MES cross-factory capacity dynamic coordination control method based on multi-objective optimization

Abstract

The invention discloses an MES cross-factory capacity dynamic coordination control method based on multi-objective optimization, and relates to the technical field of capacity regulation and control. The production data of each factory is collected and integrated by using the Internet of Things, and the data is ensured to be accurate and complete; predicting demands by using an algorithm, distributing orders, and adjusting a production plan in real time according to productivity evaluation; constructing a multi-objective optimization model, and solving to obtain an optimal scheme for a decision maker to select; and finally, monitoring production through a visual interface, and automatically feeding back and adjusting in case of abnormality, thereby realizing dynamic coordination control of cross-factory productivity. The production efficiency can be improved, the cost is reduced, and resource waste and risk loss are avoided; the product quality is ensured, the standard consistency of each factory is ensured, the resource utilization is optimized, the green manufacturing is promoted, the supply chain collaboration is enhanced, the overall operation management level of an enterprise is improved, and the market competitiveness is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of production capacity regulation, and particularly to a dynamic coordination control method for MES cross-plant production capacity based on multi-objective optimization. Background Art

[0002] In the current context of increasingly fierce global competition, the business scope of manufacturing enterprises continues to expand, and the cross-plant production mode is becoming more and more common. There are differences in geographical location, resource allocation, production process, etc. among factories. How to achieve efficient coordination control of cross-plant production capacity has become a key problem in enhancing the overall competitiveness of enterprises.

[0003] Traditional Manufacturing Execution Systems (MES) can play a certain role in dealing with single-plant production management, but expose many deficiencies in cross-plant scenarios. In terms of data management, the data of each factory is independent of each other, lacking an effective integration mechanism. The data formats are not unified, and the phenomenon of data islands is serious, resulting in the management layer being difficult to obtain comprehensive and accurate production information and unable to make timely and scientific decisions. For example, the storage methods of equipment operation data, inventory data, etc. in different factories are different, making it difficult to directly compare and analyze, so that the enterprise cannot accurately grasp the overall production capacity situation.

[0004] In terms of production capacity coordination, traditional methods mostly rely on manual experience and simple production scheduling, and cannot respond in real time to changes in market demand and emergencies in the production process. When the order volume fluctuates, equipment fails, or raw material supply is delayed, it is difficult to quickly adjust the production tasks and resource allocation of each factory, often resulting in problems such as delivery delays and cost increases. For example, when the order volume of an enterprise surges during the peak season, due to the inability to coordinate the production capacity of each factory in time, the delivery of some orders lags behind, which not only affects customer satisfaction but also causes economic losses.

[0005] With the diversification and personalization of market demand, customers have higher and higher requirements for product quality and delivery time. At the same time, enterprises are also facing multiple challenges such as cost control and optimal utilization of resources. Existing MES systems have limited capabilities in multi-objective optimization and cannot take into account multiple objectives such as production cost, product quality, delivery time, and resource utilization rate. In actual production, often one objective is sacrificed to meet another objective, making it difficult to maximize the benefits of the enterprise. For example, in order to shorten the delivery time, it may increase production costs, reduce product quality, or over-consume resources, which is not conducive to the sustainable development of the enterprise. Against this background, it is urgent to develop a dynamic coordination control method for MES cross-plant production capacity based on multi-objective optimization. Summary of the Invention

[0006] The dynamic coordination control method for MES cross-plant production capacity based on multi-objective optimization proposed by the present invention is to solve the problems mentioned in the above existing technologies.

[0007] To achieve the above object, the present invention adopts the following technical solutions: A MES cross-plant production capacity dynamic coordination control method based on multi-objective optimization, including: Data collection and integration step: Using Internet of Things technology, sensors are deployed at production equipment, material inventory points, and quality inspection links in each factory to collect production data in real time, including equipment operation status, production progress, material consumption, and product quality inspection results; the data is transmitted to the central database through industrial Ethernet or 5G network, and the ExtractTransformLoad technology is used to clean, transform, and load the data to eliminate data noise and integrate it into a unified format; Demand forecasting and order allocation step: Using time series analysis and long short-term memory network LSTM, combined with historical market data, customer order trends, and industry dynamic factors to forecast product demand; constructing an order allocation model based on the production capacity, cost, product quality level, and delivery date factors of each factory, and using the Hungarian algorithm to solve it to achieve reasonable allocation of orders among different factories; the objective function of the order allocation model is: , where O is the total order allocation cost, is the cost of factory i producing order j, is the delivery time of factory i to complete order j, is the quantity of order i allocated to factory j, n is the number of factories, and m is the number of orders; Production capacity evaluation and dynamic adjustment step: Based on the collected equipment data and production process parameters, combined with the human and material resource allocation of the factory, the production capacity of each factory is evaluated in real time through a production capacity evaluation model; the production capacity evaluation model considers equipment utilization rate, production efficiency, and production bottleneck factors, and the calculation formula is: , where is the production capacity of the factory, is the utilization rate of equipment k, is the production efficiency of equipment k, is the effective production time of equipment k, and s is the number of equipment in the factory; when the production capacity of the factory fluctuates, the production plan and resource allocation are dynamically adjusted according to order priority, delivery date, and production cost factors; Objective optimization step: Taking production cost, delivery date, product quality, and resource utilization rate as optimization objectives, constructing an objective optimization model; using the non-dominated sorting genetic algorithm NSGA-II to solve the model to obtain the Pareto solution; during the optimization process, by adaptively adjusting the crossover probability and mutation probability , the convergence speed and optimization ability of the algorithm are improved, and the adjustment formula is: , where 、 are the initial maximum and minimum values of the crossover probability, 、 are the initial maximum and minimum values of the mutation probability, f is the fitness value of the current individual, and are the maximum and minimum fitness values in the population; the decision maker selects an optimization plan from the Pareto solutions according to actual needs; Collaborative monitoring and feedback steps: Through the visualization interface of the MES system, the production progress, order execution status, and production capacity utilization of each factory are monitored in real time; when an abnormal situation occurs, the system automatically issues an alarm and feeds back the abnormal information to the management department and the factory; each factory adjusts its production strategy according to the feedback information and at the same time feeds back the adjustment results to the MES system to form a closed-loop control and achieve stable operation of the production process.

[0008] In the present invention, it further includes: Supply chain collaborative optimization steps: By establishing an information sharing platform with suppliers and logistics providers, raw material supply information and logistics distribution capacity data are obtained in real time; combined with factory production capacity and order demand, the theory of constraints TOC is used to determine the bottleneck links in the supply chain and optimize the supply chain resource allocation; the joint inventory management strategy is adopted to establish a collaborative inventory model between suppliers and factories to reduce inventory costs; the formula for the collaborative inventory model is: where I is the total inventory cost, is the inventory holding cost per unit product in factory i, is the safety inventory of factory i, is the shortage cost per unit product in factory i, is the demand forecast value of factory i.

[0009] Risk assessment and response steps: Establish a risk assessment index system, including market risk, technology risk, supply chain risk, and production risk aspects; use the analytic hierarchy process AHP to determine the weights of each risk index, and combine the fuzzy comprehensive evaluation method to evaluate the risks in the cross-factory production process; when the risk assessment result exceeds the preset threshold, start the risk response strategy, and the formula for calculating the risk assessment score is: where R is the risk assessment score, is the weight of the jth risk index, is the evaluation score of the jth risk index, and k is the number of risk indexes.

[0010] In the present invention, in the data collection and integration step, for the collected production data, distributed ledger technology is used for encrypted storage, and contract technology is used to automatically execute data verification and sharing rules. At the same time, a data compression algorithm is used to compress and store historical data.

[0011] In the present invention, in the demand forecasting and order allocation step, a deep Q-network (DQN) of the reinforcement learning algorithm is introduced to dynamically adjust the order allocation strategy according to the real-time production capacity changes and order completion status of the factory; the order allocation strategy is adapted to the production environment through trial and error and learning; the update formula of the DQN algorithm is: , where is the Q value of taking action at in state st, α is the learning rate, rt is the reward obtained by taking action at in state st, is the discount factor, is the next state.

[0012] In the present invention, in the production capacity assessment and dynamic adjustment step, a virtual model of the factory production process is constructed using digital twin technology; real-time comparison and analysis are carried out between the actual production data and the virtual model to discover production capacity bottlenecks and production problems in advance; a method based on model predictive control (MPC) is used to optimize the control of the production process and adjust the production parameters in advance according to the predicted production situation.

[0013] In the present invention, in the objective optimization step, in addition to production cost, delivery period, product quality, and resource utilization rate, carbon emissions are incorporated into the optimization objective to construct a green manufacturing objective optimization model; an improved multi-objective particle swarm optimization algorithm (MOPSO) is used to solve the problem, and sustainable development of cross-factory production is achieved by optimizing energy consumption and carbon emissions in the production process.

[0014] In the present invention, in the collaborative monitoring and feedback step, big data analysis technology is used to mine the monitoring data; the relationship between various factors in the production process is discovered through the Apriori association rule mining algorithm to provide information for production decision-making.

[0015] In the present invention, in the supply chain collaborative optimization step, distributed ledger technology is used to construct a supply chain information sharing platform; automatic settlement and trust mechanisms for each link of the supply chain are realized through contracts, and a supplier relationship management (SRM) system is adopted to classify and manage suppliers and establish stable cooperative relationships with high-quality suppliers.

[0016] In the present invention, in the risk assessment and response step, machine learning algorithms are used to learn and train historical risk data to construct a risk prediction model; by real-time monitoring of risk indicator data, the occurrence probability and impact degree of risks are predicted in advance; combined with the risk matrix, different risks are classified and managed, and targeted risk response plans are formulated.

[0017] Compared with the existing technologies, the beneficial effects of the present invention are: In terms of production efficiency, by collecting and integrating data in real time through the Internet of Things, enterprises can have a real-time grasp of the production status of each factory, promptly discover and solve production bottlenecks. Accurate demand forecasting and reasonable order allocation can make full use of the production capacity of each factory and avoid uneven production tasks. In case of emergencies, the system can quickly adjust the production plan, reduce downtime, and improve overall production efficiency.

[0018] In terms of cost control, multi-objective optimization takes into account production costs, optimizes order allocation and resource configuration, and avoids resource waste and overproduction. Supply chain collaborative optimization can reduce raw material procurement costs and inventory costs, and improve the capital turnover rate. Moreover, the risk assessment and response mechanism can prevent risks in advance and reduce additional costs caused by risk events.

[0019] In terms of product quality assurance, the production process is monitored in real time, and by combining big data analysis to mine the related factors of quality problems, quality hazards can be discovered in a timely manner and measures can be taken. Each factory produces according to a unified quality standard to ensure product quality consistency and improve customer satisfaction.

[0020] At the level of resource utilization, the system dynamically allocates resources such as human, material, and equipment resources to improve resource utilization rate. Incorporating carbon emissions into the optimization goal helps to promote green manufacturing and achieve the sustainable development of enterprises.

[0021] In terms of collaborative management, supply chain collaborative optimization strengthens the cooperation between enterprises and suppliers and logistics providers, establishes stable cooperative relationships, and ensures the smooth supply of raw materials and logistics distribution. The real-time monitoring and feedback mechanism across factories can communicate and coordinate problems in a timely manner, improve the overall operation and management level of enterprises, and enhance the competitiveness of enterprises in the market. Description of the Drawings

[0022] Figure 1 It is a schematic block diagram of the MES cross-factory production capacity dynamic coordination control method based on multi-objective optimization proposed by the present invention; Figure 2 It is a schematic block diagram for comparing the production capacity utilization rates of each factory of the MES cross-factory production capacity dynamic coordination control method based on multi-objective optimization of the present invention.

[0023] Figure 3 It is a schematic block diagram for comparing the production costs of different orders before and after applying this patent of the MES cross-factory production capacity dynamic coordination control method based on multi-objective optimization of the present invention Detailed Embodiment

[0024] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be understood as a limitation to the present invention.

[0026] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined. In addition, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations. The present invention will be further described in detail below in conjunction with the drawings.

[0027] Refer to Figures 1 to 3 : A specific implementation method of a MES cross-factory production capacity dynamic coordination control method based on multi-objective optimization I. Data collection and integration At key nodes in the production workshops of each factory, such as production equipment, material storage areas, quality inspection workstations, etc., various sensors are deployed, including temperature sensors, pressure sensors, displacement sensors, material flow sensors, etc. With the help of Internet of Things technology, real-time data collection is realized. The collected data covers information such as equipment operation status (such as rotation speed, temperature, fault alarm signal), production progress (product quantity, production batch), material consumption (material type, consumption quantity), and product quality inspection results (dimension deviation, performance parameters).

[0028] The collected data is transmitted to the central database via industrial Ethernet or 5G network. Using ETL tools, the data is cleaned to remove duplicate, incorrect, and incomplete data records. For example, for abnormal data caused by sensor failures, reasonable data thresholds are set for screening and elimination; for data with inconsistent formats, unified conversion is performed, such as unifying the recording formats of the operating times of different factory equipment into the standard time format. After that, the processed data is loaded into the database to build a complete and accurate production data warehouse, providing reliable data support for subsequent analysis and decision-making.

[0029] II. Demand Forecasting and Order Allocation Collect historical sales data, market trend data, and customer order data from channels such as the enterprise's sales database, market research institutions, and industry reports. Use time series analysis algorithms, such as the ARIMA model, to analyze the historical sales data and capture the trend, seasonality, and periodicity characteristics of the data. At the same time, input these data into the long short-term memory network (LSTM) for training. LSTM can learn the long-term dependencies in the data, thus more accurately predicting future product demand.

[0030] Based on data such as the production capacity, production cost, product quality level, and delivery date of each factory, an order allocation model is constructed. Assume that the enterprise has 3 factories (n = 3) and currently has 5 orders (m = 5). By collecting the cost of each factory to produce each order and the estimated delivery time and substituting them into the objective function of the order allocation model and using the Hungarian algorithm to solve, determine which factory each order is allocated to and the quantity allocated to achieve reasonable order allocation.

[0031] III. Capacity Assessment and Dynamic Adjustment Real-time obtain the operating data of the equipment in each factory through sensors and calculate the equipment utilization rate , for example, the ratio of the actual operating time to the planned operating time of equipment k within a shift. Obtain the equipment production efficiency from the production process documents, such as the number of products produced by the equipment per unit time. At the same time, determine the effective production time of the equipment according to the production plan and equipment maintenance arrangements. Substitute these data into the capacity assessment model to calculate the production capacity of each factory.

[0032] When there are fluctuations in production capacity due to equipment failures, insufficient raw material supply, etc. in the factory, the production plan is re-adjusted using the dynamic programming algorithm based on factors such as order priority, delivery date, and production cost. For example, for orders with urgent delivery dates and high priorities, resources are preferentially allocated for production; for orders with higher costs, they are arranged to be produced in factories with lower costs as much as possible while ensuring other goals.

[0033] IV. Multi-objective Optimization Determine production cost, delivery date, product quality, and resource utilization rate as optimization objectives, and construct a multi-objective optimization model. The non-dominated sorting genetic algorithm (NSGA-II) is used to solve this model. In the initialization stage of the algorithm, a certain number of initial populations are randomly generated. During the iterative process, the fitness value of each individual is calculated, and a new population is generated through selection, crossover, and mutation operations.

[0034] To improve the convergence speed and optimization ability of the algorithm, the crossover probability and mutation probability are adaptively adjusted. For example, in the initial stage of the algorithm, to accelerate the search speed, the crossover probability is set to 0.8, and the mutation probability is set to 0.2; as the iteration progresses, when the fitness value of the population gradually stabilizes, to avoid the algorithm falling into a local optimum, the crossover probability is set to 0.6, and the mutation probability is set to 0.1. According to the formulas and , the probability values are adjusted in real time. Finally, a set of Pareto optimal solutions are generated, and the decision maker selects the most suitable solution from the Pareto optimal solutions according to the current strategic focus and actual needs of the enterprise.

[0035] V. Collaborative Monitoring and Feedback A visual monitoring interface is developed in the MES system to display information such as the production progress of each factory, order execution status, and production capacity utilization status in an intuitive way such as charts and graphs. For example, the production progress of each order in each factory is displayed through a Gantt chart, and the production capacity utilization rates of each factory are compared using a bar chart. When abnormal situations such as production progress delays and quality problems occur, the system automatically issues an alarm according to preset rules, such as notifying relevant management personnel via text messages, emails, or system pop-ups.

[0036] After receiving the alarm, the relevant personnel promptly take measures to adjust the production strategy, such as adjusting the production sequence, increasing manpower or equipment investment, etc. After the adjustment is completed, the adjustment results are fed back to the MES system, and the system continuously monitors the adjusted production situation to form a closed-loop control to ensure that the production process is always in a stable and efficient operating state.

[0037] VI. Data Representation and Interpretation As can be seen from the data, after the implementation of the patent method, the on-time delivery rate of orders has increased significantly. This is due to accurate demand forecasting, reasonable order allocation, and dynamic adjustment of production capacity, ensuring that orders can be produced and delivered within the specified time. The production cost has been reduced by 15% because of the consideration of cost in the multi-objective optimization process and the optimization of order allocation and resource configuration, avoiding unnecessary waste. The product unqualified rate has been reduced by half. This is because the production process is monitored in real time, quality problems can be detected and measures can be taken in a timely manner. At the same time, the unified quality standards of each factory also ensure the stability of product quality. The resource utilization rate has increased by 20%. Through the dynamic allocation of resources in each factory, resources are more fully utilized, reducing idleness and waste, and comprehensively improving the production efficiency and competitiveness of the enterprise.

[0038] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes, should be covered by the protection scope of the present invention.

Claims

1. A method for dynamic coordinated control of MES cross-factory capacity based on multi-objective optimization, characterized in that: include: Data collection and integration steps: Using IoT technology, deploy sensors at production equipment, material inventory points, and quality inspection links in each factory to collect production data in real time, including equipment operating status, production progress, material consumption, and product quality inspection results; transmit data to the central database via industrial Ethernet or 5G network, and use ExtractTransformLoad technology to clean, transform, and load data to eliminate data noise and integrate it into a unified format; Demand forecasting and order allocation steps: Use time series analysis and long short-term memory network LSTM to predict product demand in combination with market historical data, customer order trends, and industry dynamics; build an order allocation model based on the production capacity, cost, product quality level, and delivery time of each factory, and use the Hungarian algorithm to solve it to achieve reasonable allocation of orders among different factories; the objective function of the order allocation model is: , where O is the total order allocation cost, The cost of producing order j for factory i, The delivery time for factory i to complete order j, is the quantity of order i allocated to factory j, n is the number of factories, and m is the order quantity; Capacity assessment and dynamic adjustment steps: Based on the collected equipment data and production process parameters, combined with the factory's human and material resource allocation, the capacity of each factory is evaluated in real time through the capacity assessment model; the capacity assessment model takes into account equipment utilization, production efficiency, and production bottleneck factors, and the calculation formula is: ,in For the factory's production capacity, is the utilization rate of device k, is the production efficiency of equipment k, is the effective production time of equipment k, and s is the number of equipment in the factory. When the factory production capacity fluctuates, the production plan and resource allocation are dynamically adjusted according to order priority, delivery time, and production cost factors.

2. The MES cross-factory capacity dynamic coordination control method based on multi-objective optimization according to claim 1 is characterized in that: Also includes: Target optimization steps: production cost, delivery time, product quality, and resource utilization are the optimization targets, and a target optimization model is constructed; The non-dominated sorting genetic algorithm NSGA-II is used to solve the model and obtain the Pareto solution; During the optimization process, the crossover probability is adjusted adaptively. and mutation probability , improve the convergence speed and optimization ability of the algorithm, and adjust the formula to: ,in , are the initial maximum and minimum values ​​of the crossover probability, , is the initial maximum and minimum value of the mutation probability, f is the fitness value of the current individual, , are the maximum and minimum fitness values ​​in the population; the decision maker selects the optimization plan from the Pareto solution according to actual needs; Collaborative monitoring and feedback steps: Through the visual interface of the MES system, the production progress, order execution, and capacity utilization of each factory are monitored in real time; when an abnormal situation occurs, the system automatically issues an alarm and feeds back the abnormal information to the management department and the factory; each factory adjusts its production strategy based on the feedback information and feeds back the adjustment results to the MES system, forming a closed-loop control to achieve stable operation of the production process; Supply chain collaborative optimization steps: Establish an information sharing platform with suppliers and logistics providers to obtain real-time raw material supply information and logistics distribution capacity data; Combine factory capacity and order demand, use constraint theory TOC to determine the bottleneck links in the supply chain and optimize supply chain resource allocation; Adopt a joint inventory management strategy and establish a collaborative inventory model between suppliers and factories to reduce inventory costs; Collaboration The inventory model formula is: , where I is the total inventory cost, is the inventory holding cost per unit of product in factory i, is the safety stock of factory i, is the stock-out cost per unit of product in factory i, is the demand forecast value of factory i.

3. The MES cross-factory capacity dynamic coordination control method based on multi-objective optimization according to claim 1 is characterized in that: Also includes: Risk assessment and response steps: Establish a risk assessment indicator system, including market risk, technical risk, supply chain risk, and production risk; The analytic hierarchy process (AHP) was used to determine the weight of each risk indicator, and the fuzzy comprehensive evaluation method was used to evaluate the risks in the cross-factory production process. When the risk assessment result exceeds the preset threshold, the risk response strategy is initiated, and the risk assessment score calculation formula is: , where R is the risk assessment score, is the weight of the j-th risk indicator, is the evaluation score of the j-th risk indicator, and k is the number of risk indicators.

4. The MES cross-factory capacity dynamic coordination control method based on multi-objective optimization according to claim 1 is characterized in that: In the data collection and integration steps, the collected production data is encrypted and stored using distributed ledger technology, and contract technology is used to automatically execute data verification and sharing rules. At the same time, data compression algorithms are used to compress and store historical data.

5. The MES cross-factory capacity dynamic coordination control method based on multi-objective optimization according to claim 1 is characterized in that: In the demand forecasting and order allocation steps, the reinforcement learning algorithm deep Q network DQN is introduced to dynamically adjust the order allocation strategy according to the real-time production capacity changes and order completion status of the factory; the order allocation strategy is adapted to the production environment through trial and error and learning; the update formula of the DQN algorithm is: ,in is the Q value of taking action at in state st, α is the learning rate, rt is the reward for taking action at in state st, is the discount factor, For the next state.

6. The MES cross-factory capacity dynamic coordination control method based on multi-objective optimization according to claim 1 is characterized in that: In the capacity assessment and dynamic adjustment steps, digital twin technology is used to build a virtual model of the factory production process. Through real-time comparative analysis between actual production data and the virtual model, capacity bottlenecks and production problems are discovered in advance. The model predictive control (MPC) method is used to optimize the production process and adjust production parameters in advance according to the predicted production situation.

7. The MES cross-factory capacity dynamic coordination control method based on multi-objective optimization according to claim 2 is characterized in that: In the target optimization step, in addition to production cost, delivery time, product quality, and resource utilization, carbon emissions are included in the optimization targets to build a green manufacturing target optimization model; the improved target particle swarm optimization algorithm MOPSO is used to solve the problem, and sustainable development of cross-factory production is achieved by optimizing energy consumption and carbon emissions in the production process.

8. The MES cross-factory capacity dynamic coordination control method based on multi-objective optimization according to claim 2 is characterized in that: In the collaborative monitoring and feedback steps, big data analysis technology is used to mine the monitoring data; the association rule mining algorithm Apriori is used to discover the relationship between various factors in the production process to provide information for production decisions.

9. The MES cross-factory capacity dynamic coordination control method based on multi-objective optimization according to claim 2 is characterized in that: In the supply chain collaborative optimization step, distributed ledger technology is used to build a supply chain information sharing platform; automatic settlement and trust mechanisms in each link of the supply chain are realized through contracts, and the supplier relationship management SRM system is used to classify and manage suppliers, and establish stable cooperative relationships with high-quality suppliers.

10. The MES cross-factory capacity dynamic coordination control method based on multi-objective optimization according to claim 3 is characterized in that: In the risk assessment and response steps, machine learning algorithms are used to learn and train historical risk data to build risk prediction models; by real-time monitoring of risk indicator data, the probability of risk occurrence and impact can be predicted in advance; Combined with the risk matrix, different risks are classified and managed, and risk response plans are formulated.

Images