An intelligent ring main unit automatic production control system and production control method

Abstract

The present application relates to the field of intelligent manufacturing technology, and discloses an intelligent ring network cabinet automatic production control system and production control method. The system includes: a data acquisition and preprocessing module, which is used to collect equipment status, task progress, and material supply data in the production process in real time, and preprocess the data; a multi-stage recursive optimization scheduling module, which is used to generate production scheduling decisions based on preprocessed data, and recursively optimize at each production stage to minimize the total production time and maximize production efficiency; the method includes: real-time collection of production equipment status, task progress, and material supply information, and preprocessing the collected data. The present invention adopts a real-time data acquisition and preprocessing technical solution based on Internet of Things devices, sensors, and production management software, achieving the technical effect of real-time and accurate collection of key data such as equipment status, task progress, and material supply in the production process.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to an intelligent ring network cabinet automatic production control system and a production control method. Background Art

[0002] In traditional production systems, the production process of ring main units usually relies on manual scheduling and traditional control systems, resulting in low production efficiency, waste of resources, and low equipment utilization. Existing production control methods are mostly based on static scheduling, lacking flexibility and intelligence, and unable to quickly respond to dynamic changes in production, such as equipment failures, material supply delays, etc. The optimization of the production scheduling process also mostly relies on manual decision-making or relatively simple algorithms, which cannot achieve coordination and cooperation among various links, and therefore cannot guarantee the efficient use of production resources and the improvement of overall production efficiency.

[0003] At the same time, traditional production systems are difficult to fully tap the potential of data. Data collection usually has information islands, resulting in insufficient timeliness and integrity of data. This makes it impossible to accurately monitor the status of the production process and effectively predict potential production bottlenecks and equipment failures. Due to the lack of a unified coordination mechanism, resource competition and conflicts between devices are more serious, resulting in instability and inefficiency in system operation.

[0004] Therefore, the existing technology has the following deficiencies: first, there is a lack of intelligent scheduling and decision support systems, and the production process cannot adapt to changes quickly; second, resource allocation is unreasonable, and the collaborative work between equipment is not effective, which easily leads to resource competition and equipment idleness; finally, data processing efficiency is low, and real-time data cannot be fully utilized for decision optimization, resulting in the inability to maximize production efficiency.

[0005] Therefore, the present invention proposes an intelligent ring main unit automatic production control system and a production control method to solve the deficiencies of the prior art. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides an intelligent ring main unit automatic production control system and a production control method, which solve the problems of low production efficiency, resource competition and inflexible scheduling response in the prior art.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent ring main unit automatic production control system, comprising: Data collection and preprocessing module, used to collect equipment status, task progress, and material supply data in real time during the production process, and preprocess the data; A multi-stage recursive optimization scheduling module is used to generate production scheduling decisions based on preprocessed data and perform recursive optimization at each production stage to minimize the total production time and maximize production efficiency; Game theory and resource competition model module, which is used to optimize resource allocation among production equipment through game theory models and solve resource competition among multiple equipment; Mixed integer programming scheduling optimization module, which is used to accurately solve the optimization problems of task scheduling sequence and resource allocation according to the needs of production scheduling; The global coordination and execution module is used to coordinate the operation of each production equipment according to the scheduling optimization results and execute the scheduling decision; The result feedback and self-optimization module is used to provide real-time feedback on production status and optimize the production scheduling plan based on the feedback information.

[0008] Preferably, the data acquisition and preprocessing module includes: Data collection unit, used to collect real-time information on the operating status, production progress, material supply, and task execution of production equipment through sensors and IoT devices; The data preprocessing unit is used to clean, denoise and standardize the collected raw data to generate a format that meets the processing requirements of subsequent modules; The data transmission unit is used to transmit the preprocessed data to the multi-stage recursive optimization scheduling module through the industrial network.

[0009] Preferably, the multi-stage recursive optimization scheduling module dynamically adjusts the scheduling decision and performs optimization of the staged production target in each stage according to the feedback results of the previous stage.

[0010] Preferably, the multi-stage recursive optimization scheduling module includes: The stage division unit is used to divide the production scheduling process into multiple stages, and each stage is adjusted according to the execution results of the previous stage; The optimization decision unit is used to generate the optimal scheduling decision according to the production status and resource status of the current stage, and perform recursive optimization at each stage to minimize the total production time and maximize production efficiency; The inter-stage feedback unit is used to feed back the scheduling results of each stage to the next stage to adjust the production progress and resource allocation.

[0011] Preferably, the mixed integer programming scheduling optimization module includes: The task and device matching unit is used to generate the best match between the task and the device according to the processing time of the task, the load capacity of the device and the priority of the task; An objective function calculation unit, used to calculate and optimize the objective function according to the equipment scheduling sequence, task execution time and resource consumption, so as to minimize the total production time and maximize resource utilization; The constraint solving unit is used to solve the constraint optimization problem according to the equipment load, task execution sequence and equipment availability conditions.

[0012] Preferably, the global coordination and execution module includes: The scheduling decision execution unit is used to control each production equipment to execute tasks in a predetermined production sequence according to the optimized scheduling decision; Resource allocation coordination unit, used to allocate resources required for production in real time, including equipment, personnel and materials, to ensure that resources do not exceed their maximum processing capacity; The production progress monitoring unit is used to monitor the execution status of each task in the production process and adjust equipment scheduling according to the real-time progress.

[0013] Preferably, the result feedback and self-optimization module includes: The production status monitoring unit is used to collect information on the equipment operation status and task execution progress during the production process in real time to evaluate the execution effect of the current scheduling plan; Feedback data analysis unit, used to analyze the feedback data collected by the production status monitoring unit, identify bottlenecks and anomalies in the production process, and generate optimization suggestions; The self-optimizing adjustment unit is used to adjust the production scheduling strategy according to the feedback data and analysis results, and optimize the resource allocation and task execution sequence.

[0014] Preferably, the data preprocessing unit of the data acquisition and preprocessing module includes: Data cleaning unit, used to remove noise information in collected data and fill in missing data; Data standardization unit, used to standardize various types of collected data to ensure that each data type has the same dimension and is suitable for subsequent analysis; The data format conversion unit is used to convert the cleaned and standardized data into a unified format for subsequent module processing.

[0015] The present invention also provides an intelligent ring main unit automatic production control method, comprising the following steps: Collect production equipment status, task progress, and material supply information in real time, and pre-process the collected data; Based on the preprocessed data, a multi-stage recursive optimization scheduling algorithm is used to generate preliminary production scheduling decisions, and recursive optimization is performed at each stage to minimize the total production time and maximize production efficiency; Optimize resource allocation between production equipment through game theory models to solve resource competition problems between equipment; Using mixed integer programming methods, we can find the optimal match between tasks and equipment according to production scheduling requirements to ensure that all tasks can be completed on time. The global coordination module is used to optimize the scheduling results, ensuring that each device performs tasks according to the optimal solution. Through feedback information, production scheduling plans can be adjusted in real time to optimize the production process and improve production efficiency and resource utilization.

[0016] Preferably, the multi-stage recursive optimization scheduling algorithm dynamically adjusts scheduling decisions and optimizes stage-by-stage production targets by providing feedback results based on the production progress of each stage.

[0017] The present invention provides an intelligent ring main unit automatic production control system and production control method, which has the following beneficial effects: The present invention adopts a real-time data collection and preprocessing technology solution based on IoT devices, sensors and production management software, achieving the technical effect of real-time and accurate collection of key data such as equipment status, task progress and material supply in the production process. Compared with the traditional production control system that only relies on manual data recording or simple automated monitoring equipment, the present invention integrates a variety of advanced sensing technologies to eliminate the problems of high delay and poor accuracy in data collection in traditional systems, thereby improving the transparency of the production process and decision-making efficiency.

[0018] The present invention adopts a multi-stage recursive optimization scheduling algorithm to make production scheduling decisions, achieving the technical effect of maximizing production efficiency and minimizing total production time. Unlike the existing scheduling system that relies on static scheduling strategies, the present invention uses recursive optimization to dynamically adjust scheduling decisions based on feedback from each stage, effectively solving the problem of the traditional scheduling system being unable to cope with dynamic production environment changes and lacking flexibility, and improving the adaptability and intelligence level of production scheduling.

[0019] The present invention optimizes resource allocation between production equipment through a game theory model, solves the problem of multi-equipment resource competition, and achieves the technical effect of reasonable resource allocation between equipment and improved resource utilization. Compared with the technical solution of overly simple resource allocation and easy resource conflict in the traditional scheduling system, the present invention ensures the optimal behavior selection of equipment under limited resources through reasonable analysis of game theory, thereby effectively avoiding resource waste and production bottlenecks.

[0020] The present invention uses a mixed integer programming method to optimize task scheduling and resource allocation, ensuring the technical effect of efficient and timely completion of production tasks. Traditional scheduling systems may be inefficient when facing multiple devices and tasks, and have difficulty in handling complex constraints. The present invention uses precise mathematical modeling and optimization algorithms to not only achieve optimal task and equipment matching, but also effectively deal with complex constraints such as equipment load and task priority, greatly improving the accuracy of scheduling and the efficiency of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a system architecture diagram of the present invention; Figure 2 is a flow chart of the method of the present invention; Figure 3 It is a structural schematic diagram of the data acquisition and preprocessing module of the present invention; Figure 4 It is a schematic diagram of the structure of the multi-stage recursive optimization scheduling module of the present invention; Figure 5 It is a schematic diagram of the structure of the mixed integer programming scheduling optimization module of the present invention; Figure 6 It is a schematic diagram of the structure of the global coordination and execution module of the present invention; Figure 7 It is a schematic diagram of the structure of the result feedback and self-optimization module of the present invention; Figure 8 It is a structural schematic diagram of the data preprocessing unit of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings of the present invention specification to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1 , Figure 3 , Figure 4 , Figure 5 , Figure 6 , Figure 7 and Figure 8 The embodiment of the present invention provides an intelligent ring main unit automatic production control system, comprising: Data collection and preprocessing module, used to collect equipment status, task progress, and material supply data in real time during the production process, and preprocess the data; A multi-stage recursive optimization scheduling module is used to generate production scheduling decisions based on preprocessed data and perform recursive optimization at each production stage to minimize the total production time and maximize production efficiency; Game theory and resource competition model module, which is used to optimize resource allocation among production equipment through game theory models and solve resource competition among multiple equipment; Mixed integer programming scheduling optimization module, which is used to accurately solve the optimization problems of task scheduling sequence and resource allocation according to the needs of production scheduling; The global coordination and execution module is used to coordinate the operation of each production equipment according to the scheduling optimization results and execute the scheduling decision; The result feedback and self-optimization module is used to provide real-time feedback on production status and optimize the production scheduling plan based on the feedback information.

[0024] As the basic module of the intelligent ring main unit automatic production control system, the data acquisition and preprocessing module mainly collects and preprocesses the equipment status, task progress, material supply and other information involved in the production process in real time, and transmits the processed data to the subsequent optimization and scheduling module. This module ensures that the subsequent modules can make decisions with the support of accurate and complete data, and improves the intelligence level of the entire production process.

[0025] In this embodiment, the data acquisition and preprocessing module collects various key data of the production site in real time through a variety of sensors and Internet of Things technologies. The collected data includes but is not limited to: the operating status of the equipment (such as voltage, temperature, load, etc.), the execution progress of the task, the material supply status between each process, etc. The source of these data is not limited to the traditional PLC (programmable logic controller) system, but also includes sensors, RFID (radio frequency identification), cameras, temperature and humidity detectors and other equipment.

[0026] This module plays a vital role in the entire intelligent ring main unit automatic production control system. It is responsible for real-time collection and pre-processing of data such as equipment status, task progress, material supply, etc. involved in the production process, ensuring that subsequent modules can make decisions and optimizations with accurate data support, thereby improving the intelligence and automation level of the production process.

[0027] The specific implementation methods of data collection and preprocessing are as follows: Data acquisition unit data, the acquisition unit uses sensor networks and IoT devices to collect data in real time. Data acquisition includes monitoring the working status of various types of equipment. For example, temperature sensors can be used to monitor temperature changes during equipment operation, and current sensors can be used to monitor the current load of power equipment. In some embodiments, cameras or visual sensors may also be used to monitor the physical status of the device and collect data.

[0028] In some embodiments, data collection not only relies on traditional hardware devices, but also connects to cloud devices through wireless networks and uploads to the cloud platform in real time for storage and processing. The cloud platform can not only provide real-time operation data for the production process, but also perform big data analysis to further optimize production scheduling.

[0029] The data preprocessing unit plays an important role in the data collection process because the data from different sources may be noisy or missing. Specifically, the data preprocessing unit includes the following steps: Data cleaning, generally speaking, the collected data will contain noise or missing values, so it needs to be processed by a data cleaning algorithm. The main task of data cleaning is to remove invalid data (such as sensor failure data) and fill in missing data. Common cleaning methods include mean filling, median filling or using Kalman filtering.

[0030] For example, suppose a temperature sensor has an abnormality during the collection process, causing the temperature data to show a sudden change. The data cleaning algorithm can detect the abnormal value and fill it with the mean or median.

[0031] Denoising and standardization, in order to further improve data quality, the preprocessing unit will eliminate the noise that may appear during the acquisition process through a denoising algorithm. These noises may be caused by environmental factors, equipment failures or sensor errors. Common denoising methods include mean filtering, wavelet denoising and other technologies.

[0032] For the standardization part, the data units and dimensions of some sensors are inconsistent, so all data need to be converted to a unified dimension for subsequent processing. For example, temperature data can be uniformly converted to degrees Celsius and voltage units can be uniformly converted to volts.

[0033] Data conversion and formatting: To ensure that the data can be correctly processed by subsequent modules, the data must be converted. The data format conversion unit converts data from different sources (such as temperature, current, humidity, etc.) into a unified format (such as structured data formats such as JSON and XML). This step helps ensure that the data can be parsed and used smoothly in the subsequent optimization scheduling module.

[0034] During the data transmission process, the cleaned, denoised, standardized and formatted data will be transmitted to the multi-stage recursive optimization scheduling module through the industrial network (such as Ethernet, wireless network, etc.). During the transmission process, the timeliness and accuracy of the data must be ensured. In order to avoid network delays affecting the overall performance of the system, the delay time of data transmission is It needs to be controlled within an acceptable range. Specifically, the data transmission delay meets the following conditions: ; in, Indicates the data transmission delay time. The maximum delay time required by the system. Ensuring that data can be transmitted in real time is crucial for real-time decision-making of the entire production control system.

[0035] Through the design of this module, the production system can collect the operating status and production progress data of various equipment on the production site in real time. After cleaning, denoising and standardization, these data will be transmitted to the scheduling optimization module in a unified format. Real-time data processing ensures that the system can respond quickly in a changing production environment and make reasonable scheduling decisions. In addition, the control of data transmission delay ensures the efficiency and stability of the system, allowing the entire production process to proceed smoothly.

[0036] In future applications, the data acquisition and preprocessing module can be further expanded to more complex data types. For example, more accurate data collection can be performed for quality inspection during the production process by integrating higher-precision visual sensors. In this way, the system can not only monitor the operating status of the equipment, but also perform real-time quality analysis of the production products. This provides further technical support for the system's automated quality control.

[0037] In addition, in some embodiments, the data acquisition and preprocessing module can also be combined with AI technology to automatically optimize data cleaning and denoising methods through machine learning algorithms, thereby further improving the intelligence level and responsiveness of the system.

[0038] For the multi-stage recursive optimization scheduling module, in the aforementioned data collection and preprocessing module, the data such as equipment status and task progress collected during the production process are effectively cleaned, standardized and prepared for use by the subsequent optimization scheduling module. Next, enter the multi-stage recursive optimization scheduling module, whose key function is to generate reasonable production scheduling decisions based on the preprocessed data. Compared with other modules, the role of this module is not just a simple calculation schedule, but a dynamic adjustment and optimization at each production stage to maximize production efficiency and minimize total production time.

[0039] In this embodiment, the multi-stage recursive optimization scheduling module adopts a recursive optimization algorithm to continuously provide feedback and optimization for the unique conditions of each production stage. Unlike other scheduling systems, this module can respond to the feedback of the previous stage in real time at each stage, which not only solves the independent optimization problems of each stage, but also ensures the coordination between different stages, making the entire production process more efficient. Recursive optimization is not only based on previous production data, but also dynamically optimized according to new data in the production process, thus realizing a closed-loop feedback mechanism for production scheduling.

[0040] Specifically, the steps within the module include: Phase division unit, as an option, this unit divides the production process into multiple phases. The goal of each phase is to complete a series of specific tasks. These tasks not only involve equipment operation, but may also include material supply, inspection, assembly, etc. The start and end of each phase are determined by the execution results of the previous phase, ensuring that the various phases proceed in an orderly manner. For example, if the equipment failure in the previous phase is not handled in time, the system will automatically postpone the execution of the subsequent phase to avoid waste of resources or production stagnation.

[0041] Optimization decision unit, specifically, the optimization decision unit generates the optimal scheduling decision based on the production status and resource status of each stage. The decision is based on a recursive algorithm, which is calculated by minimizing the total production time and maximizing resource utilization. At each stage, the recursive algorithm adjusts the resource allocation and time arrangement of the previous stage to ensure the optimal scheduling decision.

[0042] Assume that for the stage We can establish the following optimization objectives for the optimization decision: ; in, It is Tasks during the phase Execution time; It's a task Resources used; It is the maximum available capacity of the system's resources; It is The total number of tasks in the stage; through this objective function, we try to minimize the execution time of all tasks while ensuring that the resources used by the tasks do not exceed the maximum resource capacity of the system. This optimization goal ensures that the sum of the execution time of all tasks is minimized under given resource constraints.

[0043] Inter-stage feedback unit,The function of the inter-stage feedback unit is to feedback the scheduling results of each stage to the next stage at the end of each stage. The feedback information includes the execution time, resource consumption, and task completion status of the current stage. This information will affect the scheduling decisions of subsequent stages.

[0044] For example, in some embodiments, the feedback unit records the phase The feedback unit will automatically delay the production schedule of the subsequent stages and adjust the priority of the production tasks to avoid task conflicts.

[0045] The feedback mechanism is dynamically adjusted using the following formula:

[0046] in, For the The time adjustment of the stage, which represents the The execution delay or resource consumption problem of the first stage leads to Changes in stage execution time; For the The total execution time of the phase; For the The total amount of resources consumed by the stage; It is a feedback adjustment function that determines the next Adjustment of scheduling at each stage.

[0047] Through the multi-stage recursive optimization scheduling module, the production system can adjust the production scheduling decisions of each stage in real time. The scheduling of each stage is not only based on the feedback of the previous stage, but also adjusted according to real-time data. This recursive optimization method enables the system to cope with complex and dynamically changing production environments and ensure maximum production efficiency.

[0048] In practice, this recursive optimization algorithm can dynamically adjust production tasks according to production progress and equipment status. For example, when a task equipment fails, the system can adjust the order of tasks in the subsequent stages to avoid stagnation of the entire production process due to the failure. Through this optimization, the system can not only reduce waiting time in the production process, but also make efficient use of each device and resource, reducing production costs.

[0049] In order to improve the effect of recursive optimization, we can further combine machine learning algorithms to train historical data. Through machine learning models, the system can predict risks such as equipment failure and task delays, and make adjustments in advance. This will further enhance the intelligence level of the multi-stage recursive optimization scheduling module. For example, based on historical data, the system can automatically identify which equipment is more likely to fail, so that its maintenance or replacement can be prioritized during scheduling to ensure efficient operation of the production line.

[0050] By combining cloud computing and big data technology, the recursive optimization algorithm can be further optimized. The cloud platform can collect and store large-scale production data, and use this data to analyze potential problems in the production process, providing more accurate predictions and analysis for scheduling decisions. In this way, production scheduling can not only respond quickly to actual production conditions, but also provide a more scientific basis for decision-making through big data analysis.

[0051] The multi-stage recursive optimization scheduling module provided in this implementation fully demonstrates the advantages of the intelligent production system and solves the problem that the traditional production scheduling method cannot flexibly adapt to changes in the production environment. Through recursive optimization and inter-stage feedback mechanism, the system can dynamically adjust scheduling decisions, maximize production efficiency, and ensure the smooth completion of production tasks.

[0052] Regarding the game theory and resource competition model modules, in the first two modules of the intelligent ring main unit automatic production control system, we have provided a reliable input and scheduling framework for the production process through data collection, preprocessing and recursive optimization scheduling. However, with the increase of complex interactions and resource competition between devices, the system must be able to optimize the resource allocation between multiple devices to ensure that various production tasks can be completed smoothly. The core goal of this module is to optimize the resource allocation between production equipment through the game theory model and solve the resource competition problem that may arise between multiple devices.

[0053] In this embodiment, the game theory and resource competition model module ensures that each device can effectively allocate resources throughout the production process and avoid resource conflicts by simulating the game between devices. The system first establishes a resource consumption model for each device, and then analyzes the behavior decisions of each device under the current resource allocation through game theory. Finally, the system optimizes resource allocation by calculating the optimal strategy for each device to achieve global optimization.

[0054] Specifically, this module includes the following core steps: Game participant model, each device is regarded as an independent "participant" in the game theory model. Each participant (device) has a utility function, which describes the "benefit" or "satisfaction" of the device under the current resource allocation. The goal of the device is to maximize its own utility by choosing the optimal strategy.

[0055] equipment The utility function Profits from tasks completed by equipment and resource consumption costs The general form of the utility function is: ; in, For equipment The utility function represents the “satisfaction” of the device under the current resource allocation; For equipment The benefits of completing a task are usually calculated based on the quality, efficiency, or production goals of the task; For equipment Resource consumption, including equipment operating time, electricity used, consumables, etc. For equipment The resource consumption weight coefficient reflects the sensitivity of the device to resource consumption and is usually determined by the energy efficiency of the device and the importance of the task.

[0056] For example, equipment When a welding task is completed, can be a quality rating of the task completed, and This is the amount of electricity used by the device. , which can control the degree of attention paid by each device in the system to resource consumption.

[0057] Game theory strategy and optimal solution. The core of the game model is to find the "Nash equilibrium" point, that is, each device cannot increase its utility by unilaterally changing its own strategy when the strategies of other devices are fixed. The optimal strategy of the device should meet the following conditions: ; in, For equipment The optimal strategy represents the best behavior choice of the device in the current environment; To remove the equipment The policy set of other devices indicates the policies selected by other devices; On the device Select strategy When, equipment The utility of On the device Select strategy When, equipment The utility of.

[0058] In this way, the game model can calculate how each device chooses its own behavior strategy given resources and tasks, so as to achieve optimal allocation of resources and avoid excessive competition for resources.

[0059] Resource Allocation Strategy,Resource allocation is the key link in this module. In the game model, devices compete for resources by choosing different,strategies, and the system must make reasonable allocations based on device requirements and,resource availability. To this end, we represent the resource requirements of each,device as a vector: ; in, For equipment The resource requirement vector of the device The demand for resources, including is the number of resource types; For equipment For The amount of resources required is usually determined by the nature of the task and the capabilities of the equipment. Maybe the device The demand for electricity, It may be the demand that the equipment places on workers’ operating time.

[0060] The goal is to calculate the optimal resource allocation plan for each device based on the game model. By minimizing resource consumption and ensuring that production tasks are completed on time, the optimization objective function of resource allocation is: ;in, The number of devices participating in the game; For equipment About Resources The consumption weight of each resource indicates the sensitivity of the device to each resource. For equipment About Resources Quantity of demand; The number of resource types in the system.

[0061] The objective function is to adjust the resource consumption weight of the device , optimize the needs of each device for different resources, minimize the overall resource consumption, and meet the production task requirements of all devices.

[0062] Collaborative work and multi-device scheduling, when multiple devices work together, their resource requirements and scheduling will affect each other. In some embodiments, the system calculates the synergy of each device based on the game theory model, and optimizes the allocation of tasks and the scheduling order of devices based on the synergy. The synergy of the device can be expressed by the following formula: ; in, For equipment and equipment The joint utility between them represents the total utility when the two devices work together; , For equipment and equipment The individual utility of For equipment and equipment The weight coefficient of the collaborative work between them indicates the value of their collaborative work; For equipment and equipment The incremental benefits of working together may depend on their mission types and equipment capabilities.

[0063] Through the game theory and resource competition model module, the production system can optimize the resource allocation of production tasks according to the game theory method to avoid resource conflicts between multiple devices. This optimization not only improves the utilization of system resources, but also ensures that tasks are completed on time.

[0064] The introduction of game theory models makes the interaction between devices more intelligent, able to find a balance between competition and collaboration and maximize production efficiency. Through real-time feedback and dynamic adjustment, the system can continuously optimize resource allocation and adapt to changes in the production environment.

[0065] As technology continues to develop, this module can be further combined with intelligent algorithms, such as deep reinforcement learning (DRL), so that the equipment can automatically optimize decisions through learning and experience accumulation during the game process. Future systems can continuously improve resource allocation strategies through self-learning to further improve the intelligence level and adaptability of production systems.

[0066] In addition, with the promotion of Industry 4.0, game theory and resource competition model modules can be combined with the Internet of Things and big data analysis. By real-time monitoring of equipment status and production data, the system can quickly adapt to various changes in the production environment and improve the system's response speed and decision-making accuracy.

[0067] Regarding the mixed integer programming scheduling optimization module, in the intelligent ring main unit automatic production control system, the previous module optimizes the allocation of resources between devices through the game theory model. However, in actual production, the complexity of the scheduling problem is far more than resource allocation. The order of tasks, the task allocation of equipment, and the optimization of resource utilization are the key links to ensure the efficient operation of the production system. In order to better solve this problem, this module introduces the mixed integer programming (MIP) method to accurately solve the optimization problem of task scheduling order and resource allocation.

[0068] In this embodiment, the mixed integer programming scheduling optimization module transforms the problem into a mathematical programming problem by deeply modeling the production scheduling requirements, and uses the optimization algorithm to solve the optimal solution. This module can not only handle the constraints of task scheduling and resource allocation, but also dynamically adjust between multiple devices and tasks to ensure that each task in the production process is completed on time and efficiently.

[0069] The main components and functions of this module include: Task and Equipment Matching Unit,In general, tasks in production usually have different execution times, priorities, and resource requirements,,while the load capacity and availability of equipment vary.,The matching problem between tasks and equipment is a key issue in scheduling,optimization. The goal of this unit is to generate the optimal match between,tasks and equipment based on the processing time of each task, the load capacity of the equipment,and the priority of the task.

[0070] Specifically, the task Assigned to device The goal is to maximize the utilization of the equipment and minimize the overall production time without violating the constraints. is a binary decision variable, representing the task Is it assigned to the device? , then the matching between tasks and devices can be described by the following optimization objectives: ;in, For the task On the device Execution time on is a binary variable, indicating the task Is it assigned to the device? ; is the number of tasks; The number of devices.

[0071] Constraint solving unit, the constraints in the production scheduling process include equipment load, task pre-requisites, and equipment availability. In this unit, we solve the optimal scheduling solution based on these constraints. The following are common constraints and their mathematical representations: Device load constraints: the load of each device cannot exceed its maximum processing capacity. Assigned to device , then the device The load should not exceed its maximum load . This constraint can be expressed as: ; in, For equipment The maximum load capacity indicates the maximum workload that the equipment can withstand in a specific period of time; For the task On the device Resource consumption on is a binary decision variable, representing the task Is it assigned to the device? .

[0072] Task precedence constraints: some tasks must be completed before they can be executed. To this end, the system needs to arrange the execution order of tasks based on the task precedence. Must be on task Completes before completion, then the constraint is: ; in, For the task completion time; For the task completion time; predecessor_set is the set of predecessor relationships between tasks, indicating the dependency relationship between tasks.

[0073] Dynamic scheduling adjustment, in addition to static task and equipment matching and resource allocation, the system also needs to make dynamic adjustments based on task progress and emergencies that occur during the production process. For example, equipment failure may lead to adjustments to the scheduling plan. The goal of this unit is to adjust the execution order of tasks based on feedback information, reallocate equipment and resources, and ensure the smooth progress of production tasks.

[0074] The dynamic adjustment is described by the following formula:

[0075] in, is the adjusted task execution time; The currently calculated task execution time; It is the time adjustment amount caused by task delay, equipment failure, etc.

[0076] By introducing the mixed integer programming scheduling optimization module, the production system can more accurately solve the scheduling and resource allocation problems between multiple devices and multiple tasks. This module can consider multiple complex constraints, including equipment load, task priority, resource consumption, etc., to optimize the overall production plan and ensure efficient use of resources.

[0077] In actual applications, this module can effectively reduce the idle time of equipment and improve the overall equipment utilization rate through precise optimization calculations. In addition, the system can make real-time adjustments to problems such as equipment failures and task delays that may occur during the production process to ensure that the production progress is not affected.

[0078] With the development of intelligent manufacturing technology, the mixed integer programming scheduling optimization module can combine deep learning and big data analysis technology to enable the system to automatically learn changes in the production environment and thus self-optimize the scheduling strategy during the production process. In addition, by combining with the Internet of Things technology, the system can monitor the status of equipment in real time, further improving the intelligence and adaptability of scheduling.

[0079] This implementation provides an accurate scheduling optimization solution through a mixed integer programming scheduling optimization module, ensuring that the production system can operate efficiently and stably under the coordination of multiple tasks and equipment.

[0080] Regarding the global coordination and execution module, in the above modules, we have optimized the resource allocation and task arrangement in production scheduling through game theory, resource competition model and mixed integer programming optimization scheduling. However, these optimization strategies alone are not enough to complete the efficient execution of production tasks. In order to implement the optimized scheduling plan into the specific production equipment operation, the scheduling decision must be converted into actual production actions through the global coordination and execution module.

[0081] The global coordination and execution module receives the decision results from the scheduling optimization module, coordinates the operation of each production equipment, and ensures that the production tasks are carried out smoothly according to the optimization plan. This module not only needs to solve the equipment scheduling problem, but also needs to consider the reasonable allocation of resources, task progress monitoring and real-time adjustment to ensure that the tasks in the production process are not delayed, the equipment load is reasonable, and the resource consumption is minimized.

[0082] This module mainly includes the following key units: The scheduling decision execution unit is responsible for converting the task execution sequence and time arrangement generated by the scheduling optimization module into actual equipment operation. The task execution sequence of the equipment must meet the requirements of the scheduling optimization plan to ensure the smoothness of the production process. In this process, the task start time and completion time of the equipment must be accurately calculated and coordinated.

[0083] The task execution time for each device is calculated according to the following formula: ; in, For the task On the device The start time on the task indicates the time when the task starts to execute; For the task On the device The completion time on the task indicates the time when the task execution ends; For the task Completion time, task The start time of a task usually depends on the end time of the previous task; For the task On the device The execution time is usually determined by the operating speed of the device and the complexity of the task.

[0084] Through the scheduling decision execution unit, the system can ensure that tasks are assigned to equipment in the optimal order and time window, ensuring the efficient operation of the equipment.

[0085] Resource Allocation Coordination Unit,The main task of the resource allocation coordination unit is to allocate resources in real time according to the load capacity of the equipment, the priority of the task and the scheduling decision. Resources include equipment time, personnel time, materials, consumed energy, etc. This unit ensures that the system will not cause production delays or efficiency declines due to resource shortages or excessive consumption.

[0086] The system is based on the load capacity of the equipment and the resource requirements of the task on the device Dynamic adjustment is performed. The resource allocation constraint is expressed by the following formula: ; in, is a binary variable. If the task Assigned to device ,but ,otherwise ; For the task On the device Resource consumption on the task indicates the amount of resources required to perform the task (such as electricity, equipment time, materials, etc.); For equipment The maximum load capacity indicates the maximum amount of resources that the device can handle per unit time; is the total number of tasks, indicating the number of all tasks to be executed in the system; is the total number of devices, indicating the number of all available devices in the production system.

[0087] Through these constraints, the system can ensure that the load of each device does not exceed its maximum load and allocate resources reasonably to avoid resource overload or waste.

[0088] The production progress monitoring unit is responsible for tracking the execution status of each task in real time to ensure that the task is carried out as planned. If a task is delayed due to equipment failure or other reasons, the monitoring unit will dynamically adjust according to the real-time status of the task.

[0089] In this embodiment, if the device On mission Time delayed , the new task start time and completion time will be adjusted according to the delay time. The specific adjustment formula is as follows: ; in, For the adjusted tasks On the device The start time on For the adjusted tasks On the device Completion time on For equipment Delay in performing a task, usually caused by equipment failure or other reasons that delay the production schedule.

[0090] By dynamically adjusting task times, the system can ensure that production tasks can be completed as on time as possible in the face of emergencies, thereby avoiding the impact of delays on the overall production progress.

[0091] Real-time feedback and adjustment: In order to further improve the flexibility and response speed of production, the production progress monitoring unit continuously provides real-time feedback to the scheduling system to adjust the production plan. Whenever new data (such as equipment failure, task completion, etc.) appears in the production process, the system will make real-time adjustments based on this feedback information to better meet production needs.

[0092] The feedback adjustment is updated by the following formula: ; in, is the adjusted time change, which indicates the amount of time the scheduling plan needs to be adjusted according to the change in resource demand during task execution; Binary decision variables, representing tasks Is it assigned to the device? , if the task Assigned to device , ;otherwise ; For tasks on the device The initial resource demand on the device indicates the amount of resources (such as electricity, raw materials, device time, etc.) required for the task on the device; The resource requirements are updated according to the feedback information, which may be caused by the change of the task execution status; is the total number of tasks, indicating the number of tasks that need to be scheduled; is the total number of devices, indicating the number of available devices.

[0093] Through the global coordination and execution module, the production scheduling system can ensure that each device in the production process performs tasks on time and efficiently, avoiding equipment idleness or overload. In the face of emergencies such as equipment failure and task delays, the system can quickly respond and correct the production plan through real-time monitoring and dynamic adjustment, to maximize the smooth progress of production tasks.

[0094] For example, when the device On mission If a failure occurs, the production progress monitoring unit will capture the delay and provide feedback within the system to automatically adjust the task. start time, thus avoiding delays in the entire production process.

[0095] With the advancement of industrial automation and intelligent manufacturing technology, this module can further combine artificial intelligence technology, especially machine learning and reinforcement learning, to adaptively optimize production scheduling by continuously learning changes in the production environment. In addition, combined with big data analysis, the system can obtain more production data in real time, further improving the accuracy and response speed of scheduling decisions.

[0096] In future implementations, the system can also be combined with 5G communication technology to achieve more efficient communication between equipment and scheduling systems, reduce delays, and further improve the real-time and accuracy of production scheduling.

[0097] The global coordination and execution module ensures that every task in the production process can be completed on time and efficiently by precisely controlling the task execution sequence of production equipment, monitoring the production progress in real time, and dynamically adjusting according to feedback information. This module ensures the flexibility, intelligence and efficiency of the production system, and can respond quickly when emergencies occur, thereby keeping the production progress unaffected.

[0098] Regarding the result feedback and self-optimization module, in the previous module, we have discussed technical solutions for task scheduling, resource allocation, and equipment collaboration. However, a single static optimization decision is not enough to cope with the dynamic changes that may occur in the production process. The production environment often has uncertain factors such as equipment failure, resource shortages, or emergencies. Therefore, the system must have the ability to monitor and self-optimize in real time to ensure the efficiency of the production plan in a dynamic environment.

[0099] In this embodiment, the core task of the result feedback and self-optimization module is to dynamically adjust the scheduling and resource allocation based on the real-time production status feedback information. This module is not only responsible for real-time monitoring of deviations in the task execution process, but also needs to analyze the bottlenecks of the current production status based on the collected data and generate optimization suggestions to promote the continuous improvement of scheduling decisions. Specifically, this module effectively cooperates with the aforementioned scheduling optimization module through a feedback loop to dynamically adjust the production plan and further improve production efficiency and resource utilization.

[0100] The production status monitoring unit evaluates the execution effect of the current scheduling plan by collecting real-time information such as equipment operation status, task execution progress, resource consumption, etc. in the production process. Based on this data, the system can identify bottlenecks and anomalies in the production process in real time and generate targeted optimization suggestions.

[0101] In general, the system uses IoT technology, sensors and equipment monitoring tools to continuously obtain equipment status data and task progress information. On mission When the production schedule is delayed, there may be delays or other unforeseen events, causing the production schedule to lag behind. The monitoring unit will record the length of the delay and calculate the task by the following formula Actual completion time:

[0102] in, For the task On the device The actual completion time on the task, which reflects the moment when the task is actually completed; For the task On the device The scheduled start time on For the task On the device The delay time above indicates the delay caused by factors such as device failure and resource mismatch.

[0103] If the actual time of task execution exceeds expectations, the system will provide real-time feedback and adjust the schedule of subsequent tasks.

[0104] Feedback data analysis unit: The core task of the feedback data analysis unit is to analyze the real-time data collected by the production status monitoring unit. These data include the operating status of the equipment, task progress, resource consumption, etc. Through data analysis, the system can identify bottlenecks, abnormal tasks and other problems in the production process and provide optimization suggestions.

[0105] As an option, the feedback data analysis unit uses machine learning algorithms to train historical production data to automatically predict abnormal situations that may occur during the production process. For example, the probability of a certain device failing when performing a task can be estimated by the following formula: ; in, For equipment The failure probability indicates the possibility of equipment failure; For equipment The number of failures that occurred during the past period; For equipment The total running time during the past period.

[0106] If the failure probability of a device When a certain threshold is reached, the system will adjust the distribution of tasks in advance to avoid allocating too many tasks to equipment that is prone to failure, thereby optimizing the production plan.

[0107] Self-optimizing unit The self-optimization adjustment unit is responsible for optimizing production scheduling based on the results of feedback data analysis. Specifically, during the production process, when equipment failure, task delays, or insufficient resources occur, the system can adjust the production scheduling strategy based on feedback data to minimize production delays and resource waste.

[0108] Specifically, if the system detects that a task On the device If the execution time of the task is delayed, the execution order of the subsequent tasks needs to be adjusted. The adjusted task start time should be recalculated according to the delay time. The adjustment formula is as follows: ;in, For the adjusted tasks The start time of For the task The original start time of For the task The amount of delay that affects the scheduling of subsequent tasks.

[0109] This adjustment ensures that even if delays occur, subsequent tasks can still be scheduled reasonably, ensuring the continuity and overall efficiency of the production plan.

[0110] Through real-time feedback and self-optimization modules, the system can quickly respond to equipment failures, resource mismatches and other issues during the production process, and adjust the production plan in a timely manner to ensure that the production progress is not affected. Real-time monitoring and data analysis can quickly identify bottlenecks, automatically optimize resource allocation, and ensure maximum production efficiency and resource utilization.

[0111] For example, if the device The task was delayed due to a malfunction The system will monitor this delay through the feedback data analysis unit and automatically assign tasks The start time of the production process can be delayed to avoid stagnation of the entire production process.

[0112] With the continuous development of technology, this module can be combined with artificial intelligence technologies (such as deep learning and reinforcement learning) to achieve more intelligent production scheduling optimization in the future. Specifically, deep learning can be used to analyze historical production data and predict future equipment failures and production bottlenecks; reinforcement learning can enable the system to continuously optimize production scheduling strategies through trial and error learning during the production process.

[0113] In addition, combined with edge computing and 5G technology, the system can collect and process data in real time at the production site, greatly reducing delays and improving the response speed and real-time performance of production scheduling.

[0114] The result feedback and self-optimization module enables production scheduling to respond flexibly to uncertain factors through precise production status monitoring and dynamic adjustment mechanisms. This module not only improves the reliability and execution efficiency of production plans, but also maintains the continuity and efficiency of production through self-optimization adjustments in situations such as equipment failure and resource shortages.

[0115] See also Figure 2 The present invention also provides an intelligent ring main unit automatic production control method, comprising the following steps: S1. Collect production equipment status, task progress, and material supply information in real time, and pre-process the collected data; S2. Based on the preprocessed data, a multi-stage recursive optimization scheduling algorithm is used to generate preliminary production scheduling decisions, and recursive optimization is performed at each stage to minimize the total production time and maximize production efficiency; S3. Optimize resource allocation between production equipment through game theory model to solve the resource competition problem between equipment; S4. Use mixed integer programming methods to solve the optimal match between tasks and equipment according to production scheduling requirements to ensure that all tasks can be completed on time; S5. Execute the optimized scheduling results through the global coordination module to ensure that each device performs tasks according to the optimal solution; S6. Adjust the production scheduling plan in real time through feedback information, optimize the production process, and further improve production efficiency and resource utilization.

[0116] For step S1, the system uses IoT devices, sensors, production management software and other technical means to collect data such as equipment status, task execution progress, and material supply in real time during the production process. Specifically, it includes: Equipment status: Monitor key parameters of the equipment such as temperature, pressure, speed, etc. through sensors.

[0117] Task progress: records the execution status of each production task, including the task start time, current progress and expected completion time.

[0118] Material supply: Track the inventory and supply of materials in real time through the warehouse management system and material management module.

[0119] These data are pre-processed, including denoising, standardization and cleaning, to ensure data quality and provide reliable data input for subsequent processing modules.

[0120] For step S2, based on the preprocessed data, the system uses a multi-stage recursive optimization scheduling algorithm to generate preliminary production scheduling decisions. The algorithm optimizes each production stage and dynamically adjusts the task execution order based on the execution results of the previous stage.

[0121] Preliminary schedule generation: Generate preliminary production schedule based on factors such as equipment capacity, task priority, and material supply.

[0122] Recursive optimization: According to the production status and resource usage of each stage, the sequence and timing of production tasks are recursively optimized to minimize the total production time and maximize production efficiency.

[0123] This optimization step ensures that production tasks can be completed in the shortest time possible while improving overall production efficiency.

[0124] For step S3, in this stage, the game theory model is used to solve the resource competition problem between production equipment. Multiple equipment may need to share limited resources, and game theory optimizes resource allocation by simulating the interaction between equipment.

[0125] Devices are considered as participants in the game, and resource allocation is considered as strategies in the game. Each device selects resources based on its task requirements and priorities.

[0126] The system solves Nash equilibrium through game theory to ensure that each device can maximize resource utilization within its capabilities and avoid device overload or idleness.

[0127] The game theory model optimizes resource usage among devices, effectively reducing conflicts and improving resource utilization.

[0128] For step S4, at this stage, the system uses the mixed integer programming (MIP) method to solve the optimal match between tasks and equipment to ensure that the production tasks can be completed on time.

[0129] Task and device matching: Considering the load capacity of the device, the processing time and priority of the task, the system calculates the optimal match between the task and the device.

[0130] Solving constraints: Constraints such as task execution order, equipment load, and task time window are all incorporated into the optimization model for solution.

[0131] Through this method, the system can accurately schedule each task to the most appropriate equipment, ensuring the efficient progress of the production process.

[0132] For step S5, the global coordination module executes and coordinates each device in the production process according to the scheduling results optimized in the previous steps to ensure that each device performs the task according to the optimal solution.

[0133] Scheduling decision execution: According to the optimized scheduling plan, the equipment executes tasks in the predetermined order.

[0134] Real-time resource allocation: The equipment, personnel and materials required for production are reasonably allocated according to actual conditions to ensure maximum resource utilization.

[0135] The global coordination module ensures the smooth progress of production tasks and can adjust equipment scheduling in real time during the production process to avoid production stagnation or waste of resources.

[0136] For step S6, this step uses a real-time feedback mechanism to monitor the equipment status, task progress, resource consumption, etc. in the production process and adjust the production scheduling plan in a timely manner. Feedback information comes from various equipment, task management, resource scheduling and other modules, and the system optimizes based on the feedback results.

[0137] Real-time scheduling adjustment: If equipment fails or a task is delayed, the system will automatically adjust the time and resource allocation of subsequent tasks to ensure that production is not affected.

[0138] Bottleneck identification and resource reallocation: By analyzing production bottlenecks and task delays, the system optimizes resource allocation and reduces equipment idleness and resource waste.

[0139] Through real-time feedback and adjustments, the system continuously optimizes the production process and improves production efficiency and resource utilization.

[0140] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent ring main unit automatic production control system, characterized in that: include: Data collection and preprocessing module, used to collect equipment status, task progress, and material supply data in real time during the production process, and preprocess the data; A multi-stage recursive optimization scheduling module is used to generate production scheduling decisions based on preprocessed data and perform recursive optimization at each production stage to minimize the total production time and maximize production efficiency; Game theory and resource competition model module, which is used to optimize resource allocation among production equipment through game theory models and solve resource competition among multiple equipment; Mixed integer programming scheduling optimization module, which is used to accurately solve the optimization problems of task scheduling sequence and resource allocation according to the needs of production scheduling; The global coordination and execution module is used to coordinate the operation of each production equipment according to the scheduling optimization results and execute the scheduling decision; The result feedback and self-optimization module is used to provide real-time feedback on production status and optimize the production scheduling plan based on the feedback information.

2. According to claim 1, the intelligent ring main unit automatic production control system is characterized in that: The data acquisition and preprocessing module includes: Data collection unit, used to collect real-time information on the operating status, production progress, material supply, and task execution of production equipment through sensors and IoT devices; The data preprocessing unit is used to clean, denoise and standardize the collected raw data to generate a format that meets the processing requirements of subsequent modules; The data transmission unit is used to transmit the preprocessed data to the multi-stage recursive optimization scheduling module through the industrial network.

3. The intelligent ring main unit automatic production control system according to claim 1 is characterized in that: The multi-stage recursive optimization scheduling module dynamically adjusts scheduling decisions and performs optimization of staged production targets in each stage according to the feedback results of the previous stage.

4. The intelligent ring main unit automatic production control system according to claim 1 is characterized in that: The multi-stage recursive optimization scheduling module includes: The stage division unit is used to divide the production scheduling process into multiple stages, and each stage is adjusted according to the execution results of the previous stage; The optimization decision unit is used to generate the optimal scheduling decision according to the production status and resource status of the current stage, and perform recursive optimization at each stage to minimize the total production time and maximize production efficiency; The inter-stage feedback unit is used to feed back the scheduling results of each stage to the next stage to adjust the production progress and resource allocation.

5. The intelligent ring main unit automatic production control system according to claim 1 is characterized in that: The mixed integer programming scheduling optimization module includes: The task and device matching unit is used to generate the best match between the task and the device according to the processing time of the task, the load capacity of the device and the priority of the task; An objective function calculation unit, used to calculate and optimize the objective function according to the equipment scheduling sequence, task execution time and resource consumption, so as to minimize the total production time and maximize resource utilization; The constraint solving unit is used to solve the constraint optimization problem according to the equipment load, task execution sequence and equipment availability conditions.

6. The intelligent ring main unit automatic production control system according to claim 1 is characterized in that: The global coordination and execution module includes: The scheduling decision execution unit is used to control each production equipment to execute tasks in a predetermined production sequence according to the optimized scheduling decision; Resource allocation coordination unit, used to allocate resources required for production in real time, including equipment, personnel and materials, to ensure that resources do not exceed their maximum processing capacity; The production progress monitoring unit is used to monitor the execution status of each task in the production process and adjust equipment scheduling according to the real-time progress.

7. The intelligent ring main unit automatic production control system according to claim 1 is characterized in that: The result feedback and self-optimization module includes: The production status monitoring unit is used to collect information on the equipment operation status and task execution progress during the production process in real time to evaluate the execution effect of the current scheduling plan; Feedback data analysis unit, used to analyze the feedback data collected by the production status monitoring unit, identify bottlenecks and anomalies in the production process, and generate optimization suggestions; The self-optimizing adjustment unit is used to adjust the production scheduling strategy according to the feedback data and analysis results, and optimize the resource allocation and task execution sequence.

8. The intelligent ring main unit automatic production control system according to claim 1 is characterized in that: The data preprocessing unit of the data acquisition and preprocessing module includes: Data cleaning unit, used to remove noise information in collected data and fill in missing data; Data standardization unit, used to standardize various types of collected data to ensure that each data type has the same dimension and is suitable for subsequent analysis; The data format conversion unit is used to convert the cleaned and standardized data into a unified format for subsequent module processing.

9. An intelligent ring main unit automatic production control method, applied to an intelligent ring main unit automatic production control system as claimed in any one of claims 1 to 8, characterized in that: The following steps are involved: Collect production equipment status, task progress, and material supply information in real time, and pre-process the collected data; Based on the preprocessed data, a multi-stage recursive optimization scheduling algorithm is used to generate preliminary production scheduling decisions, and recursive optimization is performed at each stage to minimize the total production time and maximize production efficiency; Optimize resource allocation between production equipment through game theory models to solve resource competition problems between equipment; Using mixed integer programming methods, we can find the optimal match between tasks and equipment according to production scheduling requirements to ensure that all tasks can be completed on time. The global coordination module is used to optimize the scheduling results, ensuring that each device performs tasks according to the optimal solution. Through feedback information, production scheduling plans can be adjusted in real time to optimize the production process and improve production efficiency and resource utilization.

10. The intelligent ring main unit automatic production control method according to claim 9, characterized in that: The multi-stage recursive optimization scheduling algorithm dynamically adjusts scheduling decisions and optimizes stage-by-stage production targets by providing feedback on the production progress of each stage.

Images