A production line operation monitoring system based on digital twin technology

Abstract

The present invention discloses a production line operation monitoring system based on digital twin technology, comprising: a data acquisition module for collecting data on various tasks in the production line; a scheduling unit construction module for mapping each task instance in a virtual task relationship into a cat-shaped scheduling unit and initializing the role field based on a preset threshold; a scheduling game engine module for executing the Battle Cat algorithm on the game model to generate a scheduling solution set containing multiple candidate scheduling solutions; a simulation evaluation module for performing simulation evaluation on each candidate scheduling solution in a digital twin environment to obtain the corresponding task completion rate, resource utilization rate, and system load balance; and a policy management module for sorting the candidate scheduling solutions based on the simulation evaluation results and selecting the currently optimal scheduling solution. The present invention realizes intelligent production task scheduling, real-time response, and policy adaptive optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of production line operation monitoring, and in particular to a production line operation monitoring system based on digital twin technology. Background Art

[0002] The current manufacturing industry is accelerating its transformation towards intelligence and digitalization. Real-time monitoring and optimized scheduling of production lines have become key links in achieving flexible manufacturing and efficient operation and maintenance. To meet the needs of refined management and dynamic control, digital twin technology has been widely introduced in the manufacturing field to build virtual mappings of physical production systems and achieve data-driven state visualization, behavior prediction, and system collaboration. Existing production line monitoring systems mainly rely on traditional data collection and rule-based control models. Although they can achieve basic equipment status monitoring and alarm functions, they lack responsiveness in scenarios such as complex multi-task scheduling, multiple resource constraints, and emergency response. Scheduling solutions are difficult to adapt dynamically, and the overall operating efficiency and robustness of the system still have considerable room for improvement.

[0003] Traditional scheduling methods often employ fixed priority rules or heuristic algorithms, such as genetic algorithms and particle swarm algorithms. While these methods offer some optimization capabilities, they often encounter scheduling deadlocks, unresolved resource conflicts, and delayed emergency response in real-world production environments characterized by frequent task priority changes, intense resource competition, and volatile dynamic constraints. Furthermore, most systems lack the ability to model interdependencies between tasks, making it difficult to make reasonable scheduling decisions based on the actual urgency of tasks and the status of system resources. Furthermore, existing methods often employ static evaluation metrics for simulation evaluation and scheduling strategy selection, lacking the ability to dynamically optimize based on real-world operational feedback. This results in scheduling results being disconnected from actual production and strategy selection lacking specificity and adaptability.

[0004] To address these challenges, this paper proposes a production line operation monitoring system based on digital twin technology. This system establishes a dynamic scheduling and evaluation closed-loop mechanism by constructing a virtual mapping between production tasks and resource status, combined with a multi-round game evolution process. The system incorporates a swarm intelligence modeling mechanism, mapping tasks into cat-like scheduling units and assigning them behavioral roles and scheduling attributes. Using the Battle Cat algorithm, multiple rounds of simulation games are conducted to achieve evolutionary optimization of scheduling strategies. The system not only considers key factors such as task priority, resource request volume, and execution status, but also builds a comprehensive behavioral response mechanism for complex scenarios such as support behaviors, role switching, and resource release. Based on the candidate strategies generated by the scheduling game, the system conducts simulation evaluation using a digital twin platform and selects the scheduling solution with the best resource utilization, task completion rate, and system load balance, significantly improving the adaptability and real-time performance of the scheduling strategy.

[0005] Therefore, how to provide a production line operation monitoring system based on digital twin technology is an urgent problem that technicians in this field need to solve. Summary of the Invention

[0006] One objective of the present invention is to propose a production line operation monitoring system based on digital twin technology. This system uses the Battle Cat algorithm to intelligently model and game-evolve the multi-task scheduling process, and integrates a digital twin platform to achieve virtual simulation and dynamic evaluation of task status, resource allocation, and strategy outcomes. This system fully integrates digital twin modeling, intelligent agent role partitioning, nonlinear priority function construction, and game-based resource scheduling methods. It describes in detail the construction mechanism of the Cat-type scheduling unit, the multi-round evolutionary strategy generation process, and the strategy optimization method based on simulation feedback. It boasts the advantages of fast scheduling response, high resource utilization, and strong strategy adaptability.

[0007] A production line operation monitoring system based on digital twin technology according to an embodiment of the present invention includes:

[0008] The data collection module is used to collect the task identification, resource requirements, expected execution time and dependencies of each task in the production line;

[0009] A scheduling unit construction module is used to map each task instance into a cat-shaped scheduling unit, wherein the cat-shaped scheduling unit includes task attributes, resource request amount, priority value and role field, and initializes the role field based on a preset threshold;

[0010] The scheduling game engine module is used to execute the Fighting Cat algorithm on the task scheduling game model composed of cat-shaped scheduling units, perform multiple rounds of task scheduling evolution according to the role field behavior rules, and generate a scheduling solution set containing multiple candidate scheduling solutions;

[0011] The simulation evaluation module is used to perform simulation evaluation on each candidate scheduling solution in the digital twin environment to obtain the corresponding task completion rate, resource utilization and system load balance;

[0012] The policy management module is used to sort the candidate scheduling plans according to the simulation evaluation results and select the current optimal scheduling plan.

[0013] Optionally, modules can be connected using the following methods:

[0014] S1. Collect task data from the current production line, including task identification, resource requirements, estimated execution time, and dependencies, and establish corresponding virtual task relationships based on digital twin technology;

[0015] S2. Map each task instance in the virtual task relationship into a cat-type scheduling unit, wherein the cat-type scheduling unit includes task attributes, resource request amount, priority value, and role field;

[0016] S3. Initialize the role field of the cat-type scheduling unit according to the task data and set it to attack type, support type or defense type;

[0017] S4. Build a task scheduling game model based on all cat-type scheduling units and set role behavior rules, including that the attackers prioritize resource acquisition, the supporters coordinate conflicts, and the defenders assume delayed and redundant tasks.

[0018] S5. Run the Battle Cat algorithm to simulate the game process between cat-type scheduling units, perform several rounds of resource competition and strategy evolution, and output several candidate scheduling solutions;

[0019] S6. Simulate and evaluate the candidate scheduling solutions, calculate the task completion rate, resource utilization, and system load balance, and select the solution with the best score as the optimal scheduling solution;

[0020] S7. Apply the optimal scheduling solution to the production line operation monitoring system. During operation, the role field is reset according to the emergency trigger, and steps S4 to S6 are re-executed to achieve adaptive optimization.

[0021] Optionally, the S2 specifically includes:

[0022] S21, traverse each task instance in the virtual task relationship, and extract the resource requirements of the task instance as a resource request vector ,in, Indicates the Task 1 The demand for the resource type, is the number of resource types, and the resource request vector is used as a cat-type scheduling unit The resource request amount field;

[0023] S22. Extract task priority value from task instance , reflects the urgency of the task in the overall scheduling, as a cat-type scheduling unit The priority value field;

[0024] S23. Definition Generate a cat-shaped scheduling unit for the role field corresponding to the i-th task , and join the scheduling collection ,in Indicates the total number of scheduled tasks.

[0025] Optionally, the S3 specifically includes:

[0026] S31. Setting task priority thresholds , the total resource request threshold ;

[0027] S32. For the generated scheduling set Any cat-type scheduling unit in , extract the task priority value and resource request vector , calculate the total amount of resource requests ;

[0028] S33, according to and Comparison results, set the cat type scheduling unit Role field The classification rules are as follows:

[0029] like and , then assign , indicating an attacking role;

[0030] like and , then assign , indicating a support role;

[0031] like , then assign , indicating a defensive role;

[0032] S34, the updated cat-type scheduling unit Write Schedule Collection , complete the role field initialization operation of all task instances.

[0033] Optionally, the S4 specifically includes:

[0034] S41, in the scheduling collection Based on this, we build a task scheduling game model ,in, represents a set of schedulable resources, Represents a set of scheduling policies;

[0035] S42. Define cat-type scheduling unit Number of failed resource requests in the last round , the value comes from the previous round of the Battle Cats algorithm game Schedulable Resource Collection The number of resource types that were not satisfied in the initiated requests;

[0036] S43. According to the role field The value of determines the scheduling behavior rules, which are as follows:

[0037] like , is an attacking unit, then when this unit requests resources, it uses the task priority value as the main order and allocates the resource request amount as ,in, is the minimum function, For the The schedulable amount of class resources;

[0038] like , which is a defensive unit, is executed after the scheduling of other units is completed, and the resource request amount is ,in, The buffer coefficient set for the system;

[0039] like , is a support unit, and performs support operations based on resource conflict information during the game process. The support operations include the following three types of behaviors:

[0040] Behavior 1: Release some of the resources occupied by the unit that conflict with the attacking unit. And the attacking unit has If there is a gap in class resources, ,in, Maximum function, is the release step length;

[0041] Action 2: Adjust the scheduling order, postpone the execution of the current task, and adjust the scheduling priority value to ,in, is the delay penalty parameter;

[0042] Behavior 3: If there is an attacking unit The number of failed requests for the class resource is greater than or equal to the set threshold , the supporting unit prioritizes resource reallocation by releasing corresponding resources or delaying its own scheduling order;

[0043] S44. Define cat-type scheduling unit Scheduling priority function ;

[0044] S45, according to the scheduling priority function The cat-type scheduling units are sorted in the current round, and the sorting results are passed as input to the task scheduling game model to complete the task scheduling of this round.

[0045] Optionally, the S5 specifically includes:

[0046] S51, based on task scheduling game model , with a cat-type scheduling unit set As a game participant, resource collection is a schedulable resource pool, a policy set Contains all scheduling order and resource allocation path combinations;

[0047] S52. Set the maximum number of evolution rounds , initialize the 0th round scheduling priority function ;

[0048] S53. For each round of game iteration , do the following:

[0049] S531, cat-type scheduling unit collection Schedule priority function according to the current round Sort in descending order and build a scheduling queue;

[0050] S532, traverse each cat-type scheduling unit in the queue in turn , according to the role field Execute corresponding behavioral rules;

[0051] S533, recording cat-type scheduling unit The resource allocation status in this round, calculates the number of unsatisfied resource items and updates the number of failed resource requests , the execution status field is updated to , indicating waiting, executing and completed respectively;

[0052] S54, after completing a round of scheduling game, based on the updated Value recalculation next round scheduling priority function , enter the next round of iteration, and terminate the iteration process when any of the following conditions is met:

[0053] All cat-type dispatch units meet ;

[0054] The number of evolutionary rounds reaches the maximum ;

[0055] S55: Output the task execution trajectory, resource allocation path and game state record formed in each round of scheduling results as a scheduling solution set of candidate scheduling solutions , where each Contains the results of a round of scheduling, .

[0056] Optionally, the scheduling solution set in S55 specifically includes the following strategy combinations based on conditional judgment:

[0057] First strategy: When the attacking unit meets the priority value , and the resource type exists Satisfy the request volume , then select the priority value And the role field Scheduling unit , update the current round resource request amount to ;

[0058] Second strategy: If there are attacking units The same resource type that satisfies the request ,and , If the priority similarity threshold is In the scheduling cycle The time slice is allocated in a round-robin manner, and the execution time slice is , alternately assigned to and ;

[0059] The third strategy: If the support unit There is a resource request item , and there are offensive units satisfy and request the same resource , then For the first The requested amount of class resources is updated;

[0060] The fourth strategy: When the total number of tasks in the current round is greater than the preset number of tasks, and the total available resources If the available resource is less than the preset value, all Scheduling unit , update the scheduling priority function;

[0061] The fifth strategy: If there are scheduling units that meet the requirements in two consecutive rounds and , the priority is updated.

[0062] Optionally, the S6 simulation evaluation specifically includes: executing in a simulation platform, calculating the corresponding task completion rate, resource utilization and system load balance, and using the ternary indicator combination as an evaluation basis to form a scheduling strategy performance evaluation result.

[0063] The beneficial effects of the present invention are:

[0064] (1) By constructing a cat-type scheduling unit and introducing attacking, supporting, and defensive role behavior mechanisms, the present invention enables production tasks to have differentiated response strategies under different resource tensions and priority conditions, thereby improving the scheduling coordination capabilities between complex tasks and effectively solving the problems of scheduling deadlock and response delay in traditional systems.

[0065] (2) The present invention uses the Battle Cat algorithm to carry out multiple rounds of game evolution in a digital twin environment to generate multiple candidate scheduling schemes, and introduces a nonlinear priority function and a failure feedback mechanism to dynamically adjust the strategy selection logic. The system can continuously optimize the scheduling strategy when the resource status changes, the task failure rate increases, etc., and has the ability of self-learning and self-adjustment.

[0066] (3) By simulating and evaluating the scheduling strategy in the digital twin platform and evaluating and screening based on three indicators: task completion rate, resource utilization, and load balance, the final scheduling plan is ensured to be verifiable and efficient. This overcomes the problem of disconnection between the strategy and the actual production line in traditional methods, and significantly improves the operating efficiency and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0068] Figure 1 This is a flow chart of a production line operation monitoring system based on digital twin technology proposed in this invention. DETAILED DESCRIPTION

[0069] The present invention will now be described in further detail with reference to the accompanying drawings, which are simplified schematic diagrams that illustrate the basic structure of the present invention in a schematic manner.

[0070] refer to Figure 1 , a production line operation monitoring system based on digital twin technology, including:

[0071] The data collection module is used to collect the task identification, resource requirements, expected execution time and dependencies of each task in the production line;

[0072] A scheduling unit construction module is used to map each task instance into a cat-shaped scheduling unit, wherein the cat-shaped scheduling unit includes task attributes, resource request amount, priority value and role field, and initializes the role field based on a preset threshold;

[0073] The scheduling game engine module is used to execute the Fighting Cat algorithm on the task scheduling game model composed of cat-shaped scheduling units, perform multiple rounds of task scheduling evolution according to the role field behavior rules, and generate a scheduling solution set containing multiple candidate scheduling solutions;

[0074] The simulation evaluation module is used to perform simulation evaluation on each candidate scheduling solution in the digital twin environment to obtain the corresponding task completion rate, resource utilization and system load balance;

[0075] The policy management module is used to sort the candidate scheduling plans according to the simulation evaluation results and select the current optimal scheduling plan.

[0076] The system architecture provided by this invention covers the entire process, from data acquisition, unit modeling, scheduling game, simulation evaluation, to policy management. The modules are logically distinct and functionally closed-loop. Compared to traditional systems, where scheduling strategies are separated from control mechanisms and ontology modeling and evaluation are not integrated, this invention integrates scheduling logic and feedback mechanisms within a unified architecture through modular design. This enables the integrated generation, evaluation, and execution of scheduling strategies, improving the overall real-time performance, scalability, and intelligent decision-making capabilities of the system.

[0077] In this embodiment, the modules are connected through the following methods:

[0078] S1. Collect task data from the current production line, including task identification, resource requirements, estimated execution time, and dependencies. Establish corresponding virtual task relationships based on digital twin technology. Specifically, construct a task model in a virtual environment that corresponds one-to-one with the physical task. This virtual task model not only restores the operational characteristics of the task but also establishes logical relationships between tasks, such as sequential constraints, resource competition, and execution priority.

[0079] S2. Map each task instance in the virtual task relationship into a cat-type scheduling unit, wherein the cat-type scheduling unit includes task attributes, resource request amount, priority value, and role field;

[0080] S3. Initialize the role field of the cat-type scheduling unit according to the task data and set it to attack type, support type or defense type;

[0081] S4. Build a task scheduling game model based on all cat-type scheduling units and set role behavior rules, including that the attackers prioritize resource acquisition, the supporters coordinate conflicts, and the defenders assume delayed and redundant tasks.

[0082] S5. Run the Battle Cat algorithm to simulate the game process between cat-type scheduling units, perform several rounds of resource competition and strategy evolution, and output several candidate scheduling solutions;

[0083] S6. Simulate and evaluate the candidate scheduling solutions, calculate the task completion rate, resource utilization, and system load balance, and select the solution with the best score as the optimal scheduling solution;

[0084] S7. Apply the optimal scheduling solution to the production line operation monitoring system. During operation, the role field is reset according to the emergency trigger, and steps S4 to S6 are re-executed to achieve adaptive optimization. Specifically, when an emergency is detected, such as a task failure or resource failure, the system will trigger the role field reset of the cat-type scheduling unit, and reallocate it to an attacking, supporting or defensive role based on the current task urgency and resource status to adapt to the new scheduling strategy requirements.

[0085] The overall method flow provided by this invention achieves a complete closed-loop process, from task data collection, cat-shaped unit construction, character initialization, to game scheduling driven by the Battle Cat algorithm, simulation evaluation, and strategy feedback optimization. Compared to existing production line monitoring methods that rely solely on static rules or single-round optimization strategies, this invention, by constructing a dynamic evolution mechanism and character behavior differentiation strategy, enables the scheduling system to cope with resource conflicts, task delays, and multi-objective trade-offs. This improves response efficiency and scheduling flexibility in complex environments, significantly enhancing system intelligence and adaptability.

[0086] In this embodiment, S2 specifically includes:

[0087] S21, traverse each task instance in the virtual task relationship, and extract the resource requirements of the task instance as a resource request vector ,in, Indicates the Task 1 The demand for the resource type, is the number of resource types, and the resource request vector is used as a cat-type scheduling unit The resource request amount field;

[0088] S22. Extract task priority value from task instance , reflects the urgency of the task in the overall scheduling, as a cat-type scheduling unit The priority value field;

[0089] S23. Definition Generate a cat-shaped scheduling unit for the role field corresponding to the i-th task , and join the scheduling collection ,in Indicates the total number of scheduled tasks.

[0090] This paper introduces a modeling approach based on cat-shaped scheduling units, mapping traditional task data into scheduling agents with behavioral characteristics. This approach uses resource request quantities, priority values, and role fields as a unified scheduling parameter structure, laying the foundation for multi-agent game modeling. Compared to traditional scheduling representations based on task queues or graph structures, this paper introduces role behavior variables at the modeling stage, providing structural support for subsequent scheduling behavior games and resource coordination, enhancing the expressiveness of the scheduling model and the flexibility of the behavior-driven logic.

[0091] In this embodiment, S3 specifically includes:

[0092] S31. Setting task priority thresholds , the total resource request threshold ;

[0093] S32. For the generated scheduling set Any cat-type scheduling unit in , extract the task priority value and resource request vector , calculate the total amount of resource requests:

[0094] ;

[0095] in, is the number of resource types;

[0096] S33, according to and Comparison results, set the cat type scheduling unit Role field The classification rules are as follows:

[0097] like and , then assign , indicating an attacking role;

[0098] like and , then assign , indicating a support role;

[0099] like , then assign , indicating a defensive role;

[0100] S34, the updated cat-type scheduling unit Write Schedule Collection , complete the role field initialization operation of all task instances.

[0101] During the role field initialization process, this invention uses a combined conditional judgment based on task priority and total resource requests to clearly classify scheduling tasks into three roles: attack, support, and defense. This enables the pre-classification and structural division of behavioral rules in game scheduling. Compared to existing methods that rely solely on fixed priority ranking for decision-making, this invention uses a structured role division mechanism to pre-embed differences in scheduling game behaviors, providing a foundation for adaptive coordination of scheduling rules and improving the system's ability to handle emergencies and the flexibility of policy adjustments.

[0102] In this embodiment, the S4 specifically includes:

[0103] S41, in the scheduling collection Based on this, we build a task scheduling game model ,in, represents a set of schedulable resources, Represents a set of scheduling policies;

[0104] S42. Define cat-type scheduling unit Number of failed resource requests in the last round , the value comes from the previous round of the Battle Cats algorithm game Schedulable Resource Collection The number of resource types that were not satisfied in the initiated requests, that is:

[0105] ;

[0106] in, Cat-type dispatch unit Requested The number of class resources, Indicates in In the round of game The remaining available amount of class resources, is an indicator function, the rule is that if the condition is true, the value is 1, otherwise it is 0;

[0107] S43. According to the role field The value of determines the scheduling behavior rules, which are as follows:

[0108] like , is an attacking unit, then when this unit requests resources, it uses the task priority value as the main order and allocates the resource request amount as ,in, is the minimum function, For the The current remaining available amount of class resources;

[0109] like , which is a defensive unit, is executed after the scheduling of other units is completed, and the resource request amount is ,in, The buffer coefficient set for the system;

[0110] like , is a support unit, and performs support operations based on resource conflict information during the game process. The support operations include the following three types of behaviors:

[0111] Behavior 1: Release some of the resources occupied by the unit that conflict with the attacking unit. And the attacking unit has If there is a gap in class resources, ,in, Maximum function, is the release step length;

[0112] Action 2: Adjust the scheduling order, postpone the execution of the current task, and adjust the scheduling priority value to ,in, is the delay penalty parameter;

[0113] Behavior 3: If there is an attacking unit The number of failed requests for the class resource is greater than or equal to the set threshold , the supporting unit prioritizes resource reallocation by releasing corresponding resources or delaying its own scheduling order;

[0114] S44. Define cat-type scheduling unit Scheduling priority function , calculated as:

[0115] ;

[0116] in, is the logarithmic function with base 2, is the hyperbolic tangent function;

[0117] This scheduling priority function comprehensively considers the urgency of the task itself, the intensity of resource consumption, and historical scheduling failures. It uses logarithmic and hyperbolic tangent functions to build a nonlinear scoring mechanism to improve the rationality of scheduling and the system's ability to adaptively control resource conflicts and failed tasks.

[0118] S45, according to the scheduling priority function The cat-type scheduling units are sorted in the current round, and the sorting results are passed as input to the task scheduling game model to complete the task scheduling of this round.

[0119] This invention establishes clear behavioral rules for various scheduling roles and establishes a nonlinear scheduling scoring mechanism by integrating task priority, resource consumption, and failure feedback information through a scheduling priority function. Unlike the static weighting or linear evaluation methods used in existing technologies, the function constructed in this invention incorporates feedback on the number of failed resource types, improving the adaptability of scheduling ranking over multiple rounds of evolution. This effectively addresses the problem of high-priority tasks being repeatedly postponed and enhances the diversity and quality of strategies in resource contention scheduling.

[0120] In this embodiment, the S5 specifically includes:

[0121] S51, based on task scheduling game model , with a cat-type scheduling unit set As a game participant, resource collection is a schedulable resource pool, a policy set Contains all scheduling order and resource allocation path combinations;

[0122] S52. Set the maximum number of evolution rounds , initialize the 0th round scheduling priority function ;

[0123] S53. For each round of game iteration , do the following:

[0124] S531, cat-type scheduling unit collection Schedule priority function according to the current round Sort in descending order and build a scheduling queue;

[0125] S532, traverse each cat-type scheduling unit in the queue in turn , according to the role field Execute corresponding behavioral rules;

[0126] S533, recording cat-type scheduling unit The resource allocation status in this round, calculates the number of unsatisfied resource items and updates the number of failed resource requests , the execution status field is updated to , indicating waiting, executing and completed respectively;

[0127] S54, after completing a round of scheduling game, based on the updated Value recalculation next round scheduling priority function , enter the next round of iteration, and terminate the iteration process when any of the following conditions is met:

[0128] All cat-type dispatch units meet ;

[0129] The number of evolutionary rounds reaches the maximum ;

[0130] S55: Output the task execution trajectory, resource allocation path, and game state record generated in each round of scheduling results as candidate scheduling solutions. , where each Contains the results of a round of scheduling, .

[0131] This invention incorporates a multi-round simulation mechanism into the evolution of the BattleCat algorithm. In each round, scheduling priorities are dynamically adjusted based on resource allocation results, role behavior, and the number of failures, enabling the scheduling unit to self-learn during the evolution process. Compared to traditional single-step decision-making scheduling, the evolutionary multi-round scheduling mechanism employed in this invention can continuously optimize scheduling strategies in dynamic production environments, improving the system's adaptability and resilience to complex scenarios such as task failure feedback and resource constraints, resulting in higher practicality and robustness.

[0132] In this embodiment, the scheduling solution set in S55 specifically includes the following strategy combinations based on conditional judgment:

[0133] First strategy: When the attacking unit meets the priority value , and the resource type exists Satisfy the request volume , then select the priority value And the role field Scheduling unit , update the current round resource request amount to ;

[0134] Second strategy: If there are attacking units The same resource type that satisfies the request ,and , If the priority similarity threshold is In the scheduling cycle The time slice is allocated in a round-robin manner, and the execution time slice is , alternately assigned to and ;

[0135] The third strategy: If the support unit There is a resource request item , and there are offensive units satisfy and request the same resource , then For the first The requested amount of the class resource is updated as follows:

[0136] ;

[0137] in, For the Round The resource request amount of the class resource, For the Round The resource request amount of the class resource, is the resource release ratio coefficient;

[0138] This formula is used to enable the support unit to proactively release some resource requests in resource competition conflict scenarios, so as to transfer key resources to the attacking unit with more failures or higher priority. By proportionally reducing its own resource requirements, it can achieve resource transfer and scheduling buffer, improve the coordination of the overall system and the scheduling success rate of key tasks, and the formula is used by the parameter Control the release intensity, taking into account both local sacrifice and global optimization;

[0139] The fourth strategy: When the total number of tasks in the current round is greater than the preset number of tasks, and the total available resources If the available resource is less than the preset value, all Scheduling unit , update the scheduling priority function to:

[0140] ;

[0141] in, for Round-robin scheduling priority function, for Round-robin scheduling priority function, is the delay penalty constant;

[0142] This formula lowers the priority of defensive scheduling units and postpones their scheduling time to prioritize the execution of more urgent or critical tasks. When the number of tasks or resource pressure exceeds the threshold, this strategy helps to alleviate scheduling congestion and release resources for high-priority tasks. The priority reduction range is Control, which reflects the system's scheduling inclination and dynamic adjustment capabilities for different role tasks, thereby enhancing the stability and efficiency of the overall scheduling;

[0143] The fifth strategy: If there are scheduling units that meet the requirements in two consecutive rounds and , then update the priority to:

[0144] ;

[0145] in is the failure compensation factor.

[0146] This formula implements a dynamic priority repair mechanism based on failure feedback. When a task is not successfully scheduled in the current round, the system will automatically increase its priority based on the degree of failure, so that it will have a better execution opportunity in the next round of scheduling. By introducing the linkage between the number of failures and the linear compensation term, the system can effectively avoid the problem of long-term task pressure, improve task fairness and the overall scheduling success rate, and at the same time enhance the robustness and self-healing ability of the scheduling system.

[0147] This invention defines candidate scheduling solutions as a set of scheduling policy rules with specific trigger conditions and behavioral logic, clarifying the decision paths for inter-task resource competition, role coordination, and scheduling failure handling. Compared to existing solutions that simply output a list of scheduling results, this invention's rule-based policy set, expressed through an "if-then" structure, enhances the understandability, enforceability, and systematic expression of scheduling solutions. This provides a clear basis for the scheduling engine's automated decision-making, significantly improving the system's maintainability and scenario scalability.

[0148] In this embodiment, the S6 simulation evaluation specifically includes: executing in the simulation platform, calculating the corresponding task completion rate, resource utilization and system load balance; wherein, the task completion rate is obtained by counting the number of cat-type scheduling units with a status of "completed" in a certain time period and dividing it by the total number of tasks in the cycle; the system records the allocation and occupancy of resource types in each round of the game, and obtains the resource utilization by dividing the accumulated resource usage by the total available resource amount; the system load balance is the standard deviation of each resource utilization rate or task distribution, and the smaller the value, the more uniform the system load distribution and the more balanced the scheduling strategy; the ternary indicator combination is used as the evaluation basis to constitute the scheduling strategy performance evaluation result.

[0149] Example 1:

[0150] To verify the feasibility of this invention, it was applied to an automated assembly line at a smart equipment manufacturer. This line is responsible for the precision assembly of various electronic control modules, involving multiple processes such as placement, electrical testing, plug-in, and assembly. The average daily processing time is approximately 380 tasks. The line is equipped with 18 types of dispatchable resources, including placement machines, plug-in machines, test benches, assembly stations, intelligent AGVs, human workers, tool kits, and electrical power supply units.

[0151] In actual operation, the company's existing scheduling system, based on a static priority strategy and employing a single weighted algorithm for task sorting, was unable to dynamically handle issues such as sudden task insertion, frequent resource conflicts, and staggered night shift production capacity. Task congestion and excessive critical path wait times were common, resulting in an average equipment utilization rate of less than 65% and a task delay rate as high as 18%. To address these scheduling bottlenecks, the company introduced the proposed production line operation monitoring system based on digital twin technology and deployed it on a typical combined electrical testing and assembly production line for a 30-day comparative experiment.

[0152] The system first uses the data acquisition module of the present invention to collect all task execution logs for the production line over a 30-day period in real time, recording elements such as task identification, resource requests, estimated execution time, and task dependencies, and constructing a corresponding virtual task model. After the model is generated, the system uses a cat-type scheduling unit to model the tasks and initializes roles based on priority values ​​and resource consumption, automatically classifying them into three categories: attack, support, and defense. The system then enters the multi-round scheduling game phase of the Battle Cat algorithm, dynamically evolving task priorities based on a priority function and outputting candidate scheduling solutions.

[0153] Before deployment, scheduling plans are verified and evaluated on a digital twin simulation platform. Task completion rates, resource utilization, and system load balancing are calculated for each round of plans. After the evaluation is complete, the system selects the optimal scheduling plan and sends it directly to the MES system to update and control the production line task sequence and resource allocation instructions. During the scheduling process, the system adjusts the task scheduling strategy in real time based on task execution status and resource feedback. If a task fails due to equipment failure or an occupied workstation, the system automatically reassesses scheduling priorities and readjusts the order based on a game feedback mechanism to ensure that overall production capacity targets are not affected.

[0154] A 30-day system comparison test revealed that this invention demonstrated significant superiority on actual production lines. Compared with the original system, the average task waiting time decreased from 21.3 minutes to 9.6 minutes, resource utilization increased from 63.5% to 82.1%, and the task delay rate decreased from 18.2% to 4.7%. During two sudden task insertion events, this system was able to complete the schedule map update and achieve automatic strategy switching within 10 seconds, successfully ensuring the on-time delivery of critical work orders and avoiding approximately 30,000 yuan in wasted work hours and production line downtime.

[0155] By deploying the system of the present invention, the company has realized the practical application of multi-role game scheduling strategies in industrial-grade production lines for the first time, and demonstrated excellent scalability and stability in dimensions such as intelligent production scheduling, task plug-in scheduling, and adaptive collaborative control, verifying the feasibility, robustness, and system economy of the present invention in multi-task and high-complexity industrial scenarios.

[0156] Table 1: Performance comparison between the digital twin-based game-based scheduling system and the traditional system

[0157]

[0158] First, in terms of task scheduling efficiency, the system reduces the average task waiting time from 21.3 minutes to 9.6 minutes, a reduction of more than half, significantly improving the response speed of tasks in the queue. Furthermore, the average task completion time is reduced from 45.8 minutes to 31.2 minutes, indicating that the overall task execution cycle has been shortened, effectively alleviating idle waiting and resource switching delays between processes.

[0159] In terms of resource utilization, the system achieved a significant improvement from 63.5% to 82.1%, demonstrating its ability to more efficiently allocate and schedule multiple production resources, avoiding idle equipment and repeated waiting. This improvement also directly boosted production capacity, with the maximum daily output tasks increasing from 386 to 447, a nearly 16% increase. This expanded production line throughput without increasing hardware investment.

[0160] In terms of task delay rate, the system of this invention effectively reduced the delay ratio from 18.2% to 4.7%, reducing the risk of task delivery delays and rework, further improving delivery reliability and customer satisfaction. Furthermore, the scheduling strategy response time was shortened from 65 seconds to 9.8 seconds, and the average repair time for rescheduling was reduced from 77 seconds to 11.2 seconds, demonstrating that the system has strong rapid response and strategic recovery capabilities in the face of disturbances such as sudden task changes or equipment anomalies.

[0161] What is more noteworthy is that the performance of the present invention in the dimension of "success rate of adaptation to emergencies" is particularly outstanding. The success rate has been greatly improved from 42.3% of the original system to 91.6%, indicating that the scheduling game mechanism after the introduction of the Battle Cat algorithm has demonstrated extremely high robustness and adaptability under typical challenges such as complex task conflicts and high resource competition.

[0162] Overall, this invention not only addresses the problems of static scheduling rigidity, resource coordination imbalance, and non-tunable policies in the original system, but also establishes a complete feedback loop from modeling to evaluation and policy updates, demonstrating strong practicality, scalability, and economic benefits in real industrial production environments. While maintaining intelligent scheduling, this system significantly improves the overall operational efficiency of production lines, promising broad application potential.

[0163] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A production line operation monitoring system based on digital twin technology, characterized in that: include: The data collection module is used to collect the task identification, resource requirements, expected execution time and dependencies of each task in the production line; A scheduling unit construction module is used to map each task instance into a cat-shaped scheduling unit, wherein the cat-shaped scheduling unit includes task attributes, resource request amount, priority value and role field, and initializes the role field based on a preset threshold; A scheduling game engine module is configured to execute the Battle Cat algorithm on a task scheduling game model composed of cat-type scheduling units. The Battle Cat algorithm is a virtual task scheduling method that simulates the behavior of attacking, supporting, and defensive roles. The algorithm performs multiple rounds of task scheduling evolution according to role field behavior rules to generate a scheduling solution set containing multiple candidate scheduling solutions. The simulation evaluation module is used to perform simulation evaluation on each candidate scheduling solution in the digital twin environment to obtain the corresponding task completion rate, resource utilization and system load balance; The policy management module is used to sort the candidate scheduling plans according to the simulation evaluation results and select the current optimal scheduling plan; The modules are implemented as follows: S1. Collect task data from the current production line, including task identification, resource requirements, estimated execution time, and dependencies, and establish corresponding virtual task relationships based on digital twin technology; S2. Map each task instance in the virtual task relationship into a cat-type scheduling unit, wherein the cat-type scheduling unit includes task attributes, resource request amount, priority value, and role field; S3. Initialize the role field of the cat-type scheduling unit according to the task data and set it to attack type, support type or defense type; S4. Build a task scheduling game model based on all cat-type scheduling units and set role behavior rules, including that the attackers prioritize resource acquisition, the supporters coordinate conflicts, and the defenders assume delayed and redundant tasks. S5. Running the Battle Cat algorithm, which is a virtual task scheduling method that simulates the behaviors of attacking, supporting, and defensive roles. The Battle Cat algorithm simulates the game process between cat-type scheduling units, executes several rounds of resource competition and strategy evolution, and outputs several candidate scheduling solutions. S6. Simulate and evaluate the candidate scheduling solutions, calculate the task completion rate, resource utilization, and system load balance, and select the solution with the best score as the optimal scheduling solution; S7. Apply the optimal scheduling solution to the production line operation monitoring system. During operation, the role field is reset according to the emergency trigger, and steps S4 to S6 are re-executed to achieve adaptive optimization.

2. A production line operation monitoring system based on digital twin technology according to claim 1, characterized in that: The S2 specifically includes: S21, traverse each task instance in the virtual task relationship, and extract the resource requirements of the task instance as a resource request vector ,in, Indicates the Task 1 The demand for the resource type, is the number of resource types, and the resource request vector is used as a cat-type scheduling unit The resource request amount field; S22. Extract task priority value from task instance , reflects the urgency of the task in the overall scheduling, as a cat-type scheduling unit The priority value field; S23. Definition Generate a cat-shaped scheduling unit for the role field corresponding to the i-th task , and join the scheduling collection ,in Indicates the total number of scheduled tasks.

3. The production line operation monitoring system based on digital twin technology according to claim 2 is characterized in that: The S3 specifically includes: S31. Setting task priority thresholds , the total resource request threshold ; S32. For the generated scheduling set Any cat-type scheduling unit in , extract task priority value and resource request vector , calculate the total amount of resource requests ; S33, according to and Comparison results, set the cat type scheduling unit Role field The classification rules are as follows: like and , then assign , indicating an attacking role; like and , then assign , indicating a support role; like , then assign , indicating a defensive role; S34, the updated cat-type scheduling unit Write Schedule Collection , complete the role field initialization operation of all task instances.

4. The production line operation monitoring system based on digital twin technology according to claim 3 is characterized in that: The S4 specifically includes: S41, in the scheduling collection Based on this, we build a task scheduling game model ,in, represents a set of schedulable resources, Represents a set of scheduling policies; S42. Define cat-type scheduling unit Number of failed resource requests in the last round , the value comes from the previous round of the Battle Cats algorithm game Schedulable Resource Collection The number of resource types that were not satisfied in the initiated requests; S43. According to the role field The value of determines the scheduling behavior rules, which are as follows: like , is an attacking unit, then when this unit requests resources, it uses the task priority value as the main order and allocates the resource request amount as ,in, is the minimum function, For the The schedulable amount of class resources; like , which is a defensive unit, is executed after the scheduling of other units is completed, and the resource request amount is ,in, The buffer coefficient set for the system; like , is a support unit, and performs support operations based on resource conflict information during the game process. The support operations include the following three types of behaviors: Behavior 1: Release some of the resources occupied by the unit that conflict with the attacking unit. And the attacking unit has If there is a gap in class resources, ,in, Maximum function, is the release step length; Action 2: Adjust the scheduling order, postpone the execution of the current task, and adjust the scheduling priority value to ,in, is the delay penalty parameter; Behavior 3: If there is an attacking unit The number of failed requests for the class resource is greater than or equal to the set threshold , the supporting unit prioritizes resource reallocation by releasing corresponding resources or delaying its own scheduling order; S44. Define cat-type scheduling unit Scheduling priority function ; S45, according to the scheduling priority function The cat-type scheduling units are sorted in the current round, and the sorting results are passed as input to the task scheduling game model to complete the task scheduling of this round.

5. The production line operation monitoring system based on digital twin technology according to claim 4 is characterized in that: The S5 specifically includes: S51, based on task scheduling game model , with a cat-type scheduling unit set As a game participant, resource collection is a schedulable resource pool, a policy set Contains all scheduling order and resource allocation path combinations; S52. Set the maximum number of evolution rounds , initialize the 0th round scheduling priority function ; S53. For each round of game iteration , do the following: S531, cat-type scheduling unit collection Schedule priority function according to the current round Sort in descending order and build a scheduling queue; S532, traverse each cat-type scheduling unit in the queue in turn , according to the role field Execute corresponding behavioral rules; S533, recording cat-type scheduling unit The resource allocation status in this round, calculates the number of unsatisfied resource items and updates the number of failed resource requests , the execution status field is updated to , indicating waiting, executing and completed respectively; S54, after completing a round of scheduling game, based on the updated Value recalculation next round scheduling priority function , enter the next round of iteration, and terminate the iteration process when any of the following conditions is met: All cat-type dispatch units meet ; The number of evolutionary rounds reaches the maximum ; S55: Output the task execution trajectory, resource allocation path and game state record formed in each round of scheduling results as a scheduling solution set of candidate scheduling solutions , where each Contains the results of a round of scheduling, .

6. The production line operation monitoring system based on digital twin technology according to claim 5 is characterized in that: The scheduling solution set in S55 specifically includes the following strategy combinations based on conditional judgment: First strategy: When the attacking unit meets the priority value , and the resource type exists Satisfy the request volume , then select the priority value And the role field Scheduling unit , update the current round resource request amount to ; Second strategy: If there are attacking units The same resource type that satisfies the request ,and , If the priority similarity threshold is In the scheduling cycle The time slice is allocated in a round-robin manner, and the execution time slice is , alternately assigned to and ; The third strategy: If the support unit There is a resource request item , and there are offensive units satisfy and request the same resource , then For the first The requested amount of class resources is updated; Fourth strategy: If the total number of tasks in the current round is greater than the preset number of tasks, and the total available resources If the available resource is less than the preset value, all Scheduling unit , update the scheduling priority function; The fifth strategy: If there are scheduling units that meet the requirements in two consecutive rounds and , the priority is updated.

7. The production line operation monitoring system based on digital twin technology according to claim 6 is characterized in that: The simulation evaluation specifically includes: executing in the simulation platform, calculating the corresponding task completion rate, resource utilization and system load balance, and weightedly integrating the corresponding task completion rate, resource utilization and system load balance as the evaluation basis to form the scheduling strategy performance evaluation result.

Images