Equipment operation and abnormity management and control method based on digital twinning
By constructing a digital twin to simulate equipment anomalies, and using real-time and historical data to predict future production scenarios, the optimal solution strategy is automatically selected, which solves the problems of lag and false alarms and missed alarms in traditional detection methods, and achieves efficient production anomaly management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-26
- Publication Date
- 2026-03-24
AI Technical Summary
Traditional equipment anomaly detection methods are prone to false alarms or missed alarms under complex operating conditions, and lack flexibility, making it impossible to respond to multiple anomalies in a timely and accurate manner, leading to increased maintenance costs.
Build digital twins of production equipment within the factory, acquire real-time operation and production data, simulate future production scenarios under different solution strategies through virtual mapping, analyze the impact of each strategy on order delivery, and automatically select the optimal solution strategy.
It improves the real-time performance and accuracy of anomaly response, realizes the transformation from passive processing to proactive prediction and decision-making, ensures the reliable execution of production plans and the timely delivery of orders, and enhances the resilience and intelligent management level of the production system.
Smart Images
Figure CN121724282A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of equipment anomaly monitoring technology, and specifically to a method for equipment operation and anomaly control based on digital twins. Background Technology
[0002] In modern manufacturing, production lines are becoming increasingly complex and automated, and the operating status of equipment directly impacts production efficiency and product quality. To ensure the efficient and stable operation of production lines, real-time monitoring and anomaly detection of equipment status have become crucial. However, due to the diverse types of equipment and complex operating environments on production lines, traditional detection methods based on fixed time intervals are ill-suited to the changing working conditions and equipment statuses.
[0003] Traditional equipment anomaly detection methods typically rely on fixed detection cycles or simple threshold judgments, which can easily lead to false alarms or missed alarms when faced with complex operating conditions and multi-source data. Currently, most methods lack flexibility in setting data analysis cycles and fail to fully consider the impact of the number of devices, resulting in analysis cycles that are too long or too short, affecting the timeliness and accuracy of anomaly detection. Furthermore, after equipment anomaly detection, if multiple anomalies are found simultaneously, the inability to prioritize and issue warnings based on the severity of the anomalies can easily cause delays in maintenance of severely affected areas, thereby increasing maintenance costs. Summary of the Invention
[0004] The technical problem solved by this invention is to provide a method for equipment operation and anomaly control based on digital twins, which can improve the efficiency of equipment anomaly handling.
[0005] The basic solution provided by this invention is a method for device operation and anomaly control based on digital twins, comprising the following steps: S1. Construct a digital twin of the production equipment in the factory and acquire real-time data of the production equipment. The real-time data includes real-time operation data and real-time production data. Based on the digital twin of the production equipment, construct a virtual mapping of the entire production line in the digital twin. S2. Detect the operating data of each production equipment. When abnormal operating data is detected, simulate the production scenarios under different solution strategies in the future time period through virtual mapping of the production line based on the real-time operating data and historical data of the equipment. The historical data includes the historical operating data and historical production data of the equipment. S3. Based on the predicted production scenario for the future time period, analyze the impact of different solution strategies on order delivery, and select the optimal solution strategy based on the impact.
[0006] The principle and advantages of this invention are as follows: By constructing digital twins of production equipment within a factory and acquiring real-time operational and production data, a virtual mapping of the entire production line is established, thereby achieving comprehensive digital representation and dynamic synchronization of physical entities. When equipment malfunctions are detected, the digital twins, combined with real-time and historical data, are used to simulate production scenarios for a preset future time period under different solution strategies. Based on the prediction results, the specific impact of each strategy on order delivery is analyzed, and the optimal solution strategy is automatically selected. This method significantly improves the real-time performance and accuracy of anomaly response, overcoming the lag and false alarm / missed detection problems of traditional methods relying on fixed thresholds or periodic detection. It achieves a shift from passive processing to proactive predictive decision-making, effectively ensuring the reliable execution of production plans and on-time order delivery, and enhancing the resilience and intelligent management level of the overall production system.
[0007] Furthermore, S1 includes the following steps: S11. Construct a virtual mapping relationship between each device in the digital entity through a relational database to determine the flow of logistics; S12. Each device node defines its key capability parameters, including standard cycle time, maximum operating speed, mean time to repair faults, and changeover time. S13, Bind the dependencies between various devices.
[0008] By establishing virtual mapping relationships between equipment and clarifying the flow of materials through a relational database, a clear data structure and logical connection foundation are provided for the entire digital twin system. By defining key capability parameters for each equipment node, including standard cycle time, maximum operating speed, mean time to repair (MTBT), and changeover time, the digital twin possesses the ability to accurately reflect the actual operating characteristics and bottlenecks of the equipment. Binding the dependencies between equipment ensures the coherence and realism of the production line-level simulation, accurately depicting the interconnected effects and capacity constraints between equipment. This series of steps collectively constitutes the underlying support of the high-fidelity digital twin, enabling it to provide reliable and realistic production scenario predictions in subsequent anomaly simulations and strategy evaluations, laying a solid foundation for refined management and scientific decision-making.
[0009] Furthermore, S2 includes the following steps: S21. Identify abnormal operating data that exceeds a preset threshold based on real-time operating data, and inject the abnormal operating data into the digital twin of the production equipment; S22. Obtain the real-time production plan, and based on the production plan and the injected abnormal operation data, predict the production scenario of continuing to execute the current production plan in a future preset period. S23. Based on the production plan and the injected abnormal operation data, predict the production scenario for a future preset period after continuing to perform maintenance on the abnormal operation data and then continuing to execute the current production plan.
[0010] Anomalies are identified by comparing real-time operational data with preset thresholds, and the abnormal data is dynamically injected into the digital twin of the corresponding equipment to ensure that the virtual model can reflect changes in the actual equipment status in a timely manner. Based on this, future production scenarios under two response strategies are simulated: one is to continue executing the original plan, and the other is to first conduct operational intervention and then resume production, thereby comprehensively predicting the possible outcomes of different decision paths. This method fully utilizes historical data and real-time information to rehearse multiple response plans in virtual space, greatly enhancing the foresight of management and the comparability of strategies, avoiding the uncertainty of decisions based solely on experience, and providing rich and accurate input data for subsequent quantitative evaluation and optimization.
[0011] Furthermore, S22 includes the following steps: S221. Obtain current production plan information, wherein the production plan information includes order details, production quantity, and delivery time nodes; S222. Based on the abnormal operating data, determine the impact parameters of the abnormal operating data on the operating efficiency of the equipment, including the equipment speed reduction ratio and the probability of failure. S223. Based on the aforementioned influencing parameters, a simulation is performed in the digital twin of the production line to predict the equipment operating status, production quantity, and order completion status within a future predicted time period, assuming the current production plan continues to be executed, and the simulation results are output.
[0012] By acquiring detailed production plans including order details, production quantities, and delivery milestones, and combining these with equipment operating efficiency impact parameters derived from anomaly data, such as speed reduction ratios and failure probabilities, precise simulation input conditions are constructed. Dynamic simulations are then performed within a digital twin of the production line to predict equipment operating status, output quantities, and order completion status in future timeframes, outputting quantitative results. This process achieves a closed loop from anomaly identification to impact projection, enabling managers to clearly understand potential production delays and capacity losses without intervention. It provides direct evidence for assessing the severity of anomalies and the urgency of decisions, supporting early recognition and prevention of production risks.
[0013] Furthermore, S23 includes the following steps: S231. Based on abnormal operation data, generate one or more operation and maintenance strategies, including immediate shutdown for maintenance, adjustment of process parameters, and slowing down operation until the planned shutdown window before maintenance. S232. In the digital twin of the production line, simulate the process of executing the selected operation and maintenance strategy, and predict the resources and duration required for the operation and maintenance; S233. In the digital twin, after the simulation completes the operation and maintenance strategy, the equipment returns to normal and continues to execute production based on the updated production plan; S234. Simulate the complete production scenario starting from the current moment, going through the maintenance period and production recovery period, until the end of a preset time period in the future, predict the total output and order delivery delay under this strategy, and output the simulation results.
[0014] First, multiple feasible operation and maintenance strategies are generated, including immediate repair, parameter adjustment, or planned window repair, covering responses under different levels of urgency and resource constraints. Then, the resources and time required for operation and maintenance are simulated in a digital twin, and the production process based on the updated plan after the equipment returns to normal is further simulated. Finally, the total output and delivery delay under this strategy are output. This method enables virtual verification and pre-evaluation of the entire operation and maintenance decision-making process, allowing enterprises to coordinate resources in advance, optimize maintenance plans, minimize the impact of unplanned downtime on production continuity, and provide data support for comparing the comprehensive benefits of different maintenance strategies, thus improving the scientific and economical nature of operation and maintenance management.
[0015] Furthermore, S3 includes the following steps: S31. Construct multiple evaluation dimensions to quantify the impact of different solution strategies on order delivery. The evaluation dimensions include production delivery dimension, production efficiency dimension, and cost dimension. S32. Based on the simulation results output in steps S22 and S23, calculate the score of each solution strategy under each evaluation dimension, and calculate the comprehensive impact score of each strategy. S33. Sort all strategies according to the comprehensive impact score, and select the strategy with the best score as the recommended optimal solution strategy.
[0016] By constructing an evaluation system covering multiple aspects such as production delivery, production efficiency, and cost, simulation results under different strategies are transformed into comparable indicator scores. Weighted or comprehensive algorithms are used to calculate the overall impact score of each strategy, and based on this, ranking and optimal strategy selection are performed, thus achieving a leap from scenario prediction to decision support. This method overcomes the limitations of traditional anomaly handling that relies on single indicators or subjective experience, achieving multi-objective optimization that integrates efficiency, delivery, and cost. It can flexibly adjust evaluation weights according to the actual goals of the enterprise, supporting rapid and rational decision-making under differentiated strategic intentions, and significantly improving the comprehensive management capabilities and overall operational efficiency of the production system in responding to anomalies. Attached Figure Description
[0017] Figure 1 This is a schematic diagram of an embodiment of the present invention. Detailed Implementation
[0018] The following detailed description illustrates the specific implementation method: The basic implementation examples are as follows: Figure 1 As shown: A method for equipment operation and anomaly control based on digital twins includes the following steps: S1. Construct a digital twin of the production equipment in the factory and acquire real-time data of the production equipment. The real-time data includes real-time operation data and real-time production data. Based on the digital twin of the production equipment, construct a virtual mapping of the entire production line in the digital twin. S2. Detect the operating data of each production equipment. When abnormal operating data is detected, simulate the production scenarios under different solution strategies in the future time period through virtual mapping of the production line based on the real-time operating data and historical data of the equipment. The historical data includes the historical operating data and historical production data of the equipment. S3. Based on the predicted production scenario for the future time period, analyze the impact of different solution strategies on order delivery, and select the optimal solution strategy based on the impact.
[0019] The principle and advantages of this invention are as follows: By constructing digital twins of production equipment within a factory and acquiring real-time operational and production data, a virtual mapping of the entire production line is established, thereby achieving comprehensive digital representation and dynamic synchronization of physical entities. When equipment malfunctions are detected, the digital twins, combined with real-time and historical data, are used to simulate production scenarios for a preset future time period under different solution strategies. Based on the prediction results, the specific impact of each strategy on order delivery is analyzed, and the optimal solution strategy is automatically selected. This method significantly improves the real-time performance and accuracy of anomaly response, overcoming the lag and false alarm / missed detection problems of traditional methods relying on fixed thresholds or periodic detection. It achieves a shift from passive processing to proactive predictive decision-making, effectively ensuring the reliable execution of production plans and on-time order delivery, and enhancing the resilience and intelligent management level of the overall production system.
[0020] S1 includes the following steps: S11. Construct a virtual mapping relationship between each device in the digital entity through a relational database to determine the flow of logistics; S12. Each device node defines its key capability parameters, including standard cycle time, maximum operating speed, mean time to repair faults, and changeover time. S13, Bind the dependencies between various devices.
[0021] By establishing virtual mapping relationships between equipment and clarifying the flow of materials through a relational database, a clear data structure and logical connection foundation are provided for the entire digital twin system. By defining key capability parameters for each equipment node, including standard cycle time, maximum operating speed, mean time to repair (MTBT), and changeover time, the digital twin possesses the ability to accurately reflect the actual operating characteristics and bottlenecks of the equipment. Binding the dependencies between equipment ensures the coherence and realism of the production line-level simulation, accurately depicting the interconnected effects and capacity constraints between equipment. This series of steps collectively constitutes the underlying support of the high-fidelity digital twin, enabling it to provide reliable and realistic production scenario predictions in subsequent anomaly simulations and strategy evaluations, laying a solid foundation for refined management and scientific decision-making.
[0022] S2 includes the following steps: S21. Identify abnormal operating data that exceeds a preset threshold based on real-time operating data, and inject the abnormal operating data into the digital twin of the production equipment; S22. Obtain the real-time production plan, and based on the production plan and the injected abnormal operation data, predict the production scenario of continuing to execute the current production plan in a future preset period. S23. Based on the production plan and the injected abnormal operation data, predict the production scenario for a future preset period after continuing to perform maintenance on the abnormal operation data and then continuing to execute the current production plan.
[0023] Anomalies are identified by comparing real-time operational data with preset thresholds, and the abnormal data is dynamically injected into the digital twin of the corresponding equipment to ensure that the virtual model can reflect changes in the actual equipment status in a timely manner. Based on this, future production scenarios under two response strategies are simulated: one is to continue executing the original plan, and the other is to first conduct operational intervention and then resume production, thereby comprehensively predicting the possible outcomes of different decision paths. This method fully utilizes historical data and real-time information to rehearse multiple response plans in virtual space, greatly enhancing the foresight of management and the comparability of strategies, avoiding the uncertainty of decisions based solely on experience, and providing rich and accurate input data for subsequent quantitative evaluation and optimization.
[0024] S22 includes the following steps: S221. Obtain current production plan information, wherein the production plan information includes order details, production quantity, and delivery time nodes; S222. Based on the abnormal operating data, determine the impact parameters of the abnormal operating data on the operating efficiency of the equipment, including the equipment speed reduction ratio and the probability of failure. S223. Based on the aforementioned influencing parameters, a simulation is performed in the digital twin of the production line to predict the equipment operating status, production quantity, and order completion status within a future predicted time period, assuming the current production plan continues to be executed, and the simulation results are output.
[0025] By acquiring detailed production plans including order details, production quantities, and delivery milestones, and combining these with equipment operating efficiency impact parameters derived from anomaly data, such as speed reduction ratios and failure probabilities, precise simulation input conditions are constructed. Dynamic simulations are then performed within a digital twin of the production line to predict equipment operating status, output quantities, and order completion status in future timeframes, outputting quantitative results. This process achieves a closed loop from anomaly identification to impact projection, enabling managers to clearly understand potential production delays and capacity losses without intervention. It provides direct evidence for assessing the severity of anomalies and the urgency of decisions, supporting early recognition and prevention of production risks.
[0026] S23 includes the following steps: S231. Based on abnormal operation data, generate one or more operation and maintenance strategies, including immediate shutdown for maintenance, adjustment of process parameters, and slowing down operation until the planned shutdown window before maintenance. S232. In the digital twin of the production line, simulate the process of executing the selected operation and maintenance strategy, and predict the resources and duration required for the operation and maintenance; S233. In the digital twin, after the simulation completes the operation and maintenance strategy, the equipment returns to normal and continues to execute production based on the updated production plan; S234. Simulate the complete production scenario starting from the current moment, going through the maintenance period and production recovery period, until the end of a preset time period in the future, predict the total output and order delivery delay under this strategy, and output the simulation results.
[0027] First, multiple feasible operation and maintenance strategies are generated, including immediate repair, parameter adjustment, or planned window repair, covering responses under different levels of urgency and resource constraints. Then, the resources and time required for operation and maintenance are simulated in a digital twin, and the production process based on the updated plan after the equipment returns to normal is further simulated. Finally, the total output and delivery delay under this strategy are output. This method enables virtual verification and pre-evaluation of the entire operation and maintenance decision-making process, allowing enterprises to coordinate resources in advance, optimize maintenance plans, minimize the impact of unplanned downtime on production continuity, and provide data support for comparing the comprehensive benefits of different maintenance strategies, thus improving the scientific and economical nature of operation and maintenance management.
[0028] S3 includes the following steps: S31. Construct multiple evaluation dimensions to quantify the impact of different solution strategies on order delivery. The evaluation dimensions include production delivery dimension, production efficiency dimension, and cost dimension. S32. Based on the simulation results output in steps S22 and S23, calculate the score of each solution strategy under each evaluation dimension, and calculate the comprehensive impact score of each strategy. S33. Sort all strategies according to the comprehensive impact score, and select the strategy with the best score as the recommended optimal solution strategy.
[0029] By constructing an evaluation system covering multiple aspects such as production delivery, production efficiency, and cost, simulation results under different strategies are transformed into comparable indicator scores. Weighted or comprehensive algorithms are used to calculate the overall impact score of each strategy, and based on this, ranking and optimal strategy selection are performed, thus achieving a leap from scenario prediction to decision support. This method overcomes the limitations of traditional anomaly handling that relies on single indicators or subjective experience, achieving multi-objective optimization that integrates efficiency, delivery, and cost. It can flexibly adjust evaluation weights according to the actual goals of the enterprise, supporting rapid and rational decision-making under differentiated strategic intentions, and significantly improving the comprehensive management capabilities and overall operational efficiency of the production system in responding to anomalies.
[0030] The above are merely embodiments of the present invention. Commonly known structures and characteristics are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.
Claims
1. A method for equipment operation and anomaly control based on digital twins, characterized in that: Includes the following steps: S1. Construct a digital twin of the production equipment in the factory and acquire real-time data of the production equipment. The real-time data includes real-time operation data and real-time production data. Based on the digital twin of the production equipment, construct a virtual mapping of the entire production line in the digital twin. S2. Detect the operating data of each production equipment. When abnormal operating data is detected, simulate the production scenarios under different solution strategies in the future time period through virtual mapping of the production line based on the real-time operating data and historical data of the equipment. The historical data includes the historical operating data and historical production data of the equipment. S3. Based on the predicted production scenario for the future time period, analyze the impact of different solution strategies on order delivery, and select the optimal solution strategy based on the impact.
2. The method for equipment operation and anomaly control based on digital twins according to claim 1, characterized in that: S1 includes the following steps: S11. Construct a virtual mapping relationship between each device in the digital entity through a relational database to determine the flow of logistics; S12. Each device node defines its key capability parameters, including standard cycle time, maximum operating speed, mean time to repair faults, and changeover time. S13, Bind the dependencies between various devices.
3. The method for equipment operation and anomaly control based on digital twins according to claim 2, characterized in that: S2 includes the following steps: S21. Identify abnormal operating data that exceeds a preset threshold based on real-time operating data, and inject the abnormal operating data into the digital twin of the production equipment; S22. Obtain the real-time production plan, and based on the production plan and the injected abnormal operation data, predict the production scenario of continuing to execute the current production plan in a future preset period. S23. Based on the production plan and the injected abnormal operation data, predict the production scenario for a future preset period after continuing to perform maintenance on the abnormal operation data and then continuing to execute the current production plan.
4. The method for equipment operation and anomaly control based on digital twin according to claim 3, characterized in that: S22 includes the following steps: S221. Obtain current production plan information, wherein the production plan information includes order details, production quantity, and delivery time nodes; S222. Based on the abnormal operation data, determine the impact parameters of the abnormal operation data on the operating efficiency of the equipment, including the equipment speed reduction ratio and the probability of failure. S223. Based on the aforementioned influencing parameters, a simulation is performed in the digital twin of the production line to predict the equipment operating status, production quantity, and order completion status within a future predicted time period, assuming the current production plan continues to be executed, and the simulation results are output.
5. The method for equipment operation and anomaly control based on digital twins according to claim 4, characterized in that: S23 includes the following steps: S231. Generate one or more operation and maintenance strategies based on abnormal operation data. The operation and maintenance strategies include immediate shutdown for maintenance, adjustment of process parameters, and slowing down operation until the planned shutdown window before maintenance. S232. In the digital twin of the production line, simulate the process of executing the selected operation and maintenance strategy, and predict the resources and duration required for the operation and maintenance; S233. In the digital twin, after the simulation completes the operation and maintenance strategy, the equipment returns to normal and continues to execute production based on the updated production plan; S234. Simulate the complete production scenario starting from the current moment, going through the maintenance period and production recovery period, until the end of a preset time period in the future, predict the total output and order delivery delay under this strategy, and output the simulation results.
6. The method for equipment operation and anomaly control based on digital twin according to claim 5, characterized in that: S3 includes the following steps: S31. Construct multiple evaluation dimensions to quantify the impact of different solution strategies on order delivery. The evaluation dimensions include production delivery dimension, production efficiency dimension, and cost dimension. S32. Based on the simulation results output in steps S22 and S23, calculate the score of each solution strategy under each evaluation dimension, and calculate the comprehensive impact score of each strategy. S33. Sort all strategies according to the comprehensive impact score, and select the strategy with the best score as the recommended optimal solution strategy.