Method and system for intelligently monitoring abnormity in master control room of nuclear power station
By constructing an intelligent monitoring anomaly model based on the operator's experience and knowledge, the problems of the persistence and individual differences of monitoring anomalies in the main control room of nuclear power plants have been solved, realizing automated, timely and reliable anomaly monitoring, and improving the safety and economy of nuclear power plants.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-21
- Publication Date
- 2026-04-10
AI Technical Summary
The existing monitoring of anomalies in the main control room of nuclear power plants has problems such as the inability to continuously and uninterruptedly monitor parameters to detect anomalies due to human factors, and inconsistent standards and unstable results in detecting anomalies due to individual differences among operators.
An intelligent monitoring anomaly model based on the operator's experience and knowledge is constructed. Through knowledge collection and sorting, anomaly analysis and event tree construction, graphical configuration and debugging, an intelligent monitoring anomaly model diagram is formed and deployed to a real-time computing platform for real-time monitoring.
It enables uninterrupted automatic parameter monitoring and anomaly assessment, improving the timeliness, accuracy, and reliability of anomaly monitoring, reducing the workload of operators, and enhancing the safety and economy of nuclear power plants.
Smart Images
Figure CN121834569A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of nuclear power plant main control room monitoring technology, and in particular to a method and system for intelligent monitoring of anomalies in nuclear power plant main control rooms based on the experience and knowledge of operators. Background Technology
[0002] The main control room is the monitoring center of a nuclear power plant. Operators in the main control room monitor for anomalies by reviewing alarms from the digital control system (DCS) or by retrieving parameter change trends. When an anomaly occurs and parameters do not reach thresholds, the main control room operators are required to detect the anomaly by retrieving parameter change trends. Conversely, when an anomaly occurs and parameters reach thresholds, the main control room operators are required to detect the anomaly through DCS alarms.
[0003] Detecting anomalies through DCS alarms is reactive and delayed. Alarms are typically triggered only when parameters exceed safety thresholds, by which time the anomaly may have already progressed to a certain stage, requiring immediate intervention from operators. This passive response mode fails to provide operators with sufficient warning and preparation time, resulting in immense operational pressure and increased safety risks when anomalies occur in concentrated bursts.
[0004] The method of proactively detecting anomalies by analyzing parameter trends has limited effectiveness in practical applications. This approach is highly dependent on the individual operator's initiative, experience, and mental state. First, nuclear power plants require monitoring a vast number of parameters, and control room operators, in addition to their monitoring duties, undertake numerous other tasks, making it difficult to guarantee they consistently have sufficient time and energy to continuously and proactively analyze the trends of all key parameters. Second, due to differences in operational experience and knowledge among operators, their sensitivity to parameter changes, their standards for judging anomalies, and their ability to detect anomalies in advance vary, resulting in inconsistent monitoring effectiveness and a lack of unified and reliable judgment standards.
[0005] Therefore, at the level of nuclear power plant operation and management, although it is hoped that operators can detect anomalies in advance through proactive monitoring, existing technologies cannot effectively support the achievement of this goal. Summary of the Invention
[0006] One of the objectives of this invention is to address the problem that existing nuclear power plant main control room monitoring of anomalies is unable to continuously and proactively monitor parameters to detect anomalies due to human factors. The invention provides a method and system for intelligent monitoring of anomalies in the nuclear power plant main control room based on the experience and knowledge of operators. This method and system, by constructing an intelligent monitoring anomaly model based on the experience and knowledge of operators, can replace or assist manual work, achieving uninterrupted automatic parameter monitoring and anomaly assessment, thus freeing up the manpower and energy of operators.
[0007] The second objective of this invention is to address the problem of inconsistent standards and unstable results in detecting anomalies in the main control room of nuclear power plants due to individual differences among operators. This invention provides a method and system for intelligent anomaly monitoring in the main control room of nuclear power plants based on the experience and knowledge of operators. This method and system establish a unified, efficient, and above-average intelligent judgment standard by solidifying and integrating the experience and knowledge of excellent operators, thereby improving the consistency and reliability of anomaly monitoring by the entire main control room team.
[0008] This invention aims to effectively solidify the experience and knowledge of main control room operators by digitizing and modeling their operational experience and knowledge. It constructs an intelligent monitoring anomaly model based on the operators' experience and knowledge to overcome the limitations of human monitoring. This enables timely, reliable, and automated intelligent monitoring of abnormal states in nuclear power plants, improving the timeliness, accuracy, and reliability of anomaly monitoring, reducing the workload of operators, and enhancing the safety and economy of nuclear power plant operation. It is applicable to all types of nuclear power plants.
[0009] To achieve the above objectives, the present invention provides the following technical solution:
[0010] A method for intelligent monitoring of anomalies in the main control room of a nuclear power plant based on empirical knowledge includes the following steps:
[0011] Step 1: Analysis of intelligent monitoring anomaly model based on operator experience and knowledge, including: knowledge collection and organization; anomaly analysis and event tree construction; generation of intelligent monitoring anomaly model diagram;
[0012] Step 2: Graphical configuration and debugging of the intelligent monitoring anomaly model, including: variable definition and componentization; graphical configuration; model debugging and deployment.
[0013] As one feasible approach, step one, knowledge collection and organization, includes: comprehensively reviewing the important parameters of nuclear power plant units, and systematically collecting and analyzing technical documents and experience feedback data;
[0014] Anomaly analysis and event tree construction include: analyzing the prerequisites for unit anomaly diagnosis, which serve as the conditions for the intelligent monitoring anomaly model to take effect; analyzing the characteristics of parameter change trends caused by anomalies, and decomposing and expanding the causes of target parameter anomalies step by step to form a series of event trees with different causes;
[0015] The intelligent monitoring anomaly model diagram generation includes: forming an intelligent monitoring anomaly model diagram based on the operator's experience knowledge according to the event tree, which summarizes and unifies the logic and standards of anomaly identification.
[0016] As one possible approach, technical documents and experience feedback materials include alarm card procedures, main control room operator inspection procedures, periodic tests, system operation procedures, overhaul procedures, fault handling procedures, simulation diagrams, logic diagrams, flowcharts, main control room screens, advanced / intermediate operating procedures for nuclear power plants, main control room contingency plans, first-level analysis reports, and accident scenarios.
[0017] As one possible approach, in step one, the causes of the abnormal target parameters are decomposed and expanded step by step to form a series of event trees with different causes. Specifically, the event tree analysis method is used to logically expand the various causes that lead to the abnormal target parameters, forming a series of judgment sequences with causal relationships.
[0018] As one possible approach, in step one, multiple different intelligent monitoring anomaly models based on the operator's experience and knowledge are established for the same target parameter to cross-validate and reduce false alarms.
[0019] As one possible approach, step two involves graphical configuration, which includes: using a graphical configuration tool to bind each effective condition in the intelligent monitoring anomaly model diagram to the unit parameters; and by dragging and dropping predefined components and connections, mapping abstract effective conditions to specific, executable component combinations to form the intelligent monitoring anomaly model defined in the configuration diagram.
[0020] Model debugging and deployment include: using debugging tools to perform offline debugging and online testing of the intelligent monitoring anomaly model defined in the configuration diagram, and downloading the tested intelligent monitoring anomaly model to the real-time computing platform and connecting it to the production environment to monitor unit parameters in real time.
[0021] As one possible approach, in step two, the graphical configuration tool provides a predefined component library, which includes operators defined by IO and developed by algorithms. Users can drag and drop the required components from the component library and connect them to build an intelligent monitoring anomaly model defined by the configuration diagram.
[0022] As one possible approach, step two involves offline debugging, which includes: using the simulation function of the debugging tool to input simulated data and verify the correctness of the logic of the intelligent monitoring anomaly model; the operations provided by the debugging tool include: offline simulation, adding, modifying, deleting, and querying model information, downloading the model, and controlling the start, pause, and deletion of the model's running status.
[0023] As one feasible approach, step two involves online testing, including: downloading the intelligent monitoring anomaly model to the test environment and introducing real-time data from actual generating units for online debugging; alternatively, pre-set anomaly signals can be injected into simulated generating units to assess the early warning capabilities of the intelligent monitoring anomaly model in near-real-world scenarios.
[0024] As one feasible approach, in step two, after the test is passed, the intelligent monitoring anomaly model is officially downloaded to the real-time computing platform in the production environment to begin uninterrupted real-time monitoring of the unit parameters; the debugging tool also provides a monitoring interface for operators to view the operating status of the intelligent monitoring anomaly model, start and stop the intelligent monitoring anomaly model, and view the operating log of the intelligent monitoring anomaly model.
[0025] Secondly, the present invention provides a system for intelligent monitoring of anomalies in the main control room of a nuclear power plant based on empirical knowledge, and a method for implementing the above-mentioned intelligent monitoring of anomalies in the main control room of a nuclear power plant based on empirical knowledge, comprising:
[0026] The monitoring anomaly model construction module is used to perform intelligent monitoring anomaly model analysis based on operator experience and knowledge, and output intelligent monitoring anomaly model diagram;
[0027] The graphical configuration and debugging module provides a graphical configuration interface and debugging functions to convert intelligent monitoring anomaly model diagrams into executable intelligent monitoring anomaly models and deploy them to the production environment.
[0028] As one possible approach, the graphical configuration and debugging module integrates a real-time computing platform for running intelligent monitoring anomaly models and generating runtime logs.
[0029] Beneficial technical effects of the present invention:
[0030] Compared with the prior art, the present invention has the following beneficial effects:
[0031] The present invention relates to a method and system for intelligent monitoring of anomalies in the main control room of a nuclear power plant based on experiential knowledge, which effectively solidifies and inherits experiential knowledge. Through a systematic analysis method, the implicit operational experience and knowledge of individual operators in the main control room are transformed into explicit and reusable digital models, avoiding knowledge loss and fluctuations in monitoring standards caused by personnel turnover or individual differences, and establishing a unified and high anomaly identification benchmark.
[0032] The present invention relates to a method and system for intelligent monitoring of anomalies in the main control room of a nuclear power plant based on empirical knowledge, achieving automated and uninterrupted intelligent monitoring. The constructed intelligent monitoring anomaly model can replace manual labor, continuously and automatically analyzing parameter change trends, greatly reducing the routine monitoring burden on operators, allowing them to focus more on critical decision-making and intervention tasks, thereby solving the problem of the inability of manual proactive monitoring.
[0033] This invention presents a method and system for intelligent monitoring of anomalies in the main control room of a nuclear power plant, based on empirical knowledge, which improves the timeliness and reliability of anomaly monitoring. The intelligent monitoring anomaly model identifies anomalies based on event trees and multi-condition judgment, enabling early warnings at the initial stage of parameter change trends, providing a longer response time compared to passively waiting for DCS alarms. Simultaneously, by establishing multiple models for the same target parameter, false alarms are effectively reduced, improving monitoring accuracy.
[0034] This invention presents a method and system for intelligent monitoring of anomalies in the main control room of a nuclear power plant based on empirical knowledge, improving the system's practicality and maintainability. The graphical configuration tool allows operators without advanced programming skills to participate in model construction and adjustment, lowering the technical barrier. Combined with a complete debugging toolchain, it ensures the model can quickly adapt to changes in unit status, facilitating model optimization and maintenance, thereby guaranteeing the long-term effective operation of the system.
[0035] The present invention relates to a method and system for intelligent monitoring of anomalies in the main control room of a nuclear power plant based on empirical knowledge, which ultimately improves the safety and economy of nuclear power plants. By detecting and warning of anomalies in advance, valuable time is gained for handling potential faults, reducing the risk of small anomalies evolving into major events, and reducing unplanned reactor shutdowns. Thus, while improving nuclear safety levels, it also brings significant economic benefits. Attached Figure Description
[0036] Figure 1 A flowchart illustrating an embodiment of the method for intelligent monitoring of anomalies in the main control room of a nuclear power plant based on empirical knowledge, according to the present invention;
[0037] Figure 2 This is a flowchart illustrating an embodiment of the intelligent monitoring anomaly model based on empirical knowledge of the present invention.
[0038] Figure 3 A flowchart illustrating an embodiment of the graphical configuration and model debugging of the present invention;
[0039] Figure 4 This is a flowchart illustrating an embodiment of the intelligent monitoring anomaly model defined in the configuration diagram of the present invention. Detailed Implementation
[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
[0041] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0042] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and specific embodiments.
[0043] This embodiment provides a method and system for intelligent monitoring of anomalies in the main control room of a nuclear power plant based on the experience and knowledge of operators. The core of this method is to construct and deploy an intelligent monitoring anomaly model based on the experience and knowledge of operators.
[0044] like Figure 1-4 As shown in this embodiment, the method for intelligent monitoring of anomalies in the main control room of a nuclear power plant begins with the analysis and refinement of the operator's experience and knowledge and ends with the application of the model in the production environment. Specifically, it includes the following steps:
[0045] Step 1: Analysis of Intelligent Monitoring Anomaly Model Based on Operator Experience and Knowledge
[0046] This step aims to transform the dispersed, individualized operator experience and knowledge into a structured intelligent monitoring anomaly model diagram, specifically including:
[0047] Knowledge Collection and Organization: Collaborate with experienced operators to comprehensively organize key parameters of nuclear power plant units, systematically collect and analyze technical documents and experience feedback such as alarm card procedures, main control room operator inspection procedures, periodic tests, system operation procedures, overhaul procedures, fault handling procedures, simulation diagrams, logic diagrams, flowcharts, main control room screens, advanced / intermediate operating procedures for nuclear power plants, main control room contingency plans, first-level analysis reports, and accident scenarios, to ensure coverage of all important abnormal operating conditions;
[0048] Anomaly Analysis and Event Tree Construction: Analyze the prerequisites for anomaly diagnosis of each unit as the conditions for the intelligent monitoring anomaly model to take effect; analyze the characteristics of parameter change trends caused by anomalies, and decompose and expand the causes of target parameter anomalies step by step to form a series of event trees with different causes;
[0049] Intelligent monitoring anomaly model diagram generation: Based on the event tree, an intelligent monitoring anomaly model diagram based on the operator's experience and knowledge is generated, which summarizes and unifies the logic and standards of anomaly identification.
[0050] Step 2: Graphical configuration and debugging of the intelligent monitoring anomaly model
[0051] This step is to transform the intelligent monitoring anomaly model diagram into a workable intelligent monitoring anomaly model, specifically including:
[0052] Variable definition and componentization: First, based on the requirements of the intelligent monitoring anomaly model diagram, all unit parameter variables that need to be monitored are defined and stored in the database; these unit parameter variables are encapsulated into components in the graphical interface and stored in the component library; for example, the components in the graphical interface include comparators, function modules, timers, and logic gates;
[0053] Graphical configuration: Using a graphical configuration tool, the various effective conditions in the intelligent monitoring anomaly model diagram are bound to the actual unit parameters. By dragging and dropping predefined components and connections, the abstract effective conditions are mapped to specific, executable component combinations to form the intelligent monitoring anomaly model defined by the configuration diagram.
[0054] Model debugging and deployment: Use debugging tools to perform offline debugging and online testing of the intelligent monitoring anomaly model defined in the configuration diagram, and download the tested intelligent monitoring anomaly model to the real-time computing platform and connect it to the production environment to monitor unit parameters in real time.
[0055] The following example illustrates the steps of anomaly analysis and event tree construction. Taking an anomaly in a target parameter, "primary loop pressure," as an example, possible causes include "voltage regulator heater failure" and "coolant leakage." For each cause, further analysis is performed on its preconditions, including "related valve status" and "auxiliary parameter trends," expanding step by step to form an event tree. Figure 2 The diagram shown is an event tree-structured intelligent monitoring anomaly model. This process ensures the rigor and completeness of the anomaly identification logic.
[0056] In this embodiment, in step one, the causes of the abnormal target parameters are decomposed and expanded step by step to form a series of event trees with different causes. Specifically, the event tree analysis method is used to logically expand the various causes that lead to the abnormal target parameters to form a series of judgment sequences with causal relationships.
[0057] In this embodiment, in step one, multiple different intelligent monitoring anomaly models based on the operator's experience and knowledge are established for the same target parameter to cross-validate and reduce false alarms.
[0058] In this embodiment, in step two, the graphical configuration tool provides a predefined component library. The components include operators that have been defined by IO and developed by algorithms. Users can drag and drop the required components from the component library and connect them to build an intelligent monitoring anomaly model defined by the configuration diagram.
[0059] In this embodiment, step two, offline debugging, includes: using the simulation function of the debugging tool to input simulated data, verify the correctness of the logic of the intelligent monitoring anomaly model, and modify it at any time; the operations provided by the debugging tool include: offline simulation, adding, modifying, deleting, and querying model information, downloading the model, and controlling the start, pause, and deletion of the model's running status.
[0060] In this embodiment, step two, online testing, includes: downloading the intelligent monitoring anomaly model to the test environment and introducing real-time data from the actual unit for online debugging; it can also test the early warning capability of the intelligent monitoring anomaly model in near-real-world scenarios by injecting preset anomaly signals into the simulated unit.
[0061] In this embodiment, in step two, after the test is passed, the intelligent monitoring anomaly model is officially downloaded to the real-time computing platform of the production environment to start uninterrupted real-time monitoring of the unit parameters; the debugging tool also provides a monitoring interface for operators to view the running status of the intelligent monitoring anomaly model, start and stop the intelligent monitoring anomaly model, and view the running log of the intelligent monitoring anomaly model.
[0062] As an implementation of the above method, the present invention provides an embodiment of a system for intelligent monitoring of anomalies in the main control room of a nuclear power plant based on empirical knowledge. This device embodiment corresponds to the embodiment of the above-described method for intelligent monitoring of anomalies in the main control room of a nuclear power plant based on empirical knowledge, and the device can be specifically applied to various electronic devices.
[0063] The system for intelligent monitoring of anomalies in the main control room of a nuclear power plant based on empirical knowledge includes:
[0064] The monitoring anomaly model construction module is used to perform intelligent monitoring anomaly model analysis based on operator experience and knowledge, and output intelligent monitoring anomaly model diagram;
[0065] The graphical configuration and debugging module provides a graphical configuration interface and debugging functions, transforming the intelligent monitoring anomaly model diagram into an executable intelligent monitoring anomaly model and deploying it to the production environment.
[0066] In this embodiment, the graphical configuration and debugging module integrates a real-time computing platform for running an intelligent monitoring anomaly model and generating operation logs.
[0067] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.
Claims
1. A method for intelligent monitoring of anomalies in the main control room of a nuclear power plant, characterized in that, Includes the following steps: Step 1: Analysis of intelligent monitoring anomaly model based on operator experience and knowledge, including: knowledge collection and organization; anomaly analysis and event tree construction; generation of intelligent monitoring anomaly model diagram; Step 2: Graphical configuration and debugging of the intelligent monitoring anomaly model, including: variable definition and componentization; graphical configuration; model debugging and deployment.
2. The method for intelligent monitoring of anomalies in the main control room of a nuclear power plant according to claim 1, characterized in that, Step one, knowledge collection and organization, includes: comprehensively reviewing the important parameters of nuclear power plant units, and systematically collecting and analyzing technical documents and experience feedback data.
3. The method for intelligent monitoring of anomalies in the main control room of a nuclear power plant according to claim 1, characterized in that, In step one, anomaly analysis and event tree construction include: analyzing the prerequisites for unit anomaly diagnosis, which serve as the conditions for the intelligent monitoring anomaly model to take effect; analyzing the characteristics of parameter change trends caused by anomalies, and decomposing and expanding the causes of target parameter anomalies step by step to form a series of event trees with different causes. The intelligent monitoring anomaly model diagram generation includes: forming an intelligent monitoring anomaly model diagram based on the operator's experience knowledge according to the event tree, which summarizes and unifies the logic and standards for anomaly identification.
4. The method for intelligent monitoring of anomalies in the main control room of a nuclear power plant according to claim 3, characterized in that, In step one, the causes of the abnormal target parameters are decomposed and expanded step by step to form a series of event trees with different causes. Specifically, the event tree analysis method is used to logically expand the various causes that lead to the abnormal target parameters to form a series of judgment sequences with causal relationships.
5. The method for intelligent monitoring of anomalies in the main control room of a nuclear power plant according to claim 3, characterized in that, In step one, multiple different intelligent monitoring anomaly models based on the operator's experience and knowledge are established for the same target parameter for cross-validation.
6. The method for intelligent monitoring of anomalies in the main control room of a nuclear power plant according to claim 1, characterized in that, In step two, graphical configuration includes: using graphical configuration tools to bind each effective condition in the intelligent monitoring anomaly model diagram to the unit parameters, and by dragging and dropping predefined components and connections, mapping the abstract effective conditions to specific, executable component combinations to form the intelligent monitoring anomaly model defined in the configuration diagram. Model debugging and deployment include: using debugging tools to perform offline debugging and online testing of the intelligent monitoring anomaly model defined in the configuration diagram, and downloading the tested intelligent monitoring anomaly model to the real-time computing platform and connecting it to the production environment to monitor unit parameters in real time.
7. The method for intelligent monitoring of anomalies in the main control room of a nuclear power plant according to claim 6, characterized in that, In step two, the graphical configuration tool provides a predefined component library, which includes operators defined by IO and developed by algorithms. Users can drag and drop the required components from the component library and connect them to build an intelligent monitoring anomaly model defined by the configuration diagram.
8. The method for intelligent monitoring of anomalies in the main control room of a nuclear power plant according to claim 6, characterized in that, In step two, offline debugging includes: using the simulation function of the debugging tool to input simulated data and verify the correctness of the logic of the intelligent monitoring anomaly model; Online testing includes: downloading the intelligent monitoring anomaly model to the test environment and introducing real-time data from actual units for online debugging; and injecting preset anomaly signals into simulated units to assess the early warning capabilities of the intelligent monitoring anomaly model in near-real-world scenarios. After the test is passed, the intelligent monitoring anomaly model will be officially downloaded to the real-time computing platform in the production environment to begin uninterrupted real-time monitoring of the unit parameters. The debugging tool also provides a monitoring interface for operators to view the operating status of the intelligent monitoring anomaly model, start and stop the intelligent monitoring anomaly model, and view the operating log of the intelligent monitoring anomaly model.
9. A system for intelligent monitoring of anomalies in the main control room of a nuclear power plant, characterized in that, The method for intelligent monitoring of anomalies in the main control room of a nuclear power plant as described in any one of claims 1-8 includes: The monitoring anomaly model construction module is used to perform intelligent monitoring anomaly model analysis based on operator experience and knowledge, and output intelligent monitoring anomaly model diagram. The graphical configuration and debugging module provides a graphical configuration interface and debugging functions to convert intelligent monitoring anomaly model diagrams into executable intelligent monitoring anomaly models and deploy them to the production environment.
10. The intelligent monitoring system for anomalies in the main control room of a nuclear power plant according to claim 9, characterized in that, The graphical configuration and debugging module integrates a real-time computing platform for running intelligent monitoring anomaly models and generating operation logs.