A simulation optimization method for digital twin factories

Abstract

The present invention discloses a simulation optimization method for a digital twin factory, comprising: obtaining workshop equipment data and storing it in categories; generating task priorities and resource allocation rules based on basic equipment operation data; using 3D modeling tools to build a three-dimensional space model, and creating a digital twin simulation factory model in combination with real-time production data; constructing a dynamic programming state space and decision variables to determine the resource usage time, resource allocation location, and specific quantity of each task; evaluating the risk value of the task node based on the resource allocation plan and task chain dependency, combined with historical equipment failure data; and evaluating the task execution sequence and adjusting resource allocation and task time scheduling based on the impact range report of the production failure chain. The present invention significantly enhances the stability and adaptability of the factory system by reducing the impact of failures on production plans and resource waste, and improves the reliability and refined management level of overall production.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing and industrial automation, and in particular to a simulation optimization method for a digital twin factory. Background Art

[0002] As the manufacturing industry accelerates its transformation toward digitalization and intelligence, traditional factory task scheduling and resource management methods are increasingly exposed as inadequate for modern, complex production environments. To improve factory adaptability and production efficiency in dynamic environments, the application of digital simulation technology has become crucial. However, the construction of digital simulation factories and the optimization of task scheduling still face numerous technical challenges. Existing task scheduling systems are mostly based on task allocation rules for single processes or local equipment, failing to fully understand the entire factory production environment. For example, traditional scheduling systems are unable to effectively integrate physical information within the factory, such as building structure, equipment layout, and logistics routes. This results in a lack of a global spatial perspective for scheduling optimization. In this context, building digital simulation factories has become an effective approach to addressing this issue. However, many factories currently lack the technical means to transition from physical factories to digital twins, making it difficult to achieve global simulation and optimization of production tasks. Task chains in modern manufacturing environments often have complex dependencies, including time, resource, and data dependencies. Traditional task scheduling methods struggle to fully account for these multi-dimensional dependencies. For example, when a critical piece of equipment fails, its impact can be transmitted through the task chain to downstream tasks, significantly reducing production efficiency. However, current scheduling systems lack the ability to digitally model these complex dependencies and are unable to accurately simulate the operating logic and fault propagation of task chains. At the same time, equipment failure is a common problem in factory production. Its impact is not limited to a single device, but also propagates along the task chain, causing multiple task nodes to be affected. Traditional scheduling systems are usually unable to predict the cascading effects of failures on task chains, and it is also difficult to quantify the risk value of task nodes and the cumulative risk of equipment. Therefore, how to use digital twin factories to achieve global monitoring and dynamic scheduling of complex production tasks, optimize resource allocation based on task chain dependencies, and accurately assess the impact range of fault propagation risks and the risk value of task nodes are still important issues that need to be deeply studied and resolved in the current technical field. Summary of the Invention

[0003] To address the problems in the prior art, the present invention provides a simulation optimization method for a digital twin factory, which mainly includes:

[0004] The industrial IoT sensors in the factory workshop acquire workshop equipment data, and timestamp and categorize the production task completion time and resource consumption.

[0005] Based on the basic equipment operation data, frequent item sets are extracted and a table of key production process nodes is generated. Combined with the equipment operation parameters and resource consumption patterns, task priorities and resource allocation rules are determined, and a task allocation parameter table containing task priorities and resource allocation rules is generated.

[0006] Obtain physical factory architectural drawings, equipment layouts, and logistics route maps, use 3D modeling tools to build a three-dimensional space model, and combine it with real-time production data to create a digital twin simulation factory model;

[0007] Based on the production task data in the digital twin simulation factory model and combined with task priority rules, the task priority list and resource demand information are obtained, and the dynamic programming state space and decision variables are constructed to determine the resource usage time, resource allocation location, and specific quantity for each task;

[0008] Based on the resource allocation plan and task chain dependencies, we extract the dependencies and resource allocation information of task nodes, build a Bayesian network that includes the dependencies between tasks and equipment, simulate the scope of fault propagation, and evaluate the risk value of task nodes based on historical equipment failure data.

[0009] Based on the impact scope report of the production failure chain, extract the priority, resource requirements and completion time of the affected tasks, re-evaluate the task execution sequence and adjust resource allocation and task schedule.

[0010] Furthermore, the method of acquiring workshop equipment data through industrial Internet of Things sensors in the factory workshop, timestamping and categorizing the production task completion time and resource consumption includes:

[0011] By installing industrial Internet of Things sensors on production equipment, logistics routes, quality inspection areas and resource consumption monitoring points in the factory workshop, the equipment's location information, cargo parameters, rack parameters, equipment operating status, material logistics routes, resource consumption, production task completion time and quality inspection data are collected in real time. The collected raw data is timestamped and stored in categories to construct a workshop equipment data set. Cargo parameters include volume and weight, rack parameters include volume and maximum load-bearing capacity, equipment operating status includes speed, temperature, and vibration, resource consumption includes electricity and raw materials, and quality inspection data includes product qualification rate and defect rate. The basic operating data and process flow parameters of the equipment are obtained through the storage database, and the basic operating data are normalized to obtain the basic equipment operating data table. The basic operating data includes equipment model, operating frequency, energy consumption rate, and maintenance records. The process flow parameters include the processing time of each task, material usage and process temperature and pressure. The material status data includes the inventory quantity, processing status and location distribution of the material.

[0012] Furthermore, based on the basic equipment operation data, frequent item sets are extracted and a key production process node table is generated. In combination with the equipment operation parameters and resource consumption patterns, task priorities and resource allocation rules are determined, and a task allocation parameter table containing task priorities and resource allocation rules is generated, including:

[0013] Based on the basic equipment operation data table, support and confidence thresholds are set, and the Apriori algorithm is used to decompose the basic equipment operation data into frequent item sets. The mining results are sorted, and according to the priority of support and confidence, a key production process node table is obtained, including the equipment's interaction location, logistics nodes and key production processes; according to the equipment operation parameters, including operation frequency, usage time, energy consumption and maintenance cycle, the K-Means clustering algorithm is used to calculate the similarity between devices based on Euclidean distance, and the equipment is clustered and grouped; based on the clustering results, the resource consumption of each group of equipment is determined, and the task load of the equipment is calculated through the equipment usage time and task distribution data to determine the equipment usage pattern; based on the task completion time and task importance data, the task priority score is calculated using the weighted scoring method to generate a task priority table. Combined with the resource consumption pattern, the resource allocation rules required for each task are determined, including resource allocation time, quantity and location, and a task allocation parameter table containing task priority and resource allocation rules is generated.

[0014] Furthermore, obtaining physical factory architectural drawings, equipment layout diagrams, and logistics route maps, using 3D modeling tools to construct a three-dimensional space model, and combining real-time production data to create a digital twin simulation factory model includes:

[0015] Obtain the architectural drawings, equipment layout diagrams, and logistics route maps of the physical factory, and use the 3D modeling tool Unity to build a three-dimensional spatial model of the factory, including the workshop structure, equipment distribution, product library, raw material library, and logistics channels; embed the floor space, work area, and connection locations of all equipment, including power connections, data interfaces, and material entry and exit points into the model to generate a geometric model of each device; collect real-time production data from the production line, input it into Simulink, and connect it to the three-dimensional spatial model to simulate the execution status of production tasks and display the operating status of each device in real time. Real-time production data includes equipment status, production task progress, and equipment The interaction between them, the equipment status includes whether it is on or off, operating speed, and energy consumption; the production task progress includes task start time, task completion time, and processing progress; the digital twin platform GEPredix is ​​used to combine the three-dimensional space model with the real-time data access interface to create a digital twin simulation factory model; using real-time production data, a dynamic process simulation model is constructed to simulate the execution process of production tasks in the factory, set production environment parameters, and calculate task scheduling and resource allocation in real time through simulation to obtain dynamic process simulation results including task completion time and equipment utilization. Production environment parameters include equipment failure, production task priority, and resource constraints.

[0016] Furthermore, based on the production task data in the digital twin simulation factory model, combined with the task priority rules, the task priority list and resource requirement information are obtained, the dynamic programming state space and decision variables are constructed, and the resource usage time, resource allocation location and specific quantity of each task are determined, including:

[0017] The production task data in the digital twin simulation factory model is used to extract the completion time, required resource type, and quantity of each task. Priority rules are defined based on the characteristics of the tasks, with tasks with shorter completion times or higher resource requirements being given higher priority. Based on the execution requirements of the tasks, the resource requirement information of each task is obtained and arranged in order of priority to obtain a task priority list. The resource requirement information includes equipment, workstations, and raw materials. Based on the task priority list, the state space and decision variables of the dynamic programming model are determined. The state space includes the resource allocation at each moment, and the decision variables are the resource allocation decisions for the task. Scheduling efficiency is evaluated by calculating the resource usage time, total resource consumption, and task completion time of each task. Resource scheduling efficiency is set as the objective function. Based on the dynamic programming model, a bottom-up dynamic programming method is used to gradually deduce the task from its initial state to its final state. The optimal resource configuration at each moment is calculated. The resource usage efficiency of each task at different time points is evaluated during the calculation process to determine whether the resource constraints are met. The resource allocation plan for each task is then determined, including the resource usage time, location, and quantity of each task.

[0018] Furthermore, according to the resource allocation scheme and task chain dependencies, the dependencies and resource allocation information of task nodes are extracted, a Bayesian network containing the dependencies between tasks and equipment is constructed, the scope of fault propagation impact is simulated, and the risk value of task nodes is evaluated in combination with historical equipment failure data, including:

[0019] According to the resource allocation plan, obtain each task node, resource allocation location, time and equipment information, and identify the sequential dependency between tasks; based on each task node in the task chain and its dependency, construct a Bayesian network structure, set the task node as a random variable, and the state of each device as its parent node, to obtain the structure of the Bayesian network, in which the node represents the task and the device, and the edge represents the dependency between the task and the device; obtain historical equipment failure data, task completion time and equipment failure records, and use the maximum likelihood estimation method to set a conditional probability table for each node to represent the conditional probability of equipment failure or task failure; for each node in the task chain, obtain the probability of the task being affected, and incorporate it into the calculation of the Bayesian network to determine the conditional probability of each task and device status. The affected tasks include task completion delay and task failure; if a device or task node fails, use Bayesian to The network performs forward propagation to simulate the process of fault expansion from the node to the dependent nodes; the probability of subsequent task delay or failure caused by a single fault is calculated for each task node, and the degree of impact of each subsequent task node is obtained; the impact of fault propagation in the task chain is calculated through the Bayesian network, the fault propagation probability of each task node is obtained, and the impact range of the fault propagating from the initial node to the task chain is determined; according to the fault propagation probability of each task node, the cumulative probability of each task node in the task chain being affected by equipment failure is evaluated, and the risk value of each task node and the cumulative risk value of shared equipment are obtained. All task nodes in the task chain are ranked by risk value to determine the task node most seriously affected by fault propagation; based on the fault propagation analysis results, the risk value of the task node, the cumulative risk value of the shared equipment and the impact range of the fault propagation are integrated to generate an impact range report for the production fault chain.

[0020] It also includes evaluating the cumulative probability of each task node in the task chain being affected by device failure based on the fault propagation probability of each task node, and obtaining the risk value of each task node and the cumulative risk value of the shared device, specifically including:

[0021] Obtain historical dependency data between tasks, including resource sharing, time delay, and data interaction. Use recurrent neural networks for model training, build a task dependency weight prediction model, and predict the task dependency weights between nodes. Obtain the dependency relationship and initial failure probability P0 of each task node in the task chain, and use the failure propagation impact formula of the task node. Calculate the fault propagation probability P of node i at time t+1 i (t+1), where α is the node's own fault self-recovery attenuation factor, β is the fault propagation amplification factor, which indicates the degree of impact of external faults on the node, obtained by fitting historical data, N(i) represents the set of all upstream dependent tasks of node i, and γ ijis the task dependency weight between nodes i and j, indicating the impact strength of task j on i. For each node in the task chain, starting from time t = 0, the fault propagation influence formula is used for multiple iterations to calculate the fault propagation probability P of the node. i (t), record the fault propagation increment ΔP of the node in each iteration i (t) = P i (t+1)-P i (t), and judge whether a stable state is reached based on the preset increment threshold; if Then stop the iteration and obtain the final fault propagation probability of each node in the stable state, where ε is the iterative convergence threshold; according to the weighted value of the fault propagation probability and the importance of the equipment, use the task node risk value evaluation formula R i =P i (final) W i , calculate the risk value of the device shared node in the task chain, where W i is the contribution weight of node i to the production chain, indicating the importance of the task to the overall production chain. It can be calculated by the historical task completion rate or resource consumption ratio. i (final) represents the final fault propagation probability of the task being affected by device failure or other task failure after the task node i reaches a stable state in the fault propagation model; for the node set G(e) sharing the device, the cumulative value of the device risk is calculated Determine the risk value R of each node i and the cumulative risk value R of shared devices e .

[0022] Furthermore, the report on the scope of impact of the production failure chain extracts the priority, resource requirements, and completion time of the affected tasks, re-evaluates the task execution sequence, and adjusts resource allocation and task schedule, including:

[0023] Based on the impact range report of the production fault chain, the priority, resource requirements and completion time of each affected task are extracted. Based on the task priority and resource requirements, the task execution order is re-evaluated to obtain the task execution sequence table; based on the re-determined task execution order, the task execution order is optimized using a genetic algorithm, and the optimization objective function is set to minimize the fault recovery time, maximize resource utilization and minimize the task completion time. The tasks are dynamically adjusted and rearranged to obtain the optimized production task execution sequence table, including the task re-execution order, resource allocation and task completion time; the optimized task execution sequence table is input into a multi-task dynamic scheduling simulation environment to simulate the environment of multi-task concurrent execution, evaluate resource competition, equipment usage and scheduling conflicts during task execution, and verify the effectiveness of the optimized task execution sequence table based on task completion time, resource utilization and equipment idle time; if the effectiveness is lower than expected, the task execution order is adjusted again until the execution time, resource allocation and priority of all task nodes are met.

[0024] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0025] The present invention provides a simulation optimization method for a digital twin factory. The present invention collects real-time data through industrial Internet of Things sensors, and combines factory building drawings, equipment layout diagrams and logistics route maps to generate a three-dimensional digital twin model, thereby realizing accurate visualization of the factory production environment and providing comprehensive global view support for scheduling optimization. Through frequent item set mining and task priority rules, task priorities can be dynamically adjusted, and resource allocation can be optimized in combination with a dynamic programming model, significantly improving resource utilization efficiency and the rationality of task scheduling. The present invention can also accurately evaluate the risk value of task nodes and the cumulative risk of equipment by analyzing the dependencies and resource allocation status in the task chain, effectively predict the cascading impact of equipment failures on the task chain, thereby realizing quantitative analysis of the impact of task chain failure propagation, and providing support for scheduling optimization and risk avoidance. The present invention can flexibly adjust the task execution sequence and resource allocation scheme in a dynamic production environment, optimize production plans, reduce equipment idleness and resource conflicts, and improve production efficiency. This invention comprehensively uses digital twins, industrial Internet of Things and risk assessment technologies to significantly improve the accuracy and flexibility of task scheduling, enhance the adaptability and production efficiency of the production system, improve the overall production reliability and refined management level, and provide strong guarantees for the efficient operation of modern smart factories. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a flow chart of a simulation optimization method for a digital twin factory of the present invention;

[0027] Figure 2This is a schematic diagram of a simulation optimization method for a digital twin factory of the present invention. DETAILED DESCRIPTION

[0028] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0029] like Figure 1-2 In this embodiment, a simulation optimization method for a digital twin factory may specifically include:

[0030] Step S101: obtain workshop equipment data through industrial Internet of Things sensors in the factory workshop, and timestamp and classify the production task completion time and resource consumption.

[0031] Industrial IoT sensors installed on production equipment, logistics routes, quality inspection areas, and resource consumption monitoring points within the factory floor collect real-time information on equipment location, cargo parameters, rack parameters, equipment operating status, material logistics routes, resource consumption, production task completion time, and quality inspection data. The collected raw data is timestamped and stored in categories to construct a workshop equipment dataset. Cargo parameters include volume and weight, rack parameters include volume and maximum load capacity, equipment operating status includes speed, temperature, and vibration, resource consumption includes electricity and raw materials, and quality inspection data includes product qualification rate and defect rate. Basic equipment operating data and process flow parameters are obtained from a storage database and normalized to produce a basic equipment operating data table. Basic operating data includes equipment model, operating frequency, energy consumption rate, and maintenance records. Process flow parameters include processing time for each task, material usage, and process temperature and pressure. Material status data includes material inventory, processing status, and location distribution.

[0032] For example, in a factory workshop, industrial IoT sensors are installed to collect real-time equipment and production-related data. For example, at machining center A, the equipment's location is recorded as Workshop 1, Area B. The equipment's operating status includes a speed of 1200 rpm, a temperature of 75 degrees Celsius, and a vibration amplitude of 0.02 mm. Simultaneously, logistics route sensors indicate that the equipment is processing product numbered P001. The material logistics route shows that the material departs from warehouse W1, passes through logistics nodes L2 and L3, and finally arrives at machining center A. After processing, it is sent to quality inspection area C2. Resource consumption monitoring points record that the equipment consumed 2.5 kilowatt-hours of electricity and 1.2 kilograms of raw materials during processing. Sensors in the quality inspection area indicate that the qualified rate for this batch of product P001 is 95% and the defect rate is 5%. Furthermore, cargo parameters and rack parameters are collected for the transported goods. The cargo parameters include a volume of 0.5 cubic meters and a weight of 80 kilograms, while the rack parameters include a volume of 1 cubic meter and a maximum load capacity of 100 kilograms. On this basis, all collected data is timestamped, such as processing start time (2020-10-16-10:15:00) and completion time (2020-10-16-10:35:00), and categorized and stored in the workshop equipment dataset. Basic equipment operating data is obtained from the storage database, revealing that machining center A is an MCX-500 model, operating at a 50 Hz frequency, with an energy consumption rate of 1.8 kWh / h, and its most recent maintenance record is 2020-07-15. Normalized to the maximum standard of 2.5 kWh / h, the energy consumption rate in the basic operating data table is normalized to 0.72. Process flow parameters indicate that task P001 has a processing time of 20 minutes, material usage of 1.2 kg, a processing temperature of 75°C, and a pressure of 50 MPa. The material status data further shows that the current inventory is 500 pieces, of which 50 are in processing and 450 are in warehouse W1. The location distribution shows that the number of materials on the logistics route is 10.

[0033] Step S102: Based on the basic equipment operation data, frequent item sets are extracted and a key production process node table is generated. The task priority and resource allocation rules are determined in combination with the equipment operation parameters and resource consumption patterns, and a task allocation parameter table containing the task priority and resource allocation rules is generated.

[0034] Based on the basic equipment operation data table, support and confidence thresholds were set. The Apriori algorithm was used to decompose the basic equipment operation data into frequent item sets. The mining results were sorted and prioritized based on support and confidence. A table of key production process nodes was generated, including equipment interaction locations, logistics nodes, and key production steps. Based on equipment operating parameters, including operating frequency, usage time, energy consumption, and maintenance cycle, the K-Means clustering algorithm was used to calculate the similarity between devices based on Euclidean distance, and the devices were clustered and grouped. Based on the clustering results, the resource consumption of each group of devices was determined. The task load of the devices was calculated based on device usage time and task distribution data to determine the device usage patterns. Based on task completion time and task importance data, a weighted scoring method was used to calculate task priority scores. This generated a task priority table. Combined with resource consumption patterns, the resource allocation rules required for each task were determined, including resource allocation time, quantity, and location. A task allocation parameter table containing task priorities and resource allocation rules was then generated.

[0035] For example, based on a table of basic equipment operation data, with a support threshold of 40% and a confidence threshold of 65%, the Apriori algorithm was used to analyze the basic operation data. The resulting frequent item set contained the combination of equipment model ZX-750, operating frequency of 60 Hz, and energy consumption of 2.2 kWh / h, with a support of 45% and a confidence of 70%. After sorting, based on the support and confidence priorities, a table of key production process nodes was obtained. The primary interaction location for equipment ZX-750 was area D, the key logistics nodes were M3-M4, and the key production process was steel stamping task R101. Next, the K-Means clustering algorithm was used to group the equipment based on their operating parameters, including operating frequency, usage time, energy consumption, and maintenance cycle. Similarity was measured using Euclidean distance, resulting in a cluster of the ZX-750 and another equipment, DF-450. This group of equipment had an average operating frequency of 55 Hz, an average energy consumption of 2.3 kWh / h, and a maintenance cycle of 50 days. Another group of equipment, including the LK-200 and TY-310, had an average operating frequency of 35 Hz, an energy consumption rate of 1.6 kWh / hour, and a maintenance cycle of 80 days. Clustering results allowed further calculation of equipment resource consumption, revealing a total energy consumption of 450 kWh / day and a total usage time of 90 hours / day for the ZX-750 group. Task distribution data revealed that each device in this group undertook an average of 12 tasks per day, with the ZX-750 carrying 18 tasks, resulting in an extremely high load and intermittent, high-intensity operation. Task priority was calculated using a weighted scoring method based on task completion time and task importance. For example, stamping task R101 had a completion time of 25 minutes, an importance weight of 0.9, and a calculated priority score of 22.5. Welding task R102 had a completion time of 15 minutes, an importance weight of 0.7, and a priority score of 10.5. The generated task priority table indicated that R101 took precedence over R102. Based on the resource consumption pattern, the resource allocation rules for task R101 are: ZX-750 equipment, operating hours 09:00-11:30, raw material location warehouse Q2, and resource quantity 20. The resource allocation rules for task R102 are: DF-450 equipment, operating hours 13:00-14:00, raw material location warehouse Q3, and resource quantity 12. The resulting task allocation parameter table contains the priorities and resource allocation rules for tasks R101 and R102, which guide task scheduling and resource allocation.

[0036] Step S103: Obtain physical factory building drawings, equipment layout drawings, and logistics route maps, use 3D modeling tools to build a three-dimensional space model, and create a digital twin simulation factory model in combination with real-time production data.

[0037] Obtain architectural drawings, equipment layouts, and logistics route maps for the physical factory, and use the 3D modeling tool Unity to build a three-dimensional spatial model of the factory, including the workshop structure, equipment distribution, product library, raw material library, and logistics channels. The floor space, work area, and connection locations of all equipment, including power connections, data interfaces, and material entry and exit points, are embedded into the model to generate a geometric model of each device. Real-time production data is collected from the production line and input into Simulink for docking with the three-dimensional spatial model. The execution status of production tasks is simulated, and the operating status of each device is displayed in real time. Real-time production data includes equipment status, production task progress, and interactions between equipment. Equipment status includes whether it is on or off, operating speed, and energy consumption. Production task progress includes task start time, task completion time, and processing progress. Use the digital twin platform GEPredix to combine the three-dimensional spatial model with the real-time data access interface to create a digital twin simulation factory model. Using real-time production data, a dynamic process simulation model is constructed to simulate the execution process of production tasks in the factory, set production environment parameters, and calculate task scheduling and resource allocation in real time through simulation. The dynamic process simulation results include task completion time and equipment utilization. The production environment parameters include equipment failure, production task priority, and resource constraints.

[0038] For example, a 3D spatial model was constructed using the 3D modeling tool Unity, capturing architectural drawings, equipment layout diagrams, and logistics routes. The factory consists of two main workshops: Workshop 1, measuring 50 meters by 30 meters and 10 meters high, and Workshop 2, measuring 40 meters by 20 meters and 8 meters high. The equipment layout diagram shows that Workshop 1 has 10 pieces of equipment, including a ZX-750 stamping press. It occupies a 4-square-meter floor area and a 6-square-meter work area. Material access points are located on the north side of the machine, power connections are located on the east side, and data interfaces are located on the west side. Workshop 2, on the other hand, has 8 pieces of equipment, including a DF-450 welding machine. It occupies a 3-square-meter floor area and a 5-square-meter work area. Material access points are located on the south side, power connections are located on the west side, and data interfaces are located on the north side. Special areas for product storage and raw material storage are also designated for storing finished products and raw materials, respectively. The product warehouse, located in the northeast corner of Workshop 1, covers an area of ​​20 square meters, while the raw material warehouse, located in the southwest corner of Workshop 2, covers an area of ​​15 square meters. By embedding this information into the 3D spatial model, a geometric model of each piece of equipment was generated, accurately representing its footprint and workspace. Real-time production data was collected from the production line and imported into Simulink, where it was integrated with the 3D spatial model to simulate the execution of production tasks and display the equipment's operating status in real time. Real-time data shows that the ZX-750 stamping machine is currently operating at a speed of 1200 cycles per hour and consuming 2.5 kWh. The DF-450 welding machine is currently in standby mode, consuming 0.5 kWh. Furthermore, the real-time progress of production task P301 shows its start time as 2025-10-16 09:00:00, a current processing progress of 75%, and an estimated completion time of 2020-10-16 09:30:00. Upon completion, task P301 will be automatically transferred to the DF-450 welding machine. Using the digital twin platform GEPredix, a three-dimensional spatial model was combined with a real-time data access interface to create a digital twin factory simulation model. This model displays the operating status of all equipment in the workshop, the progress of production tasks, and the interactions between equipment in real time. Based on real-time production data, a dynamic process simulation model was constructed to simulate the execution of tasks in the factory. For example, production parameters were set in the simulation environment, including a failure probability of 0.02% for the ZX-750 punch press, a priority task weight of 1.5 for the DF-450 welder, and a resource limit of only 50 pieces of available raw materials. Simulation calculations determined that the actual completion time for task P301 was 2020-10-16 09:35:00, and the completion time for task P302 was 2020-10-16 10:00:00. The dynamic process simulation results also showed a utilization rate of 90% for the ZX-750 punch press and 60% for the DF-450 welder.After building the digital twin simulation factory model, users can independently adjust various parameters of the model, including but not limited to process sequence, equipment configuration, task priority, resource allocation, etc.

[0039] In step S104, based on the production task data in the digital twin simulation factory model and combined with the task priority rules, the task priority list and resource demand information are obtained, the dynamic programming state space and decision variables are constructed, and the resource usage time, resource allocation location and specific quantity of each task are determined.

[0040] Using production task data from the digital twin factory simulation model, the completion time, required resource type, and quantity of each task are extracted. Priority rules are defined based on task characteristics, with tasks with shorter completion times or higher resource requirements being given higher priority. Based on the task execution requirements, resource requirement information for each task is obtained and ranked in order of priority to create a task priority list. Resource requirement information includes equipment, workstations, and raw materials. Based on the task priority list, the state space and decision variables of the dynamic programming model are determined. The state space includes the resource allocation at each moment, and the decision variables represent the resource allocation decisions for each task. Scheduling efficiency is evaluated by calculating the resource usage time, total resource consumption, and task completion time of each task. Resource scheduling efficiency is set as the objective function. Based on the dynamic programming model, a bottom-up dynamic programming approach is used to progressively deduce the task from its initial state to its final state. The optimal resource allocation at each moment is calculated. The resource usage efficiency of each task at different time points is evaluated during the calculation process to determine whether resource constraints are met. A resource allocation plan for each task is then determined, including the resource usage time, location, and quantity for each task.

[0041] For example, in a digital twin simulation factory, production task data was extracted. Task Q1 has a completion time of 3 hours and requires resources including one XT-800 stamping machine, three workstations, and eight steel sheets. Task Q2 has a completion time of 2 hours and requires resources including one RW-450 welding machine, one workstation, and 12 welding rods. Task Q3 has a completion time of 4 hours and requires resources including one CT-200 cutting machine, two workstations, and five aluminum sheets. Priority rules are defined based on the characteristics of the tasks, whereby tasks with shorter completion times or higher resource requirements are given higher priority. Based on calculations, Task Q2 has the highest priority due to its short completion time and moderate resource requirements, followed by Task Q1, which has a higher resource requirement, and finally Task Q3. Based on these rules, a task priority list is generated: Task Q2 > Task Q1 > Task Q3. Based on the task priority list, the state space and decision variables of the dynamic programming model are constructed. The state space includes the resource allocation status at each moment, and the decision variables are the resource allocation decisions at each moment. For example, task Q2 is prioritized to the RW-450 welding machine, workstation X1, and 12 welding rods, and is scheduled to be completed within 1-2 hours. Task Q1 is then assigned the XT-800 punching machine, workstation X3, and 8 steel plates, and is scheduled to be completed within 2-5 hours. Task Q3 is finally assigned the CT-200 cutting machine, workstation X2, and 5 aluminum plates, and is scheduled to be completed within 5-9 hours. To evaluate scheduling efficiency, resource scheduling efficiency is set as the objective function, aiming to minimize the ratio of total resource consumption to task completion time, where resource scheduling efficiency = total resource consumption during total task completion time / total task completion time. Using a bottom-up dynamic programming model, we progressively deduced the resource allocation at each moment, starting from the initial state at hour 0 and continuing to the final state at hour 9. We then evaluated the resource utilization efficiency of each task at different time points. The efficiency of task Q2 was 2 hours / 12 welding rods = 0.1667, the efficiency of task Q1 was 3 hours / 8 steel plates = 0.375, and the efficiency of task Q3 was 4 hours / 5 aluminum plates = 0.8. Therefore, the resulting resource allocation plan is: Task Q2's resource utilization is from hour 1 to hour 2, located at workstation X1, using an RW-450 welding machine and 12 welding rods; Task Q1's resource utilization is from hour 2 to hour 5, located at workstation X3, using an XT-800 punch press and 8 steel plates; and Task Q3's resource utilization is from hour 5 to hour 9, located at workstation X2, using a CT-200 cutting machine and 5 aluminum plates.

[0042] In step S105, based on the resource allocation plan and task chain dependencies, the dependencies and resource allocation information of the task nodes are extracted, a Bayesian network including the task and equipment dependencies is constructed, the impact range of fault propagation is simulated, and the risk value of the task node is evaluated in combination with historical equipment failure data.

[0043] Based on the resource allocation plan, information about each task node, resource allocation location, time, and equipment is obtained, and the sequential dependencies between tasks are identified. A Bayesian network structure is constructed based on each task node in the task chain and its dependencies. Task nodes are set as random variables, and the status of each device is its parent node. This results in a Bayesian network structure where nodes represent tasks and devices, and edges represent the dependencies between tasks and devices. Historical equipment failure data, task completion times, and equipment failure records are obtained. A conditional probability table is constructed for each node using maximum likelihood estimation, representing the conditional probability of equipment failure or task failure. For each node in the task chain, the probability of the affected task is obtained and incorporated into the Bayesian network calculations to determine the conditional probability of each task and device status. Impacted tasks include delayed completion and task failure. If a device or task node fails, forward propagation is performed using the Bayesian network to simulate the propagation of the failure from that node to dependent nodes. For each task node, the probability of subsequent task delays or failures caused by a single failure is calculated to determine the degree of impact on each subsequent task node. Using a Bayesian network, the impact of fault propagation in the task chain is calculated, determining the fault propagation probability for each task node and the scope of the fault's impact from the initial node to the rest of the task chain. Based on the fault propagation probability for each task node, the cumulative probability of each task node in the task chain being affected by equipment failure is assessed, resulting in a risk value for each task node and the cumulative risk value for shared equipment. All task nodes in the task chain are ranked by risk value to identify the task nodes most severely impacted by fault propagation. Based on the fault propagation analysis results, the risk values ​​of task nodes, the cumulative risk values ​​of shared equipment, and the scope of fault propagation are integrated to generate a production fault chain impact report.

[0044] For example, in a factory's production process, according to the resource allocation plan, the resource allocation location, time, and equipment information of each task node are obtained. Task T1 is assigned to equipment ZX-800 in Workshop A, with a time period of 9:00-10:30 and a location of B1. Task T2 is assigned to equipment DF-300 in Workshop B, with a time period of 10:30-12:00 and a location of C2. Task T3 is assigned to equipment RT-200 in Workshop C, with a time period of 12:00-13:30 and a location of D3. The sequential dependency between tasks is that T1 must complete before T2 can start, and T2 must complete before T3 can start. Based on these task nodes and their dependencies, a Bayesian network structure was constructed. Task nodes T1, T2, and T3 are random variables, and the equipment ZX-800, DF-300, and RT-200 are their parent nodes. Edges represent dependencies between tasks and equipment. For example, task T1 directly depends on the operating status of equipment ZX-800, and task T2 depends on the status of DF-300. Historical factory data was used to obtain equipment failure records and task completion times. For example, historical data for equipment ZX-800 shows an average failure probability of 5%, while historical data for task T1 shows an 80% probability of task failure and a 50% probability of delay when equipment fails. A conditional probability table was constructed for each node using maximum likelihood estimation. The resulting conditional probability table for task T1 is: if equipment ZX-800 is operating normally, the probability of successful completion of task T1 is 95%, and if it fails, the probability of failure is 80%. Similarly, the conditional probabilities for tasks T2 and T3 are generated based on the historical data for DF-300 and RT-200, respectively. Using a Bayesian network, the probability of each task being affected by a device failure is calculated for each node in the task chain. If device ZX-800 fails at 9:30, the Bayesian network performs forward propagation, simulating the failure's spread from ZX-800 to T1. The calculated probability of failure for task T1 is 80%, and the probability of delay is 50%. Because the delay of T1 directly affects the startup time of T2, the probability of delay for T2 is calculated to be 40%, and the probability of failure for T2 is calculated to be 30%. Similarly, this effect propagates through T2 to T3, resulting in a calculated probability of delay of 20% and a probability of failure of 10%. By calculating the impact of fault propagation, the fault propagation probability for each node in the task chain is determined. For example, the fault propagation probability for task T1 is 80%, for task T2 is 40%, and for task T3 is 20%. Based on these probabilities, the risk value for each task node is further calculated using the formula: risk value = fault propagation probability × task importance weight. If the importance weight of task T1 is 0.8, T2 is 0.6, and T3 is 0.5, then the risk value of T1 is 64%, T2 is 24%, and T3 is 10%.The cumulative risk value of the shared device ZX-800 was calculated by summing the risk values ​​of all task nodes that depend on it, resulting in a cumulative risk value of 64%. Based on the risk value ranking, task node T1 was identified as the most severely affected by fault propagation, followed by T2 and T3. Based on the fault propagation analysis results, the risk values ​​of the task nodes, the cumulative risk values ​​of the devices, and the impact range of the fault propagation were integrated to generate a production fault chain impact report. The report details the propagation path of the fault at 9:30 AM, from the ZX-800 to T1, and then to T2 and T3. The report also indicates the delay probability, failure probability, and risk value of each node.

[0045] Among them, according to the fault propagation probability of each task node, the cumulative probability of each task node in the task chain being affected by equipment failure is evaluated, and the risk value of each task node and the cumulative risk value of the shared equipment are obtained.

[0046] Obtain historical dependency data between tasks, including resource sharing, time delay, and data interaction, use recurrent neural network for model training, build a task dependency weight prediction model, and predict the task dependency weights between nodes. Obtain the dependency relationship and initial failure probability P0 of each task node in the task chain, and use the failure propagation impact formula of the task node Calculate the fault propagation probability P of node i at time t+1 i (t+1), where α is the node's own fault self-recovery attenuation factor, β is the fault propagation amplification factor, which indicates the degree of impact of external faults on the node, obtained by fitting historical data, N(i) represents the set of all upstream dependent tasks of node i, and γ ij is the task dependency weight between nodes i and j, indicating the impact of task j on i. For each node in the task chain, starting from time t = 0, the fault propagation impact formula is used for multiple iterations to calculate the node's fault propagation probability P i (t), record the fault propagation increment ΔP of the node in each iteration i (t) = P i (t+1)-P i (t), and judge whether it reaches a stable state based on the preset increment threshold. Then stop the iteration and obtain the final fault propagation probability of each node in the stable state, where ε is the iterative convergence threshold. According to the weighted value of the fault propagation probability and the importance of the equipment, the task node risk value evaluation formula R is used i =P i (final) W i , calculate the risk value of the device shared node in the task chain, where W iis the contribution weight of node i to the production chain, indicating the importance of the task to the overall production chain. It can be calculated by the historical task completion rate or resource consumption ratio. i (final) represents the final fault propagation probability of the task node i after it reaches a stable state in the fault propagation model, when the task is affected by the device failure or other task failure. For the node set G(e) sharing the device, the cumulative value of the device risk is calculated. Determine the risk value R of each node i and the cumulative risk value R of shared devices e .

[0047] For example, in a production task chain at a certain factory, tasks T1, T2, and T3 are dependent on each other. Task T1 is the initial task, and upon completion, it triggers task T2, which in turn triggers task T3. Task T1 depends on device A, while tasks T2 and T3 share device B. Historical dependency data between tasks is obtained, including resource sharing status, time delay, and data interaction. The resource sharing status is that tasks T1 and T2 use device A, with T1 occupying 40% of device A's running time and T2 occupying 60% of device A's running time. Tasks T2 and T3 share device B, with T2's running time on device B accounting for 50% and T3's running time on device B accounting for 50%. Time delay means that the completion time of task T1 has a direct impact on the start time of T2. Historical data shows that if task T1 is delayed by 1 hour, task T2 is delayed by an average of 0.8 hours. Similarly, if task T2 is delayed by 1 hour, task T3 is delayed by an average of 0.6 hours. Data interaction means that the output data volume of task T1 is 70% of the total input data volume of task T2. The output data volume of task T2 is 80% of the total input data volume of task T3. Using a recurrent neural network, we built a task dependency weight prediction model and predicted that the dependency weight of task T2 on task T1 is 0.6, and the dependency weight of task T3 on task T2 is 0.8. Based on historical data, we obtained the initial failure probability of each task node, where the initial failure probability of task T1 is 10%, task T2 is 8%, and task T3 is 5%. Using the task node failure propagation impact formula Calculate the fault propagation probability P of node i at time t+1 i (t+1), where α is the node's own fault self-recovery attenuation factor, β is the fault propagation amplification factor, which indicates the degree of impact of external faults on the node, obtained by fitting historical data, N(i) represents the set of all upstream dependent tasks of node i, and γ ijis the task dependency weight between nodes i and j, indicating the influence of task j on i. If α = 0.9, β = 0.7, starting from time t = 0, multiple rounds of iterations are performed using the fault propagation influence formula to calculate the fault propagation probability of each task node. Then, in the first round of iteration, the fault propagation probability of task T2 is calculated based on the initial fault probability and dependency relationship: P2(1) = 0.108, P3(1) = 0.0866. Record the fault propagation increment ΔP of each iteration. i (t) = P i (t+1)-P i (t), the increment of task T2 is 0.028. The iteration continues until the fault propagation increment of each node is less than the preset convergence threshold ε = 0.01. In the fourth round of iteration, the fault propagation increment of all task nodes is lower than the threshold, the iteration is stopped, and the fault propagation probability in the stable state is obtained, which is 10% for task T1, 12% for task T2, and 9% for task T3. According to the fault propagation probability of the task node and the node importance weight, the risk value of each task node is calculated. If the contribution weights of tasks T1, T2, and T3 are 0.7, 0.6, and 0.5 respectively, then according to the task node risk value evaluation formula R i =P i (final) W i , we get the risk value of the task node is R1 = 0.07, R2 = 0.072, R3 = 0.045, for the node set {T2, T3} of the shared device B, using the formula Calculate the cumulative risk value of the equipment

[0048] R2 + R3 = 0.072 + 0.045 = 0.117. Therefore, we can derive the risk value of each node in the task chain and the cumulative risk value of the shared devices. Task T2 has the highest risk value, and device B has a cumulative risk value of 0.117, making it the device with the highest risk in the entire task chain.

[0049] Step S106 , based on the impact scope report of the production fault chain, extract the priority, resource requirements and completion time of the affected tasks, re-evaluate the task execution sequence and adjust resource allocation and task time scheduling.

[0050] Based on the impact report of the production fault chain, the priority, resource requirements, and completion time of each affected task are extracted. Based on the task priorities and resource requirements, the task execution order is re-evaluated to obtain a task execution sequence table. Based on the re-determined task execution order, a genetic algorithm is used to optimize the task execution order. The optimization objective functions are set as minimizing fault recovery time, maximizing resource utilization, and minimizing task completion time. Tasks are dynamically adjusted and rescheduled to obtain an optimized production task execution sequence table, including the re-execution order, resource allocation, and task completion time. The optimized task execution sequence table is input into a multi-task dynamic scheduling simulation environment to simulate the concurrent execution of multiple tasks. Resource contention, equipment usage, and scheduling conflicts during task execution are evaluated. The effectiveness of the optimized task execution sequence table is verified based on task completion time, resource utilization, and equipment idle time. If the effectiveness is lower than expected, the task execution order is adjusted again until the execution time, resource allocation, and priority of all task nodes are met.

[0051] For example, in a factory's production fault chain impact report, tasks V1, T2, T3, and T4 are affected by the failure of equipment A. Task V1 has a priority of 0.9, requires resources including workstation X1, equipment ZX-800, and five steel plates, and has an estimated completion time of two hours. Task V2 has a priority of 0.8, requires resources including workstation X2, equipment DF-500, and ten welding rods, and has an estimated completion time of three hours. Task V3 has a priority of 0.7, requires resources including workstation X3, equipment CT-300, and three aluminum plates, and has an estimated completion time of four hours. Task V4 has a priority of 0.6, requires resources including workstation X4, equipment RT-200, and two copper pipes, and has an estimated completion time of two hours. Based on the task priorities and resource requirements, the execution order of the tasks was re-evaluated. The results show that task V1 takes precedence over T2, which takes precedence over T3, which takes precedence over T4. The resulting preliminary task execution order is: T1 > T2 > T3 > T4. Based on the redefined task execution order, a genetic algorithm is used to optimize the order. The optimization objectives are minimizing fault recovery time, maximizing resource utilization, and minimizing task completion time. The initial population contains different task execution order combinations, such as [T1, T2, T3, T4] and [T2, T1, T4, T3]. Through crossover and mutation operations, new task orders are generated. The fault recovery time, resource utilization, and task completion time for each order are calculated. The optimal task execution sequence table obtained after optimization is [T1, T3, T2, T4], where task V1 is executed at workstation X1 and equipment ZX-800 from 8:00 to 10:00, task V3 is executed at workstation X3 and equipment CT-300 from 10:00 to 14:00, task V2 is executed at workstation X2 and equipment DF-500 from 14:00 to 17:00, and task V4 is executed at workstation X4 and equipment RT-200 from 17:00 to 19:00. The optimized task execution sequence table was input into a multi-task dynamic scheduling simulation environment to simulate concurrent multi-task execution and evaluate resource contention, device usage, and scheduling conflicts during task execution. The simulation results showed a resource utilization rate of 92%, with idle times for the ZX-800 and DF-500 devices of 0 and 1 hour, respectively. The actual completion times for tasks V1 and T3 were consistent with expectations, but task V2 was slightly delayed by 0.5 hours due to resource contention. Task V4 was completed on schedule. The simulation results demonstrate that the optimized task execution sequence table meets expected effectiveness, reducing fault recovery time by 15%, improving resource utilization by 12%, and reducing task completion time by 10%.If the simulation results do not meet the expected goals, the task execution sequence table is further adjusted. For example, in this optimization, if it is found that the delay of task V2 causes the start time of task V4 to be postponed, resource scheduling can be optimized by increasing the priority of T2 or changing its equipment allocation until the simulation results meet the completion time, resource allocation and priority requirements of all tasks, ultimately ensuring that the factory's production efficiency reaches the optimal level.

[0052] The above description is only a preferred embodiment of the present application and an illustration of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalents without departing from the concept of this application. The above exemplary features are replaced with (but not limited to) technical features with similar functions disclosed in this application to form a technical solution.

Claims

1. A simulation optimization method for a digital twin factory, characterized in that: The method comprises: The industrial IoT sensors in the factory workshop acquire workshop equipment data, and timestamp and categorize the production task completion time and resource consumption. Based on the basic equipment operation data, frequent item sets are extracted and a table of key production process nodes is generated. Combined with the equipment operation parameters and resource consumption patterns, task priorities and resource allocation rules are determined, and a task allocation parameter table containing task priorities and resource allocation rules is generated. Obtain physical factory architectural drawings, equipment layouts, and logistics route maps, use 3D modeling tools to build a three-dimensional space model, and combine it with real-time production data to create a digital twin simulation factory model; Based on the production task data in the digital twin simulation factory model and combined with task priority rules, the task priority list and resource demand information are obtained, and the dynamic programming state space and decision variables are constructed to determine the resource usage time, resource allocation location, and specific quantity for each task; Based on the resource allocation plan and task chain dependencies, we extract the dependencies and resource allocation information of task nodes, build a Bayesian network that includes the dependencies between tasks and equipment, simulate the scope of fault propagation, and evaluate the risk value of task nodes based on historical equipment failure data. Based on the impact report of the production failure chain, extract the priority, resource requirements and completion time of the affected tasks, re-evaluate the task execution sequence and adjust resource allocation and task schedule; The method extracts the dependency relationships and resource allocation information of task nodes based on the resource allocation plan and task chain dependencies, constructs a Bayesian network containing the dependency relationships between tasks and equipment, simulates the impact range of fault propagation, and evaluates the risk value of task nodes in combination with historical equipment failure data. The method is characterized by: According to the resource allocation plan, obtain each task node, resource allocation location, time and equipment information, and identify the sequential dependency between tasks; based on each task node in the task chain and its dependency, construct a Bayesian network structure, set the task node as a random variable, and the state of each device as its parent node, to obtain the structure of the Bayesian network, in which the node represents the task and the device, and the edge represents the dependency between the task and the device; obtain historical equipment failure data, task completion time and equipment failure records, and use the maximum likelihood estimation method to set a conditional probability table for each node to represent the conditional probability of equipment failure or task failure; for each node in the task chain, obtain the probability of the task being affected, and incorporate it into the calculation of the Bayesian network to determine the conditional probability of each task and device status. The affected tasks include task completion delay and task failure; if a device or task node fails, use Bayesian to The network performs forward propagation to simulate the process of fault expansion from the node to dependent nodes; the probability of subsequent task delays or failures caused by a single fault is calculated for each task node, and the degree of impact of each subsequent task node is obtained; the impact of fault propagation in the task chain is calculated through a Bayesian network, the fault propagation probability of each task node is obtained, and the impact range of the fault propagating from the initial node to the task chain is determined; based on the fault propagation probability of each task node, the cumulative probability of each task node in the task chain being affected by equipment failure is evaluated, and the risk value of each task node and the cumulative risk value of shared equipment are obtained. All task nodes in the task chain are ranked by risk value to determine the task node most seriously affected by fault propagation; based on the fault propagation analysis results, the risk value of the task node, the cumulative risk value of the shared equipment, and the impact range of the fault propagation are integrated to generate an impact range report for the production fault chain; The method of evaluating the cumulative probability of each task node in the task chain being affected by a device failure based on the fault propagation probability of each task node, and obtaining the risk value of each task node and the cumulative risk value of the shared device, is characterized in that: Obtain historical dependency data between tasks, including resource sharing, time delay, and data interaction. Use recurrent neural networks for model training, build a task dependency weight prediction model, and predict the task dependency weights between nodes. Obtain the dependency relationship and initial failure probability P0 of each task node in the task chain, and use the failure propagation impact formula of the task node. Calculate the fault propagation probability P of node i at time t+1 i (t+1), where α is the node's own fault self-recovery attenuation factor, β is the fault propagation amplification factor, which indicates the degree of impact of external faults on the node, obtained by fitting historical data, N(i) represents the set of all upstream dependent tasks of node i, and γ ij is the task dependency weight between nodes i and j, indicating the impact of node j’s task on node i’s task. For each node in the task chain, starting from time t = 0, the fault propagation impact formula is used for multiple iterations to calculate the node’s fault propagation probability P. i (t), record the fault propagation increment ΔP of the node in each iteration i (t) = P i (t+1)-P i (t), and judge whether a stable state is reached based on the preset increment threshold; if If ΔPi(t)|<ε, the iteration is stopped and the final fault propagation probability of each node in the stable state is obtained, where ε is the iterative convergence threshold; according to the weighted value of the fault propagation probability and the importance of the equipment, the task node risk value evaluation formula R is used i =P i (final) W i , calculate the risk value R of the device sharing node i in the task chain i , where W i is the contribution weight of node i to the production chain, indicating the importance of the task to the entire production chain. It can be calculated by the historical task completion rate or resource consumption ratio. i (final) represents the final fault propagation probability of the task being affected by device failure or other task failure after the task node i reaches a stable state in the fault propagation model; for the node set G(e) sharing the device, the cumulative value of the device risk is calculated Determine the risk value R of each node i and the cumulative risk value R of shared devices e .

2. The method according to claim 1, wherein The method uses industrial IoT sensors in the factory workshop to obtain workshop equipment data, timestamps production task completion time and resource consumption, and stores them in a classified manner, which is characterized by: By installing industrial Internet of Things sensors on production equipment, logistics routes, quality inspection areas and resource consumption monitoring points in the factory workshop, the equipment's location information, cargo parameters, rack parameters, equipment operating status, material logistics routes, resource consumption, production task completion time and quality inspection data are collected in real time. The collected raw data is timestamped and stored in categories to construct a workshop equipment data set. Cargo parameters include volume and weight, rack parameters include volume and maximum load-bearing capacity, equipment operating status includes speed, temperature, and vibration, resource consumption includes electricity and raw materials, and quality inspection data includes product qualification rate and defect rate. The basic operating data and process flow parameters of the equipment are obtained through the storage database, and the basic operating data are normalized to obtain the basic equipment operating data table. The basic operating data includes equipment model, operating frequency, energy consumption rate, and maintenance records. The process flow parameters include the processing time of each task, material usage and process temperature and pressure. The material status data includes the inventory quantity, processing status and location distribution of the material.

3. The method according to claim 1, wherein The method extracts frequent item sets based on basic equipment operation data and generates a key production process node table. Combined with equipment operation parameters and resource consumption patterns, it determines task priorities and resource allocation rules, and generates a task allocation parameter table containing task priorities and resource allocation rules. The method is characterized by: Based on the basic equipment operation data table, support and confidence thresholds are set, and the Apriori algorithm is used to decompose the basic equipment operation data into frequent item sets. The mining results are sorted, and according to the priority of support and confidence, a key production process node table is obtained, including the equipment's interaction location, logistics nodes and key production processes; according to the equipment operation parameters, including operation frequency, usage time, energy consumption and maintenance cycle, the K-Means clustering algorithm is used to calculate the similarity between devices based on Euclidean distance, and the equipment is clustered and grouped; based on the clustering results, the resource consumption of each group of equipment is determined, and the task load of the equipment is calculated through the equipment usage time and task distribution data to determine the equipment usage pattern; based on the task completion time and task importance data, the task priority score is calculated using the weighted scoring method to generate a task priority table. Combined with the resource consumption pattern, the resource allocation rules required for each task are determined, including resource allocation time, quantity and location, and a task allocation parameter table containing task priority and resource allocation rules is generated.

4. The method according to claim 1, wherein The method involves obtaining physical factory architectural drawings, equipment layout diagrams, and logistics route maps, using 3D modeling tools to construct a three-dimensional spatial model, and combining real-time production data to create a digital twin simulation factory model, which is characterized by: Obtain the architectural drawings, equipment layout diagrams, and logistics route maps of the physical factory, and use the 3D modeling tool Unity to build a three-dimensional spatial model of the factory, including the workshop structure, equipment distribution, product library, raw material library, and logistics channels; embed the floor space, work area, and connection locations of all equipment, including power connections, data interfaces, and material entry and exit points into the model to generate a geometric model of each device; collect real-time production data from the production line, input it into Simulink, and connect it to the three-dimensional spatial model to simulate the execution status of production tasks and display the operating status of each device in real time. Real-time production data includes equipment status, production task progress, and equipment The interaction between them, the equipment status includes whether it is on or off, operating speed, and energy consumption; the production task progress includes task start time, task completion time, and processing progress; the digital twin platform GEPredix is ​​used to combine the three-dimensional space model with the real-time data access interface to create a digital twin simulation factory model; using real-time production data, a dynamic process simulation model is constructed to simulate the execution process of production tasks in the factory, set production environment parameters, and calculate task scheduling and resource allocation in real time through simulation to obtain dynamic process simulation results including task completion time and equipment utilization. Production environment parameters include equipment failure, production task priority, and resource constraints.

5. The method according to claim 1, wherein The method is characterized by: obtaining a task priority list and resource requirement information based on the production task data in the digital twin simulation factory model and combining task priority rules, constructing a dynamic programming state space and decision variables, and determining the resource usage time, resource allocation location, and specific quantity for each task. The production task data in the digital twin simulation factory model is used to extract the completion time, required resource type, and quantity of each task. Priority rules are defined based on the characteristics of the tasks, with tasks with shorter completion times or higher resource requirements being given higher priority. Based on the execution requirements of the tasks, the resource requirement information of each task is obtained and arranged in order of priority to obtain a task priority list. The resource requirement information includes equipment, workstations, and raw materials. Based on the task priority list, the state space and decision variables of the dynamic programming model are determined. The state space includes the resource allocation at each moment, and the decision variables are the resource allocation decisions for the task. Scheduling efficiency is evaluated by calculating the resource usage time, total resource consumption, and task completion time of each task. Resource scheduling efficiency is set as the objective function. Based on the dynamic programming model, a bottom-up dynamic programming method is used to gradually deduce the task from its initial state to its final state. The optimal resource configuration at each moment is calculated. The resource usage efficiency of each task at different time points is evaluated during the calculation process to determine whether the resource constraints are met. The resource allocation plan for each task is then determined, including the resource usage time, location, and quantity of each task.

6. The method according to claim 1, wherein The impact scope report based on the production failure chain extracts the priority, resource requirements and completion time of the affected tasks, re-evaluates the task execution sequence and adjusts resource allocation and task schedule, which is characterized by: Based on the impact range report of the production fault chain, the priority, resource requirements and completion time of each affected task are extracted. Based on the task priority and resource requirements, the task execution order is re-evaluated to obtain the task execution sequence table; based on the re-determined task execution order, the task execution order is optimized using a genetic algorithm, and the optimization objective function is set to minimize the fault recovery time, maximize resource utilization and minimize the task completion time. The tasks are dynamically adjusted and rearranged to obtain the optimized production task execution sequence table, including the task re-execution order, resource allocation and task completion time; the optimized task execution sequence table is input into a multi-task dynamic scheduling simulation environment to simulate the environment of multi-task concurrent execution, evaluate resource competition, equipment usage and scheduling conflicts during task execution, and verify the effectiveness of the optimized task execution sequence table based on task completion time, resource utilization and equipment idle time; if the effectiveness is lower than expected, the task execution order is adjusted again until the execution time, resource allocation and priority of all task nodes are met.

Images