness of the work may be inferred based on this trained model.
  • the flow of inference processing (optimal work procedure extraction step) is as shown in the flowchart of FIG. 5B.
  • the data acquisition unit 2181 of the inference device 218 acquires new data of the fastest working time (step S401).
  • the inference unit 2182 inputs a new fastest working time into the learned model stored in the learned model storage unit 223 (step S402), infers the appropriateness of the work, and outputs it (step S403).
  • the optimum work procedure extraction unit 213 determines and outputs the optimum work procedure with the highest appropriateness for the target model based on the appropriateness of the output work (step S404). Specifically, the optimum work procedure extraction unit 213 is the most wasteful based on the content of each work procedure included in the series of work related to the new fastest work time and the procedure work time which is the time required for them. Extract the optimal procedure with few. When there are a plurality of actual works related to the new fastest work time, the optimum work procedure with the least waste is extracted from the work procedures of the actual work related to the fastest work time.
  • the optimum work procedure is determined at the discretion of the technician, and there is a problem that it may not match the actual situation of the setup worker.
  • the optimum work procedure utilizing artificial intelligence is used.
  • the extraction unit 213 can determine the optimum work procedure based on an objective evaluation.
  • the optimum work procedure extracted by the optimum work procedure extraction unit 213 is output to the work procedure update unit 214 and the work time comparison unit 215.
  • the work procedure update unit 214 updates the work procedure of the setup work stored in the work procedure storage unit 224 to the operator to the optimum work procedure input from the optimum work procedure extraction unit 213 (work procedure). Update step).
  • the work time comparison unit 215 calculates the procedure work time for each procedure in the actual work based on the video acquired by the actual work video acquisition unit 211, and the procedure work time in the optimum work procedure input from the optimum work procedure extraction unit 213. Compare with. Procedure Work time When the actual work time is longer, the work information is output.
  • the actual work data to be compared with the optimum work procedure may be the actual work data of the target worker stored in the actual work database 221, and is the actual work data related to the shortest work time of the target worker. There may be.
  • the work improvement plan output unit 216 creates a work improvement plan in the work time comparison unit 215 indicating that the procedure in which the actual work procedure work time is longer is changed to the procedure included in the optimum work procedure. It is displayed on the display unit 230.
  • the display form of the work improvement plan may be any form, and for example, an improvement plan display sheet in which the extracted difference portion is visualized using a commercially available table comparison tool may be used. By presenting the improvement plan display sheet to the operator, it is possible to obtain the effect of suppressing the variation in the setup work time.
  • FIGS. 6A and 6B are diagrams for explaining the operation of the fastest work time update unit 212 and the optimum work procedure extraction unit 213 for an example of work
  • FIGS. 6A shows the fastest work time and the shortest actual work time per day. It is a graph which shows
  • FIG. 6B is a table which shows the optimum work procedure.
  • the actual work video acquisition unit 211 acquires the actual work video taken by the photographing device 100 and saves it in the actual work database 221.
  • the fastest work time update unit 212 calculates the actual work time based on the actual work video stored in the actual work database 221 and compares the shortest actual work time and the fastest work time in one day. As a result of comparison, when the shortest actual work time per day is shorter than the current fastest work time, the fastest work time is updated.
  • the fastest working time is 25 minutes
  • the shortest actual working time per day changes as shown by black dots
  • the shortest actual working time on October 5 is shorter than the fastest working time.
  • the shortest actual work time on October 10 is shorter than the shortest actual work time on October 5. Therefore, the fastest working time update unit 212 updates the next fastest working time to the shortest actual working time on October 10.
  • the fastest work time update unit 212 stores the updated fastest work time and the procedure work time of each work procedure included in the actual work related to the fastest work time in the fastest work time database 222.
  • the trained model storage unit 223 stores the trained model learned based on the fastest working time in the past and the appropriateness of the work.
  • the optimum work procedure extraction unit 213 extracts the optimum work procedure using the trained model based on the fastest work time and the procedure work time stored in the fastest work time database 222.
  • the optimum work procedure extracted by the optimum work procedure extraction unit 213 is represented by, for example, an identification number (procedure No.) of each work procedure and work contents as shown in FIG. 6B. If there are multiple actual works with the same fastest work time within the analysis period, the optimum work procedure extraction unit 213 selects the procedure with less waste of work based on the trained model and performs the optimum work. It is a procedure.
  • FIG. 7A and 7B are diagrams for explaining the operation of the work time comparison unit 215 for an example of work
  • FIG. 7A is a table showing the work time of the optimum work procedure
  • FIG. 7B is the work of the actual work procedure. It is a table showing the time.
  • the work time comparison unit 215 acquires the optimum work procedure extracted by the optimum work procedure extraction unit 213 and the procedure work time which is the time required for each work procedure.
  • FIG. 7A shows the work content and the work time for each work procedure of the optimum work procedure.
  • the work time comparison unit 215 is based on the actual work video of the worker A acquired by the actual work video acquisition unit 211, for each procedure in the actual work in which the work time is the shortest among the setup work of the worker A. Procedure Calculate the working time.
  • FIG. 7B shows the work content and the work time for each work procedure of the actual work.
  • the work time comparison unit 215 compares the optimum work procedure with the work content of the actual work and the work time, and extracts the item whose time is longer in the actual work. In FIG. 7B, items that take longer in actual work are shaded.
  • the field worker can grasp how much the difference is from the optimum work time and which work procedure deviates from the optimum work procedure.
  • the work improvement plan output unit 216 creates a work improvement plan in the work time comparison unit 215 indicating that the procedure in which the actual work procedure work time is longer is changed to the procedure included in the optimum work procedure. Output.
  • FIG. 8 is a table of work improvement plans for the examples shown in FIGS. 7A and 7B.
  • the actual work showed the improvement contents for the work procedures 1, 2 and 10 which took longer.
  • the content of the improvement may be an independent content for each work procedure, or may be a content related to a plurality of work procedures.
  • the improvement contents for the work procedures 1 and 2 are the change of the order of the work procedures 1 and 2 and the change of the flow line for searching the tool of the work procedure 2.
  • the display unit 230 displays at least one of the fastest work time, the optimum work procedure, and the work improvement plan.
  • the fastest working time, the optimum working procedure, and the method of presenting the work improvement plan are arbitrary, and may be displayed on the display unit 230 or distributed as educational materials to the workers.
  • the fastest working time update unit 212 updates the fastest working time, so that the fastest working time that matches the actual situation at that time can be shown.
  • the optimum work procedure extraction unit 213 can extract the optimum work procedure based on the new fastest work time and create a work procedure manual based on the optimum work procedure.
  • the work procedure manual may be created using general-purpose work analysis software from the updated actual work video related to the fastest work time.
  • a general-purpose work analysis software for example, analysis software OTRS (registered trademark) that can create a work procedure manual from a moving image file can be used.
  • the created procedure manual may be displayed on the display unit 230, or may be a paper medium.
  • the work improvement plan output unit 216 can show the improvement contents for the daily actual work by comparing with the optimum work procedure.
  • the work improvement plan output unit 216 must match the conditions of the analysis method in order to compare the work procedure of the actual work with the optimum work procedure. Therefore, the same analysis software as the analysis of the optimum work procedure is used for the work procedure of the actual work analyzed by the work time comparison unit 215.
  • the fastest work time update unit 212 extracts the shortest actual work time from the actual work time calculated based on the actual work video, and the shortest.
  • the fastest work time is updated when the actual work time is shorter than the fastest work time.
  • the optimum work procedure extraction unit 213 extracts the optimum work procedure based on the fastest work time by using the trained model learned in advance.
  • the work time comparison unit 215 compares each procedure work time of the optimum work procedure extracted by the optimum work procedure extraction unit 213 with each procedure work time of the actual work, and the work improvement plan output unit 216 is based on the comparison result. Decided to output a work improvement plan from the actual work. This makes it possible to present the fastest work time, the optimum work procedure, and the work improvement plan that match the actual work state.
  • the trained model used by the optimum work procedure extraction unit 213 is generated by learning the fastest work time and work aptitude for products including a vacuum cleaner, a dehumidifier, and a dishwasher.
  • the learning target may be a plurality of types of products.
  • the learning device 217 may learn about the actual work in one area, or may learn about the actual work performed independently in a plurality of different areas.
  • the training target product of the trained model may be added in the middle, or may be removed from the training target in the middle.
  • an arbitrary trained model may be applied to a trained model of another model, or the other model may be retrained based on the arbitrary trained model.
  • the hardware configuration and flowchart shown in the above embodiment are examples, and can be arbitrarily changed and modified.
  • Each function realized by the arithmetic processing unit 210 and the storage unit 220 can be realized by using a normal computer system without using a dedicated system.
  • a computer-readable CD-ROM Compact Disc Read-Only Memory
  • DVD Digital Versatile Disc
  • MO Magnetic Optical Disc
  • a computer capable of realizing each function may be configured by storing and distributing it in a recording medium of the above and installing a program on the computer.
  • OS Operating System
  • the application or by cooperating with the OS and the application, only the part other than the OS may be stored in the recording medium.
  • 1 work procedure update system 100 shooting device, 200 work procedure update device, 210 arithmetic processing unit, 211 actual work video acquisition unit, 212 fastest work time update unit, 213 optimal work procedure extraction unit, 214 work procedure update unit, 215 work Time comparison unit, 216 work improvement plan output unit, 217 learning device, 218 inference device, 220 storage unit, 221 actual work database, 222 fastest work time database, 223 trained model storage unit, 224 work procedure storage unit, 230 display unit. , 2171 data acquisition unit, 2172 model generation unit, 2181 data acquisition unit, 2182 inference unit.

Landscapes

  • Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Automation & Control Theory (AREA)
  • General Factory Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Une unité de mise à jour de temps de travail le plus rapide (212) acquiert un temps de travail effectif sur la base d'une vidéo de travail réel capturant le travail, et si le temps de travail effectif est plus court qu'un temps de travail le plus rapide stocké dans une unité de stockage (220), alors met à jour le temps de travail le plus rapide au temps de travail effectif. Une unité d'extraction de procédure de travail optimale (213) extrait une procédure de travail optimale, sur la base du temps de travail le plus rapide mis à jour, à l'aide d'un modèle entraîné qui a été entraîné à l'avance en ce qui concerne le temps de travail le plus rapide et l'adéquation du travail. Une unité de mise à jour de procédure de travail (214) met à jour une procédure de travail stockée dans l'unité de stockage (220) à la procédure de travail optimale extraite.
PCT/JP2021/032074 2020-11-02 2021-09-01 Dispositif de mise à jour de procédure de travail, procédé de mise à jour de procédure de travail, et programme WO2022091571A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2022558891A JP7387025B2 (ja) 2020-11-02 2021-09-01 作業手順更新装置、作業手順更新方法及びプログラム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020183842 2020-11-02
JP2020-183842 2020-11-02

Publications (1)

Publication Number Publication Date
WO2022091571A1 true WO2022091571A1 (fr) 2022-05-05

Family

ID=81383998

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/032074 WO2022091571A1 (fr) 2020-11-02 2021-09-01 Dispositif de mise à jour de procédure de travail, procédé de mise à jour de procédure de travail, et programme

Country Status (2)

Country Link
JP (1) JP7387025B2 (fr)
WO (1) WO2022091571A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017159562A1 (fr) * 2016-03-14 2017-09-21 オムロン株式会社 Dispositif de génération d'information d'action
WO2019087275A1 (fr) * 2017-10-31 2019-05-09 株式会社日立製作所 Dispositif d'analyse de travail et procédé d'analyse de travail
US20200327465A1 (en) * 2019-04-12 2020-10-15 University Of Iowa Research Foundation System and method to predict, prevent, and mitigate workplace injuries
JP6777266B1 (ja) * 2019-09-18 2020-10-28 三菱電機株式会社 作業要素分析装置及び作業要素分析方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017159562A1 (fr) * 2016-03-14 2017-09-21 オムロン株式会社 Dispositif de génération d'information d'action
WO2019087275A1 (fr) * 2017-10-31 2019-05-09 株式会社日立製作所 Dispositif d'analyse de travail et procédé d'analyse de travail
US20200327465A1 (en) * 2019-04-12 2020-10-15 University Of Iowa Research Foundation System and method to predict, prevent, and mitigate workplace injuries
JP6777266B1 (ja) * 2019-09-18 2020-10-28 三菱電機株式会社 作業要素分析装置及び作業要素分析方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
KOMIYA MASATO, OSAMU SATO, REIMI KAKUO: "Special Feature Manufacturing Strategy in the Digital Age Impact of 5G on the manufacturing industry and the next trends of "skilled IoT" and "digitalization of on-site capabilities"", INTELLECTUAL ASSET CREATION, NOMURA RESEARCH INSTITUTE CO., LTD., 1 August 2020 (2020-08-01), pages 24 - 39, XP055926657 *

Also Published As

Publication number Publication date
JPWO2022091571A1 (fr) 2022-05-05
JP7387025B2 (ja) 2023-11-27

Similar Documents

Publication Publication Date Title
CN109816624A (zh) 外观检查装置
US20190188110A1 (en) Industrial control system, and assistance apparatus, control assist method, and program thereof
JP2020144660A (ja) 情報処理装置、情報処理方法及びプログラム
CN107817762A (zh) 教育辅助装置
CN110750567A (zh) 一种基于智能衣柜的穿搭数据生成方法及系统
US11562567B2 (en) Observed-object recognition system and method
US20220366244A1 (en) Modeling Human Behavior in Work Environment Using Neural Networks
CN107817778A (zh) 教育辅助装置
US20180336477A1 (en) Information processing apparatus and non-transitory computer readable medium
WO2022091571A1 (fr) Dispositif de mise à jour de procédure de travail, procédé de mise à jour de procédure de travail, et programme
CN115135463A (zh) 工业系统的预测模型学习方法、装置和系统
JP2019003545A (ja) 操作支援装置、操作支援方法、操作支援プログラム及び記録媒体
WO2020053991A1 (fr) Appareil d'aide à la conception d'un système de fabrication
JP2022021437A (ja) 作業支援装置、作業支援方法及びプログラム
JP6947029B2 (ja) 制御装置、それを使用する情報処理装置、制御方法、並びにコンピュータ・プログラム
JP7165108B2 (ja) 作業訓練システム及び作業訓練支援方法
JP2009245043A (ja) ライン生産管理支援方法および装置
JP2020087091A (ja) 熟練度判定システム
JP7005463B2 (ja) 学習装置、学習方法及びプログラム
JP2021096549A (ja) プログラム作成装置、プログラム作成方法、及びプログラム
CN115167582A (zh) 一种基于数字孪生的玫瑰烘干处理监控方法及设备
US20210097884A1 (en) Work support apparatus, work support system, and work support method
JP2023054769A (ja) 柔軟で適応的なロボット学習のための人間ロボット協働
CN110198471A (zh) 异常识别方法、装置、智能设备及存储介质
JP2021082367A (ja) シミュレーション装置、シミュレーション方法およびシミュレーションプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21885690

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022558891

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21885690

Country of ref document: EP

Kind code of ref document: A1