Industrial MES monitoring system with data interaction function

Abstract

The invention provides an industrial MES monitoring system with a data interaction function. According to the system, the high efficiency and intelligence of factory capacity coordination management are improved. The method comprises the steps that firstly, an MES system collects real-time data of all factories and stores the real-time data; predicting the capacity demand of each factory, dynamically adjusting the prediction model and the scheduling optimization model in combination with historical production data, equipment states and market change trends, automatically generating a scheduling scheme based on a capacity demand prediction value, transmitting the generated scheduling scheme to an MES system of each factory, and sending the scheduling scheme to the MES system of each factory. And finally, the factory automatically allocates resources according to the scheme and the actual production condition, the factory adjusts the priority and the production sequence of the tasks according to the actual execution condition, and when the problems of equipment failure, production progress lag, personnel absence and the like occur, the scheduling scheme is automatically adjusted. According to the invention, through dynamic adjustment capability and a self-adaptive optimization mechanism, the efficiency and intelligence of factory capacity coordination management are significantly improved.

Description

Technical Field

[0001] The present invention relates to the field of industrial capacity management, and in particular to an industrial MES monitoring system with a data interaction function. Background Art

[0002] With the rapid development of the global manufacturing industry, especially in multinational and multi-factory production environments, how to effectively coordinate the production capacity of each factory, ensure that production tasks are completed on time, and maximize the use of resources has become a major challenge facing manufacturing companies. Traditional production scheduling methods mostly rely on manual operations or simple calculation models. These methods are difficult to cope with complex and changeable production situations, and cannot fully utilize real-time data and intelligent decision-making mechanisms.

[0003] In the prior art, the MES system is used to monitor data such as production status, equipment utilization, and personnel scheduling in real time, and can generate production tasks and scheduling plans. This method enables the production process to respond to data changes in real time, thereby improving production efficiency and accuracy, and automatically generates production scheduling plans through production demand and equipment status prediction, reducing manual intervention and improving the automation level of the scheduling process.

[0004] Although existing technologies can automatically generate scheduling plans, they lack the ability to adjust scheduling plans based on real-time data during the execution of production tasks. Traditional systems can often only make adjustments based on predetermined plans, and cannot optimize plans in real time based on actual changes in production (such as equipment failures, personnel absences, etc.). This means that in emergencies, production progress may be affected, and scheduling plans often fail to provide effective feedback and optimization after execution. Although task adjustments can be made, feedback data cannot be fully utilized for continuous optimization, resulting in inconsistent performance of scheduling plans in different production cycles, and the inability to continuously improve the system's adaptability and production efficiency. Summary of the invention

[0005] In order to solve the above problems, the present invention introduces real-time data collection, prediction model adjustment and feedback mechanism, so that production scheduling can not only be automatically adjusted during task execution, but also optimize the scheduling model according to actual production feedback. Based on this, the present invention proposes an industrial MES monitoring system with data interaction function.

[0006] To this end, the technical solution adopted in the present invention is as follows: Module 1: Factory status collection module, which monitors the production status, equipment capacity, personnel scheduling and order requirements of each factory in real time through the MES system, and generates real-time data including equipment utilization, production equipment load, personnel scheduling and order progress according to the production status, equipment capacity, personnel scheduling and order requirements of each factory; Module 2: Factory capacity forecasting module, which uses data analysis algorithms to forecast the capacity demand of each factory based on the real-time data, generates forecast values ​​of the capacity demand of each factory, and dynamically adjusts the forecasting model based on historical production data, equipment status and market change trends; Module 3: Production scheduling module, which establishes a scheduling optimization model. The model automatically generates a cross-factory production scheduling plan based on the predicted capacity demand value. The MES system transmits the production scheduling plan to each factory. The MES system generates specific production tasks based on the production scheduling plan, and executes the production tasks and updates the production status. Module 4: Dynamic scheduling optimization module. During the execution of the production task, the MES system adjusts the scheduling plan according to the real-time data in the production process, generates a new scheduling plan, analyzes the new scheduling plan through the system feedback mechanism, and optimizes the scheduling optimization model based on the analysis results.

[0007] Furthermore, the real-time data includes equipment utilization, production equipment load, personnel scheduling, and order progress. The equipment utilization rate is calculated by monitoring the operation of the equipment through the MES system, collecting equipment status information and automatically collecting it through sensors, PLC and SCADA systems. The formula is: ; in, is the utilization rate of equipment i, is the actual working time of device i, is the available time of device i, The production equipment load situation: The MES system obtains the equipment operation load through the integrated equipment sensor and calculates it through the following formula: ; in, is the load of device i, is the actual output of equipment i, is the maximum output capacity of device i, The personnel scheduling situation, the MES system records and manages the personnel scheduling situation of each factory in real time, and the personnel scheduling information is calculated by the following formula: ; in, is the workload of worker j, is the working time assigned to worker j, is the available working time of worker j, The order progress, the MES system tracks the progress of each order in real time through integration with the enterprise resource planning system (ERP) and the order management system. The formula is: ; in, For order completion, is the actual production volume, is the order quantity, All real-time data is collected, calculated and processed and then stored in the MES system. The formula is: ; in, is the sum of all real-time production data, is the real-time production data of factory k, and k is the total number of factories.

[0008] Furthermore, the capacity demand forecast includes historical data processing, and forecasting based on the weighted average of historical data and real-time data. The historical data processing: the historical production data is processed, including removing noise, filling missing values ​​and correcting outliers. It consists of the factory's production records, including equipment utilization, production equipment load, personnel scheduling, and order progress. The prediction based on the weighted average of historical data and real-time data: Based on the historical data and the real-time data of the current factory, the capacity demand forecast value is generated by weighted average. The prediction formula is as follows: ; in, is the predicted capacity demand of factory k at time point t, is a smoothing factor used to balance the impact of historical data and real-time data. is the predicted capacity value at the previous moment, is the real-time production data of factory k, is the weight factor of historical data, is the historical production data of factory k.

[0009] Furthermore, the prediction model is adjusted as follows: during the production process, the MES system will collect data such as equipment operation status, personnel scheduling, production progress, etc. in real time, and feed it back to the prediction model in real time. Whenever these data change, the model will be adjusted according to the feedback results. The formula is: ; in, is the prediction error of plant k, is the predicted capacity demand value of factory k, is the actual production capacity of factory k, Based on the error value, the system corrects the prediction by adjusting the model parameters. Through real-time data feedback, the prediction model can learn automatically.

[0010] Furthermore, the market trend, market demand and raw material price fluctuations directly affect the forecast of production capacity demand. Therefore, it is necessary to integrate market data into the model and adjust the forecast results by analyzing the market trend. The formula is: ; in, is the adjusted forecast value of factory k’s production capacity based on market demand, is the weight factor of market data.

[0011] Furthermore, the scheduling optimization model automatically generates a cross-factory production scheduling plan based on the predicted capacity demand value. The key steps of the scheduling optimization model are: 1) Determine the optimization goal; maximize resource utilization; reduce production cycle; the objective function is: ; Where Z is the total production cost, is the production cost associated with factory k, is the dispatch quantity of factory k; 2) Determine the constraints, including the maximum capacity constraint of each factory; equipment utilization constraint; personnel scheduling constraint; order delivery date constraint; the formula is: ; in, is the maximum production capacity of factory k, is the maximum dispatch quantity of factory k, 3) Model solving: The specific steps are: input data, input the predicted value of production capacity demand, the production capacity of each factory, the availability of equipment and personnel, the priority of orders and the delivery time into the optimization model; optimize the calculation, calculate the optimal production scheduling plan by solving the objective function; output the scheduling plan, generate a specific production scheduling plan, 4) Generate a production scheduling plan. The key contents of the scheduling plan include: task allocation, production sequence, resource allocation. The generated scheduling plan is transmitted to the MES system of each factory in the following format: Production scheduling plan = {task, production plant, equipment, personnel, production sequence, priority, delivery date}.

[0012] Furthermore, the transmission and execution of the production scheduling plan, after the scheduling plan is generated, is transmitted to each factory. After the factory's MES system receives the scheduling plan, it will generate specific production tasks according to the content of the plan. The generation process is specifically as follows: 1) Task content definition, define the specific content of the production task, 2) Resource allocation, 3) Production planning, assigning tasks to specific production lines and shifts, and determining the production sequence 4) Execute production tasks. The MES system starts the production line and executes the tasks. During the production process, the MES system monitors the progress of the tasks in real time and updates the task status based on the actual execution status. The execution progress of the production task is updated by the following formula: ; in, is the new progress of task a, is the old progress of task a, is the progress adjustment of task a, It is a smoothing factor used to adjust the update speed of production tasks.

[0013] Furthermore, for the new scheduling scheme, when the system receives real-time feedback data from various factories during the execution of production tasks, the scheduling optimization module will automatically adjust the scheduling scheme according to these real-time data. The formula is: ; in, For the new task priority, is the original task priority, is the actual operation data of device i, For expected data, is the adjustment factor.

[0014] Furthermore, the scheduling scheme analysis states that during the execution of production tasks, the system will collect the execution results in real time through a feedback mechanism. The feedback data includes production progress, resource usage, and production bottlenecks. Through the feedback data, the system analyzes the actual effect of the execution of production tasks. By analyzing the feedback data of production status, the MES system evaluates the effect of the adjusted scheduling plan. The specific analysis steps include: 1) Differences from forecasts, comparing the differences between actual production progress and forecast progress, 2) Resource utilization efficiency, analyzing the use of equipment and personnel, 3) Bottleneck analysis: identifying bottlenecks in the production process through feedback data.

[0015] Furthermore, the scheduling optimization model is optimized. Through the scheduling scheme analysis, the MES system will optimize the scheduling optimization model. The optimization process makes the scheduling scheme flexible and accurate by adjusting model parameters and updating algorithms.

[0016] Compared with the prior art, the advantages of the present invention are: 1. The present invention can dynamically adjust the scheduling plan during the execution of production tasks by real-time monitoring of various data in the production process, which can effectively avoid production bottlenecks and resource waste, and improve production efficiency and resource utilization.

[0017] 2. The present invention collects the actual results of task execution through a feedback mechanism, analyzes the effect of production task execution in real time, and optimizes the scheduling plan based on the feedback data. Through this process, the system can self-learn and optimize to adapt to different production environments and task requirements, thereby continuously improving scheduling accuracy and production efficiency in long-term operation.

[0018] 3. The present invention further integrates factors such as market demand data and changes in raw material prices, and can adjust the capacity forecast model in real time, so that the scheduling plan not only responds to changes in the production process, but can also be adjusted according to market changes. This flexible prediction and adjustment mechanism makes production scheduling more in line with actual needs, reduces uncertainty in the production process, and enables production scheduling to be optimized on a wider level, enhancing the market adaptability and flexibility of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 It is a schematic diagram of the overall framework of the present invention.

[0021] Figure 2 It is a schematic diagram of module 1 of the present invention.

[0022] Figure 3 It is a schematic diagram of module 2 of the present invention.

[0023] Figure 4 It is a schematic diagram of module 3 of the present invention. DETAILED DESCRIPTION

[0024] To achieve the above objectives, the present invention is implemented through the following technical solutions, combined with the attached Figure 1 The present invention provides an industrial MES monitoring system with data interaction function, the system comprising: Module 1: Factory status collection module, combined with the attached Figure 2, through the MES system, real-time monitoring of each factory's production status, equipment capacity, personnel scheduling and order demand, and generates real-time data including equipment utilization, production equipment load, personnel scheduling, and order progress based on each factory's production status, equipment capacity, personnel scheduling and order demand.

[0025] Equipment utilization: The MES system collects the status information of each device by real-time monitoring of the equipment's operation, including the equipment's start and stop status, operating speed, workload, etc. The equipment's operating status is automatically collected through sensors, programmable logic controllers (PLCs) and supervisory control and data acquisition systems (SCADA), and the data is converted into digital signals and uploaded to the MES system. The equipment utilization is obtained through the following formula: ; in, is the utilization rate of equipment i, is the actual working time of device i, is the available time of equipment i. Through this formula, the MES system can obtain the status of each equipment in real time and monitor its utilization rate.

[0026] Production equipment load: The MES system obtains the operating load of the equipment through integrated equipment sensors and calculates the ratio of the equipment load to its maximum load capacity. The equipment load data is updated based on real-time information during the production process to ensure that the working status of the equipment is reflected in real time. The load information is calculated using the following formula: ; in, is the load of device i, is the actual output of equipment i, is the maximum output capacity of device i.

[0027] Personnel scheduling: The MES system records and manages the personnel scheduling of each factory in real time, including each worker's work tasks, working hours, vacation status, etc. Personnel scheduling information is collected in real time through wireless radio frequency identification (RFID) systems or face recognition technology. The work status and location information of each worker is uploaded to the MES system in real time. The system automatically calculates each worker's workload and task allocation to ensure the efficiency of personnel scheduling. Personnel scheduling information is calculated using the following formula: ; in, is the workload of worker j, is the working time assigned to worker j, is the available working time of worker j.

[0028] Order progress: The MES system tracks the progress of each order in real time through integration with the enterprise resource planning system (ERP) and the order management system, including the order acceptance date, production progress, expected delivery date, and actual delivery date. This information is obtained through the automated order tracking module to ensure the accuracy and timeliness of order progress data. The order demand data is expressed by the following formula: ; in, For order completion, is the actual production volume, Based on the demand for orders and by calculating the order completion rate, the MES system can adjust production tasks in real time to ensure on-time delivery.

[0029] Data upload and storage: After all real-time data is collected, calculated and processed, it is uploaded to the central database or cloud platform for storage through the unified data transmission module of the MES system. The data storage format is unified to support subsequent data analysis and processing. The data collection module verifies all collected data in real time to ensure the integrity, accuracy and consistency of the data. The data storage method is achieved through the following methods: ; in, is the sum of all real-time production data, is the real-time production data of factory k, where k is the total number of factories. In this way, the MES system can realize centralized storage and rapid query of data for subsequent scheduling optimization and capacity forecasting.

[0030] Module 2: Factory capacity forecast module, combined with the attached Figure 3 , use data analysis algorithms to predict the production capacity demand of each factory, generate the predicted value of the production capacity demand of each factory, and dynamically adjust the prediction model according to historical production data, equipment status and market trends.

[0031] Capacity demand forecasting includes historical data processing and forecasting based on the weighted average of historical data and real-time data.

[0032] Historical data processing: In the prediction process, the historical production data must first be processed, including removing noise, filling missing values, and correcting outliers. It consists of the factory's production records, including equipment utilization, production equipment load, personnel scheduling, and order progress.

[0033] Forecast based on weighted average of historical data and real-time data: Based on historical data and the real-time data of the current factory, the capacity demand forecast value is generated by weighted average. The forecast formula is as follows: ; in, is the predicted capacity demand of factory k at time point t, is a smoothing factor used to balance the impact of historical data and real-time data. is the predicted capacity value at the previous moment, is the real-time production data of factory k, is the weight factor of historical data, is the historical production data of factory k. This formula combines the weighted average of historical production data and real-time production data. and The value of enables the model to adapt to changes in actual production and accurately predict future production capacity requirements.

[0034] Adjustment of prediction model: During the production process, the MES system will collect data such as equipment operation status, personnel scheduling, and production progress in real time, and provide real-time feedback to the prediction model. Whenever these data change, the model will be adjusted based on the feedback results. For example, when the equipment load is higher than expected, or the production progress lags behind, the model needs to be dynamically adjusted to reflect these changes. Feedback adjustment formula: Assume that the error between the model's predicted value and the actual capacity is , the feedback mechanism is adjusted by the following formula: ; in, is the prediction error of plant k, is the predicted capacity demand value of factory k, is the actual production capacity of factory k, Based on the error value, the system corrects the prediction by adjusting the parameters of the model. For example, if the prediction error is large, the weight of historical data or real-time data needs to be increased to reduce the error of future predictions. Through real-time data feedback, the prediction model can learn automatically. Specifically, the prediction model can be updated through the back-propagation algorithm. Every time new production data is received, the model calculates the error and updates the weight, so that the model can continuously adapt to the new production environment. For example, the model can identify the complex relationships between variables such as equipment status, production progress, and personnel scheduling, and by optimizing its internal parameters, the model's prediction accuracy for long time series is continuously improved.

[0035] Market trends: Fluctuations in market demand and raw material prices directly affect the forecast of production capacity demand. Therefore, it is necessary to integrate market data into the model and adjust the forecast results by analyzing market trends. For example, when market demand increases, the production capacity forecast value can be increased accordingly, and vice versa. The changing trend of market data can be modeled through regression analysis or time series analysis, and the parameters of the capacity forecasting model can be automatically adjusted according to market changes. The specific market trend adjustment formula is as follows: ; in, is the adjusted forecast value of factory k’s production capacity based on market demand, is the weight factor of market data.

[0036] Module 3: Production Scheduling Module, combined with the attached Figure 4 ,The model automatically generates cross-factory production scheduling plans based on the ,capacity demand forecast value, and transmits the production scheduling plans to the ,MES system of each factory. The MES system generates specific ,production tasks based on the production scheduling plans, and executes the ,production tasks and updates the production status.

[0037] The establishment of the scheduling optimization model is based on the predicted value of production capacity demand. The goal of the model is to automatically generate the optimal production scheduling plan based on factors such as production demand, equipment load, personnel scheduling, order priority, etc. of each factory. The optimization model mainly includes the following key steps: 1) Determine the optimization goal. The optimization goal is usually to minimize production costs, including equipment use costs, labor costs, material transportation costs, etc.; maximize resource utilization, ensure efficient use of production resources such as equipment and personnel; reduce production cycles, shorten production cycles and improve production efficiency through reasonable task arrangements. The objective function can be expressed as: ; Where Z is the total production cost, is the production cost associated with factory k, is the dispatch quantity of factory k, 2) Determine the constraints. When establishing a scheduling optimization model, various constraints in the production process must be considered, including: the maximum capacity constraint of each factory, to ensure that the production capacity of each factory will not be overloaded; equipment utilization constraint, the production tasks of the equipment need to be scheduled according to the actual equipment available time and load; personnel scheduling constraints, the personnel of each factory need to be reasonably arranged according to the task requirements to avoid overtime work or excess personnel; order delivery date constraints, the scheduling plan must ensure that the customer's order requirements are completed on time, the formula is: ; in, is the maximum production capacity of factory k, is the maximum scheduling quantity of factory k. These constraints ensure the feasibility of the production scheduling plan while optimizing the priority of production tasks, resource utilization and maximization of production capacity.

[0038] 3) Model solution: The solution of the scheduling optimization model adopts optimization algorithms such as linear programming (LP) or integer programming (IP). These algorithms can efficiently solve the production task arrangement of each factory and ensure the optimal allocation of resources. In practice, it may be necessary to combine heuristic algorithms or genetic algorithms (GA) to deal with complex multi-objective optimization problems. The specific steps of solving the model are as follows: input data, input the predicted value of capacity demand, the production capacity of each factory, the availability of equipment and personnel, the priority of orders and delivery time and other data into the optimization model; optimize the calculation, by solving the objective function, calculate the optimal production scheduling plan; output the scheduling plan, generate a specific production scheduling plan, including the production tasks, production sequence, resource allocation and other information of each factory.

[0039] 4) Generate a production scheduling plan. The production scheduling plan includes the production task arrangement, equipment scheduling, personnel scheduling, material distribution, etc. of each factory. The key contents of the scheduling plan include: task allocation, each production task is assigned to a specific factory and equipment to ensure that production is completed on time; production sequence, arrange the production sequence of each factory to avoid resource conflicts and ensure production continuity; resource allocation, reasonably allocate production resources according to the equipment utilization and personnel load of each factory to maximize resource utilization.

[0040] The generated scheduling plan can be delivered to the MES system of each factory in the following format: Production scheduling plan = {task, production plant, equipment, personnel, production sequence, priority, delivery date}.

[0041] Transmission and execution of production scheduling plans: Once a scheduling plan is generated, the MES system transmits the plan to each factory. After receiving the scheduling plan, the MES system will generate specific production tasks based on the plan content and execute production according to the actual production conditions and resource allocation of the factory. The MES system automatically generates specific production tasks based on the production scheduling plan and automatically allocates resources based on the task content. The task generation process includes the following: Task content definition: the specific content of the production task, such as production quantity, production process requirements, required equipment, etc. Resource allocation: Allocate resources based on equipment availability, staffing, material inventory, etc.; Production planning and scheduling: Assign tasks to specific production lines and shifts, and determine the production sequence.

[0042] Execute production tasks: Once a production task is generated, the MES system will start the production line and execute the task. During the production process, the MES system will monitor the progress of the task in real time and update the task status based on the actual execution status.

[0043] The execution progress of the production task is updated by the following formula: ; in, is the new progress of task a, is the old progress of task a, is the progress adjustment of task a, It is a smoothing factor used to adjust the update speed of production tasks.

[0044] Module 4: Dynamic scheduling optimization module. During the execution of the production task, the MES system adjusts the scheduling plan according to the real-time data in the production process, generates a new scheduling plan, analyzes the new scheduling plan through the system feedback mechanism, and optimizes the scheduling optimization model based on the analysis results.

[0045] New scheduling plan: When the system receives real-time feedback data from various factories during the execution of production tasks, the scheduling optimization module will automatically adjust the scheduling plan based on these real-time data, for example: Equipment failure: When a device fails, the system will adjust the production task of the device and assign the task to other available devices to avoid delays in production progress; Production progress is lagging. If the production task progress lags behind expectations, the system will speed up the production progress by rescheduling the production sequence, adjusting working hours or increasing manpower; Staff absence: If a worker is absent or the production line is understaffed, the system will reschedule production tasks and adjust staff allocation based on the scheduling of the remaining staff; Order demand changes. If market demand or order volume changes, the system will adjust the priority of production tasks to meet the new demand.

[0046] Based on these changes, the MES system adjusts the scheduling plan based on real-time data, for example, when equipment load When it is higher than expected, the system reduces the load by adjusting the task allocation of the equipment. The adjustment formula is: ; in, For the new task priority, is the original task priority, is the actual load of device i, is the expected load, is the adjustment factor.

[0047] Based on the feedback and adjustment of real-time data, the system automatically generates a new scheduling plan and reallocates production tasks, adjusts equipment load, adjusts workers' working hours and tasks, etc. The new scheduling plan will reflect all changes in the production process, ensuring that production tasks can be completed on time and maximizing resource utilization efficiency.

[0048] Scheduling plan analysis: During the execution of production tasks, the system will collect execution results in real time through a feedback mechanism. These feedback data will be used to analyze whether the current scheduling plan is effective and help the system identify problems in the production process (such as equipment failures, production delays, etc.). Feedback data includes: Production progress, task completion and delays; Resource usage: usage of equipment, personnel and materials; Production bottlenecks: Which tasks or links have bottlenecks, causing production delays.

[0049] Through these feedback data, the system can analyze the actual results of production task execution and judge the effectiveness of the scheduling plan. If the system finds that the current plan cannot meet production requirements or there are problems, it will readjust the scheduling plan.

[0050] By analyzing the feedback data of production status, the MES system can evaluate the effect of the adjusted scheduling plan. The specific analysis steps include: Differences from forecasts: compare the actual production progress with the forecasted progress, calculate the error and analyze the reasons; Resource utilization efficiency: Analyze the use of equipment and personnel to evaluate whether resources are fully utilized; Bottleneck analysis: Identify bottlenecks in the production process through feedback data and analyze the causes of the bottlenecks.

[0051] Based on the feedback analysis results, the MES system will optimize the scheduling optimization model. The optimization process makes the scheduling plan more flexible and accurate by adjusting model parameters or updating algorithms. For example, by introducing dynamic learning algorithms (such as deep learning, reinforcement learning, etc.), the MES system can make adaptive adjustments based on historical feedback data and real-time data, thereby improving the accuracy of the scheduling model and production efficiency.

[0052] The present invention proposes an industrial MES monitoring system with data interaction function, which ensures the smooth execution of production tasks through real-time data collection, dynamic adjustment of scheduling schemes and feedback mechanism, and can automatically optimize the scheduling scheme according to real-time changes in the production process. Through this adaptive adjustment mechanism, production resources are optimally configured, production efficiency is improved, and costs are effectively controlled. This method provides an efficient and intelligent solution for cross-factory production capacity coordination management.

[0053] The present invention provides an industrial MES monitoring system with data interaction function, which aims to optimize the execution process of production tasks, improve production efficiency and reduce costs through dynamic scheduling and real-time data feedback. Compared with the existing technology, the present invention has significant advantages, and can adjust production tasks, equipment and personnel scheduling in real time, and optimize through feedback mechanism during the production process, thereby effectively improving capacity utilization and reducing production cycle and production cost.

[0054] First, the MES system collects real-time data from each factory and stores it. Then, it predicts the production capacity demand of each factory through the weighted average method, and dynamically adjusts the prediction model in combination with historical production data, equipment status and market trends. This process improves the adaptability of the prediction to complex and changeable production environments through the self-learning ability of the model. The scheduling optimization model automatically generates a scheduling plan based on the predicted value of production capacity demand. After the generated scheduling plan is transmitted to the MES system of each factory, the factory automatically allocates resources according to the plan and according to the actual production situation. The factory adjusts the priority and production sequence of the task according to the actual execution situation. When there are problems such as equipment failure, delayed production progress, and absent personnel, the scheduling plan is automatically adjusted. This adaptive adjustment enables the production process to respond quickly to emergencies and ensure that production tasks are completed on time.

[0055] In summary, the advantages of the present invention lie in its dynamic adjustment capability and adaptive optimization mechanism. It can automatically adjust production tasks according to real-time data and continuously optimize through a feedback mechanism to ensure that the production process is more efficient, flexible and accurate. In particular, when facing changes in the production environment, it can respond quickly, minimize production delays and optimize resource utilization. The present invention provides an efficient and intelligent solution for cross-factory production capacity coordination management.

[0056] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An industrial MES monitoring system with data interaction function, characterized in that: The system includes: Module 1: Factory status collection module, which monitors the production status, equipment capacity, personnel scheduling and order requirements of each factory in real time through the MES system, and generates real-time data including equipment utilization, production equipment load, personnel scheduling and order progress according to the production status, equipment capacity, personnel scheduling and order requirements of each factory; Module 2: Factory capacity forecasting module, which uses data analysis algorithms to forecast the capacity demand of each factory based on the real-time data, generates forecast values ​​of the capacity demand of each factory, and dynamically adjusts the forecasting model based on historical production data, equipment status and market change trends; Module 3: Production scheduling module, which establishes a scheduling optimization model. The model automatically generates a cross-factory production scheduling plan based on the predicted capacity demand value. The MES system transmits the production scheduling plan to each factory. The MES system generates specific production tasks based on the production scheduling plan, and executes the production tasks and updates the production status. Module 4: Dynamic scheduling optimization module. During the execution of the production task, the MES system adjusts the scheduling plan according to the real-time data in the production process, generates a new scheduling plan, analyzes the new scheduling plan through the system feedback mechanism, and optimizes the scheduling optimization model based on the analysis results.

2. An industrial MES monitoring system with data interaction function according to claim 1, characterized in that: The formula for equipment utilization is: ； in, is the utilization rate of equipment i, is the actual working time of device i, is the available time of device i, The production equipment load is calculated by the following formula: ； in, is the load of device i, is the actual output of equipment i, is the maximum output capacity of device i, The calculation formula for the personnel dispatch situation is: ； in, is the workload of worker j, is the working time assigned to worker j, is the available working time of worker j, The calculation formula for the order progress is: ； in, For order completion, is the actual production volume, is the order quantity, All real-time data is collected, calculated and processed and then stored in the MES system. The formula is: ； in, is the sum of all real-time production data, is the real-time production data of factory k, and k is the total number of factories.

3. The industrial MES monitoring system with data interaction function according to claim 1 is characterized in that: The capacity demand forecast includes historical data processing, and forecasting based on the weighted average of historical data and real-time data. The historical data processing: the historical production data is processed, including removing noise, filling missing values ​​and correcting outliers. It consists of the factory's production records, including equipment utilization, production equipment load, personnel scheduling, and order progress. The prediction based on the weighted average of historical data and real-time data: Based on the historical data and the real-time data of the current factory, the capacity demand forecast value is generated by weighted average. The prediction formula is as follows: ； in, is the predicted capacity demand of factory k at time point t, is a smoothing factor used to balance the impact of historical data and real-time data. is the predicted capacity value at the previous moment, is the real-time production data of factory k, is the weight factor of historical data, is the historical production data of factory k.

4. The industrial MES monitoring system with data interaction function according to claim 3 is characterized in that: The dynamic adjustment prediction model is that during the production process, the MES system will collect real-time data and feed it back to the prediction model. When the real-time data changes, the model will be adjusted according to the feedback results. The formula is: ； in, is the prediction error of plant k, is the predicted capacity demand of factory k, is the actual production capacity of factory k, According to the error value ,The system corrects the prediction by adjusting the parameters of the model, and the ,prediction model can learn automatically through real-time data feedback.

5. The industrial MES monitoring system with data interaction function according to claim 4 is characterized in that: Integrate market data into the model and adjust the forecast results by analyzing market trends. The formula is: ； in, is the adjusted forecast value of factory k’s production capacity based on market demand, is the weight factor of market data.

6. The industrial MES monitoring system with data interaction function according to claim 5 is characterized in that: The scheduling optimization model automatically generates a cross-factory production scheduling plan based on the predicted capacity demand value. The steps of the scheduling optimization model are: 1) Determine the optimization goal, maximize resource utilization, and reduce production cycle; the optimization objective function is: ； Where Z is the total production cost, is the production cost associated with factory k, is the dispatch quantity of factory k 2) Determine the constraints, including the maximum capacity constraint of each factory, equipment utilization constraint, personnel scheduling constraint, and order delivery date constraint; the formula is: ； in, is the maximum production capacity of factory k, is the maximum dispatch quantity of factory k, 3) Model solution: The specific steps are: input the predicted value of capacity demand, the production capacity of each factory, the availability of equipment and personnel, the priority of orders and the delivery time into the optimization model; calculate the optimal production scheduling plan by solving the objective function; 4) Generate a production scheduling plan. The content of the scheduling plan includes: task allocation, production sequence, resource allocation, and the generated scheduling plan is transmitted to the MES system of each factory in the following format: Production scheduling plan = {task, production plant, equipment, personnel, production sequence, priority, delivery date}.

7. The industrial MES monitoring system with data interaction function according to claim 1 is characterized in that: The transmission and execution of the production scheduling plan. After the scheduling plan is generated, it is transmitted to each factory. After the factory's MES system receives the scheduling plan, it will generate specific production tasks according to the content of the plan. The generation process is specifically as follows: 1) Task content definition, define the specific content of the production task, 2) Resource allocation, 3) Production planning, assigning tasks to specific production lines and shifts, and determining the production sequence 4) Execute production tasks. The MES system starts the production line and executes the tasks. During the production process, the MES system monitors the progress of the tasks in real time and updates the task status based on the actual execution status. The execution progress of the production task is updated by the following formula: ； in, is the new progress of task a, is the old progress of task a, is the progress adjustment of task a, It is a smoothing factor used to adjust the update speed of production tasks.

8. An industrial MES monitoring system with data interaction function according to claim 7, characterized in that: The scheduling optimization module automatically adjusts the scheduling plan according to real-time data. The formula is: ； in, For the new task priority, is the original task priority, is the actual operation data of device i, For expected data, is the adjustment factor.

9. The industrial MES monitoring system with data interaction function according to claim 1 is characterized in that: The scheduling plan analysis, during the execution of production tasks, the system will collect the execution results in real time through the feedback mechanism. The feedback data includes production progress, resource usage, and production bottlenecks. Through the feedback data, the system analyzes the actual effect of the execution of production tasks. By analyzing the feedback data of production status, the MES system evaluates the effect of the adjusted scheduling plan. The specific analysis steps include: 1) Differences from forecasts, comparing the differences between actual production progress and forecast progress, 2) Resource utilization efficiency, analyzing the use of equipment and personnel, 3) Bottleneck analysis: identifying bottlenecks in the production process through feedback data.

10. An industrial MES monitoring system with data interaction function according to claim 1 or 9, characterized in that: The scheduling optimization model is optimized. Through the scheduling solution analysis, the MES system will optimize the scheduling optimization model. The optimization process is achieved by adjusting model parameters and updating algorithms.

Images