An automated test method and system applicable to large current process control

Abstract

The present invention relates to the technical field of electrical performance testing, and particularly to an automated testing method and system applicable to large current program control. The method includes the following steps: obtaining the large current program control system log and the large current program control system monitoring data, and performing system state modeling to obtain a system state dynamic model; performing upsampling on the system state dynamic model in the workflow environment to obtain scenario simulation data; performing simulation state mode recognition on the system state dynamic model according to the scenario simulation data, so as to obtain system process simulation state mode data; calculating the system state mode score for the system process simulation state mode data based on the system state constraint dynamic model to obtain the program control system state score data; selecting a process control system repair strategy according to the program control system state score data and the large current program control system log, so as to obtain a system repair strategy. The present invention can improve the stability of the large current program control system.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical performance testing, and particularly to an automated testing method and system suitable for large current process control. Background Art

[0002] Large current process control systems manage and monitor complex processes in an automated manner, ensuring the stability and efficiency of the production process. However, in the design and application of these systems, how to ensure their reliability, stability, and security, especially the accuracy in complex working environments, has always been a key concern in the industrial community. To ensure the performance and stability of these control systems, automated testing has become a crucial technical means. Traditional testing methods for large current process control systems can be roughly divided into manual testing, script-based testing, and simulation testing, etc. Although these traditional testing methods can play a role in some cases, they have many defects that cannot be ignored. The manual testing method is one of the earliest methods used in traditional testing. Testers operate the control system manually, observe its responses, and record test data. However, manual testing usually relies on human judgment, which is prone to human errors during the testing process, and at the same time, the testing efficiency is low and the reproducibility is poor. Especially when facing large-scale systems or complex processes, manual testing is difficult to cover all test scenarios and difficult to ensure the stability and repeatability of test results. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide an automated testing method and system suitable for large current process control to solve at least one of the above technical problems.

[0004] To achieve the above object, an automated testing method suitable for large current process control includes the following steps:

[0005] Step S1: Obtain the large current process control system log and the large current process control system monitoring data, and perform a workflow topology structure modeling based on the large current process control system log to obtain a workflow topology structure model; perform a system state modeling based on the workflow topology structure model and the large current process control system monitoring data to obtain a system state dynamic model;

[0006] Step S2: Perform a program control system requirement mapping on the system state dynamic model to obtain a system state constraint dynamic model, and perform a real-time system state anomaly detection based on the system state constraint dynamic model to obtain system anomaly state data; perform a workflow environment upsampling based on the system anomaly state data and the system state dynamic model to obtain scenario simulation data;

[0007] Step S3: Perform program-controlled system state simulation on the system state dynamic model according to the scenario simulation data, so as to obtain program-controlled system simulation state data, and perform simulation state mode recognition based on the program-controlled system simulation state data, so as to obtain system process simulation state mode data;

[0008] Step S4: Calculate the system state mode score for the system process simulation state mode data based on the system state constraint dynamic model, so as to obtain program-controlled system state score data;

[0009] Step S5: Select a process control system repair strategy according to the program-controlled system state score data and the large power process control system log, so as to obtain a system repair strategy, and upload it to the large power process control system to execute the program repair task.

[0010] Through the construction of an accurate model and simulation mechanism, the present invention can greatly improve the reliability, stability, and security of the large-scale power process control system in a complex working environment. By acquiring and analyzing the log data and monitoring data of the large-scale power process control system, the modeling of the working process topology structure can be realized first, and then the structural relationship and dynamic characteristics of the large-scale power process control system can be clarified, ensuring that the state of the large-scale power process control system can be accurately monitored and understood during the testing and operation processes. Based on this model, the dynamic state characteristics of the large-scale power process control system can be further obtained to ensure that the large-scale power process control system can always maintain a predetermined stable state in a changing environment. Through the dynamic modeling and requirement mapping of the large-scale power process control system state, abnormal states can be captured in real time during the operation of the large-scale power process control system, so as to timely discover potential faults of the large-scale power process control system. This real-time anomaly detection and data collection provide high-quality data support for subsequent simulation and repair of the large-scale power process control system, ensuring the comprehensiveness and accuracy of the testing. With the generation of scenario simulation data, the operation state of the large-scale power process control system in different environments can be simulated, which lays a foundation for further state simulation and pattern recognition, and more abundant system behavior data can be obtained through simulation. The recognition of the simulation state mode not only helps to understand the possible different states during system operation, but also can reveal potential process patterns and the relationships between states, providing a strong basis for subsequent performance optimization and fault prevention. The calculation of the state mode score based on the state constraint model of the large-scale power process control system can quantitatively evaluate the overall state of the large-scale power process control system, further providing data support for the maintenance and optimization of the large-scale power process control system. Through these scores, the performance of the large-scale power process control system can be accurately evaluated, abnormal performance can be timely discovered, and a scientific basis can be provided for formulating effective repair strategies. This data-driven repair strategy selection not only improves the stability of the process control system, but also reduces manual intervention through automated means, reducing the possibility of human errors, thus significantly enhancing the reliability and security of the entire system. Generally speaking, these steps together achieve the accurate monitoring and efficient testing of the system in a complex environment, can automatically detect and repair system anomalies, and while ensuring the stability of the production process, ensure the long-term efficient operation of the large-scale power process control system. The core advantage of this method lies in providing an automated, efficient, and repeatable testing and repair solution through data-driven modeling and simulation, reducing the need for manual intervention, and improving the reliability and maintainability of the overall large-scale power process control system.

[0011] Optionally, step S1 is specifically as follows:

[0012] Step S11: Obtain the log of the large-scale power process control system and the monitoring data of the large-scale power process control system;

[0013] Step S12: Perform data preprocessing on the large-scale process control system logs and the large-scale process control system monitoring data respectively, so as to obtain the process control system logs to be analyzed and the process control system monitoring data to be analyzed;

[0014] Step S13: Integrate the system function module features according to the process control system logs to be analyzed, so as to obtain the system function module data;

[0015] Step S14: Based on the system function module data, perform modeling of the workflow topology structure, so as to obtain the workflow topology structure model;

[0016] Step S15: According to the workflow topology structure model and the large-scale process control system monitoring data, perform system state modeling, so as to obtain the system state dynamic model.

[0017] Through the step-by-step analysis and modeling of the logs and monitoring data of the large-scale process control system, the present invention can effectively improve the transparency of system operation and the monitoring efficiency. By obtaining the logs and monitoring data of the system, it provides real and comprehensive original data for subsequent analysis. This process lays a solid foundation for the data preprocessing stage, ensuring that the data required for analysis is accurate, complete, and representative. During the data preprocessing process, the system can remove noise data, fill in missing values, and perform standardization processing, thereby ensuring the quality of the data to be analyzed and providing reliable data support for subsequent steps. The integration of system function module features can extract the key function module information of the system from complex log data, laying a foundation for building a more accurate model. Through this feature integration, the system can more clearly identify the correlation and dependence between different function modules, thus providing strong support for the structural analysis of the entire system. In the further process of modeling the workflow topology structure, through the analysis of system function modules, the collaborative relationship and information flow of each part of the system can be accurately constructed. This model not only reveals the internal organizational structure of the system, but also can intuitively present the workflow and interaction methods between different modules, providing an important basis for system optimization and fault troubleshooting. The system state dynamic modeling based on the topology structure model and monitoring data can realize the real-time monitoring and dynamic prediction of the system state. This dynamic model can reflect the behavior changes of the system under different operating conditions, helping managers to identify potential problems in a timely manner and issue early warnings, effectively improving the safety and stability of the system.

[0018] Optionally, step S14 is specifically:

[0019] Step S141: Extract function module interaction events and function module communications from the system function module data, so as to obtain function module interaction data and function module communication data;

[0020] Step S142: Connect the communication nodes of the function modules according to the communication data of the function modules, so as to obtain the connection data of the function module communication nodes;

[0021] Step S143: Perform time series analysis on the function module interaction data to obtain the time series data of the function module interaction events;

[0022] Step S144: Identify the time series dependence relationship based on the time series data of the function module interaction events to obtain the function module dependence relationship data;

[0023] Step S145: Model the topological structure of the work process according to the connection data of the function module communication nodes and the function module dependence relationship data, so as to obtain the topological structure model of the work process.

[0024] By extracting and analyzing the data of the system function modules, the present invention can effectively identify the interaction and communication modes between the function modules, thereby providing data support for subsequent system optimization and troubleshooting. First, extracting the function module interaction events and communication data can help clarify the actual data flow and interaction between the modules, and then reveal potential efficiency bottlenecks or communication problems. Through further analysis of the communication data, the connection methods and dependence relationships between the function modules can be identified, providing a clear framework for the optimized design of the program control system. At the same time, performing time series analysis and dependence relationship identification helps to reveal the temporal associations and work dependencies between the modules, further enhancing the stability and reliability of the system under different load conditions. Based on these analysis results, establishing a topological structure model of the work process not only helps to comprehensively understand the overall work process of the system, but also provides strong support for system optimization, automated scheduling, and fault prediction, thereby improving the operation efficiency of the system and its ability to handle complex tasks.

[0025] Optionally, step S15 is specifically as follows:

[0026] Step S151: Define the state space based on the topological structure model of the work process to obtain the system state space;

[0027] Step S152: Extract the system operation data from the logs of the large-scale power process control system to obtain the system operation data, and define the state transition rules for the system operation data and the monitoring data of the large-scale power process control system to obtain the state transition rules;

[0028] Step S153: Statistically calculate the state transition matrix according to the state transition rules and the system state space to obtain the system state transition matrix;

[0029] Step S154: Perform time series dynamic modeling based on the system state transition matrix and the large power process control system monitoring data, so as to obtain the system state dynamic model.

[0030] Through constructing a workflow topology structure model and defining the state space based on this model, the present invention can accurately identify possible operating states and the range of state changes, providing a comprehensive framework for subsequent state analysis. This process helps to quantify the entire process, thereby clarifying the working modes and state transitions under different conditions, and contributing to further dynamic monitoring and optimization. On this basis, extracting system operation data and defining state transition rules for it and the monitoring data can refine the logical relationship between each operation and state change, revealing the dynamic evolution mechanism of each link within the system. The definition of this rule not only provides a basis for accurate modeling, but also provides basic data support for later state prediction and fault diagnosis. By combining the state transition rules with the state space, a state transition matrix is formed. This matrix can accurately describe the conversion relationship between different states, providing the probability and conditions for the transition between system states, and providing a systematic perspective for dynamic monitoring. Based on this matrix, combined with the monitoring data for time series dynamic modeling, it can capture the trends and laws of state changes in real time, helping managers to make timely responses when the system state changes. Time series dynamic modeling not only helps to understand the past behavior of the system, but also can predict the possible future states of the system, providing a powerful tool for the long-term stability, early warning mechanism and fault troubleshooting of the system. Through this series of steps, the monitoring ability of the entire system is greatly improved, enabling it to more efficiently identify potential problems, optimize resource allocation, and improve the automation of the workflow and the reliability of the system.

[0031] Optionally, step S2 is specifically as follows:

[0032] Step S21: Obtain the large power process control system performance index data, and perform system requirement statistics on the large power process control system performance index data, so as to obtain the large power process control system requirement data;

[0033] Step S22: Perform program control system requirement mapping on the system state dynamic model according to the large power process control system requirement data, so as to obtain the system state constraint dynamic model;

[0034] Step S23: Obtain the large power process control system real-time monitoring data, and perform real-time system state anomaly detection on the large power process control system real-time monitoring data according to the system state constraint dynamic model, so as to obtain the system abnormal state data;

[0035] Step S24: Integrate the system operation process structure of the system state dynamic model, so as to obtain the system operation process structure model;

[0036] Step S25: Perform workflow environment upsampling based on the system exception status data and the system operation process structure model to obtain scenario simulation data.

[0037] By obtaining and statistically analyzing the performance index data of the large power process control system, the present invention can effectively understand the operation requirements of the system, providing detailed system requirement information for subsequent analysis. These requirement data can not only reflect the performance standards of the system during normal operation but also provide data support for system optimization. Based on these requirement data, mapping them into the system state dynamic model can construct a system state constraint dynamic model, which provides clearer constraint conditions for the operation of the system, ensuring that system operations are carried out within the predetermined requirement range, thereby improving the stability and reliability of the system. By obtaining and detecting anomalies in real-time monitoring data, potential problems and state anomalies in the system can be identified in real-time, ensuring that the system can respond and handle emergencies in a timely manner. This process can not only detect and locate faults in advance but also provide important data basis for fault troubleshooting and system recovery, thereby reducing system downtime and production losses. By integrating the system state dynamic model and the operation process structure, the overall architecture of system operations can be further sorted out, helping to analyze the associations and dependencies between various links. This integration process provides a clear framework for more efficient system scheduling, operation optimization, and process reconstruction. Using the abnormal state data and the system operation process structure model for environmental upsampling to generate scenario simulation data helps to perform multi-scenario simulations and tests on the system under different operating conditions. Scenario simulation can help analyze the performance and responses of the system under various complex environments and operating conditions, thereby providing reliable decision-making support, identifying potential risks in advance, and optimizing system design and work processes, further improving the emergency handling ability and overall operation efficiency of the system. Through these steps, the monitoring, optimization, and fault management capabilities of the entire large power process control system have been significantly improved, providing strong support for achieving efficient and stable power process control.

[0038] Optionally, step S23 is specifically as follows:

[0039] Step S231: Obtain the real-time monitoring data of the large power process control system and perform data preprocessing on the real-time monitoring data of the large power process control system to obtain the real-time monitoring data of the system to be analyzed;

[0040] Step S232: Perform system real-time dynamic state prediction on the real-time monitoring data of the system to be analyzed according to the system state constraint dynamic model to obtain the system real-time dynamic state data; perform system expected dynamic state integration on the performance index data of the large power process control system according to the system state constraint dynamic model to obtain the system expected dynamic state data;

[0041] Step S233: Calculate the deviation of the system's expected dynamic state from the real-time dynamic state data of the system and the system's expected dynamic state data, so as to obtain the system dynamic state deviation data;

[0042] Step S234: Identify the non-linear deviation state of the system's real-time dynamic state data according to the system dynamic state deviation data, so as to obtain the system abnormal state data.

[0043] Through the preprocessing of real-time monitoring data, the present invention makes the data clearer and more standardized, providing accurate basic information for subsequent analysis. Then, through real-time dynamic state prediction based on the system state constraint dynamic model, the current operating state of the system can be accurately captured, improving the understanding and control of the actual situation of the system. At the same time, the integration of the expected dynamic state of the performance index data helps to comprehensively evaluate the working performance of the system, and further provides a basis for system optimization and adjustment. By calculating the deviation between the real-time dynamic state and the expected dynamic state of the system, the deviation of the system can be quantified, so as to more accurately monitor various anomalies that may occur during the operation of the system. Through non-linear deviation state identification, various abnormal states that occur during the actual operation of the system can be effectively identified, so as to give early warnings in time and take corresponding measures to avoid serious system failures. The implementation of this series of steps can greatly improve the stability and reliability of the system, reduce the system downtime, optimize the resource allocation, and thus improve the overall production efficiency and economic benefits.

[0044] Optionally, step S25 is specifically as follows:

[0045] Step S251: Generate the abnormal operating system working scenarios based on the system abnormal state data for the system operation process structure model, so as to obtain the abnormal working process scenario dataset; generate the normal operating system working scenarios based on the system expected dynamic state data for the system operation process structure model, so as to obtain the normal working process scenario dataset;

[0046] Step S252: Perform Monte Carlo upsampling processing on the abnormal working process scenario dataset and the normal working process scenario dataset, so as to obtain the random working process scenario dataset;

[0047] Step S253: Parameterize the working scenarios based on the system operation process structure model, so as to obtain the working scenario parameter set;

[0048] Step S254: Perform working process scenario simulation on the random working process scenario dataset and the working scenario parameter set, so as to obtain the scenario simulation data.

[0049] By generating system working scenario datasets for abnormal and normal operations, the present invention can comprehensively reflect the performance of the system under different working states. This helps to analyze the operation of the system from different perspectives, especially the working process under abnormal states, providing valuable data support for system optimization and fault diagnosis. Then, through Monte Carlo upsampling processing, the diversity of the dataset can be enhanced by a randomization method, making the dataset more abundant, thereby improving the robustness and adaptability of model training, avoiding overfitting, and being able to better simulate complex and random operation scenarios in reality. In addition, the parameterization of the working scenario can simplify and structure complex working processes, providing a clear parameter framework for subsequent simulation and analysis, ensuring the efficiency and accuracy of the simulation process. The working process scenario simulation can convert theoretical data into simulation data in actual applications, providing sufficient experimental support for system verification, testing, and optimization, making the performance evaluation of the system more accurate, and being able to detect potential problems in a timely manner and make improvements.

[0050] Optionally, step S3 is specifically as follows:

[0051] Step S31: Extract historical working scenario features from the monitoring data of the program-controlled system to be analyzed, so as to obtain historical working scenario data;

[0052] Step S32: Based on the system state dynamic model, perform system historical state backtracking on the log of the program-controlled system to be analyzed, so as to obtain historical system state data;

[0053] Step S33: Perform correlation analysis on the historical working scenario data and the historical system state data, so as to obtain scenario-state correlation data;

[0054] Step S34: According to the scenario-state correlation data, and using the scenario simulation data to perform program-controlled system state simulation on the system state dynamic model, so as to obtain program-controlled system simulation state data;

[0055] Step S35: Based on the program-controlled system simulation state data, perform simulation state pattern recognition, so as to obtain system process simulation state pattern data.

[0056] Through the extraction of historical work scenario features, the present invention can help to deeply understand the working state and operation characteristics of the program control system over a period of time in the past, providing detailed background data for subsequent analysis. By combining the system state dynamic model to perform historical state backtracking on the program control system logs, the historical operation state of the system can be accurately restored, helping to identify potential operation problems and performance bottlenecks. The collection and backtracking of this historical data provide a comprehensive perspective for subsequent analysis. Conducting a correlation analysis between historical work scenario data and historical system state data can reveal the internal relationship between the system and its state under different work scenarios, helping to identify which working conditions and states are most likely to cause anomalies or performance degradation, thereby providing guidance for optimizing the system. These scenario-state correlation data provide a scientific basis for subsequent simulation and optimization models. Using these correlation data and scenario simulation data to simulate the system state dynamic model can generate more accurate system state simulation data, thereby improving the prediction ability of the model and enabling the system to operate more efficiently and reliably when facing future work scenarios. Based on the simulated state data for pattern recognition, the simulated state pattern of the system process can be refined, thereby identifying potential risks and optimization space of the system, helping to early warn of the abnormal state of the system and avoid possible failures and performance degradation. After the comprehensive application of this series of steps, not only can the reliability, stability and efficiency of the system operation be improved, but also more accurate decision-making support can be provided for the long-term maintenance and optimization of the system.

[0057] Optionally, step S35 is specifically as follows:

[0058] Step S351: Set the system state mode category based on the performance index data of the large-scale electric process control system, so as to obtain the system state mode category data;

[0059] Step S352: Extract the simulation state features from the simulation state data of the program control system, so as to obtain the simulation state feature data;

[0060] Step S353: Calculate the simulation state similarity according to the simulation state feature data, so as to obtain the simulation state feature similarity data;

[0061] Step S354: Perform simulation state clustering calculation on the simulation state data of the program control system based on the simulation state feature similarity data, so as to obtain the clustered simulation state data of the program control system;

[0062] Step S355: Perform simulation state pattern recognition on the clustered simulation state data of the program control system according to the system state mode category data, so as to obtain the simulation state pattern data of the system process.

[0063] Optionally, this specification also provides an automated test system applicable to large current process control for performing the automated test method applicable to large current process control as described above. The automated test system applicable to large current process control includes:

[0064] A system state modeling module, configured to obtain the large current process control system log and the large current process control system monitoring data, and perform a workflow topology structure modeling based on the large current process control system log to obtain a workflow topology structure model; perform a system state modeling based on the workflow topology structure model and the large current process control system monitoring data to obtain a system state dynamic model;

[0065] A system state anomaly detection module, configured to perform a program control system requirement mapping on the system state dynamic model to obtain a system state constraint dynamic model, and perform real-time system state anomaly detection based on the system state constraint dynamic model to obtain system anomaly state data; perform a workflow environment upsampling based on the system anomaly state data and the system state dynamic model to obtain scenario simulation data;

[0066] A program control system state simulation module, configured to perform a program control system state simulation on the system state dynamic model based on the scenario simulation data to obtain program control system simulation state data, and perform a simulation state pattern recognition based on the program control system simulation state data to obtain system process simulation state pattern data;

[0067] A pattern score calculation module, configured to perform a system state pattern score calculation on the system process simulation state pattern data based on the system state constraint dynamic model to obtain program control system state score data;

[0068] A repair strategy selection module, configured to select a process control system repair strategy based on the program control system state score data and the large current process control system log to obtain a system repair strategy, and upload it to the large current process control system to execute a program repair task.

[0069] The automated test system applicable to large current process control of the present invention can implement any one of the automated test methods applicable to large current process control of the present invention, and is used as a medium for coordinating the operations and signal transmissions between various modules to complete the automated test method applicable to large current process control. The internal modules of the system cooperate with each other, thereby improving the stability of the large current process control system and the test efficiency of the program control test. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, objectives, and advantages of the present invention will become more apparent:

[0071] Figure 1This is a schematic diagram of the step flow of the automated test method applicable to large current process control according to the present invention;

[0072] Figure 2 This is a detailed schematic diagram of the step flow of step S1 in the present invention;

[0073] Figure 3 This is a detailed schematic diagram of the step flow of step S2 in the present invention;

[0074] The realization of the object, functional features and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings. Specific embodiments

[0075] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative work fall within the scope of protection of the present invention.

[0076] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0077] It should be understood that although the terms "first", "second", etc. may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed associated items.

[0078] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides an automated test method applicable to large current process control, and the method includes the following steps:

[0079] Step S1: Obtain the large power process control system logs and the large power process control system monitoring data, and perform a workflow topology structure modeling based on the large power process control system logs to obtain a workflow topology structure model; perform a system state modeling based on the workflow topology structure model and the large power process control system monitoring data to obtain a system state dynamic model;

[0080] In this embodiment, by integrating with the large power process control system (such as the SCADA system) in the power system, real-time control data, device operation logs, and alarm information are automatically extracted. These data include the operating status of devices, sensor data, control instructions, fault records, etc. Use an API or a data interface to obtain this information regularly (such as every hour, daily) and store it in a central database for subsequent analysis. Based on the log data of the large power process control system, construct a workflow topology model of the power system. The topology structure includes information such as the connection relationships between various devices, control logic, and fault transfer paths. Use graph theory methods (such as directed graphs) to represent the topology structure of the process, where nodes represent devices or control nodes, and edges represent signal transmission or control relationships between devices. Suppose in a power grid control system, the topology model can be used to represent how generators, transformers, distribution equipment, etc. are interconnected and interact to ensure that each device and system can work correctly. Utilize the information obtained from the topology model and real-time monitoring data (such as device temperature, current, voltage, load, etc.) to construct a system state dynamic model. This model can reflect the operating state of the system, reflect the health status of the power system at any time, dynamically adjust the operating state of devices, and simulate different operating scenarios. For example, the system state dynamic model may include variables such as real-time load prediction of the system, device health, and energy flow path.

[0081] Step S2: Perform a program control system requirement mapping on the system state dynamic model to obtain a system state constraint dynamic model, and perform a real-time system state anomaly detection based on the system state constraint dynamic model to obtain system anomaly state data; perform a workflow environment upsampling based on the system anomaly state data and the system state dynamic model to obtain scenario simulation data;

[0082] In this embodiment, the requirements of the large-current control system are mapped into the system state dynamic model. That is, by comparing the goals of the control system with the current system state, it is identified which states do not meet the expected requirements. For example, if the system requires that the load of a certain transformer does not exceed a certain threshold, but the system state shows that its load has reached or exceeded the threshold, then this state can be marked as abnormal. During system operation, the states of each device are monitored in real time by comparing with a predetermined threshold for anomaly detection. Data-driven anomaly detection methods are adopted, such as control charts based on statistics or anomaly detection models based on machine learning, to identify abnormal states in the system in a timely manner. For example, when the current of a transformer exceeds the set safety threshold, the system automatically identifies it as an abnormal state and generates an alarm. According to the identified abnormal state data, possible working scenario data is generated. By upsampling the data of these abnormal states, the possibility of abnormal scenarios is extended. For example, when the current of a certain device is abnormal, different load change situations and system responses can be simulated to generate a series of new simulation data.

[0083] Step S3: Perform program-controlled system state simulation on the system state dynamic model according to the scenario simulation data, so as to obtain program-controlled system simulation state data, and perform simulation state pattern recognition based on the program-controlled system simulation state data, so as to obtain system process simulation state pattern data;

[0084] In this embodiment, according to the obtained scenario simulation data, the state of the power system is simulated through simulation software (such as MATLAB, Simulink, etc.), and the system responses under different faults, equipment aging or load fluctuations are simulated. For example, the simulation system will simulate how the system ensures the stable operation of the power grid by automatically switching to standby equipment after a transformer fault. Pattern recognition is performed on the simulation data, and machine learning algorithms (such as clustering analysis, support vector machines, neural networks, etc.) are used to identify different state patterns from the simulation data. For example, the simulation data will show different working states such as "normal operation mode", "overload mode", "equipment failure mode", etc., to help identify potential problems.

[0085] Step S4: Calculate the system state pattern score for the system process simulation state pattern data based on the system state constraint dynamic model, so as to obtain program-controlled system state score data;

[0086] In this embodiment, based on the simulation state mode data and the system state constraint dynamic model, the calculation of the state mode score is carried out. By evaluating the impact of different state modes on the overall stability, reliability and safety of the system, the score of each mode is calculated. Using, for example, the weighted method, fuzzy logic or optimization algorithm, the influence degree of each state mode is converted into a score value to evaluate its impact on the system. For example, if a certain mode (such as the overloaded mode) causes the system to frequently fail in the simulation, then the score of this mode will be lower, indicating that it poses a greater threat to the system stability. By synthesizing the score data of multiple state modes, the current overall state score of the system is calculated. This score reflects the health status, operation efficiency and risk level of the system.

[0087] Step S5: Select a process control system repair strategy according to the program control system state score data and the large power process control system log, so as to obtain a system repair strategy and upload it to the large power process control system to execute the program repair task.

[0088] In this embodiment, according to the program control system state score and the abnormal data in the system log, a suitable repair strategy is selected. The repair strategies include adjusting control parameters, switching to standby equipment, increasing load balancing, enabling redundant lines, etc. For example, when it is detected that a certain transformer is overloaded, select to start a standby transformer to share the load, or adjust the power distribution network to reduce the load in this area. After the repair strategy is selected, the repair plan will be automatically uploaded to the large power process control system, and the repair task will be executed according to the uploaded control instructions. For example, the large power process control system will automatically issue control instructions to adjust the working load of the transformer or switch to the standby system. During the execution process, the system monitors the repair effect in real time and performs rollback or re-attempt when it is found that the repair fails.

[0089] Optionally, step S1 is specifically:

[0090] Step S11: Obtain the large power process control system log and the large power process control system monitoring data;

[0091] In this embodiment, the log information and monitoring data of the large-scale power process control system are obtained through the system's management platform or data acquisition terminal. Specifically, the Industrial Internet of Things (IIoT) platform can be used to connect to various devices and sensors in the large-scale power process control system to collect the operation logs and real-time monitoring data of the system. The log information usually includes the device running time, alarm records, fault information, etc.; the monitoring data includes the operating status of power equipment and the data collected by various sensors (such as current, voltage, temperature, pressure, etc.). Standard data interfaces (such as Modbus, OPC-UA, etc.) can be used for data pulling to ensure the timeliness and integrity of the data. The communication protocols of the data acquisition system (such as the SCADA system) and each device can be configured to obtain the device status and data logs every 5 minutes. The REST API interface is used to extract real-time data (such as voltage, current, load, etc.) from different monitoring modules and save them as structured log files or database records.

[0092] Step S12: Perform data preprocessing on the large-scale power process control system logs and the large-scale power process control system monitoring data respectively to obtain the to-be-analyzed process control system logs and the to-be-analyzed process control system monitoring data;

[0093] In this embodiment, data preprocessing is to ensure that subsequent analysis can be carried out on clean and structured data. For system log data, the original logs can be first cleaned through regular expressions or log parsing tools (such as Logstash) to remove irrelevant noise information and extract key information (such as event type, timestamp, device ID, etc.). For monitoring data, data interpolation algorithms (such as linear interpolation method, K-nearest neighbor interpolation method, etc.) can be used to fill in the missing data due to communication failures or sensor failures, and outliers can be detected and corrected (such as outlier detection based on Z-score). A data cleaning program is written in Python to preprocess the log and monitoring data through the pandas library, remove useless fields and interpolate missing values. The system logs are classified, and the events are marked according to the severity level and stored in an easy-to-analyze format (such as CSV or JSON). The Savgol smoothing method (such as Savgol smoothing method) is used to smooth the monitoring data to reduce the influence of fluctuations caused by noise.

[0094] Step S13: Integrate the system function module features according to the to-be-analyzed process control system logs to obtain the system function module data;

[0095] In this embodiment, the system log is a record describing the operation history of the large power process control system, including various events that occur in the system. Analyze the program-controlled system log to be analyzed, and group the log data according to functional modules (such as power monitoring, equipment control, alarm management, etc.). Through event time series analysis, the activity characteristics of each functional module within a specific time period can be extracted (such as the execution of operation commands, the response to alarms, etc.). Extract features from the log information of each functional module. For example, extract common event types through frequency analysis, and find the correlation relationships between functional modules through association rule analysis. Use machine learning models (such as decision trees or random forests) to classify the log data, and extract the features of different functional modules such as the equipment control module, the monitoring module, and the alarm module. Integrate the features into the performance index data of each functional module, such as failure rate, response time, number of equipment startups, etc., and save them in the database for subsequent analysis.

[0096] Step S14: Based on the system functional module data, perform a workflow topology structure modeling to obtain a workflow topology structure model;

[0097] In this embodiment, according to the data of each functional module and their interactions, a workflow topology structure model of the system is constructed. Specifically, the graph theory method can be used. Each functional module in the system is regarded as a node of the graph, and the dependency relationship between functional modules is regarded as an edge of the graph. Use in-depth analysis techniques (such as co-occurrence analysis) to find the interaction relationships between modules, and then construct a topology graph reflecting the information flow, control flow, and event flow between modules. The state transition rules of each module can be further modeled using Bayesian networks or Markov decision processes (MDP). Graph visualization tools such as Gephi can be used to draw the workflow topology graph between functional modules, where nodes represent functional modules and edges represent the relationships between them. Analyze the bottlenecks of the workflow based on the topology graph, and propose optimization solutions such as adding redundant modules and optimizing the data transmission path.

[0098] Step S15: According to the workflow topology structure model and the large power process control system monitoring data, perform a system state modeling to obtain a system state dynamic model.

[0099] In this embodiment, a dynamic state model of the system is established by combining the workflow topology structure model and the monitoring data. Through the topological relationship of the workflow, the state change paths and dependency relationships of each module in the system are determined. Based on the real-time monitoring data (such as device status, sensor data, etc.), a state space model (such as Markov chain) or a time series data modeling method (such as long short-term memory network LSTM) is used to model the state of the system. The dynamic model can be used to simulate the changes in the system state under different conditions and predict possible system failures or performance degradation. The LSTM model can be used to model the monitoring data to predict the state changes of each module in the future time period and determine whether there is a fault risk. According to the workflow topology and the monitoring data, weights are assigned to each node in the graph model to simulate the behavior of the system under different loads and operating modes, thereby realizing the dynamic prediction of the system health state.

[0100] Optionally, step S14 is specifically as follows:

[0101] Step S141: Extract function module interaction events and function module communications from the system function module data, so as to obtain function module interaction data and function module communication data;

[0102] In this embodiment, interaction events and communication data are extracted from different function modules of the system. For example, in an automated production control system, the function modules may include a sensor module, an actuator module, a monitoring module, etc. These modules exchange data through specific communication protocols (such as Modbus, CAN, Ethernet, etc.). By analyzing the system log files to capture system communications, the interaction event data between different function modules can be extracted. Interaction events include actions such as signal transmission and data exchange between modules. The extracted communication data may include the timestamp of each event occurrence, the event type (such as read, write, request response, etc.), and the function modules involved.

[0103] Step S142: Connect the function module communication nodes according to the function module communication data, so as to obtain function module communication node connection data;

[0104] In this embodiment, based on the extracted communication data of functional modules, a communication node connection diagram of each functional module in the system is constructed. Taking a production system controlled by a PLC (Programmable Logic Controller) as an example, the functional modules of the control system include sensors, actuators, and a central control unit. By analyzing the communication data, the communication nodes of each functional module and the connection relationships between them can be determined. For example, assuming that the sensor module communicates with the central control unit via Ethernet, and the actuator module is connected to the central control unit via a serial port, then in the communication node connection diagram, the sensor, the central control unit, and the actuator are respectively used as nodes, and the communication connections are from the sensor to the central control unit and from the central control unit to the actuator. The finally generated data will include the identifiers of each communication node and the connection methods between the nodes (such as point-to-point, broadcast, cluster, etc.).

[0105] Step S143: Perform time series analysis on the functional module interaction data to obtain time series data of functional module interaction events;

[0106] In this embodiment, time series analysis is performed on the interaction event data extracted in the previous step. Assuming that in an industrial automation control system, there is a certain time delay between sensor data acquisition and actuator actions. By sorting and statistically analyzing the interaction data, the time relationships and sequences of event occurrences can be analyzed. For example, by analyzing the timestamps, the time intervals between each interaction event (such as the acquisition time of sensor data and the control command time of the actuator) can be determined, thereby obtaining a clear time series data set. These time series data will reflect the order and timeliness of the interaction between functional modules, revealing the working dependencies between modules.

[0107] Step S144: Identify time series dependency relationships based on the time series data of functional module interaction events to obtain functional module dependency relationship data;

[0108] In this embodiment, based on the time series data of functional module interaction events, the dependency relationships between modules are further identified. For example, by analyzing the event sequences of each module, it can be found that the outputs of some modules depend on the inputs of other modules. In a robot control system, the input data of sensors (such as temperature sensors, pressure sensors) depends on the states of actuators (such as motor speed or position). Through correlation analysis of time series data, the dependency relationship between the sensor module and the actuator module can be identified. At this time, methods such as association rules and time window analysis can be used to obtain which modules have events in sequence and the sequence and dependency relationships between them, thereby obtaining functional module dependency relationship data.

[0109] Step S145: Model the workflow topology structure based on the functional module communication node connection data and the functional module dependency relationship data, so as to obtain the workflow topology structure model.

[0110] In this embodiment, the functional module communication node connection data and the dependency relationship data obtained previously are used to construct the workflow topology structure model of the system. Taking a complex automated production line as an example, there are multiple functional modules in the system. Each module exchanges data through specific communication nodes and has a time-dependent relationship. Based on these data, a graph theory method can be used. Each functional module of the system is regarded as a node of the graph, the communication connection between modules is regarded as the edge of the graph, and the dependency relationship is regarded as the constraint of the graph. In this way, a clear topology structure model can be constructed to show the communication paths, data flows, and the order of dependency relationships of each functional module. This topology structure model can provide an important basis for system optimization, fault diagnosis, and performance improvement.

[0111] Optionally, step S15 is specifically:

[0112] Step S151: Define the state space based on the workflow topology structure model, so as to obtain the system state space;

[0113] In this embodiment, based on the structure of the topology model, the states of each node are discretely defined. For example, for a substation, "normal operation", "fault", or "under maintenance" can be defined as states. In this process, it is necessary to ensure that the defined state space covers all possible operating or fault conditions in the system. The output of this step is the state space of the system, which is a multi-dimensional space containing the states of all possible combinations of devices or operations. Suppose a power generation system includes generators, substations, and distribution equipment. The state space can be defined as the set of discrete states of each device. For example, the state space of a generator is {"normal operation", "out of service", "fault"}, the state space of a substation is {"operating", "out of service", "awaiting repair"}, and the state space of distribution equipment is {"normal", "overloaded", "short-circuited"}. By combining these states, the state space of the entire system can be obtained.

[0114] Step S152: Extract the system operation data from the large-scale power process control system log, so as to obtain the system operation data, and define the state transition rules for the system operation data and the large-scale power process control system monitoring data, so as to obtain the state transition rules;

[0115] In this embodiment, operation logs are extracted from the large-scale power process control system, and these logs record the real-time state changes of each device or operation in the system. Specifically, the logs contain information such as timestamps, device IDs, operation types (such as startup and shutdown, load regulation), and operation results (such as success, failure). Through log parsing algorithms (such as regular expressions or time series analysis methods), these operation data are extracted. By analyzing the extracted system operation data and monitoring data, state transition rules can be defined. These rules describe the conditions for transitioning from one state to another. For example, if the operation of a certain device (such as startup) is successful, the system state changes from "shutdown" to "running" state. If the operation fails, the state rolls back or enters the "fault" state. For instance, in the logs of a generator set, the following transitions can be observed: from the state "generator out of service" to "generator startup", provided that the device operation signal is startup and there is no fault report. From the state "generator startup" to "generator running", provided that certain stable operation parameters are reached after the device starts. In the extracted logs, assume that the operation log of a certain substation shows that a certain maintenance operation is successful, resulting in the state changing from "to be repaired" to "normal operation". This event can be part of the state transition rule. If no fault is found during the next maintenance of the same substation, the state remains "normal operation"; if a fault occurs, the state changes to the "fault" state.

[0116] Step S153: According to the state transition rules and the system state space, conduct state transition matrix statistics to obtain the system state transition matrix;

[0117] In this embodiment, based on the previously defined state space and state transition rules, a state transition matrix can be constructed. The state transition matrix is a matrix representing the probability of state changes, where each element represents the transition probability from one state to another. According to the log data, count the transition frequencies from one state to another. For example, by analyzing the operation logs of the system, record the frequency of the state changing from "generator normal operation" to "generator out of service", and convert these frequencies into transition probabilities. Through the statistics of multiple operations and state changes, gradually construct a complete state transition matrix. Assume that by analyzing the historical data of the large-scale power process control system, it is found that when the system state changes from "normal operation" to "fault", the transition frequency is 30%; the frequency of transitioning from "normal operation" to the "maintenance" state is 20%; and the remaining 50% of the transitions remain in the "normal operation" state. Based on these statistics, form the corresponding state transition matrix.

[0118] Step S154: Based on the system state transition matrix and the large-scale power process control system monitoring data, conduct time series dynamic modeling to obtain the system state dynamic model.

[0119] In this embodiment, based on the constructed state transition matrix and real-time monitoring data (such as real-time status monitoring information from the SCADA system), time series modeling methods (such as ARIMA, LSTM, etc.) can be used to establish the state dynamic model of the system. This model can predict the future state evolution of the system based on past state transition patterns and real-time data. By collecting monitoring data and corresponding state transition matrices at multiple time points, machine learning methods (such as deep learning models) can be used for training. The time series model needs to consider the time delay of state transition, external perturbations (such as power demand fluctuations), and the impact of system failures to achieve more accurate predictions. Suppose an LSTM model is used to model the state of the power system, and the input data includes the state transition matrix and historical monitoring data, such as the output power and load of generators. By training this model, the state evolution of each device in the system can be predicted in the future, potential failures can be detected in a timely manner, and maintenance or adjustment can be carried out in advance.

[0120] Optionally, step S2 is specifically as follows:

[0121] Step S21: Obtain the performance index data of the large-scale process control system, and conduct system requirement statistics on the performance index data of the large-scale process control system to obtain the system requirement data of the large-scale process control system;

[0122] In this embodiment, performance index data related to the system operation is collected from the large-scale process control system. Specifically, data such as system load, equipment operation efficiency, response time, processing capacity, and failure rate can be obtained through real-time monitoring devices or collectors. Data collection devices can be implemented using tools such as PLC (Programmable Logic Controller) and SCADA (Supervisory Control and Data Acquisition System). The collected raw data needs to be subjected to data cleaning, denoising, and standardization processing to ensure its quality and reliability. Then, these data are sorted through data statistical analysis methods (such as regression analysis and time series analysis), and indicators such as average value, maximum value, minimum value, fluctuation range, and standard deviation are calculated. Further analyze the system performance requirements (such as load fluctuation range, response speed, etc.) to extract the key indicators affecting the system performance, and finally form the system requirement data. These requirement data will provide a basis for the subsequent creation of the dynamic model. Suppose a power process control system monitors the operation status and load data of 10 generator sets in real time through the SCADA system. The performance indicators of each generator set include operating power, fuel consumption, temperature, pressure, etc. After data cleaning and denoising, the time series analysis method is used to statistically obtain data such as the average load fluctuation range and failure occurrence frequency of each unit, and finally generate the requirement data of the power system, such as "the maximum value of the system load requirement is 400 MW, the minimum value is 100 MW, and the target load fluctuation range is ±10%."

[0123] Step S22: Perform a program control system requirement mapping on the system state dynamic model according to the large power process control system requirement data, so as to obtain a system state constraint dynamic model;

[0124] In this embodiment, the system requirement data will be used to perform requirement mapping on the existing system state dynamic model. The system state dynamic model is usually a mathematical model based on the power process, such as a model based on the state space model (State Space Model), Markov chain model, etc., to describe the change of the system state over time. On this basis, according to the obtained system requirement data, the parameters or constraint conditions in the model are dynamically adjusted to enable it to reflect the current system requirements. For example, if the system load demand increases, the relationship between power output and load in the model needs to be adjusted to ensure that the model can stably predict the system state during actual operation. Suppose in a power control system, the power load demand fluctuates greatly. According to the demand data analysis, the system load demand range is 100MW to 400MW. According to these demand data, modify the dynamic model of the system and add constraint conditions during load fluctuations to ensure the stability and security of the power system under different load conditions. For example, add a constraint condition: "When the load demand fluctuation exceeds ±10%, the system scheduling model should adjust the output of the generator set to ensure system stability."

[0125] Step S23: Obtain the real-time monitoring data of the large power process control system, and perform real-time system state anomaly detection on the real-time monitoring data of the large power process control system according to the system state constraint dynamic model, so as to obtain system anomaly state data;

[0126] In this embodiment, it is necessary to obtain the monitoring data of the large power process control system in real time. These data usually come from on-site sensors, monitoring devices or real-time data acquisition systems. The monitoring data includes data such as the temperature, pressure, power, and frequency of the generator set. By comparing with the system state constraint dynamic model, it is detected whether the system state is abnormal. Anomaly detection can identify data that does not conform to the normal operating state by setting a predetermined threshold or using machine learning algorithms (such as anomaly detection algorithms, clustering analysis). Once the system detects an anomaly, it can be marked as system anomaly state data. Suppose the real-time monitoring data of the power system includes the temperature (normal range is 70°C to 90°C), pressure (normal range is 2MPa to 4MPa), etc. of generator set A. If the monitoring data shows that the temperature of generator set A suddenly rises to 95°C, exceeding the set temperature threshold of 90°C, the system will mark this state as an abnormal state through the anomaly detection algorithm, trigger an alarm and record the abnormal state data.

[0127] Step S24: Integrate the system operation process structure of the system state dynamic model to obtain a system operation process structure model;

[0128] In this embodiment, the actual operation process topology structure in the obtained system state dynamic model is integrated to form an operation process structure model of the system. This process structure model not only includes the state changes of each component or link of the system, but also involves specific operation steps, control logics and decision rules. For example, in a power process control system, the control mode of the system, the start-stop sequence of equipment, the scheduling strategy, the emergency response mechanism, etc. can be represented in the forms of flowcharts, state machine diagrams, etc. In a power system, it is assumed that power production includes multiple operation processes such as the start-stop of generator sets, power dispatching, and load distribution. Through the analysis of the system state dynamic model, these operation processes are integrated step by step to form a comprehensive operation process model. This model includes control processes such as "when the load demand increases, start the standby generator set" and "when the system state is abnormal, trigger the emergency shutdown operation".

[0129] Step S25: Perform upsampling on the workflow environment according to the system abnormal state data and the system operation process structure model, so as to obtain scenario simulation data.

[0130] In this embodiment, the system abnormal state data and the operation process structure model are combined to perform simulation and upsampling of the workflow environment. The purpose of this step is to simulate the performance and response mechanism of the system under different abnormal states through virtual simulation or numerical simulation, and generate scenario simulation data. The sampling process can be completed based on the dynamic response characteristics of the model and historical data through simulation experiments or virtual simulation platforms. In a power system, when the system detects a fault in generator set A, workflow simulation is performed according to the obtained abnormal state data and operation process model. For example, simulate how to adjust the load distribution and start the standby unit after the fault occurs. Through multiple simulations, generate the state change data that the system may present under different conditions, and finally form scenario simulation data such as "the system load balancing time is 10 minutes after the fault occurs".

[0131] Optionally, step S23 is specifically:

[0132] Step S231: Obtain the real-time monitoring data of the large power process control system, and perform data preprocessing on the real-time monitoring data of the large power process control system, so as to obtain the real-time monitoring data of the system to be analyzed;

[0133] In this embodiment, various monitoring data are collected in real time from the large-scale power process control system through means such as Internet of Things devices and sensors. These monitoring data include, but are not limited to, information such as current, voltage, temperature, pressure, flow rate, and equipment operation status. This data is sent to the central data processing system through a data acquisition gateway. The acquired data often contains noise, missing values, outliers, etc., and needs to be preprocessed. The preprocessing process includes data denoising (such as using a filtering algorithm to remove high-frequency noise), data filling (filling missing values through interpolation methods), and data standardization (standardizing data with different dimensions to ensure the accuracy of subsequent analysis). For example, Gaussian filtering is used to remove noise from temperature data, and linear interpolation is used to fill missing data for flow rate data, and finally, the real-time monitoring data of the system to be analyzed for subsequent analysis is obtained.

[0134] Step S232: Perform system real-time dynamic state prediction on the real-time monitoring data of the system to be analyzed according to the system state constraint dynamic model, so as to obtain system real-time dynamic state data; perform system expected dynamic state integration on the performance index data of the large-scale power process control system according to the system state constraint dynamic model, so as to obtain system expected dynamic state data;

[0135] In this embodiment, based on historical data and real-time monitoring data, a system state constraint dynamic model (such as a prediction algorithm based on a Kalman filter or a deep learning model) is used for dynamic state prediction. This model predicts the dynamic changes of the system in the future period through known real-time monitoring data, such as current and pressure, combined with the state constraint conditions of the system (such as the maximum allowable load of the equipment and the temperature range). For example, a machine learning regression model is used to predict the operation status of the equipment in the next few minutes based on historical current and pressure data. Based on the performance index data of the system, such as power utilization rate, efficiency, energy consumption, etc., combined with the operation constraints of the system reflected by the system state constraint dynamic model (such as the upper limit of energy consumption and the requirement of load balancing), expected state integration is performed. A multivariable state integration method (such as weighted average method, state fusion method, etc.) is used to integrate performance index data from different sources to obtain the expected dynamic state data of the system under ideal conditions. For example, the power and load information of different devices are integrated into the overall expected dynamic state of the system using the weighted average method.

[0136] Step S233: Calculate the system expected dynamic state deviation amount for the system real-time dynamic state data and the system expected dynamic state data, so as to obtain system dynamic state deviation amount data;

[0137] In this embodiment, the deviation amount between the real-time dynamic state and the expected dynamic state of the computing system is calculated. The deviation amount can be obtained by calculating the difference or proportional difference between two state data. Specifically, the real-time dynamic state data and the expected dynamic state data are compared item by item to calculate the deviation of each item of data. For example, if the real-time temperature data is 95°C and the expected temperature is 90°C, the deviation is +5°C; if the real-time pressure data is 1.2 MPa and the expected pressure is 1.0 MPa, the deviation is +0.2 MPa. The deviations of all data items will form a system dynamic state deviation amount vector, which will reflect the difference between the actual operating state and the expected state of the system. By performing statistical analysis (such as mean value, variance analysis) on these deviation amounts, the operation deviation trend of the system is further analyzed.

[0138] Step S234: Based on the system dynamic state deviation amount data, perform non-linear deviation state identification on the system real-time dynamic state data to obtain system abnormal state data.

[0139] In this embodiment, based on the calculated dynamic state deviation amount data, a non-linear deviation state identification algorithm is used to diagnose whether the system is abnormal. Common non-linear deviation state identification methods include classification methods based on support vector machines (SVMs), abnormal detection methods based on neural networks, etc. Specifically, the system dynamic state deviation amount data is used as input features, and the data is classified through a trained model (such as an SVM model, a deep neural network, etc.). By comparing the real-time data with the preset normal state model, the abnormal state is identified. For example, if the system deviation amount exceeds the set threshold range, the model will mark it as an abnormal state, thereby triggering an alarm mechanism to notify the operation and maintenance personnel for processing. In practical applications, an abnormal threshold can be set. For example, a situation where the deviation amount exceeds ±10% is defined as an abnormal state.

[0140] Optionally, step S25 is specifically:

[0141] Step S251: Based on the system abnormal state data, generate abnormal operating system working scenarios for the system operation process structure model to obtain an abnormal working process scenario dataset; based on the system expected dynamic state data, generate normal operating system working scenarios for the system operation process structure model to obtain a normal working process scenario dataset;

[0142] In this embodiment, it is necessary to obtain the abnormal state data and normal state data of the system. The abnormal state data includes data of abnormal operations such as system failures, misconfigurations, and hardware failures, while the normal state data includes standard parameters and behaviors when the system operates under expected conditions. Using system operation process structure models (such as UML activity diagrams, workflow models, etc.), these data can be mapped to actual work scenarios. In specific implementations, methods such as fault tree analysis (FTA) can be used to generate corresponding abnormal workflow scenarios according to different abnormal state data. These scenarios include the workflow of the system when a certain failure occurs, such as network latency, hard disk failure, service interruption, etc. The generation of normal workflow scenarios is based on the normal dynamic behavior of the system without failures or errors, and usually combines the historical operation data of the system, expected business processes, and workload predictions to generate. Suppose the operation process of a production system includes steps such as "equipment startup", "temperature detection", and "data collection". The abnormal state data of the system includes equipment failures, overloads, or power outages, etc. In this step, the system uses historical fault records and real-time monitoring data to simulate abnormal situations in the operation process by modeling abnormal state scenarios (for example, power outage or automatic equipment shutdown). This can be achieved by introducing conditional decision models such as fault tree analysis (FTA) or Markov chain models to simulate the operation behavior of the system under specific abnormal conditions, and then generating a dataset of abnormal workflow scenarios. On the other hand, based on the normal operation state (such as the equipment operating under normal workload) and expected dynamic state data (such as the load, temperature, rotation speed, etc. of the equipment), normal workflow scenarios are generated. This can be done by summarizing the normal operation patterns in historical data and then using the state space model in control theory to simulate various workflow processes of the system under normal conditions. For example, when an automated production line is running normally, sensor data will show that the temperature, humidity, etc. are within the ideal range, and the system executes each operation task step by step according to the preset time step.

[0143] Step S252: Perform Monte Carlo upsampling processing on the abnormal workflow scenario dataset and the normal workflow scenario dataset to obtain a random workflow scenario dataset;

[0144] In this embodiment, the Monte Carlo upsampling technique is used to augment the abnormal workflow scenario dataset and the normal workflow scenario dataset. The Monte Carlo method is a statistical simulation method based on random sampling. By randomly selecting data points in the abnormal and normal datasets and performing repeated sampling, a large number of different workflow scenarios are generated. Specifically, assuming that the occurrence probabilities of certain operation processes (such as task scheduling, data processing, user requests, etc.) in specific scenarios are known, then these scenarios can be randomly simulated through Monte Carlo sampling, and possible workflow situations can be generated according to the probability distribution. For example, if the occurrence probability of a certain operation process is 0.8, then it is decided whether this operation process will occur in each scenario through random sampling. The finally generated random workflow scenario dataset has high diversity and representativeness.

[0145] Step S253: Parameterize the work scenarios based on the system operation process structure model to obtain a work scenario parameter set;

[0146] The parameterization of the work scenarios in this embodiment is a process of quantifying the relevant parameters in different workflow scenarios. Based on the system operation process structure model, each workflow step, task, event, etc. are abstracted into a set of parameters, such as execution time, resource consumption, response time, network bandwidth, system load, etc. In specific implementation, the system operation process can be modeled, and each node (operation step) and edge (relationship between tasks) are associated with corresponding performance indicators, environmental variables, etc. For example, assuming that a task corresponding to a certain workflow step requires a certain amount of CPU time, then its parameterization result will be the execution time of this task and the required CPU resources. Similarly, each step of each workflow is transformed into specific parameters, and these parameter sets constitute the work scenario parameter set. Each work scenario is mapped to a parameter set, which includes: the execution order of operation steps, the input and output conditions of each step, time delay, device status, environmental conditions, etc. For example, assuming that a typical operation process involves three steps: "start", "run", and "stop", the parameter set for the "start" step includes the time required for device startup, the energy required during startup, etc.; while the parameter set for the "stop" step contains data such as the time for device shutdown, the temperature and pressure of the device during shutdown. Assuming that in a pipeline operation, the startup time is usually 5 seconds and the device temperature is 20°C under normal circumstances. At this step, the state information of each link is extracted through the system model and transformed into quantifiable parameters, such as "device startup time = 5 seconds", "environmental temperature = 20°C", etc.

[0147] Step S254: Perform workflow scenario simulation on the random workflow scenario dataset and the work scenario parameter set to obtain scenario simulation data.

[0148] In this embodiment, the simulation of the workflow scenario is carried out by inputting the random workflow scenario data set and the work scenario parameter set into the simulation system to generate possible workflow execution results. Through simulation, the behavior, performance, and stability of the system under different work scenarios can be evaluated. Specifically, the method based on discrete event simulation (DES) can be used to perform event-driven simulation for each workflow scenario. For example, if a certain abnormal scenario is caused by insufficient network bandwidth resulting in data transmission delay, the impact of this scenario under different network conditions can be simulated, and the impact of network delay on the task execution time can be analyzed. Through this kind of simulation, the possible bottlenecks or failure modes of the system under different conditions can be predicted, and based on this, the performance of the system can be optimized or emergency handling strategies can be formulated. During the simulation process, simulation tools such as Simulink and Arena can be used to implement it, and the simulation results can include key performance indicators such as the completion time of each workflow, the consumption of system resources, and the response time. Assume that the system is an automated production line, including multiple work steps (such as "preparing materials", "operating equipment", "inspecting quality"). The generated random workflow scenario data set and parameter set are input into the simulation tool to simulate the performance of the production line under various normal and abnormal conditions. Through simulation, indicators such as the work efficiency, reliability, and failure rate of the system under different scenarios are evaluated. For example, in the normal operation scenario, the system completes a certain task within 10 seconds; while in the abnormal scenario, due to equipment failure, the task completion time may be extended or even the task may fail.

[0149] Optionally, step S3 is specifically as follows:

[0150] Step S31: Extract historical work scenario features from the monitoring data of the program-controlled system to be analyzed, so as to obtain historical work scenario data;

[0151] In this embodiment, historical monitoring data (such as sensor data, event logs, alarm records, etc.) is extracted from the program-controlled system. Then, based on these data, through time series analysis and data mining techniques, different work scenario features are identified, such as load status, equipment operation status, external environmental factors, etc. Feature selection algorithms (such as LASSO regression) can be used to screen the most representative features. Assume that a certain program-controlled system involves temperature sensor and pressure sensor data, and the historical data of these sensors can be divided into "high temperature and high pressure state" and "normal state", so as to extract relevant work scenario features.

[0152] Step S32: Based on the system state dynamic model, trace back the historical state of the program-controlled system to be analyzed from the system logs, so as to obtain historical system state data;

[0153] In this embodiment, the system state dynamic model (such as Markov chain or state transition diagram model) is used to trace back the system logs to be analyzed. Suppose the program control system includes multiple subsystems (such as temperature control system, power system, control system, etc.). By analyzing the historical logs, the path of historical state changes can be traced according to the occurrence order and timestamp of events. For example, the "power-on" operation log record of a certain control system can be mapped to the system state transition process through the dynamic model, and traced back to the initial startup state of the system and subsequent state changes. This process will be traced back in combination with the state transition rules in the model to obtain the system state data at each time point.

[0154] Step S33: Perform correlation analysis on the historical working scenario data and historical system state data to obtain scenario-state correlation data;

[0155] In this embodiment, statistical methods (such as Pearson correlation coefficient, mutual information method or regression analysis) are used to analyze the correlation between the historical working scenario data and system state data. For example, by analyzing the change rules of the system state (such as "power demand", "temperature change") under a specific working scenario (such as "high load working state"), the behavior pattern of the system and its relevance to the external environment can be revealed. Suppose that under the "high load" working scenario, the system state shows a correlation of high temperature and high pressure, which indicates that there is a strong correlation between temperature and pressure under high load conditions, reflecting the state characteristics of the system under high load.

[0156] Step S34: According to the scenario-state correlation data, and using the scenario simulation data to perform program control system state simulation on the system state dynamic model, so as to obtain the program control system simulation state data;

[0157] In this embodiment, according to the obtained scenario-state correlation data, in this step, combined with the scenario simulation data, the simulation of the system state dynamic model is carried out. For example, a multiple regression model fitted based on historical data and scenario-state correlation data is used to construct a system state simulation model, and the system state of the system state dynamic model is predicted through scenario simulation data (such as factors such as workload and environmental changes). Suppose for a temperature control system, the scenario data includes the working temperature range, and the system state dynamic model can simulate and predict the temperature change trend under different environmental conditions according to this data. This simulation result can help optimize the system operation strategy or give early warning of potential faults.

[0158] Step S35: Perform simulation state pattern recognition based on the program control system simulation state data to obtain the system process simulation state pattern data.

[0159] In this embodiment, the simulation state data of the program control system is analyzed through pattern recognition algorithms (such as K-means clustering, support vector machine SVM, neural network, etc.) to identify different simulation state patterns. For example, assuming that the simulation state data includes multiple indicators (such as pressure, temperature, flow rate, etc.), through clustering analysis, the system can divide the simulation state data into several patterns, such as "normal operation mode", "overload mode", "fault warning mode", etc. This process can use unsupervised learning algorithms (such as K-means) to cluster the simulation state data and identify patterns related to different states that occur in actual operations, providing support for subsequent process optimization and early warning system design.

[0160] Optionally, step S35 is specifically as follows:

[0161] Step S351: Set the system state mode categories based on the performance index data of the large-scale power process control system, so as to obtain the system state mode category data;

[0162] In this embodiment, the system state mode categories are set according to the performance indicators of the equipment (such as temperature, pressure, flow rate, current, etc.). By analyzing the historical performance indicator data and combining the normal operation state and abnormal state of the equipment, different state patterns are defined. For example, when the temperature and pressure exceed the preset thresholds at the same time, it can be defined as an "overload" state; when the flow rate is normal but the temperature is low, it is defined as an "inefficient" state. By setting thresholds or applying machine learning-based classification methods (such as decision trees, support vector machines, etc.) to classify the data, the system state mode category data is obtained. Suppose a control system of a chemical plant is monitored, and the system continuously records the data of various sensors. Use data processing tools (such as Pandas or Scikit-learn in Python) to read this data and apply the threshold method (for example, the temperature exceeding 100°C is the "overheat" mode) to classify the data, and finally form the state mode category data.

[0163] Step S352: Extract the simulation state features from the simulation state data of the program control system, so as to obtain the simulation state feature data;

[0164] In this embodiment, after obtaining the simulation state data of the program control system, it is necessary to extract representative feature information from it. Common features include the average value, standard deviation, maximum value, minimum value, and the trend of the data (such as the change rate or periodicity of the data). Assuming that the simulation data includes equipment temperature, flow rate, pressure, etc., the feature extraction process can use time series analysis methods, such as the sliding window method, to calculate the average temperature and the amplitude of pressure fluctuations in each time period, so as to extract features such as "temperature fluctuation" or "pressure stability". For example, for the pressure data, first preprocess the simulation state data (denoising, standardization, etc.), and then use a window function (such as a sliding window) to extract the average value and change rate in each time period to form state feature data, which can be used as the input for the next simulation state similarity calculation.

[0165] Step S353: Calculate the simulation state similarity based on the simulation state feature data, so as to obtain the simulation state feature similarity data;

[0166] In this embodiment, the simulation state similarity calculation is usually based on a certain similarity measurement method, such as Euclidean distance, cosine similarity, or Manhattan distance, etc. For each simulation state, by calculating the similarity between its feature vector and the feature vectors of other states, the similarity data between the simulation states is obtained. For example, assume that there are two simulation states, and their features are (temperature, pressure) = (100°C, 50MPa) and (102°C, 52MPa) respectively. The Euclidean distance formula can be used to calculate the similarity between the two, so as to obtain the similarity data. Based on the feature data of the simulation states, calculate the similarity between the features of each two simulation states. Assume that the extracted state feature data contains multiple dimensions (such as temperature, pressure, flow rate), use the Euclidean distance formula to calculate the similarity, and then obtain the similarity matrix between each two simulation states, which is used as the basis for the next clustering calculation.

[0167] Step S354: Perform simulation state clustering calculation on the program control system simulation state data based on the simulation state feature similarity data, so as to obtain the program control system clustering simulation state data;

[0168] In this embodiment, clustering calculations are performed based on the similarity data of simulation states. Common clustering methods include K-means clustering, DBSCAN (density clustering), and hierarchical clustering, etc. Through clustering, similar simulation states are divided into the same category to form a clustering result. For example, in K-means clustering, first, a preset K value (such as 3) is selected, and then the category to which each state belongs is iteratively optimized, so that the feature differences within each category are as small as possible, and the differences between categories are as large as possible. The final result is that each simulation state is classified into a specific state pattern category. Taking K-means clustering as an example, the previously calculated similarity matrix is used as the input data, and first, K = 3 is selected as the number of clusters. Then, the simulation state data is clustered by the K-means algorithm, and finally, three different simulation state clusters (such as "normal state", "minor fault state", and "severe fault state") are obtained.

[0169] Step S355: Perform simulation state pattern recognition on the clustered simulation state data of the program control system according to the system state pattern category data, so as to obtain the system process simulation state pattern data.

[0170] In this embodiment, based on the set system state pattern category data, pattern recognition is performed on the clustering result to determine the actual meaning of each clustering cluster. This process can be completed by comparing the actual operation performance of various simulation states with the corresponding pattern categories. For example, compare the states in the "normal state" cluster with the states in the "overload" cluster, and analyze the relationship between the clustering result and the preset pattern category from it. Finally, assign a specific process pattern (such as "normal operation", "high-temperature overload", etc.) to each clustering result. Assume that in step S354, three types of clustering results are obtained, namely clustering 1, clustering 2, and clustering 3. By comparing the performance of the normal operation state, minor fault state, and severe fault state in the historical data, clustering 1 is matched with the "normal operation" state pattern, clustering 2 is matched with the "minor fault" state, and clustering 3 is matched with the "severe fault" state. In this way, the recognition of the simulation state pattern is completed, and finally, the "system process simulation state pattern data" is generated.

[0171] Optionally, this specification also provides an automated test system applicable to large-scale power process control for executing the automated test method applicable to large-scale power process control as described above. The automated test system applicable to large-scale power process control includes:

[0172] A system state modeling module, configured to obtain the large-scale power process control system log and the large-scale power process control system monitoring data, and perform a workflow topology structure modeling according to the large-scale power process control system log, so as to obtain a workflow topology structure model; perform a system state modeling according to the workflow topology structure model and the large-scale power process control system monitoring data, so as to obtain a system state dynamic model;

[0173] The system status anomaly detection module is used to perform program-controlled system requirement mapping on the system status dynamic model to obtain the system status constraint dynamic model, and perform real-time system status anomaly detection based on the system status constraint dynamic model to obtain system anomaly status data; perform workflow environment upsampling based on the system anomaly status data and the system status dynamic model to obtain scenario simulation data;

[0174] The program-controlled system status simulation module is used to perform program-controlled system status simulation on the system status dynamic model according to the scenario simulation data to obtain program-controlled system simulation status data, and perform simulation status pattern recognition based on the program-controlled system simulation status data to obtain system process simulation status pattern data;

[0175] The pattern score calculation module is used to calculate the system status pattern score for the system process simulation status pattern data based on the system status constraint dynamic model to obtain program-controlled system status score data;

[0176] The repair strategy selection module is used to select a process control system repair strategy based on the program-controlled system status score data and the large power process control system log to obtain a system repair strategy, and upload it to the large power process control system to execute the program repair task.

[0177] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0178] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. An automated testing method suitable for large current process control, characterized in that: The following steps are involved: Step S1: Obtain the log of the large electric process control system and the monitoring data of the large electric process control system, and perform workflow topology modeling according to the log of the large electric process control system, so as to obtain the workflow topology model; perform system state modeling according to the workflow topology model and the monitoring data of the large electric process control system, so as to obtain the system state dynamic model; Step S2: mapping the system state dynamic model to the program control system requirements, thereby obtaining the system state constraint dynamic model, and performing real-time system state anomaly detection according to the system state constraint dynamic model, thereby obtaining system abnormal state data; Perform workflow environment upsampling based on system abnormal state data and system state dynamic model to obtain scenario simulation data; Step S3: performing program-controlled system state simulation on the system state dynamic model according to the scenario simulation data, thereby obtaining program-controlled system simulation state data, and performing simulation state pattern recognition based on the program-controlled system simulation state data, thereby obtaining system process simulation state pattern data; Step S4: Calculate the system state mode score of the system process simulation state mode data based on the system state constraint dynamic model, thereby obtaining the program control system state score data; Step S5: Select a process control system repair strategy based on the program control system status score data and the large-scale program control system log to obtain a system repair strategy, and upload the system repair strategy to the large-scale program control system to execute the program repair task.

2. The automated testing method for large current process control according to claim 1, characterized in that: Step S1 is specifically as follows: Step S11: Obtaining the large current process control system log and the large current process control system monitoring data; Step S12: performing data preprocessing on the large electric process control system log and the large electric process control system monitoring data respectively, so as to obtain the process control system log to be analyzed and the process control system monitoring data to be analyzed; Step S13: integrating system function module features according to the program-controlled system log to be analyzed, thereby obtaining system function module data; Step S14: Modeling the workflow topology structure based on the system function module data, thereby obtaining a workflow topology structure model; Step S15: System state modeling is performed according to the workflow topology model and the large power process control system monitoring data, so as to obtain a system state dynamic model.

3. The automated testing method for large current process control according to claim 2, characterized in that: Step S14 is specifically as follows: Step S141: extracting function module interaction events and function module communication from system function module data, thereby obtaining function module interaction data and function module communication data; Step S142: Connecting the function module communication nodes of the program control system according to the function module communication data, thereby obtaining the function module communication node connection data; Step S143: performing a function module interaction event time series analysis on the function module interaction data, thereby obtaining the function module interaction event time series data; Step S144: identifying time series dependency relationships based on the time series data of the functional module interaction events, thereby obtaining functional module dependency relationship data; Step S145: Modeling the workflow topology structure according to the functional module communication node connection data and the functional module dependency data, thereby obtaining a workflow topology structure model.

4. The automated testing method for large current process control according to claim 2, characterized in that: Step S15 is specifically as follows: Step S151: define the state space based on the workflow topology model, so as to obtain the system state space; Step S152: extracting system operation data from the large-scale process control system log, thereby obtaining system operation data, and defining state transition rules for the system operation data and the large-scale process control system monitoring data, thereby obtaining state transition rules; Step S153: performing state transfer matrix statistics according to the state transfer rule and the system state space, thereby obtaining the system state transfer matrix; Step S154: Perform time series dynamic modeling based on the system state transfer matrix and the large-scale power process control system monitoring data to obtain a system state dynamic model.

5. The automated testing method for large current process control according to claim 1, characterized in that: Step S2 is specifically as follows: Step S21: acquiring performance index data of a large current process control system, and performing system demand statistics on the performance index data of the large current process control system, thereby obtaining demand data of the large current process control system; Step S22: mapping the program control system requirements to the system state dynamic model according to the large electric program control system requirement data, thereby obtaining the system state constraint dynamic model; Step S23: acquiring the real-time monitoring data of the large-scale electric process control system, and performing real-time system state abnormality detection on the real-time monitoring data of the large-scale electric process control system according to the system state constraint dynamic model, thereby obtaining system abnormal state data; Step S24: integrating the system operation process structure of the system state dynamic model, thereby obtaining a system operation process structure model; Step S25: Perform workflow environment upsampling according to the system abnormal state data and the system operation process structure model, so as to obtain scenario simulation data.

6. The automated testing method for large current process control according to claim 5, characterized in that: Step S23 is specifically as follows: Step S231: acquiring real-time monitoring data of a large electric process control system, and performing data preprocessing on the real-time monitoring data of the large electric process control system, thereby obtaining real-time monitoring data of the system to be analyzed; Step S232: predicting the real-time dynamic state of the system to be analyzed based on the system state constraint dynamic model, thereby obtaining the real-time dynamic state data of the system; integrating the performance indicator data of the large electric process control system based on the system state constraint dynamic model, thereby obtaining the expected dynamic state data of the system; Step S233: calculating the system expected dynamic state deviation amount for the system real-time dynamic state data and the system expected dynamic state data, thereby obtaining the system dynamic state deviation amount data; Step S234: performing nonlinear deviation state identification on the system real-time dynamic state data according to the system dynamic state deviation data, thereby obtaining system abnormal state data.

7. The automated testing method for large current process control according to claim 5, characterized in that: Step S25 is specifically as follows: Step S251: generating an abnormal operating system working scenario for the system operation process structure model based on the system abnormal state data, thereby obtaining an abnormal workflow scenario data set; generating a normal operating system working scenario for the system operation process structure model based on the system expected dynamic state data, thereby obtaining a normal workflow scenario data set; Step S252: performing Monte Carlo upsampling processing on the abnormal workflow scenario data set and the normal workflow scenario data set, thereby obtaining a random workflow scenario data set; Step S253: parameterizing the work scenario based on the system operation process structure model, thereby obtaining a work scenario parameter set; Step S254: Perform workflow scenario simulation on the random workflow scenario data set and the workflow scenario parameter set to obtain scenario simulation data.

8. The automated testing method for large current process control according to claim 1, characterized in that: Step S3 is specifically as follows: Step S31: extracting historical working scene features according to the program control system monitoring data to be analyzed, thereby obtaining historical working scene data; Step S32: based on the system state dynamic model, the system historical state backtracking is performed on the program-controlled system log to be analyzed, so as to obtain historical system state data; Step S33: performing correlation analysis on the historical working scene data and the historical system status data, thereby obtaining scene-status correlation data; Step S34: simulating the state of the program-controlled system on the system state dynamic model according to the scene-state correlation data and using the scene simulation data, thereby obtaining the program-controlled system simulation state data; Step S35: Perform simulation state pattern recognition based on the program control system simulation state data, thereby obtaining system process simulation state pattern data.

9. The automated testing method for large current process control according to claim 8, characterized in that: Step S35 is specifically as follows: Step S351: setting the system state mode category based on the large current process control system performance indicator data, thereby obtaining the system state mode category data; Step S352: extracting simulation state features from the program control system simulation state data, thereby obtaining simulation state feature data; Step S353: performing simulation state similarity calculation according to the simulation state feature data, thereby obtaining simulation state feature similarity data; Step S354: performing simulation state clustering calculation on the program control system simulation state data based on the simulation state feature similarity data, thereby obtaining the program control system clustered simulation state data; Step S355: Perform simulation state pattern recognition on the clustered simulation state data of the program-controlled system according to the system state pattern category data, thereby obtaining system process simulation state pattern data.

10. An automated testing system suitable for large current process control, characterized in that: Used to execute the automated testing method applicable to large current process control as claimed in claim 1, the automated testing system applicable to large current process control comprises: The system state modeling module is used to obtain the log of the large-scale electric process control system and the monitoring data of the large-scale electric process control system, and to model the workflow topology structure according to the log of the large-scale electric process control system, so as to obtain the workflow topology structure model; and to model the system state according to the workflow topology structure model and the monitoring data of the large-scale electric process control system, so as to obtain the system state dynamic model; The system state anomaly detection module is used to map the system state dynamic model to the requirements of the program-controlled system, thereby obtaining the system state constraint dynamic model, and to perform real-time system state anomaly detection based on the system state constraint dynamic model, thereby obtaining system abnormal state data; and to perform workflow environment upsampling based on the system abnormal state data and the system state dynamic model, thereby obtaining scenario simulation data; The program-controlled system state simulation module is used to simulate the program-controlled system state on the system state dynamic model according to the scenario simulation data, thereby obtaining the program-controlled system simulation state data, and to perform simulation state pattern recognition based on the program-controlled system simulation state data, thereby obtaining the system process simulation state pattern data; A mode score calculation module is used to calculate the system state mode score of the system process simulation state mode data based on the system state constraint dynamic model, so as to obtain the program control system state score data; The repair strategy selection module is used to select the process control system repair strategy according to the program control system status score data and the large-scale program control system log, so as to obtain the system repair strategy, and upload the system repair strategy to the large-scale program control system to execute the program repair task.

Images