Dynamic simulation optimization model construction method based on digital twin

Abstract

The present invention discloses a method for constructing a dynamic simulation optimization model based on digital twins, and relates to the technical field of manufacturing production simulation. The method for constructing a dynamic simulation optimization model based on digital twins improves the overall efficiency and production capacity of the production line, reduces invalid process flow and space waste, and optimizes the configuration of production line resources by identifying bottleneck areas in the electronic product production line and analyzing the operation fluidity and space allocation rationality between process blocks through a simulated annealing algorithm. The accuracy and efficiency of path planning are improved by combining the K nearest neighbor algorithm with the Dijkstra algorithm. By predicting key features and optimizing paths, transportation time and costs are reduced, and the operating efficiency and reliability of logistics tracks are improved. By testing and evaluating different logistics demand scenarios, the production line layout and path planning can be continuously optimized and adjusted to help continuously improve the performance and efficiency of the production line.

Description

Technical Field

[0001] The present invention relates to the technical field of manufacturing production simulation, and specifically to a method for constructing a dynamic simulation optimization model based on digital twins. Background Art

[0002] With the rapid development of digital technology, traditional manufacturing and production models are transforming towards intelligence and digitalization. Digital twin technology and dynamic simulation technology have become important supports for this transformation. The manufacturing industry is undergoing a transformation from traditional production methods to intelligent manufacturing. Digital twin and dynamic simulation technologies can provide real-time monitoring, predictive analysis and optimized decision-making, helping enterprises to improve production efficiency and quality.

[0003] For example, a method and device for constructing a dynamic simulation model of an electronic product production line with announcement number CN117077458B includes: providing layout information, manufacturing information and logistics task information of the electronic product production line based on the process route of the electronic product production line; building an electronic product production line layout model according to the layout information of the electronic product production line; providing layout link parameters of the electronic product production line according to the layout model of the electronic product production line in combination with a preset coding strategy, and the layout link parameters are used to associate the layout information and manufacturing information of the electronic product production line; embedding a calling module in the layout model of the electronic product production line to obtain a dynamic simulation model of the electronic product production line, and the calling module is used to call the logistics task information according to the layout link parameters. The present invention obtains a dynamic simulation model quickly and accurately from the layout model of the electronic product production line, has extremely strong universality, and improves the dynamic simulation effect of the electronic product production line.

[0004] However, in the process of building traditional dynamic simulation optimization models, process blocks, equipment, logistics paths, etc. are over-simplified, details and changes in reality are ignored, and fixed layout configurations are usually adopted, which lack flexibility to adapt to changes in production needs. This limits the application effect of the model in actual production. In order to solve these problems, it is necessary to improve the model precision and data accuracy, realize dynamic and flexible layout adjustment, adopt advanced path planning algorithms, and enhance dynamic simulation and feedback mechanisms, while improving computing efficiency and expansion capabilities. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a method for constructing a dynamic simulation optimization model based on digital twins, which solves the problems of the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for constructing a dynamic simulation optimization model based on digital twins, characterized in that it includes the following steps: S1. constructing an initial digital twin model according to an electronic product production line through digital twins; S2. Based on the initial digital twin model, identifying the bottleneck area in the electronic product production line, analyzing the operation fluidity and spatial allocation rationality between process blocks through a simulated annealing algorithm, and optimizing the process block layout; S3. Using the K nearest neighbor algorithm to predict the path characteristics of each process block, generating the key features affecting the logistics path planning of each process block, and combining the Dijkstra algorithm to construct a graph model, converting the key features affecting the logistics path planning into the edge weights of the graph, obtaining the optimal path between each process block layout, and optimizing the logistics track path planning; S4. Loading the location and layout optimization information of the process block and the logistics track layout optimization information into the initial digital twin model, and constructing a dynamic simulation model of the electronic product production line; S5. Testing different logistics demand scenarios through the electronic product production line optimization layout model, obtaining the process block layout optimization index and the logistics track path planning index, and evaluating the optimization degree of the dynamic simulation model based on the test history data.

[0007] Furthermore, the specific process of identifying the bottleneck area in the electronic product production line is as follows: determine the workload of each process block based on the historical operation time, equipment utilization and material backlog data of the process block, and identify the process blocks with excessive load.

[0008] Furthermore, the specific process of analyzing the rationality of job fluidity and spatial allocation between process blocks through the simulated annealing algorithm is as follows: maximizing the overall efficiency of the production line, minimizing the job flow time, and minimizing the material handling cost are set as the objective function, and the objective function is used to quantify and reflect the rationality of job fluidity and spatial allocation between process blocks; the job flow time, material handling cost and space utilization before each process block are defined as the spatial constraints of the process block and the constraints of the job flow, and the objective function value between each process block is calculated; through the simulated annealing algorithm, the objective function will calculate the pros and cons of the current process block layout in each iteration, find the minimum objective function value, and determine the optimal process block layout.

[0009] Furthermore, the K nearest neighbor algorithm is used to predict the path characteristics of each process block, and the specific process of generating key features that affect logistics path planning for each process block is as follows: obtain logistics data and historical path data between process blocks, and construct feature vectors and label data; use the K nearest neighbor algorithm to calculate the path characteristics based on the feature vector, select the K value and distance metric, and perform weighted average prediction on the path characteristics of the query point to generate key features that affect logistics path planning for each process block; the key features that affect logistics path planning include transportation time, transportation cost, path capacity, and delay risk.

[0010] Furthermore, a graph model is constructed in combination with the Dijkstra algorithm, and the key features that affect logistics path planning are converted into edge weights of the graph. The specific process of obtaining the optimal path between the layouts of each process block is as follows: a graph model is constructed in combination with the Dijkstra algorithm, and the key features that affect logistics path planning predicted by the K-nearest neighbor algorithm are converted into edge weights in the graph model; the comprehensive weight of each edge is calculated for weighting, and the shortest path calculation is performed on the graph model using the Dijkstra algorithm. The distance of each node is initialized to infinity, and the distance of the starting node is set to zero. The shortest path distance is updated iteratively, and the node with the smallest distance among the currently unprocessed nodes is selected for update until the shortest path of all nodes is determined.

[0011] Furthermore, the specific process of obtaining the process block layout optimization index and the logistics track path planning index is as follows: through the testing of the electronic product production line optimization layout model in different logistics demand scenarios, the operation time, conflict occurrence rate and space utilization rate of each process block are obtained, and compared with the set optimization thresholds to obtain the process block layout optimization index; the transportation time, transportation cost and delay risk rate of each process block are obtained, and compared with the set optimization thresholds to obtain the logistics track path planning index.

[0012] Furthermore, based on the test historical data, the specific process of evaluating the optimization degree of the dynamic simulation model is as follows: based on the process block layout optimization index and the logistics track path planning index, comprehensive calculations are performed with the historical process block layout optimization index and the historical logistics track path planning index respectively to obtain the optimization index of the dynamic simulation model; the optimization index of the dynamic simulation model is compared with the set optimization index threshold of the dynamic simulation model to evaluate the optimization degree of the dynamic simulation model.

[0013] The present invention has the following beneficial effects:

[0014] (1) This dynamic simulation optimization model construction method based on digital twins improves the overall efficiency and capacity of the production line by identifying the bottleneck areas in the electronic product production line. It analyzes the operation fluidity and space allocation rationality between process blocks through the simulated annealing algorithm, reduces invalid process flow and space waste, and optimizes the configuration of production line resources.

[0015] (2) This dynamic simulation optimization model construction method based on digital twins improves the accuracy and efficiency of path planning by combining the K nearest neighbor algorithm with the Dijkstra algorithm. By predicting key features and optimizing paths, transportation time and costs are reduced, and the operating efficiency and reliability of logistics tracks are improved. By testing and evaluating different logistics demand scenarios, the production line layout and path planning can be continuously optimized and adjusted to ensure the effectiveness and sustainability of the optimization plan. The calculation and evaluation of the optimization index provides quantitative indicators to help continuously improve the performance and efficiency of the production line.

[0016] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of the method for constructing a dynamic simulation optimization model based on digital twins in the present invention.

[0018] Figure 2 A flow chart of a dynamic simulation model for constructing an electronic product production line for the present invention. DETAILED DESCRIPTION

[0019] The embodiment of the present application solves the problems of traditional electronic product production line models, such as insufficient accuracy, static layout, non-optimized path planning, lack of simulation capabilities, slow response speed and poor scalability, through a dynamic simulation optimization model construction method based on digital twins.

[0020] The overall idea of ​​the problem in the embodiment of this application is as follows:

[0021] Use digital twins to build an initial digital twin model based on the electronic product production line.

[0022] Based on the initial digital twin model, the bottleneck areas in the electronic product production line are identified, and the operational fluidity and spatial allocation rationality between process blocks are analyzed through the simulated annealing algorithm to optimize the process block layout.

[0023] The K-nearest neighbor algorithm is used to predict the path characteristics of each process block, and the key features that affect the logistics path planning of each process block are generated. The Dijkstra algorithm is combined to build a graph model, and the key features that affect the logistics path planning are converted into the edge weights of the graph. The optimal path between the layouts of each process block is obtained, and the logistics track path planning is optimized.

[0024] The location and layout optimization information of the process blocks and the logistics track layout optimization information are loaded into the initial digital twin model to build a dynamic simulation model of the electronic product production line.

[0025] Different logistics demand scenarios are tested through the electronic product production line optimization layout model to obtain the process block layout optimization index and logistics track path planning index, and the optimization degree of the dynamic simulation model is evaluated based on the test historical data.

[0026] See also Figure 1 , the embodiment of the present invention provides a technical solution: a method for constructing a dynamic simulation optimization model based on digital twins, characterized in that it includes the following steps: S1. constructing an initial digital twin model according to an electronic product production line through digital twins; S2. identifying the bottleneck area in the electronic product production line based on the initial digital twin model, analyzing the operation fluidity and spatial allocation rationality between process blocks through a simulated annealing algorithm, and optimizing the process block layout; S3. using a K-nearest neighbor algorithm to predict the path characteristics of each process block, generating key features affecting the logistics path planning of each process block, and combining the Dijkstra algorithm to construct a graph model, converting the key features affecting the logistics path planning into edge weights of the graph, obtaining the optimal path between each process block layout, and optimizing the logistics track path planning; S4. loading the position and layout optimization information of the process block and the logistics track layout optimization information into the initial digital twin model, and constructing a dynamic simulation model of the electronic product production line; S5. testing different logistics demand scenarios through the electronic product production line optimization layout model, obtaining the process block layout optimization index and the logistics track path planning index, and evaluating the optimization degree of the dynamic simulation model based on the test history data.

[0027] In this embodiment, in step S1, real-time data collection is performed through sensors and IoT devices, and the collected data is processed and analyzed using data modeling technology to generate a preliminary production line data model, and its accuracy and reliability are verified; with the help of computer-aided design software or other three-dimensional modeling tools, a three-dimensional virtual model of the production line is established based on the results of data modeling to accurately reproduce the physical layout and process flow of the production line; the data model is integrated with the three-dimensional virtual model to build a digital twin simulation platform. Digital twin is a method for monitoring, simulating and optimizing physical entities through real-time data interaction between virtual models and physical entities. The bottleneck area represents the part of the production process that limits the overall efficiency, usually due to resource limitations, poor process flow or equipment failure. Simulated annealing algorithm is a global optimization algorithm that simulates the physical annealing process and finds the optimal solution through random search and progressively reduced disturbances. Process block is a functional unit or operating unit in a production line, and each process block performs a specific manufacturing task or operation. K nearest neighbor algorithm is a classification and regression algorithm that selects the nearest K sample points by calculating the distance from the sample point to the query point, and predicts based on the attributes of these neighboring points. Path characteristics are the key attributes of the logistics path, such as transportation time, cost, path capacity and delay risk. Dijkstra algorithm is a classic algorithm for calculating the shortest path from a single source in a weighted graph. The dynamic simulation model is based on the initial digital twin model and simulates the dynamic operation of the production line by loading the optimized process block and logistics track layout information. The process block layout optimization index is an indicator to measure the degree of optimization of the process block layout, which is calculated based on the efficiency and process smoothness of the optimized process block. The logistics track path planning index is an indicator to evaluate the optimization effect of the logistics track path planning, taking into account factors such as transportation time, cost, path capacity and delay risk.

[0028] See also Figure 2 ,Specifically, the specific process of identifying the bottleneck area in the ,electronic product production line is as follows: the workload of each process block is determined ,according to the historical operation time, equipment utilization and material backlog data of the ,process block, and the overloaded process block is identified.

[0029] In this implementation scheme, equipment with excessive utilization indicates that it has a large workload and may need to be optimized or have additional equipment added to improve overall efficiency. Analyze the material backlog in the process block. If the material backlog before and after a process block is large, it means that the process block has insufficient processing capacity and may be a bottleneck in the production line. Combine the operating time, equipment utilization, and material backlog data to calculate the workload of each process block. The weighted average method can be used to assign weights to each indicator according to importance and then perform a comprehensive calculation. Based on the calculated workload, identify the overloaded process blocks. Overloaded process blocks are bottleneck areas and need to be optimized as a priority.

[0030] Specifically, the specific process of analyzing the rationality of job fluidity and spatial allocation between process blocks through the simulated annealing algorithm is as follows: maximizing the overall efficiency of the production line, minimizing the job flow time, and minimizing the material handling cost are set as the objective function, and the objective function is used to quantify and reflect the rationality of job fluidity and spatial allocation between process blocks; the job flow time, material handling cost and space utilization before each process block are defined as the spatial constraints of the process block and the constraints of the job flow, and the objective function value between each process block is calculated; through the simulated annealing algorithm, the objective function will calculate the pros and cons of the current process block layout in each iteration, find the minimum objective function value, and determine the optimal process block layout.

[0031] In this embodiment, the simulated annealing algorithm is an optimization technique that mimics the metal annealing process, gradually cooling at high temperature to reach a low energy state. The following is an explanation of the detailed process and calculation formula for optimizing the process block layout through the simulated annealing algorithm. The objective function is used to quantify the rationality of the operation flow and space allocation between process blocks. The goal is to maximize the overall efficiency of the production line, minimize the operation flow time, and minimize the material handling cost. The calculation formula of the objective function is as follows: ; In the formula, F represents the objective function, E represents the total efficiency of the process block, represents the operation flow time between process blocks i and j, represents the material handling cost between process blocks i and j, The weight factor representing the overall efficiency of the process block, represents the weight factor of the job flow time, Weight factor representing material handling cost. Set the initial solution for process block layout , layout of current process blocks , calculate the objective function value F, by the current solution Make small perturbations to generate neighborhood solutions ,like Better than , then accept ,like Inferior , then with probability

[0032] PAccept , the calculation formula of the acceptance probability of the simulated annealing algorithm is ; In the formula, P represents probability, It represents the change in the objective function value, T represents the current temperature in the simulated annealing algorithm, and exp represents an exponential function with the natural constant e as the base. As the number of iterations increases, when the maximum number of iterations is reached, the iteration is stopped and the optimal layout is output.

[0033] Specifically, the K-nearest neighbor algorithm is used to predict the path characteristics of each process block, and the specific process of generating key features that affect logistics path planning for each process block is as follows: obtain logistics data and historical path data between process blocks, and construct feature vectors and label data; use the K-nearest neighbor algorithm to calculate path characteristics based on feature vectors, select K value and distance metric, and perform weighted average prediction on the path characteristics of query points to generate key features that affect logistics path planning for each process block; key features that affect logistics path planning include transportation time, transportation cost, path capacity, and delay risk.

[0034] In this embodiment, the feature vector represents various attribute characteristics of the process block, including location, transportation time, transportation cost, path capacity, and delay risk. Label data represents the characteristics of historical path data, including past transportation time, cost, capacity, and delay. K value: represents the number of nearest neighbors used for prediction. A smaller K value may cause the prediction results to be sensitive to noise, and a larger K value may make the prediction results too smooth. Distance metrics are used to calculate the similarity between different process blocks. Commonly used distance metrics include Euclidean distance and Manhattan distance. Weighted average prediction is based on the weighted average of the path characteristics of the nearest neighbors to generate the path characteristics of the current query point. It is calculated based on the distance between the query point and the neighbor. The closer the distance, the greater the weight and the greater the impact on the prediction result.

[0035] Specifically, a graph model is constructed in combination with the Dijkstra algorithm, and the key features that affect logistics path planning are converted into edge weights of the graph. The specific process of obtaining the optimal path between the layouts of each process block is as follows: a graph model is constructed in combination with the Dijkstra algorithm, and the key features that affect logistics path planning predicted by the K-nearest neighbor algorithm are converted into edge weights in the graph model; the comprehensive weight of each edge is calculated for weighting, and the Dijkstra algorithm is used to perform the shortest path calculation on the graph model, the distance of each node is initialized to infinity, and the distance of the starting node is set to zero, and the shortest path distance is updated iteratively, and the node with the smallest distance among the currently unprocessed nodes is selected for update until the shortest path of all nodes is determined.

[0036] In this implementation, the process blocks are regarded as nodes in the graph model, and the key features that affect logistics path planning (transportation time, transportation cost, path capacity, and delay risk) predicted by the K-nearest neighbor algorithm are converted into edge weights in the graph model. The edge weight calculation formula is: ; In the formula, represents the comprehensive weight of process block edge n to process block m, t represents the transportation time from process block edge n to process block m, c represents the transportation cost from process block edge n to process block m, p represents the transportation cost from process block edge n to process block m, r represents the delay risk rate from process block edge n to process block m, represents the weight factor of transportation time, represents the weight factor of transportation cost, represents the weight factor of transportation cost, The weight factor representing the delay risk rate. In each iteration, select the node with the smallest distance among the currently unprocessed nodes and update the distance of its adjacent nodes. Update rule: If the path distance from the current node u to an adjacent node v is less than the current distance of node v, update the distance of node v. Repeat the iteration until the shortest path of all nodes is determined.

[0037] Specifically, the specific process of obtaining the process block layout optimization index and the logistics track path planning index is as follows: through the testing of the electronic product production line optimization layout model in different logistics demand scenarios, the operation time, conflict occurrence rate and space utilization rate of each process block are obtained, and compared with the set optimization thresholds to obtain the process block layout optimization index; the transportation time, transportation cost and delay risk rate of each process block are obtained, and compared with the set optimization thresholds to obtain the logistics track path planning index.

[0038] In this implementation scheme, the calculation formula of the process block layout optimization index is as follows: ; In the formula, Represents the process block layout optimization index, jk represents the operation time of the process block, bu represents the conflict incidence rate of the process block, ey represents the space utilization rate of the process block, vg represents the threshold of the operation time of the process block, rt represents the threshold of the conflict incidence rate of the process block, and vh represents the threshold of the space utilization rate of the process block. The operation time threshold represents the ideal value or maximum tolerance value of the pre-set operation time, which is used to evaluate the pros and cons of the current operation time. The conflict incidence threshold represents the ideal value or maximum tolerance value of the pre-set conflict incidence rate, which is used to evaluate the pros and cons of the current conflict incidence rate. The space utilization threshold represents the ideal value or maximum tolerance value of the pre-set space utilization, which is used to evaluate the pros and cons of the current space utilization. The calculation formula of the logistics track path planning index is as follows: ; In the formula, represents the logistics track path planning index, tg represents the transportation time of the process block, represents the transportation cost of the process block, Pn represents the delay risk rate of the process block, Qx represents the threshold of the transportation time of the process block, Wz represents the threshold of the transportation cost of the process block, and Xm represents the threshold of the delay risk rate of the process block. The transportation time threshold represents the preset ideal value or maximum tolerance value of the transportation time, which is used to evaluate the pros and cons of the current transportation time. The transportation cost threshold represents the preset ideal value or maximum tolerance value of the transportation cost, which is used to evaluate the pros and cons of the current transportation cost. The delay risk rate threshold represents the preset ideal value or maximum tolerance value of the delay risk rate, which is used to evaluate the pros and cons of the current delay risk rate.

[0039] Specifically, according to the test historical data, the specific process of evaluating the optimization degree of the dynamic simulation model is as follows: based on the process block layout optimization index and the logistics track path planning index, comprehensive calculations are performed with the historical process block layout optimization index and the historical logistics track path planning index respectively to obtain the optimization index of the dynamic simulation model; the optimization index of the dynamic simulation model is compared with the set optimization index threshold of the dynamic simulation model to evaluate the optimization degree of the dynamic simulation model.

[0040] In this implementation scheme, the calculation formula of the optimization index of the dynamic simulation model is as follows: ; In the formula, It represents the optimization index of the dynamic simulation model, DRG represents the historical process block layout optimization index, and DVB represents the historical logistics track path planning index. The optimization index of the dynamic simulation model is compared with the pre-set threshold value to evaluate the optimization degree of the model, and the optimization degree of the model is judged according to the calculated difference.

[0041] In summary, this application has at least the following effects:

[0042] The dynamic simulation optimization model construction method based on digital twins improves the overall efficiency and capacity of the production line by identifying the bottleneck area in the electronic product production line. The simulated annealing algorithm is used to analyze the operation fluidity and space allocation rationality between process blocks, reduce invalid process flow and space waste, and optimize the configuration of production line resources. The accuracy and efficiency of path planning are improved by combining the K nearest neighbor algorithm with the Dijkstra algorithm. By predicting key features and optimizing paths, transportation time and costs are reduced, and the operating efficiency and reliability of logistics tracks are improved. Through testing and evaluation of different logistics demand scenarios, the production line layout and path planning can be continuously optimized and adjusted to ensure the effectiveness and sustainability of the optimization plan. The calculation and evaluation of the optimization index provides quantitative indicators to help continuously improve the performance and efficiency of the production line.

[0043] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0044] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0045] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0046] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0047] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0048] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for constructing a dynamic simulation optimization model based on digital twins, characterized in that: The following steps are involved: S1. Build an initial digital twin model based on the electronic product production line through digital twin; S2. Based on the initial digital twin model, identify the bottleneck area in the electronic product production line, analyze the operation fluidity and space allocation rationality between process blocks through the simulated annealing algorithm, and optimize the process block layout; S3. Use the K-nearest neighbor algorithm to predict the path characteristics of each process block, generate the key features that affect the logistics path planning of each process block, and build a graph model in combination with the Dijkstra algorithm to convert the key features that affect the logistics path planning into the edge weights of the graph, obtain the optimal path between the layouts of each process block, and optimize the logistics track path planning; S4. Load the location and layout optimization information of the process blocks and the logistics track layout optimization information into the initial digital twin model to build a dynamic simulation model of the electronic product production line; S5. Test different logistics demand scenarios through the electronic product production line optimization layout model, obtain the process block layout optimization index and logistics track path planning index, and evaluate the optimization degree of the dynamic simulation model based on the test history data.

2. The method for constructing a dynamic simulation optimization model based on digital twins according to claim 1, characterized in that: The specific process for identifying bottleneck areas in an electronics production line is as follows: Determine the workload of each process block based on the historical operation time, equipment utilization and material backlog data of the process block, and identify the process blocks with excessive load.

3. The method for constructing a dynamic simulation optimization model based on digital twins according to claim 2, characterized in that: The specific process of analyzing the operation fluidity and space allocation rationality between process blocks through simulated annealing algorithm is as follows: Maximizing the total efficiency of the production line, minimizing the operation flow time, and minimizing the material handling cost are set as the objective function. The objective function is used to quantify and reflect the rationality of the operation flow and space allocation between process blocks; The operation flow time, material handling cost and space utilization rate before each process block are defined as the space constraints of the process block and the constraints of the operation flow, and the objective function value between each process block is calculated; Through the simulated annealing algorithm, the objective function will calculate the pros and cons of the current process block layout in each iteration, find the minimum objective function value, and determine the optimal process block layout.

4. The method for constructing a dynamic simulation optimization model based on digital twins according to claim 3 is characterized in that: The specific process of using the K-nearest neighbor algorithm to predict the path characteristics of each process block and generate the key features of each process block that affect logistics path planning is as follows: Obtain logistics data and historical path data between process blocks, and construct feature vectors and label data; Use the K nearest neighbor algorithm to calculate the path characteristics based on the feature vector, select the K value and distance metric, and make a weighted average prediction of the path characteristics of the query point to generate the key features that affect the logistics path planning for each process block; The key features that affect logistics route planning include transportation time, transportation cost, route capacity, and delay risk.

5. The method for constructing a dynamic simulation optimization model based on digital twins according to claim 4 is characterized in that: The graph model is constructed in combination with the Dijkstra algorithm, and the key features that affect logistics path planning are converted into edge weights of the graph. The specific process of obtaining the optimal path between each process block layout is as follows: The graph model is constructed by combining the Dijkstra algorithm, and the key features affecting logistics path planning predicted by the K-nearest neighbor algorithm are converted into edge weights in the graph model. The comprehensive weight of each edge is calculated and weighted, and the Dijkstra algorithm is used to perform the shortest path calculation on the graph model. The distance of each node is initialized to infinity, and the distance of the starting node is set to zero. The shortest path distance is updated iteratively, and the node with the smallest distance among the currently unprocessed nodes is selected for update until the shortest path of all nodes is determined.

6. The method for constructing a dynamic simulation optimization model based on digital twins according to claim 5, characterized in that: The specific process of obtaining the process block layout optimization index and logistics track path planning index is as follows: By testing the electronic product production line optimization layout model in different logistics demand scenarios, the operation time, conflict occurrence rate and space utilization rate of each process block are obtained, and compared with the set optimization thresholds to obtain the process block layout optimization index; The transportation time, transportation cost and delay risk rate of each process block are obtained, and compared with the set optimization thresholds to obtain the logistics track path planning index.

7. The method for constructing a dynamic simulation optimization model based on digital twins according to claim 6, characterized in that: Based on the test history data, the specific process of evaluating the optimization degree of the dynamic simulation model is as follows: Based on the process block layout optimization index and the logistics track path planning index, comprehensive calculations are performed with the historical process block layout optimization index and the historical logistics track path planning index to obtain the optimization index of the dynamic simulation model; The optimization index of the dynamic simulation model is compared with a set optimization index threshold of the dynamic simulation model to evaluate the optimization degree of the dynamic simulation model.

Images