Production line optimization control system based on data fusion

Abstract

The invention discloses a production line optimization control system based on data fusion, relates to the technical field of production control, and discloses a production link division module, a production line control analysis module, a production line control judgment module and a production line control optimization module. By arranging the production link division module, the production line control analysis module and the production line control judgment module, the production line can be split and analyzed according to the production links, the production process of the production line can be accurately controlled, and the production purpose of each production link of the production line can be comprehensively analyzed; when it is judged that the production line of the corresponding production link needs optimization control, optimization control marking is carried out in time, optimization control is carried out on the production line of the production link according to the priority, a production line control optimization module is arranged, and a plurality of optimization control simulation processes are simulated in a mode of constructing an optimization control simulation environment; and determining an optimal optimization control simulation process to perform control optimization on the production line.

Description

Technical Field

[0001] The present invention relates to the technical field of production control, and more specifically, to a production line optimization control system based on data fusion. Background Art

[0002] With the advent of the Industrial 4.0 era, the automation level of production lines continues to improve, which puts higher requirements on the monitoring, optimization and fault warning of the production process. Traditional production line control systems mostly make decisions based on a single data source, which makes it difficult to fully and accurately reflect the production status. At the same time, the optimization and decision-making of a single data source often have limitations, resulting in low optimization efficiency and poor optimization efficiency of the production line. Therefore, how to conduct comprehensive analysis and optimization of multi-source data of the entire production line during the production process is an urgent problem to be solved. Summary of the invention

[0003] In view of the deficiencies in the prior art, the present invention aims to provide a production line optimization control system based on data fusion.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A production line optimization control system based on data fusion, including a production link division module, a production line control analysis module, a production line control determination module, and a production line control optimization module;

[0006] The production link division module: divides the production line according to the production link to obtain multiple link production lines;

[0007] The production line control analysis module: during the production process of the production line, multiple time nodes with equal time intervals are set, and at each time node, the link control analysis value of each link of the production line is obtained;

[0008] The production line control determination module determines whether to mark a link production line as an optimized control production line based on the comparison result between the link control analysis value of the link production line and the link control analysis value, and sets the control optimization order;

[0009] The production line control optimization module: when performing control optimization on each optimized control production line, constructs an optimized control simulation environment for the optimized control production line, and selects an optimized control target process based on the optimized control simulation environment to perform control optimization on the optimized control production line.

[0010] Furthermore, the link control analysis value of the link production line is obtained in the following way: obtain all the production purpose data of the link production line, and then obtain the production purpose compliance value of each production purpose data, set the production purpose compliance threshold, when the production purpose compliance value of the production purpose data is greater than or equal to the production purpose compliance threshold, no processing is performed, when the production purpose compliance value of the production purpose data is less than the production purpose compliance threshold, the production purpose data is marked as non-compliance data, all non-compliance data are grouped together, the production purpose compliance values ​​of the two non-compliance data in the same group are summed up to obtain the non-compliance superposition value, set the non-compliance superposition threshold, when the non-compliance superposition value is greater than or equal to the non-compliance superposition threshold, no processing is performed, when the non-compliance superposition value is less than the non-compliance superposition threshold, the non-compliance number of protrusions is increased by one, the non-compliance number of protrusions is marked as SEP, the non-compliance gap value TKb of the non-compliance data is obtained, the non-compliance gap value coefficient is set to DRg, and the formula is used. The link control analysis value WSZ of the link production line is obtained, where b = 1, 2, ..., B, B is the total number of data that fail to meet the purpose, and L1 is the coefficient of the number of times of failure to hit.

[0011] Furthermore, based on the comparison result between the link control analysis value of the link production line and the link control analysis value, determine whether to mark the link production line as the optimized control production line, and set the control optimization order, specifically: set the link control analysis threshold, when the link control analysis value of the link production line is greater than or equal to the link control analysis value, mark the link production line as the optimized control production line, when the link control analysis value of the link production line is less than the link control analysis value, do not process it, sort all the optimized control production lines in order from large to small according to the link control analysis value, and perform control optimization on the optimized control production lines in the sorted order.

[0012] Furthermore, the unattained gap value of the unattained purpose data is obtained by the following method: the unattained gap value of the unattained purpose data can be obtained by calculating the difference between the production purpose compliance threshold and the production purpose compliance value of the unattained purpose data.

[0013] Furthermore, the production purpose compliance value of each production purpose data is obtained by the following method: obtaining the production purpose compliance model of each production purpose data in the production line of this link, inputting each production purpose data into the corresponding production purpose compliance model respectively, and the production purpose compliance model of each production purpose data outputs the production purpose compliance value of each production purpose data.

[0014] Furthermore, when control optimization is performed on each optimized control production line, an optimized control simulation environment of the optimized control production line is constructed, specifically: all production purpose data of the optimized control production line are obtained, the environmental data of the optimized control production line is simultaneously obtained, the target data of all production purposes and the expected simulation time are set, and the optimized control simulation environment of the optimized control production line is constructed based on the production purpose data, environmental data, target data and expected simulation time.

[0015] Furthermore, based on the optimization control simulation environment, an optimization control target process is selected to perform control optimization on the optimization control production line. Specifically, multiple optimization control simulation processes are obtained according to the optimization control simulation environment, and the optimization control value of each optimization control simulation process is obtained. The optimization control simulation process with the largest optimization control value is marked as the optimization control target process, and the optimization control production line is control optimized based on the optimization control target process, and then the next optimization control production line is control optimized.

[0016] Furthermore, the optimized control value of the optimized control simulation process is obtained in the following way: the optimized control production line is simulated and optimized according to the optimized control simulation process, a plurality of periodic nodes with equal time intervals are set in the optimized control simulation process, and the link control analysis value of the optimized control production line is obtained at each periodic node, and the link control analysis upper value and link control analysis lower value are set. When the link control analysis value is greater than or equal to the link control analysis upper value, no processing is performed. When the link control analysis value is less than or equal to the link control analysis lower value, the ideal optimization times are increased once. When the link control analysis value is between the link control analysis upper value and the link control analysis lower value, the ordinary optimization times are increased once, and the ideal optimization times are marked as ek. The ordinary optimization times are increased once, and the ordinary optimization times are marked as gr. All link control analysis values ​​of the optimized control production line are summed and averaged to obtain the link control analysis mean sw. The formula is used The optimized control value AGD of the optimization control simulation process is obtained, where s1 is the ideal optimization times coefficient, s2 is the common optimization times coefficient, and s3 is the mean value coefficient of the link control analysis.

[0017] Compared with the prior art, the present invention has the following beneficial effects:

[0018] 1. Set up the production link division module, production line control analysis module and production line control judgment module, which can split and analyze the production line according to the production link, which is more conducive to accurately controlling the production process of the production line, and comprehensively analyzing the production purpose of each production link of the production line. When it is determined that the production line of the corresponding production link needs to be optimized and controlled, it will be marked for optimization and control in time, and the production line of the production link will be optimized and controlled according to the priority;

[0019] 2. Set up a production line control optimization module, simulate multiple optimization control simulation processes by building an optimization control simulation environment, and conduct a comprehensive analysis of each optimization control simulation process to determine the optimal optimization control simulation process to optimize the production line and ensure that the production of the production line meets the production needs of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is an operation flow chart of a production line optimization control system based on data fusion;

[0021] Figure 2 It is a block diagram of a production line optimization control system based on data fusion;

[0022] Figure 3 A flowchart for optimizing the control of the optimal control production line in order to select the optimal control target process. DETAILED DESCRIPTION

[0023] Reference Figures 1 to 3 A production line optimization control system based on data fusion includes a production link division module, a production line control analysis module, a production line control judgment module, and a production line control optimization module.

[0024] Production link division module: Divide the production line according to the production link (divided according to the tasks and characteristics of each stage in the entire production process from raw materials to finished products, such as dividing it into primary processing, fine processing, assembly, etc., and the above links can also be further refined, such as the primary processing link is refined into cutting, grinding, etc.), and divide it into multiple link production lines.

[0025] Production line control analysis module: During the production process of the production line, set multiple time nodes with equal time intervals (the length of the time interval can be adjusted according to actual needs). At each time node, obtain the link control analysis value of each link of the production line.

[0026] Production line control judgment module: Set the link control analysis threshold (system threshold, modified and adjusted according to actual needs). When the link control analysis value of the link production line is greater than or equal to the link control analysis value, the link production line is marked as the optimized control production line. When the link control analysis value of the link production line is less than the link control analysis value, no processing is performed. All optimized control production lines are sorted in descending order according to the link control analysis value, and the optimized control production lines are controlled and optimized in the sorted order.

[0027] By setting up the production link division module, the production line control analysis module and the production line control judgment module, the production line can be split and analyzed according to the production link, which is more conducive to accurately controlling the production process of the production line, and conducting a comprehensive analysis of the production purpose of each production link of the production line. When it is determined that the production line of the corresponding production link needs to be optimized and controlled, it is marked for optimization control in a timely manner, and the production line of the production link is optimized and controlled according to priority.

[0028] Production line control optimization module: When performing control optimization on each optimized control production line, all production purpose data of the optimized control production line are obtained, and the environmental data of the optimized control production line (environmental data includes but is not limited to workshop temperature and humidity, production line layout) are simultaneously obtained, and the target data of all production purposes (the target data is the expected data of each production purpose, and the production purpose data needs to be improved in the direction of the target data) and the expected simulation time (that is, the expected time for optimizing the control of the optimized control production line) are set. Based on the production purpose data, environmental data, target data and expected simulation time, an optimized control simulation environment for the optimized control production line is constructed (a digital twin model is constructed based on the above data, and then an optimized control simulation environment is constructed based on the digital twin model, and the optimization process of the optimized control production line can be simulated in the optimized control simulation environment). According to the optimized control simulation environment, multiple optimized control simulation processes are obtained, and the optimized control value of each optimized control simulation process is obtained. The optimized control simulation process with the largest optimized control value is marked as the optimized control target process, and the optimized control production line is optimized based on the optimized control target process, and then the next optimized control production line is optimized.

[0029] Set up a production line control optimization module, simulate multiple optimization control simulation processes by building an optimization control simulation environment, conduct a comprehensive analysis of each optimization control simulation process, determine the optimal optimization control simulation process to optimize the production line, and ensure that the production of the production line meets the production needs of the enterprise.

[0030] The optimized control value of the optimization control simulation process is obtained in the following way: simulate and optimize the optimization control production line according to the optimization control simulation process, set multiple periodic nodes with equal time intervals in the optimization control simulation process, obtain the link control analysis value of the optimization control production line at each periodic node, set the link control analysis upper value and link control analysis lower value, when the link control analysis value is greater than or equal to the link control analysis upper value, no processing is performed, when the link control analysis value is less than or equal to the link control analysis lower value, increase the ideal optimization times once, when the link control analysis value is between the link control analysis upper value and the link control analysis lower value, increase the ordinary optimization times once, mark the ideal optimization times as ek, increase the ordinary optimization times once, mark the ordinary optimization times as gr, sum and average all link control analysis values ​​of the optimization control production line, obtain the link control analysis mean sw, and use the formula The optimized control value AGD of the optimization control simulation process is obtained, where s1 is the ideal optimization times coefficient, s2 is the ordinary optimization times coefficient, s3 is the mean coefficient of link control analysis, the value of s1 is 0.87, the value of s2 is 0.41, and the value of s3 is 0.63.

[0031] The link control analysis value of the link production line is obtained in the following way: obtain all the production purpose data of the link production line, and then obtain the production purpose compliance value of each production purpose data, set the production purpose compliance threshold, when the production purpose compliance value of the production purpose data is greater than or equal to the production purpose compliance threshold, no processing is performed, when the production purpose compliance value of the production purpose data is less than the production purpose compliance threshold, the production purpose data is marked as non-compliance data, all non-compliance data are grouped together, the production purpose compliance values ​​of the two non-compliance data in the same group are summed up to obtain the non-compliance superposition value, set the non-compliance superposition threshold, when the non-compliance superposition value is greater than or equal to the production purpose compliance threshold, When the superposition threshold of the purpose is not reached, no processing is performed. When the superposition value of the purpose is less than the superposition threshold of the purpose, the number of times of failure to hit is increased by one, and the number of times of failure to hit is marked as SEP. The failure gap value TKb of the failure data is obtained, and the failure gap value coefficient is set to DRg, g = 1, 2, 3, ... g; DR1 < DR2 < DR3 < ... < DRg, each failure gap value coefficient is set to correspond to a range of failure gap values, and the range of failure gap values ​​includes (0, TK1], (TK1, TK2], ..., (TKB-1, TKB], when the failure gap value is TKb∈(0, TK1], the failure gap value coefficient is DR1, and the formula is used The link control analysis value WSZ of the link production line is obtained, where b=1, 2, ..., B, B is the total number of data that fail to reach the target, L1 is the coefficient of the number of times of failure to hit, the value of L1 is 0.92, and the value range of DRg is (0.5~1.5).

[0032] The non-attainment gap value of the non-attainment data is obtained by the following method: the non-attainment gap value of the non-attainment data can be obtained by calculating the difference between the production purpose compliance threshold and the production purpose compliance value of the non-attainment data.

[0033] The production purpose compliance value of each production purpose data is obtained by the following method: obtaining the production purpose compliance model of each production purpose data in the production line of this link, inputting each production purpose data into the corresponding production purpose compliance model respectively, and the production purpose compliance model of each production purpose data outputs the production purpose compliance value of each production purpose data.

[0034] In the same production line, different production purpose data correspond to different production purpose compliance models. For example, in the primary processing production line, production safety data and production quality data correspond to two different production purpose compliance models. In production lines at different links, the same production purpose data also correspond to different production purpose compliance models. For example, in the primary processing production line and the fine processing production line, the production safety data of the primary processing production line and the production safety data of the fine processing production line also correspond to two different production purpose compliance models. Although different production purpose compliance models are different, the construction methods of different models are similar. It is only necessary to replace the sample data in the model construction process. Therefore, this application only needs to introduce the construction of one production purpose compliance model to obviously know the construction methods of other production purpose compliance models. This application The example takes the production safety data of the primary processing link as an example to introduce the construction method of the production purpose compliance model: collect production safety data of multiple primary processing links, each production safety data is displayed in the form of a data set, and the data set of the production safety data contains relevant data related to production safety. The relevant data of production safety includes but is not limited to equipment maintenance data, the number of safety hazards, and the type of safety hazards. The collection method of relevant data is not the research and development focus of this application, so it is not repeated. Construct a deep learning model, mark the production safety data of multiple primary processing links as sample data of the deep learning model, assign a production purpose compliance value to each sample data, divide the sample data into a training set and a verification set according to a preset ratio, adjust the preset ratio according to demand, iterate the training set and the verification set to obtain a production purpose compliance model. Among them, the value range of the production purpose compliance value is (1 to 10), the larger the value of the production purpose compliance value, the more the production safety data of the primary processing link production line meets the standard, and the smaller the value of the production purpose compliance value, the less the production safety data of the primary processing link production line meets the standard; the value range of the production purpose compliance value of different production purpose compliance models is the same.

[0035] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0036] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0037] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0038] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0039] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0040] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0041] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0042] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A production line optimization control system based on data fusion, characterized in that: It includes production link division module, production line control analysis module, production line control determination module and production line control optimization module; The production link division module: divides the production line according to the production link to obtain multiple link production lines; The production line control analysis module: during the production process of the production line, multiple time nodes with equal time intervals are set, and at each time node, the link control analysis value of each link of the production line is obtained; The production line control determination module determines whether to mark a link production line as an optimized control production line based on the comparison result between the link control analysis value of the link production line and the link control analysis value, and sets the control optimization order; The production line control optimization module: when performing control optimization on each optimized control production line, constructs an optimized control simulation environment for the optimized control production line, and selects an optimized control target process based on the optimized control simulation environment to perform control optimization on the optimized control production line.

2. The production line optimization control system based on data fusion according to claim 1 is characterized in that: The link control analysis value of the link production line is obtained in the following way: obtain all the production purpose data of the link production line, and then obtain the production purpose compliance value of each production purpose data, set the production purpose compliance threshold, when the production purpose compliance value of the production purpose data is greater than or equal to the production purpose compliance threshold, no processing is performed, when the production purpose compliance value of the production purpose data is less than the production purpose compliance threshold, the production purpose data is marked as non-compliance data, all non-compliance data are grouped into one group, the production purpose compliance values ​​of the two non-compliance data in the same group are summed up to obtain the non-compliance superposition value, set the non-compliance superposition threshold, when the non-compliance superposition value is greater than or equal to the non-compliance superposition threshold, no processing is performed, when the non-compliance superposition value is less than the non-compliance superposition threshold, the non-compliance highlight times are increased once, the non-compliance highlight times are marked as SEP, the non-compliance gap value TKb of the non-compliance data is obtained, the non-compliance gap value coefficient is set as DRg, and the formula is used. The link control analysis value WSZ of the link production line is obtained, where b = 1, 2, ..., B, B is the total number of data that fail to reach the target, and L1 is the coefficient of the number of times of failure to hit.

3. The production line optimization control system based on data fusion according to claim 1 is characterized in that: Based on the comparison result between the link control analysis value of the link production line and the link control analysis value, determine whether to mark the link production line as the optimized control production line, and set the control optimization order, specifically: set the link control analysis threshold, when the link control analysis value of the link production line is greater than or equal to the link control analysis value, mark the link production line as the optimized control production line, when the link control analysis value of the link production line is less than the link control analysis value, no processing is done, all optimized control production lines are sorted in descending order according to the values ​​of the link control analysis values, and control optimization is performed on the optimized control production lines in the sorted order.

4. The production line optimization control system based on data fusion according to claim 2 is characterized in that: The non-attainment gap value of the non-attainment data is obtained by the following method: the non-attainment gap value of the non-attainment data can be obtained by calculating the difference between the production purpose compliance threshold and the production purpose compliance value of the non-attainment data.

5. The production line optimization control system based on data fusion according to claim 2 is characterized in that: The production purpose compliance value of each production purpose data is obtained by the following method: obtaining the production purpose compliance model of each production purpose data in the production line of this link, inputting each production purpose data into the corresponding production purpose compliance model respectively, and the production purpose compliance model of each production purpose data outputs the production purpose compliance value of each production purpose data.

6. The production line optimization control system based on data fusion according to claim 1 is characterized in that: When performing control optimization on each optimized control production line, an optimized control simulation environment for the optimized control production line is constructed. Specifically, all production purpose data of the optimized control production line are obtained, and the environmental data of the optimized control production line is simultaneously obtained. The target data of all production purposes and the expected simulation time are set, and the optimized control simulation environment of the optimized control production line is constructed based on the production purpose data, environmental data, target data and expected simulation time.

7. The production line optimization control system based on data fusion according to claim 1 is characterized in that: Based on the optimization control simulation environment, the optimization control target process is selected to perform control optimization on the optimization control production line. Specifically, multiple optimization control simulation processes are obtained according to the optimization control simulation environment, and the optimization control value of each optimization control simulation process is obtained. The optimization control simulation process with the largest optimization control value is marked as the optimization control target process, and the optimization control production line is controlled and optimized based on the optimization control target process, and then the next optimization control production line is controlled and optimized.

8. The production line optimization control system based on data fusion according to claim 7 is characterized in that: The optimized control value of the optimization control simulation process is obtained in the following way: simulate and optimize the optimization control production line according to the optimization control simulation process, set multiple periodic nodes with equal time intervals in the optimization control simulation process, obtain the link control analysis value of the optimization control production line at each periodic node, set the link control analysis upper value and link control analysis lower value, when the link control analysis value is greater than or equal to the link control analysis upper value, no processing is performed, when the link control analysis value is less than or equal to the link control analysis lower value, increase the ideal optimization times once, when the link control analysis value is between the link control analysis upper value and the link control analysis lower value, increase the ordinary optimization times once, mark the ideal optimization times as ek, increase the ordinary optimization times once, mark the ordinary optimization times as gr, sum and average all link control analysis values ​​of the optimization control production line, obtain the link control analysis mean sw, and use the formula The optimized control value AGD of the optimization control simulation process is obtained, where s1 is the ideal optimization times coefficient, s2 is the common optimization times coefficient, and s3 is the mean value coefficient of the link control analysis.

Images