Production line process flow optimization method and device based on industrial internet, equipment and medium
By obtaining and processing production operation videos of each station in the production line, the target operation time of the production process is automatically determined, and the optimization algorithm is used to optimize the process process, the traditional optimization efficiency and reliability problems of production line process process optimization that relies on manual experience is solved, and more efficient and reliable production line process optimization is achieved.
Patent Information
- Application Number
- CN202411980871.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-30
- Publication Date
- 2025-05-09
AI Technical Summary
In the prior art, the adjustment of production line process flow depends on manual experience and is greatly affected by subjective factors, resulting in low reliability and efficiency of optimization results.
By obtaining the production operation videos of each station in the production line, the target operation time of each production process is automatically determined, and the process constraints are used as the hard constraints, the production balance rate and the number of workers' needs are optimized. The preset optimization algorithm is used to reorganize the production line.
It improves the efficiency of production line process process optimization and the reliability of optimization results, and is more accurate and efficient than traditional methods based on manual experience.
Smart Images
Figure CN119962722A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of production and manufacturing technology, and in particular to a production line process optimization method, device, equipment and computer-readable storage medium based on the Industrial Internet. Background Art
[0002] With the development of artificial intelligence, the management model of traditional factories is changing, and information management systems are gradually replacing the traditional business model of factories. However, the adjustment of production line process flow still basically relies on manual experience.
[0003] However, adjusting the production line process flow by relying on manual experience and other methods is greatly affected by human subjective factors, and the reliability of the process flow optimization results is poor and the efficiency is also very low. Summary of the invention
[0004] The present application provides a production line process flow optimization method, device, equipment and computer-readable storage medium based on the Industrial Internet, which can improve the optimization efficiency of the production line process flow and the reliability of the optimization results.
[0005] In a first aspect, an embodiment of the present application provides a production line process optimization method based on the industrial Internet, including:
[0006] Obtain the collected production operation videos of each workstation in the production line;
[0007] For each workstation, based on the production operation video, determine the target operation time of each production process in the workstation;
[0008] Get process constraints;
[0009] Taking the process constraint conditions as hard constraints, the production balance rate of the production line and the number of workers required as optimization targets, a preset optimization algorithm is used to carry out process flow reorganization planning for the production line; wherein the production balance rate is related to the target operation time of each production process of the production line.
[0010] In a second aspect, an embodiment of the present application provides a production line process optimization device based on the industrial Internet, including:
[0011] An acquisition module is used to acquire the production operation videos of each workstation in the production line;
[0012] A processing module, for determining, for each workstation, a target operation time for each production process in the workstation based on the production operation video;
[0013] The acquisition module is also used to acquire process constraints;
[0014] The processing module is also used to use the process constraint conditions as hard constraints, the production balance rate of the production line and the number of workers required as optimization targets, and adopt a preset optimization algorithm to carry out process flow reorganization planning for the production line; wherein the production balance rate is related to the target operation time of each production process of the production line.
[0015] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the production line process optimization method based on the industrial Internet provided in the first aspect of the embodiment of the present application are implemented.
[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the production line process optimization method based on the industrial Internet provided in the first aspect of the embodiment of the present application are implemented.
[0017] The technical solution provided in the embodiment of the present application automatically determines the target operation time of each production process in the production line by processing the production operation video of each workstation in the production line. Compared with the manual statistical method, the accuracy of the production process operation time is improved, and the process constraints of the production line are used as hard constraints, the production balance rate of the production line and the number of workers required are used as optimization goals, and a preset optimization algorithm is used to automatically reorganize the process flow of the production line. Compared with the traditional method based on manual experience, the reliability of the production line process flow optimization results is higher and the efficiency is higher. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 A schematic diagram of a process flow of a production line process optimization method based on the industrial Internet provided in an embodiment of the present application;
[0019] Figure 2 Another schematic diagram of a process flow of a production line process optimization method based on the industrial Internet provided in an embodiment of the present application;
[0020] Figure 3 Another schematic diagram of a process flow of a production line process optimization method based on the industrial Internet provided in an embodiment of the present application;
[0021] Figure 4 A schematic diagram of a structure of a production line process optimization device based on the industrial Internet provided in an embodiment of the present application;
[0022] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0023] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application are further described in detail through the following embodiments and in combination with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. Those skilled in the art can make adjustments to them as needed to suit specific application scenarios. It should also be noted that, for ease of description, only the parts related to the present application are shown in the accompanying drawings, rather than all structures.
[0024] At present, the optimization of production line process flow mainly relies on manual experience and other methods, which are greatly affected by human subjective factors, have low optimization efficiency, and the reliability of the obtained optimization results is poor, which may not meet production needs. In response to the technical problems existing in the above-mentioned traditional methods, the technical solution provided in the embodiment of the present application automatically determines the operation time of each production process in the production line by processing the production operation video of each workstation in the production line, and uses the operation time of each production process as the input parameter of the optimization algorithm, takes the process constraint conditions as hard constraints, and the production balance rate of the production line and the number of workers required as optimization targets. A preset optimization algorithm is used to reorganize the process flow of the production line. Compared with the traditional method, the optimization efficiency of the production line process flow and the reliability of the optimization results are improved.
[0025] The production line process flow optimization method based on the industrial Internet provided in the embodiment of the present application can be executed by the production line process flow optimization device based on the industrial Internet provided in the embodiment of the present application, which can be implemented by software and / or hardware, and integrated in the electronic device that executes the method. Exemplarily, the electronic device can be a multi-access edge computing (EMC) server or a cloud server, or any client device, including but not limited to smartphones, tablet computers, e-book readers, and vehicle-mounted terminals. The embodiment of the present application does not limit the specific form of the electronic device, and the following method embodiment is described by taking the execution subject as an electronic device as an example.
[0026] Figure 1 A flow chart of a production line process optimization method based on the industrial Internet provided in an embodiment of the present application. Figure 1 As shown, the method may include:
[0027] S101, obtaining the collected production operation videos of each workstation in the production line.
[0028] In a possible implementation, the production operation video of each workstation can be collected by a collection device such as a camera, and the production operation video is a complete video containing all the production processes in the workstation. In order to improve the reliability of the production line process optimization results, for each workstation, the production scene of the workstation can be filmed in a loop so that the obtained production operation video contains multiple sets of cyclic production processes. Exemplarily, for workstation 1, assuming that workstation 1 contains production process 1, production process 2, and production process 3, the production scenes of these three production processes can be filmed in a loop so that the obtained production operation video contains multiple sets of cyclic production processes. For example, the production operation video contains 5 sets of cyclic production processes.
[0029] S102. For each workstation, determine the target operation time of each production process in the workstation based on the production operation video.
[0030] The production operation video of each workstation is processed using an artificial intelligence algorithm to determine the target operation time of each production process in each workstation from the production operation video.
[0031] For example, assume that workstation 1 includes three production processes, namely, picking up the skeleton, installing the oil-bearing bearing, and changing the skeleton. By processing the production operation video of workstation 1 through the artificial intelligence algorithm, the target operation time of "picking up the skeleton", the target operation time of "installing the oil-bearing bearing", and the target operation time of "changing the skeleton". For other workstations in the production line, the processing method is similar to that of workstation 1, so that the target operation time of all production processes in the production line can be obtained.
[0032] S103. Obtain process constraints.
[0033] The process constraints refer to the conditions that must be followed during the process flow optimization. Optionally, the process constraints may include process sequence dependencies and / or factory-defined constraints.
[0034] Process sequence dependency means that during the production process, certain processes must be performed in a specific order to ensure product quality and smooth production flow. Specifically, for each production process, it is necessary to determine the predecessor production process of each production process, that is, the production process that must be completed before the production process can be started. For example, before painting, the surface of the object must be cleaned and polished, so the painting order must be after cleaning and polishing; and it is also necessary to determine whether the position of each production process is fixed. If the position is fixed, the position of the production process cannot be adjusted; in this way, based on the predecessor process information of each production process and the fixedness of the position, the process sequence dependency can be generated.
[0035] The above factory-customized constraint rules may include production resource restrictions, worker shifts and working hours, the number of workers, equipment maintenance and shutdown, and order delivery dates.
[0036] S104. Taking the process constraints as hard constraints, the production balance rate of the production line and the number of workers required as optimization targets, a preset optimization algorithm is used to reorganize the process flow of the production line; wherein the production balance rate is related to the target operation time of each production process of the production line.
[0037] In one possible implementation, the production balance rate of the production line is determined by the following formula:
[0038] Production balance rate = total process beat / (bottleneck beat*number of workstations)
[0039] Among them, the total process beat refers to the total time consumed by all production processes, and the bottleneck beat refers to the longest production beat of the workstation on the production line. The above total process beat and bottleneck beat are related to the target operation time of the production process.
[0040] The above-mentioned number of worker requirements is related to the number of optimized workstations, for example, one workstation corresponds to one worker.
[0041] The above-mentioned optimization algorithm can be any algorithm for solving the optimal value. For example, the optimization algorithm can be a heuristic algorithm, a genetic algorithm, a particle swarm algorithm or a simulated annealing algorithm. Hard constraints refer to constraints that must be followed. After obtaining the process constraints and the target operation time of each production process, the process constraints and the target operation time of each production process are used as input parameters, and the above-mentioned process constraints are used as hard constraints. The production balance rate of the production line and the number of workers required are used as optimization targets, and a preset optimization algorithm is used to reorganize the process flow planning of the production line. Here, the process flow reorganization planning can include which workstations are involved in the production line and which production processes are assigned to each workstation.
[0042] The technical solution provided in the embodiment of the present application automatically determines the target operation time of each production process in the production line by processing the production operation video of each workstation in the production line. Compared with the manual statistical method, the accuracy of the production process operation time is improved, and the process constraints of the production line are used as hard constraints, the production balance rate of the production line and the number of workers required are used as optimization goals, and a preset optimization algorithm is used to automatically reorganize the process flow of the production line. Compared with the traditional method based on manual experience, the reliability of the production line process flow optimization results is higher and the efficiency is higher.
[0043] On the basis of the above-mentioned embodiment, optionally, determining the target operation time of each production process in the workstation based on the production operation video may include: determining the actual operation time of each production process in the workstation based on the production operation video; determining the target operation time of each production process based on the actual operation time, the allowance rate and proficiency information of each production process.
[0044] Specifically, the production operation video of each workstation is processed using an artificial intelligence algorithm, so as to determine the actual operation time of each production process in each workstation from the production operation video.
[0045] As an optional implementation, the process of determining the actual operation time of each production process in the workstation based on the production operation video may include: extracting the feature value of each video frame in the production operation video through the resnet model, calculating the similarity value between the feature values of the two video frames, combining all the similarity values to obtain a similarity matrix, using the similarity matrix as a feature, and inputting it into the pre-trained target model, thereby obtaining the actual operation time corresponding to each production process in the production operation video. Among them, the training process of the above target model may include: obtaining a sample operation video, extracting the feature value of each video frame in the sample operation video through the resnet model, calculating the similarity value between the feature values of the two video frames, combining all the similarity values to obtain the corresponding sample similarity matrix, using the sample similarity matrix as a feature, using the operation time corresponding to each production process contained in the above sample operation video as a label, training transformers, and obtaining the target model after reaching the preset model convergence condition.
[0046] Furthermore, after the actual operation time of each production process is obtained, the target operation time of each production process is determined by the following formula or a variation of the formula according to the actual operation time of each production process, the preset tolerance rate and proficiency information of each production process (for example, proficiency percentage):
[0047] Target operation time = actual operation time * (1 + allowance) * proficiency information
[0048] In the process of determining the target operation time of the production process, parameters such as the tolerance rate and proficiency information of the production process are added, which fully considers the variables that may appear in the production operation and the skill level of the workers. It can more accurately estimate the operation time required to complete the production process in the actual production scenario, thereby further improving the reliability of the process flow optimization results.
[0049] Based on the above embodiment, optionally, Figure 2As shown, the above-mentioned determination of the actual operation time of each production process in the workstation based on the production operation video may include:
[0050] S201. Extract feature values of each video frame in the production operation video through the resnet model.
[0051] S202: Match the feature value of each video frame with the process feature set corresponding to the workstation to determine the start frame and end frame of each production process from the production operation video.
[0052] The process feature set includes the feature values of the start frame and the end frame of each production process in the workstation. For each workstation in the current production line, the production process at each workstation is known, so the feature values of the start frame and the end frame of each production process contained in each workstation can be stored to obtain the process feature set corresponding to each workstation.
[0053] For the production operation video of each workstation, the feature value of each video frame in the production operation video is extracted through the ResNet model, and the extracted feature value of each video frame is matched with the process feature set corresponding to the workstation, so as to determine the start frame and end frame of each production process at the workstation from the production operation video.
[0054] S203, determining the actual operation time of each production process in the workstation according to the time corresponding to the start frame and the end frame of each production process.
[0055] In one possible implementation, for each production process at the workstation, the time interval between the start frame and the end frame of the production process can be determined based on the times corresponding to the start frame and the end frame of the production process, and the time interval can be determined as the actual operation time of the production process.
[0056] As another possible implementation, the above S203 may include: for each production process, determining a first number of start frames and a second number of end frames of the production process; selecting the minimum value of the first number and the second number as the target number; and determining the actual operation time of the production process based on the time corresponding to the start frame and the end frame of the production process and the target number.
[0057] Specifically, for the same production process, if multiple start frames and end frames are matched, it indicates that the production operation video is a video containing multiple groups of cyclic production processes. Therefore, after matching the start frame and the end frame of the production process, the electronic device can respectively determine the first number of start frames and the second number of end frames of the production process, and take the minimum value of the first number and the second number as the target number of cycles of the production process, and group the matched multiple start frames and end frames according to the target number, so that each group after grouping contains a start frame and an end frame, and the time of an end frame is greater than the time of a start frame; further, the time interval between a start frame and an end frame of each group is calculated respectively, and the ratio between the sum of the time intervals of each group and the target number is determined as the actual operation time of the production process.
[0058] In this embodiment, the feature value of each video frame in the production operation video is matched with the process feature set corresponding to the workstation to determine the time corresponding to the start frame and the end frame of each production process from the production operation video. Then, based on the time corresponding to the start frame and the end frame of each production process, the actual operation time of each production process at the workstation is determined, thereby achieving the purpose of automatically determining the operation time of each production process. Compared with manually counting time or determining the operation time based on experience, the possibility of human error is reduced and the reliability of the production process operation time is improved.
[0059] In one embodiment, optionally, Figure 3 As shown, the above S104 may include:
[0060] S301. Construct a fitness function based on the production balance rate and the number of workers required.
[0061] Specifically, the fitness function can be designed to maximize the production balance rate while minimizing the number of workers required. For example, the fitness function can be positioned as a linear combination of two indicators, the production balance rate and the number of workers required, and each indicator can be assigned different weights based on actual needs.
[0062] S302: Initialize the population.
[0063] The individuals in the population represent the initial process flow planning results of the production line. In specific implementation, the initial process flow planning results of the production line can be randomly generated or created according to some heuristic rules.
[0064] S303. Determine the fitness function value of the individuals in the population.
[0065] For each individual in the population, the fitness function is used to calculate its fitness function value, which reflects the quality of each individual.
[0066] S304: Perform a selection operation on the population based on the fitness function value, and perform a crossover operation and a mutation operation on the selection result to obtain a new individual.
[0067] Specifically, excellent individuals in the population are selected for reproduction according to the fitness function value of each individual. Optionally, the selection method may include roulette selection, tournament selection, etc. For the selected individuals, the gene recombination process in biological evolution is simulated, and some characteristics of the two parent individuals are exchanged to generate new offspring individuals, and some characteristics of the individuals are randomly mutated with a certain probability to increase the diversity of the population and avoid the search process falling into the local optimum.
[0068] S305. Form a next generation population based on the new individuals, and continue to execute the step of determining the fitness function value of the individuals in the population until a preset convergence condition is reached to obtain the target process flow planning result of the production line.
[0069] The new individuals obtained after the selection, crossover and mutation operations form a new generation population, and continue to calculate the fitness function value of each individual in the new generation population, and repeat the above selection, crossover and mutation operations until the preset convergence condition is reached, and the individual with the highest fitness function value is determined as the target process flow planning result of the production line. Among them, the above preset convergence condition can be a preset number of iterations or a preset fitness threshold, etc.
[0070] In this embodiment, a genetic algorithm is used to continuously optimize the process flow planning results, so that the final process flow planning results can meet the goals of maximizing the production balance rate and minimizing the number of workers required. Compared with the method based on manual experience, the reliability of the production line process flow planning results is improved and the efficiency is higher.
[0071] In one embodiment, optionally, after obtaining the production line process flow planning result, the production line process flow planning result and the production parameters corresponding to the current process flow of the production line (ie, the existing process flow that has not been optimized) may be compared and displayed.
[0072] Among them, the production parameters include the production balance rate, the number of workers required and / or the production line rhythm. Exemplarily, the electronic device can display the workstations included in the production line and the production processes assigned to each workstation in a list or graphical form, and can determine the time taken for each workstation to complete all production processes based on the target operation time of the production process assigned to each workstation, as well as determine the production balance rate, the number of workers required and / or the production line rhythm of the optimized production line, and display the above information in a list or graphical form. Furthermore, this information of the optimized production line can also be compared with this information of the production line before optimization. Among them, the display method includes a list method or a graphical method, such as a bar chart, a line chart, etc.
[0073] By comparing and displaying the process flow planning results of the production line with the production parameters corresponding to the current process flow, factory personnel can intuitively understand the differences between the optimized process flow and the existing process, thereby assisting relevant personnel to evaluate the optimized process flow and improving user experience.
[0074] Figure 4 A schematic diagram of a production line process optimization device based on the industrial Internet provided in an embodiment of the present application. Figure 4 As shown, the device may include: an acquisition module 401 and a processing module 402.
[0075] Specifically, the acquisition module 401 is used to acquire the collected production operation video of each workstation in the production line;
[0076] The processing module 402 is used to determine, for each workstation, a target operation time for each production process in the workstation based on the production operation video;
[0077] The acquisition module 401 is also used to acquire process constraints;
[0078] The processing module 402 is also used to use the process constraint conditions as hard constraints, the production balance rate of the production line and the number of workers required as optimization targets, and adopt a preset optimization algorithm to perform process flow reorganization planning for the production line; wherein the production balance rate is related to the target operation time of each production process of the production line.
[0079] Based on the above embodiment, optionally, the processing module 402 is specifically used to determine the actual operation time of each production process in the workstation based on the production operation video; based on the actual operation time, the tolerance rate and proficiency information of each production process, determine the target operation time of each production process.
[0080] On the basis of the above embodiment, optionally, the processing module 402 is also specifically used to extract the feature value of each video frame in the production operation video through the resnet model; match the feature value of each video frame with the process feature set corresponding to the workstation to determine the start frame and end frame of each production process from the production operation video; the process feature set includes the feature values of the start frame and end frame of each production process in the workstation; and determine the actual operation time of each production process in the workstation according to the time corresponding to the start frame and end frame of each production process.
[0081] Based on the above embodiment, optionally, the processing module 402 is also specifically used to determine, for each production process, a first number of start frames and a second number of end frames of the production process; select the minimum value of the first number and the second number as the target number; and determine the actual operation time of the production process based on the times corresponding to the start frame and the end frame of the production process and the target number.
[0082] Optionally, the process constraint conditions include process sequence dependencies and / or factory-defined constraint rules.
[0083] On the basis of the above embodiments, optionally, the processing module 402 is also specifically used to construct a fitness function based on the production balance rate and the number of workers required; initialize a population; the individuals in the population represent the initial process flow planning results of the production line; determine the fitness function values of the individuals in the population; perform a selection operation on the population based on the fitness function value, and perform a crossover operation and a mutation operation on the selection results to obtain new individuals; form a next generation population based on the new individuals, and continue to execute the step of determining the fitness function values of the individuals in the population until a preset convergence condition is reached to obtain the target process flow planning result of the production line.
[0084] Based on the above embodiment, optionally, the processing module 402 is also used to compare and display the process flow planning results of the production line and the production parameters corresponding to the current process flow; wherein the production parameters include the production balance rate, the number of workers required and / or the production line rhythm.
[0085] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 5 As shown, the device includes a processor 50, a memory 51, an input device 52 and an output device 53; the number of the processor 50 in the device can be one or more. Figure 5 A processor 50 is taken as an example; the processor 50, memory 51, input device 52 and output device 53 in the device can be connected by a bus or other means. Figure 5 The example of connecting through bus is taken in the following.
[0086] The memory 51, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the production line process flow optimization method based on the industrial Internet in the embodiment of the present application (for example, the acquisition module 401 and the processing module 402 used in the production line process flow optimization device based on the industrial Internet). The processor 50 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 51, that is, realizing the above-mentioned production line process flow optimization method based on the industrial Internet.
[0087] The memory 51 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created during the process optimization of a production line process based on the industrial Internet, etc. In addition, the memory 51 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 51 may further include a memory remotely arranged relative to the processor 50, and these remote memories may be connected to the device / terminal / server via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0088] The input device 52 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the electronic device. The output device 53 may include a display device such as a display screen.
[0089] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:
[0090] Obtain the collected production operation videos of each workstation in the production line;
[0091] For each workstation, based on the production operation video, determine the target operation time of each production process in the workstation;
[0092] Get process constraints;
[0093] Taking the process constraint conditions as hard constraints, the production balance rate of the production line and the number of workers required as optimization targets, a preset optimization algorithm is used to carry out process flow reorganization planning for the production line; wherein the production balance rate is related to the target operation time of each production process of the production line.
[0094] The production line process optimization device based on the industrial Internet, the electronic device, and the computer-readable storage medium provided in the above embodiments can execute the production line process optimization method based on the industrial Internet provided in any embodiment of the present application, and have the corresponding functional modules and beneficial effects of executing the method. For technical details not described in detail in the above embodiments, please refer to the production line process optimization method based on the industrial Internet provided in any embodiment of the present application.
[0095] Through the above description of the implementation method, the technicians in the relevant field can clearly understand that the present application can be implemented with the help of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.
[0096] It is worth noting that the various units and modules included in the above embodiments are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.
[0097] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.
Claims
1. A production line process optimization method based on industrial Internet, characterized in that: include: Obtain the collected production operation videos of each workstation in the production line; For each workstation, based on the production operation video, determine the target operation time of each production process in the workstation; Get process constraints; Taking the process constraint conditions as hard constraints, the production balance rate of the production line and the number of workers required as optimization targets, a preset optimization algorithm is used to carry out process flow reorganization planning for the production line; wherein the production balance rate is related to the target operation time of each production process of the production line.
2. The method according to claim 1, characterized in that The step of determining the target operation time of each production process in the workstation based on the production operation video includes: Based on the production operation video, determine the actual operation time of each production process in the workstation; Based on the actual operation time, the tolerance rate of each production process and the proficiency information, the target operation time of each production process is determined.
3. The method according to claim 2, characterized in that The determining the actual operation time of each production process in the workstation based on the production operation video includes: Extracting feature values of each video frame in the production operation video through a resnet model; Matching the feature value of each video frame with the process feature set corresponding to the workstation to determine the start frame and the end frame of each production process from the production operation video; the process feature set includes the feature values of the start frame and the end frame of each production process in the workstation; According to the time corresponding to the start frame and the end frame of each production process, the actual operation time of each production process in the workstation is determined.
4. The method according to claim 3, characterized in that Determining the actual operation time of each production process in the workstation according to the time corresponding to the start frame and the end frame of each production process includes: For each production process, determining a first number of start frames and a second number of end frames of the production process; Selecting the minimum value between the first quantity and the second quantity as the target quantity; Based on the time corresponding to the start frame and the end frame of the production process and the target quantity, the actual operation time of the production process is determined.
5. The method according to any one of claims 1 to 4, characterized in that The process constraints include process sequence dependencies and / or factory-defined constraints.
6. The method according to any one of claims 1 to 4, characterized in that The process constraint condition is used as a hard constraint, the production balance rate of the production line and the number of workers required are used as optimization targets, and a preset optimization algorithm is used to perform process flow reorganization planning on the production line, including: Constructing a fitness function based on the production balance rate and the number of workers required; Initialize a population; the individuals in the population represent the initial process flow planning results of the production line; Determining fitness function values of individuals in the population; Performing a selection operation on the population based on the fitness function value, and performing a crossover operation and a mutation operation on the selection result to obtain a new individual; A next generation population is formed based on the new individuals, and the step of determining the fitness function value of the individuals in the population is continued until a preset convergence condition is reached, thereby obtaining a target process flow planning result of the production line.
7. The method according to any one of claims 1 to 4, characterized in that Also includes: The process flow planning results of the production line are compared with the production parameters corresponding to the current process flow; wherein the production parameters include the production balance rate, the number of workers required and / or the production line rhythm.
8. A production line process optimization device based on industrial Internet, characterized in that: include: An acquisition module is used to acquire the production operation videos of each workstation in the production line; A processing module, for determining, for each workstation, a target operation time for each production process in the workstation based on the production operation video; The acquisition module is also used to acquire process constraints; The processing module is also used to use the process constraint conditions as hard constraints, the production balance rate of the production line and the number of workers required as optimization targets, and adopt a preset optimization algorithm to carry out process flow reorganization planning for the production line; wherein the production balance rate is related to the target operation time of each production process of the production line.
9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.