Nuclear power plant working state analysis method and device, electronic equipment and storage medium

Abstract

The application relates to the technical field of nuclear power plant equipment safety, in particular to a nuclear power plant working state analysis method and device, electronic equipment and a storage medium. According to the nuclear power plant working state analysis method, an operation behavior sample library is obtained; the operation behavior sample library comprises a plurality of candidate operation behavior data and a candidate working state corresponding to each candidate operation behavior data; working log information of a target nuclear power plant is obtained; operation behavior recognition is performed on the working log information, target operation behavior data matched with the working log information is obtained, the target operation behavior data is compared with the plurality of candidate operation behavior data in the operation behavior sample library, and hit operation behavior data is obtained; and the candidate working state corresponding to the hit operation behavior data is determined as target working state of the target nuclear power plant. In this way, the accuracy of nuclear power plant equipment operation safety evaluation can be improved.

Description

Technical Field

[0001] This application relates to the field of nuclear power plant technology, and in particular to a method and apparatus for analyzing the operating status of a nuclear power plant, as well as electronic equipment and storage media. Background Technology

[0002] Since nuclear power plant equipment control is widely integrated into digital control systems (DCS), nuclear power plant personnel can control nuclear power equipment through the main control room. Therefore, controlling the operating status of nuclear power plant equipment based on the system operation behavior of the main control room personnel is a key behavior to ensure the safe operation of nuclear power equipment. However, with the increasing control requirements of nuclear power equipment and the increasing number of equipment control steps requiring manual intervention, the nuclear power plant process execution process has become increasingly complex. This increases the workload of the main control room operators and makes them more susceptible to errors due to human operation, causing abnormal operating status of nuclear power plant equipment and thus leading to operational safety problems.

[0003] To address this issue, platform logs and operating system logs from non-safety-grade DCS systems are typically collected in real time. These logs are then aggregated and analyzed at a central processing unit to generate statistical results, which are then visualized on a display screen. This approach enables analysis of operating system log information during DCS system operation, ensuring stable system operation. However, this method only analyzes the equipment and status of the system itself. Furthermore, log analysis requires associating logs with predefined event types (such as event IDs), resulting in a limited scope of analysis and an inability to accurately detect the actual operational status of equipment. Consequently, the accuracy of safety assessments for nuclear power plant equipment during actual operation remains low. Therefore, improving the accuracy of safety assessments for nuclear power plant equipment operation remains a pressing challenge for the industry. Summary of the Invention

[0004] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a method, apparatus, electronic equipment, and storage medium for analyzing the operating status of nuclear power plants, which can improve the accuracy of safety assessments of nuclear power plant equipment operation.

[0005] The nuclear power plant operating status analysis method according to the first aspect of this application includes:

[0006] Obtain an operational behavior sample library; wherein, the operational behavior sample library includes multiple candidate operational behavior data and a candidate working state corresponding to each candidate operational behavior data;

[0007] Obtain the operational log information of the target nuclear power plant;

[0008] The operation behavior is identified by performing operation behavior recognition on the work log information to obtain target operation behavior data that matches the work log information;

[0009] The target operation behavior data is compared with multiple candidate operation behavior data in the operation behavior sample library to obtain the hit operation behavior data, and the candidate working state corresponding to the hit operation behavior data is determined as the target working state of the target nuclear power plant.

[0010] According to some embodiments of this application, obtaining the operational behavior sample library includes:

[0011] Based on the historical operating status of the target nuclear power plant, obtain the historical log information and historical operating condition parameters corresponding to the historical operating status;

[0012] Operating condition feature detection is performed on the historical operating condition parameters to obtain operating condition feature data;

[0013] Operation behavior identification is performed on the historical log information to obtain historical operation behavior data;

[0014] Operation feature data is obtained by performing operation feature detection on the historical operation behavior data.

[0015] When the operation feature data and the working condition feature data match the same historical working state, the historical working state is determined as the candidate working state, and the historical operation behavior data is determined as the candidate operation behavior data of the candidate working state.

[0016] Based on the candidate working status and the candidate operation behavior data, construct the operation behavior sample library.

[0017] According to some embodiments of this application, the historical working state corresponds to a plurality of the historical working condition parameters;

[0018] The step of performing operating condition feature detection on the historical operating condition parameters to obtain operating condition feature data includes:

[0019] Based on the pre-constructed working condition feature detector, the working condition feature status detection is performed on each of the historical working condition parameters to obtain the working condition feature parsing data corresponding to each of the historical working condition parameters.

[0020] For each of the historical operating condition parameters, the operating condition feature data is obtained by performing operating condition feature fusion on the corresponding operating condition feature parsing data.

[0021] According to some embodiments of this application, the step of identifying operational behavior from the historical log information to obtain historical operational behavior data includes:

[0022] The historical log information is used to identify the operating device to obtain the historical operating device that matches the historical log information.

[0023] The historical operation device is identified to obtain historical operation behavior data that matches the historical log information.

[0024] According to some embodiments of this application, the historical working status corresponds to multiple historical operation behavior data;

[0025] The operation feature detection performed on the historical operation behavior data to obtain operation feature data includes:

[0026] Based on the pre-constructed operational feature detector's behavioral feature logic rules, operational feature state detection is performed on each of the historical operational behavior data to obtain operational feature parsing data corresponding to each of the historical operational behavior data.

[0027] For each historical operation behavior data, the operation feature data is obtained by fusing the operation feature parsing data.

[0028] According to some embodiments of this application, before the operational feature data and the working condition feature data match the same historical working state, the method further includes:

[0029] If the operation feature data and the working condition feature data do not match the same historical working state, then a working state deviation detection is performed on the historical working state to obtain working state deviation data.

[0030] If the working state deviation data represents the working state deviation corresponding to the working condition feature data, then a first integrity check is performed on the historical working condition parameters to obtain first integrity check data. Based on the first integrity check data, the pre-constructed reinforcement learning model is used to optimize the working condition feature detector parameters. Then, the step of obtaining the historical log information and historical working condition parameters corresponding to the historical working state is returned to be executed until the operation feature data and the working condition feature data match the same historical working state.

[0031] If the work status deviation data represents the work status deviation corresponding to the operation feature data, then the historical operation behavior data is subjected to an integrity check to obtain second integrity check data. Based on the second integrity check data, the pre-built reinforcement learning model is used to optimize the operation feature detector parameters. Then, the process of performing operation behavior recognition on the historical log information to obtain historical operation behavior data is returned until the operation feature data and the work status feature data match the same historical work status.

[0032] According to some embodiments of this application, the step of optimizing the working condition detector parameters of the pre-constructed reinforcement learning model based on the first integrity detection data includes:

[0033] If the first integrity detection data indicates that the historical operating condition parameters are incomplete, then obtain the operating condition parameter update indication data corresponding to the historical operating condition parameters;

[0034] If the first integrity detection data indicates that the historical operating condition parameters are complete, then obtain the detector update indication data corresponding to the operating condition feature detector;

[0035] Based on the operating condition parameter update indication data and the detector update indication data, the reinforcement learning model is instructed to update the operating condition feature detector parameters.

[0036] A nuclear power plant operating status analysis apparatus according to a second aspect embodiment of this application includes:

[0037] The behavior sample library acquisition module is used to acquire an operation behavior sample library; wherein, the operation behavior sample library includes multiple candidate operation behavior data and a candidate working state corresponding to each candidate operation behavior data;

[0038] The nuclear power plant log acquisition module is used to acquire the working log information of the target nuclear power plant.

[0039] An operation behavior recognition module is used to recognize the operation behavior of the work log information and obtain target operation behavior data that matches the work log information.

[0040] The operation behavior comparison module is used to compare the target operation behavior data with multiple candidate operation behavior data in the operation behavior sample library to obtain the hit operation behavior data, and to determine the candidate working state corresponding to the hit operation behavior data as the target working state of the target nuclear power plant.

[0041] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the nuclear power plant operating status analysis method as described in any one of the embodiments of the first aspect of this application.

[0042] Fourthly, embodiments of this application provide a computer-readable storage medium storing a program that is executed by a processor to implement the nuclear power plant operating status analysis method as described in any one of the embodiments of the first aspect of this application.

[0043] The nuclear power plant operating status analysis method, apparatus, electronic device, and storage medium according to embodiments of this application have at least the following beneficial effects: First, by acquiring an operational behavior sample library, which includes multiple candidate operational behavior data and candidate operating states corresponding to each candidate operational behavior data, a database containing the mapping relationship between operational behaviors and nuclear power plant equipment operating states is established, rather than associating with equipment through simple event IDs, thus enabling more effective traceability of nuclear power plant equipment operating states. Second, by acquiring the operating log information of the target nuclear power plant and identifying operational behaviors in the operating log information, target operational behavior data matching the operating log information is obtained, allowing subsequent equipment operating status analysis to go beyond just the equipment itself. Finally, by comparing the target operational behavior data with multiple candidate operational behavior data in the operational behavior sample library, matching operational behavior data is obtained, enabling rapid location of historical operational behaviors similar to the current operational behavior, and determining the candidate operating states corresponding to the matching operational behavior data as the target operating states of the target nuclear power plant, thus enabling analysis of the specific impact of the current operational behavior on the equipment operating state. In this way, the accuracy of nuclear power plant equipment operation safety assessment can be improved.

[0044] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0045] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0046] Figure 1 A flowchart illustrating the nuclear power plant operating status analysis method provided in this application embodiment;

[0047] Figure 2 for Figure 1 The flowchart of step S101 in the text;

[0048] Figure 3 for Figure 2The flowchart of step S202 in the text;

[0049] Figure 4 for Figure 2 The flowchart of step S203 in the process;

[0050] Figure 5 for Figure 2 The flowchart of step S204 in the process;

[0051] Figure 6 Another flowchart illustrating the nuclear power plant operating status analysis method provided in this application embodiment;

[0052] Figure 7 for Figure 6 The flowchart of step S602 in the document;

[0053] Figure 8 This is a schematic diagram of the structure of the nuclear power plant operating status analysis device provided in the embodiments of this application;

[0054] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0055] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0056] In the description of this application, "several" means one or more, "more than" means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. The use of "first" and "second" in the description is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0057] In the description of this application, it should be understood that the orientation descriptions, such as up, down, left, right, front, and back, are based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0058] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0059] In the description of this application, it should be noted that, unless otherwise explicitly defined, terms such as "setting," "installation," and "connection" should be interpreted broadly. Those skilled in the art can reasonably determine the specific meaning of the above terms in this application based on the specific content of the technical solution. Furthermore, the identification of specific steps in the following text does not imply a limitation on the order of steps or execution logic. The execution order and logic between each step should be understood and inferred from the content described in the embodiments.

[0060] As the control requirements for nuclear power equipment increase and the number of equipment control steps requiring manual intervention also increases, the process of nuclear power plant execution becomes increasingly complex. This increases the workload of operators in the main control room and makes them more prone to errors due to human operation, which can cause abnormalities in the working status of nuclear power plant equipment and lead to operational safety issues.

[0061] To address this issue, platform logs and operating system logs from non-safety-grade DCS systems are typically collected in real-time. These logs are then aggregated and analyzed at a central processing unit to generate statistical results, which are then visualized on a display screen. This approach enables analysis of operating system log information during DCS system operation, ensuring stable system operation. However, this method only analyzes the equipment and status of the system itself. Furthermore, log analysis requires association with predefined event types (such as fixed IDs) and cannot be linked to specific maintenance personnel actions or the specific operating scenarios of nuclear power plant equipment. This results in low accuracy in assessing the operational safety of nuclear power plant equipment during actual operation. Therefore, improving the accuracy of nuclear power plant equipment operational safety assessments remains a pressing challenge for the industry.

[0062] Therefore, firstly, by constructing a database containing historical operational behaviors and their corresponding equipment operating states, the correlation between operational behaviors and equipment operating states is realized, thereby enabling the traceability of the operating status of nuclear power plant equipment. Secondly, by acquiring the work logs of the target nuclear power plant and extracting the current operational behaviors, the analysis of equipment operating status is not limited to the equipment information of the system itself. Finally, by matching operational behaviors with candidate operational behaviors in the database, the optimal matching historical operational patterns can be automatically associated to determine the equipment operating status corresponding to the current operational behavior. This breaks through the limitation of traditional log analysis that only focuses on the equipment itself and significantly improves the accuracy of safety assessment of the operating status of nuclear power equipment.

[0063] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a method, apparatus, electronic equipment, and storage medium for analyzing the operating status of nuclear power plants, which can improve the accuracy of safety assessments of nuclear power plant equipment operation.

[0064] The following explanation is based on the attached diagram:

[0065] Reference Figure 1 The nuclear power plant operating status analysis method according to the embodiments of this application may include, but is not limited to:

[0066] Step S101: Obtain the operation behavior sample library; wherein, the operation behavior sample library includes multiple candidate operation behavior data and the candidate working status corresponding to each candidate operation behavior data;

[0067] Step S102: Obtain the work log information of the target nuclear power plant;

[0068] Step S103: Perform operation behavior recognition on the work log information to obtain target operation behavior data that matches the work log information;

[0069] Step S104: Compare the target operation behavior data with multiple candidate operation behavior data in the operation behavior sample library to obtain the hit operation behavior data, and determine the candidate working state corresponding to the hit operation behavior data as the target working state of the target nuclear power plant.

[0070] The nuclear power plant operating status analysis method described in steps S101 to S104 of this application embodiment requires obtaining an operational behavior sample library. This library includes multiple candidate operational behavior data and corresponding candidate operating statuses for each candidate operational behavior data. This establishes a database containing the mapping relationship between operational behaviors and nuclear power plant equipment operating statuses, rather than associating with equipment through simple event IDs, thus enabling more effective tracing of nuclear power plant equipment operating statuses. Secondly, it obtains the target nuclear power plant's work log information and identifies operational behaviors within the work log information to obtain target operational behavior data matching the work log information. This allows subsequent equipment operating status analysis to go beyond just the equipment itself. Finally, by comparing the target operational behavior data with multiple candidate operational behavior data in the operational behavior sample library, it obtains matching operational behavior data. This allows for the rapid location of historical operational behaviors similar to the current operational behavior, and the candidate operating status corresponding to the matching operational behavior data is determined as the target operating status of the target nuclear power plant. This enables analysis of the specific impact of the current operational behavior on the equipment operating status. In this way, the accuracy of nuclear power plant equipment operation safety assessment can be improved.

[0071] Reference Figure 2 According to some embodiments of this application, step S101, obtaining the operational behavior sample library, may include, but is not limited to:

[0072] Step S201: Based on the historical operating status of the target nuclear power plant, obtain the historical log information and historical operating condition parameters corresponding to the historical operating status;

[0073] Step S202: Perform condition feature detection on historical operating parameters to obtain operating feature data;

[0074] Step S203: Perform operation behavior identification on historical log information to obtain historical operation behavior data;

[0075] Step S204: Perform operation feature detection on historical operation behavior data to obtain operation feature data;

[0076] Step S205: When the operation feature data and working condition feature data match the same historical working state, the historical working state is determined as a candidate working state, and the historical operation behavior data is determined as the candidate operation behavior data of the candidate working state.

[0077] Step S206: Construct an operation behavior sample library based on candidate working status and candidate operation behavior data.

[0078] In step S201 of some embodiments, specifically, the historical operating state refers to the operating state of nuclear power plant equipment in historical operating scenarios, including: the normal operating state of nuclear power equipment and the abnormal operating state of nuclear power equipment (such as nuclear power equipment startup failure, abnormal fluctuation of reactor power, etc.).

[0079] For example, the normal starting working state of the water pump in a nuclear power plant, or the abnormal state of the water pump starting failure.

[0080] Specifically, historical log information is a log of various operational instructions (such as adjusting the opening of the main steam isolation valve to 75%), equipment operating status (such as water pump start-up failure status), and events (such as "low pressure regulator" alarm) of nuclear power plant equipment recorded by the Digital Control System (DCS) during a historical period.

[0081] Specifically, historical operating parameters refer to the combination of operating parameters of various equipment and systems in a nuclear power plant during its historical operation, used to reflect the historical operating conditions of the nuclear power plant.

[0082] For example, reactor core power, temperature, and pressure; steam generator temperature, pressure, and flow rate; and turbine generator power, speed, and frequency.

[0083] In this embodiment, by acquiring historical log information and historical operating parameters corresponding to historical operating states, rich data support can be provided for subsequent detection of operating conditions and behavioral characteristics and construction of sample libraries, thereby providing data support for the analysis of the operating status of nuclear power plants.

[0084] In step S202 of some embodiments, specifically, the operating condition characteristic data refers to the historical parameter index characteristics extracted from the original operating condition parameters.

[0085] For example, by analyzing historical temperature data of reactor coolant, characteristics such as average temperature, fluctuation range, and trend of reactor coolant can be extracted.

[0086] In this embodiment, working condition feature detection is performed on historical working condition parameters to obtain working condition feature data. This simplifies complex working condition parameters into more representative feature data, providing data support for matching subsequent operational behaviors with working states, thereby improving the accuracy of constructing a sample library of subsequent operational behaviors.

[0087] Reference Figure 3 According to some embodiments of this application, in step S202, operating condition feature detection is performed on historical operating condition parameters to obtain operating condition feature data, which may include, but is not limited to:

[0088] Step S301: Perform condition feature state detection on each historical condition parameter according to the pre-constructed condition feature detector to obtain condition feature parsing data corresponding to each historical condition parameter.

[0089] Step S302: Perform condition feature fusion on the condition feature parsing data corresponding to each historical condition parameter to obtain condition feature data.

[0090] In step S301 of some embodiments, specifically, the operating condition feature detector is a detection network based on the experience and knowledge of nuclear power business experts who have configured the threshold of operating condition parameters. The output of the operating condition feature detector is a 0 / 1 logical result, which is used to analyze and statistically analyze the operating condition features in historical operating condition parameters.

[0091] Specifically, operating condition characteristic analysis data refers to the quantitative characterization data of operating condition parameters, which are represented by logical results of 0 / 1. This data is used to reflect the fluctuation and average level of operating condition parameters of nuclear power plant equipment in different time periods.

[0092] For example, the stable operating condition parameter thresholds for a nuclear power plant under full-power operation can be that the average temperature of the primary loop should be 310℃, the average temperature fluctuation range should be ±0.5℃, and the temperature change rate should not exceed 28℃ / h. By analyzing the average temperature of the primary loop under full-power operation using an operating condition feature detector, we obtain 305℃, which is lower than the threshold of 309.5℃. This indicates that the operating condition feature analysis data does not meet the stable operating condition parameter thresholds.

[0093] In this embodiment, the operating condition feature detection is performed on each historical operating condition parameter according to the pre-constructed operating condition feature detector. This can reduce the dimensionality of high-dimensional operating condition parameters to interpretable operating condition features, which helps to understand whether the operating condition of the equipment itself is abnormal when no operational behavior intervenes.

[0094] In step S302 of some embodiments, specifically, the operating condition feature data refers to the feature vector extracted from the operating condition parameters that can reflect the operating conditions of nuclear power plant equipment. This feature vector is used to characterize whether the operating conditions are met or not.

[0095] For example, in a nuclear power plant operating at full power under stable conditions, the primary loop power, temperature, pressure, flow rate, and other operating parameters can only be determined to be in a stable full-power operating condition if they simultaneously meet the threshold values ​​for operating parameters at full power.

[0096] Specifically, the working condition feature parsing data corresponding to each historical working condition parameter is concatenated with 0 / 1 logical results to obtain a fused set of working condition feature vectors.

[0097] In this embodiment, operating condition feature fusion is performed on the operating condition feature parsing data corresponding to each historical operating condition parameter, which can eliminate the limitations of single operating condition parameter detection. By associating all operating condition parameters involved in the equipment operation scenario, the true operating condition status of the nuclear power equipment can be accurately represented.

[0098] The embodiments of this application shown in steps S301 to S302 can accurately extract key features reflecting the operating conditions of nuclear power plants. Combined with the operating condition feature fusion step, multiple related operating condition feature parsing data can be integrated to generate more representative and comprehensive operating condition feature data. It not only considers the features of each operating condition parameter, but also the global operating condition parameter features, so as to eliminate the limitations of single operating condition parameter detection and more accurately represent the real operating conditions of nuclear power equipment.

[0099] Reference Figure 4 According to some embodiments of this application, step S203, which involves identifying operational behaviors in historical log information to obtain historical operational behavior data, may include, but is not limited to:

[0100] Step S401: Identify the operating device in the historical log information to obtain the historical operating device that matches the historical log information;

[0101] Step S402: Identify the device operation actions of the historical operation device to obtain historical operation behavior data that matches the historical log information.

[0102] In step S401 of some embodiments, specifically, the historical operating equipment refers to the operating equipment involved in the specific operating scenarios of nuclear power plant equipment during historical periods.

[0103] For example, in the scenario of starting up a water pump in a nuclear power plant, the operating equipment involved may include the operating status of the lubricating oil pump, the inlet valve, the outlet valve, the inlet pressure, and the outlet pressure.

[0104] Specifically, device operation action recognition can be achieved by parsing the device operation instructions in historical log information to identify the specific device involved in the operation.

[0105] For example, if historical log information records the operator's start-up operation of the water pump, by analyzing the operator's start-up operation command, it can be determined that the operating equipment involved in this operation is the operating status of the lubricating oil pump, the inlet valve, the outlet valve, the inlet pressure, and the outlet pressure, etc.

[0106] In this embodiment, by identifying the operating devices in the historical log information, the historical operating devices that match the historical log information can be obtained, enabling a readable representation of the operating instructions. This allows for the rapid location of other devices or device components associated with different devices in the operating scenario, providing clear analysis device objects for subsequent operation behavior analysis.

[0107] In step S402 of some embodiments, specifically, historical operation behavior data refers to specific action data performed on the identified historical operation device.

[0108] For example, in the scenario of starting up water pumps in a nuclear power plant, the operation behavior of the lubricating oil pump can be to stop or start, and the operation behavior of the inlet valve and outlet valve can be to open or close, etc.

[0109] Specifically, by analyzing the operation instructions of the operating device recorded in the historical log information using regular expressions, the corresponding operation actions of the operating device can be extracted.

[0110] For example, historical log information records the operation information of the inlet valve operator manually changing the inlet valve from closed to open at time T1. By using regular expressions to match the inlet valve operation instruction format in the log, the operation action information of the inlet valve can be extracted.

[0111] In this embodiment, by identifying the device operation actions of historical operating devices, historical operation behavior data matching historical log information is obtained. This can transform the operation details of the operating devices into structured operation behavior data, providing data support for subsequent operation behavior feature analysis.

[0112] The embodiments of this application shown in steps S401 to S402 can transform unstructured equipment operation records in historical log information into structured operation behavior data. This not only solves the heterogeneity problem of multi-source logs in the nuclear power field and improves the availability of operation behavior data, but also helps to analyze the impact of erroneous or abnormal operation behavior on the safe operation of nuclear power equipment in a timely manner.

[0113] Reference Figure 5 According to some embodiments of this application, step S204 performs operation feature detection on historical operation behavior data to obtain operation feature data, which may include, but is not limited to:

[0114] Step S501: Perform operation feature state detection for each historical operation behavior data according to the pre-constructed operation feature detector behavior feature logic rules to obtain operation feature parsing data corresponding to each historical operation behavior data.

[0115] Step S502: Perform behavioral feature fusion on the operational feature parsing data corresponding to each historical operational behavior data to obtain operational feature data.

[0116] In some embodiments, step S501 specifically involves an operation feature detector that is a network for detecting operational behaviors built on a behavior feature logic rule engine. The output of this operation feature detector is a 0 / 1 logical result used to analyze and statistically analyze the operation features in historical operation behaviors. The behavior feature logic rules include, but are not limited to: behavior timing constraints (e.g., minimum interval between two operations), behavior causal relationships (e.g., "disconnecting the external power grid" is required before "starting the emergency diesel engine"), behavior sequence relationships (e.g., the water pump's inlet valve opening and outlet valve closing), and the rationality of behavior parameters (e.g., the outlet pressure adjustment range).

[0117] Specifically, operational feature parsing data refers to operational behavior characteristics represented by logical results of 0 / 1, used to reflect the specific operational characteristics of nuclear power plant equipment under different operating scenarios.

[0118] For example, in the scenario of starting a water pump in a nuclear power plant, the operational feature parsing data can be represented by a 1 logic result, such as the lubricating oil pump changing from stopped to started, the inlet valve being open, the outlet valve changing from closed to open, the inlet pressure not being lower than the allowable start-up limit, and the outlet pressure changing from low to high.

[0119] In this embodiment, based on the behavioral feature logic rules of the pre-constructed operational feature detector, operational feature state detection is performed on each historical operational behavior data, which can reduce high-dimensional operational behavior to operational features with clear meaning.

[0120] In step S502 of some embodiments, specifically, the operation feature data refers to the operation feature vector extracted from historical operation behavior that can reflect the operation of historical nuclear power plant equipment. The operation feature vector is used to characterize the set of operation behaviors that conform to or do not conform to the nuclear power plant equipment in a specific scenario.

[0121] For example, in the scenario of starting a water pump in a nuclear power plant, the water pump can only be started if the following operations are met: the lubricating oil pump is switched from shutdown to startup, the inlet valve is open, the outlet valve is switched from closed to open, the inlet pressure is not lower than the allowable startup limit, and the outlet pressure is switched from low to high.

[0122] Specifically, the operation feature parsing data corresponding to each historical operation behavior is concatenated with 0 / 1 logical results to obtain a fused set of operation feature vectors.

[0123] In this embodiment, the operation feature fusion is performed on the operation feature parsing data corresponding to each historical operation behavior, which can eliminate the limitations of single operation behavior detection. By associating all operation behaviors involved in the equipment operation scenario, the true operating status of the nuclear power equipment can be accurately represented.

[0124] The embodiments of this application provided through steps S501 to S502 can extract key information from historical operational behavior data and integrate it into operational feature data with clear meaning. It can also help technicians more efficiently identify and analyze potential problems or abnormal patterns in operational behavior. Thus, in the safety assessment of nuclear power plant equipment, it is not limited to considering the information of the equipment itself, but also combines the impact of operator behavior on the working state of the equipment. This helps to analyze whether there is a risk of equipment failure due to operational errors, and facilitates the improvement of the accuracy of subsequent safety assessments of nuclear power plant equipment.

[0125] Reference Figure 6 According to some embodiments of this application, before step S205 where the operational characteristic data and operating condition characteristic data match the same historical operating state, the nuclear power plant operating state analysis method may further include, but is not limited to:

[0126] Step S601: If the operation feature data and the working condition feature data do not match the same historical working state, then the historical working state is subjected to working state deviation detection to obtain working state deviation data.

[0127] Step S602: If the working state deviation data represents the working state deviation corresponding to the working condition feature data, then perform a first integrity check on the historical working condition parameters to obtain the first integrity check data, and optimize the working condition feature detector parameters according to the first integrity detection data instructing the pre-built reinforcement learning model. Then return to the step of obtaining the historical log information and historical working condition parameters corresponding to the historical working state until the operation feature data and the working condition feature data match the same historical working state.

[0128] Step S603: If the working state deviation data represents the working state deviation corresponding to the operating feature data, then perform an integrity check on the historical operating behavior data to obtain the second integrity check data. Based on the second integrity check data, the pre-built reinforcement learning model is used to optimize the operating feature detector parameters. Then, return to execute the step of identifying the operating behavior of the historical log information to obtain the historical operating behavior data, until the operating feature data and the working condition feature data match the same historical working state.

[0129] In some embodiments, step S601 specifically refers to the working state deviation data, which is at least one of the operating characteristic data or working condition characteristic data that does not match the historical working state. The working state deviation data is used to characterize the working state deviation corresponding to the working condition characteristic data or the working state deviation corresponding to the operating characteristic data.

[0130] For example, in a nuclear power plant, when the operation involves starting the emergency feedwater pump, but the operating parameters do not show the expected characteristic of a rise in the steam generator water level, it indicates that the operation characteristic data and the operating condition characteristic data do not match the same historical operating state.

[0131] Specifically, by identifying the first working state corresponding to the operation feature data and the second working state corresponding to the working condition feature data, the first working state and the second working state are compared with the historical working states respectively. If at least one of the first working state and the second working state does not match the historical working state, the mismatched working state is identified as working state deviation data.

[0132] For example, the historical operating state is the water pump normal start state; the first operating state is the water pump normal start state; the second operating state is that after the water pump starts, the cooling water flow rate does not reach the set value (e.g., 1000 m³ / h). 3 / h), and at the same time, the pump start-up fault state where the pump outlet pressure is not stable at 2MPa indicates that the second working state is not matched with the historical working state. The working state deviation data is due to the working condition characteristic data identification error.

[0133] In this embodiment, when the operation feature data and the working condition feature data do not match the same historical working state, the working state deviation detection is performed on the historical working state to obtain working state deviation data. This can quickly identify the inconsistency between the operation feature data or working condition feature data and the working state, indicating that the operation feature data or working condition feature data is inaccurate during the inspection process, and the detection process of the operation feature data or working condition feature data needs to be further improved.

[0134] In step S602 of some embodiments of this application, specifically, the first integrity check data can be used to characterize the incompleteness of historical operating condition parameters, thus determining that there are invalid parameters in the historical operating condition parameters, or to characterize the completeness of historical operating condition parameters, thus determining that the operating condition parameters were detected due to problems with the parameters or detection rules of the operating condition feature detector.

[0135] Specifically, the first integrity check involves examining whether these historical operating parameters are missing, abnormal, or erroneous.

[0136] Specifically, based on the first integrity check data, the parameters of the operating condition feature detector can be optimized through a pre-built reinforcement learning model. The steps of obtaining historical log information and historical operating condition parameters corresponding to historical operating states are returned until the operation feature data and operating condition feature data match the same historical operating state. This enables automatic adjustment of detector parameters to improve the detection accuracy of operating condition features by the operating condition feature detector, thereby improving the accuracy of nuclear power plant equipment operating status identification.

[0137] Reference Figure 7 According to some embodiments of this application, step S602, which optimizes the parameters of the condition feature detector based on the pre-built reinforcement learning model indicated by the first integrity detection data, may include, but is not limited to:

[0138] Step S701: If the first integrity detection data indicates that the historical operating condition parameters are incomplete, then obtain the operating condition parameter update indication data corresponding to the historical operating condition parameters.

[0139] Step S702: If the first integrity detection data indicates that the historical operating condition parameters are complete, then obtain the detector update indication data corresponding to the operating condition feature detector.

[0140] Step S703: Based on the working condition parameter update indication data and the detector update indication data, the reinforcement learning model is instructed to update the working condition feature detector parameters.

[0141] In some embodiments, step S701 specifically describes a reinforcement learning model as an algorithmic model that optimizes performance by continuously learning and adjusting parameters.

[0142] Specifically, the operating condition parameter update indication data is used to instruct the reinforcement learning model to update the historical operating condition parameter content.

[0143] Specifically, if the first integrity detection data indicates that the historical operating condition parameters are incomplete, it means that there are invalid operating condition parameters in the historical operating condition parameters, and indication data can be generated to supplement or delete the invalid operating condition parameters.

[0144] For example, many operating parameters in nuclear power plants are usually set with both wide-range and narrow-range instruments. Taking steam generator water level measurement as an example, during the power operation phase, the operating parameters of the narrow-range instrument are accurate, while the wide-range instrument needs to be corrected. That is, the operating parameters of the wide-range instrument need to be supplemented or deleted according to the actual operating scenario of the nuclear power equipment.

[0145] In this embodiment, if the first integrity detection data indicates that the historical operating condition parameters are incomplete, the corresponding operating condition parameter update indication data is obtained, which can timely supplement or correct the incomplete operating condition parameters, thereby improving the integrity and reliability of the operating condition parameters.

[0146] In some embodiments, step S702 specifically involves using detector update indication data to instruct the reinforcement learning model to update the parameters of the condition feature detector.

[0147] Specifically, if the first integrity detection data indicates that the historical operating condition parameters are complete, it means that there is no problem with the content of the operating condition parameters. The reason for the inaccuracy of the operating condition feature detection is the rule or detector parameter set in the operating condition feature detector. Then, the indicator information that tells the parameters of the operating condition feature detector to be optimized can be generated.

[0148] For example, if there is a delay in the condition characteristic detector when detecting changes in reactor coolant pressure, the detector update indication data may generate indication information to adjust the detector's time window parameters in order to respond to pressure changes more quickly.

[0149] In this embodiment, if the first integrity detection data indicates that the historical operating condition parameters are complete, then the detector update indication data corresponding to the operating condition feature detector is obtained, which can optimize the detection performance of the operating condition feature detector and improve the detection accuracy and response speed of the operating condition features.

[0150] In some embodiments, step S703 specifically involves using a reinforcement learning model to update the input operating condition parameter update indication data and detector update indication data, analyzing the performance of the current operating condition feature detector and the completeness of the operating condition parameters, adjusting the parameters of the operating condition feature detector based on the internal strategy and reward function of the reinforcement learning model (such as correcting the equipment operating condition threshold or optimizing the feature extraction algorithm), and applying these adjustments to the operating condition feature detector to update the parameter settings of the operating condition feature detector. The updated operating condition feature detector then re-detects the operating condition features. The reinforcement learning optimization model further optimizes the reward function based on the new operating condition feature detection results and reward feedback until the performance of the operating condition feature detector reaches its optimal level, thereby ensuring the accuracy and reliability of the operating condition feature detection.

[0151] The embodiments of this application shown through steps S701 to S703 can promptly supplement or correct incomplete operating condition parameters and optimize the performance of the operating condition feature detector, thereby improving the accuracy and response speed of operating condition feature detection and helping to improve the accuracy of nuclear power plant operating equipment identification.

[0152] In some embodiments, step S205 specifically involves analyzing the correlation between operational feature data and operating condition feature data and historical operating states in the actual operating scenario of a nuclear power plant to determine historical operating states and operational behavior data as candidate samples.

[0153] For example, if the operational characteristic data (such as operating frequency) and operating condition characteristic data (such as temperature fluctuation range) of nuclear power plant equipment at full power operation match the historical operating state (such as the nuclear power plant equipment operating normally at full power), it indicates that the data has a certain representativeness and correlation under the historical operating state. Therefore, the historical operating state can be used as a candidate operating state, and the corresponding historical operational behavior data can be used as candidate operational behavior data for the candidate operating state.

[0154] In this embodiment of the application, when the operation feature data and working condition feature data match the same historical working state, the historical working state is determined as a candidate working state, and the historical operation behavior data is determined as the candidate operation behavior data of the candidate working state. This can filter out representative operation behavior sample data, provide an accurate sample basis for the subsequent construction of the sample library, and thus improve the quality and practicality of the sample library.

[0155] In some embodiments, step S206 specifically refers to the operation behavior sample library being a collection containing multiple candidate operation behavior data and their corresponding candidate working states.

[0156] Specifically, all matching candidate working states and corresponding candidate operational behaviors are stored in a database or data structure to form an operational behavior sample library.

[0157] In this embodiment, an operational behavior sample library is constructed based on candidate operating status and candidate operational behavior data. This provides an important reference for the identification and analysis of the operating status of nuclear power plants. It facilitates the rapid identification and judgment of the current operating status of nuclear power plants by comparing and analyzing the current operational behavior with the behavioral data in the sample library.

[0158] The embodiments of this application shown in steps S201 to S206 can make full use of the historical equipment operation data of nuclear power plants, and select representative sample data through detection and matching of operating conditions and operational characteristics. This provides a high-quality reference for the subsequent identification and analysis of the working status of nuclear power plants. Furthermore, by constructing an operational behavior sample library, it is possible to quickly and accurately identify the current working status of nuclear power plants, providing strong data support for the safe operation of nuclear power plants.

[0159] In some embodiments, step S603 specifically involves the second integrity check data being used to characterize incomplete historical operation behavior data, thus determining that the historical operation behavior is invalid, or to characterize complete historical operation behavior data, thus determining that the operation parameters were faulty during the detection process due to problems with the parameters or behavior feature logic rules of the operation feature detector.

[0160] Specifically, the second integrity check involves examining whether these historical operational behaviors took into account the operating conditions of nuclear power plant equipment.

[0161] Specifically, based on the second integrity check data, the parameters of the operation feature detector can be optimized through a pre-built reinforcement learning model. The process then returns to the step of identifying operation behavior based on historical log information to obtain historical operation behavior data, until the operation feature data and operating condition feature data match the same historical working state. This enables automatic adjustment of the operation feature detector parameters to improve the detection accuracy of operation features by the operation feature detector, thereby improving the accuracy of identifying the working state of nuclear power plant equipment.

[0162] Furthermore, the operation detector parameters of the operation feature detector are optimized by the pre-constructed reinforcement learning model based on the second integrity check data, including: if the second integrity check data indicates that the historical operation behavior data is incomplete, then the operation behavior update indication data corresponding to the historical operation behavior data is obtained; if the second integrity check data indicates that the historical operation behavior data is complete, then the operation logic update indication data corresponding to the operation feature detector is obtained; and the operation detector parameters of the operation feature detector are updated by the reinforcement learning model based on the operation behavior update indication data and the operation logic update indication data.

[0163] Specifically, if the second integrity detection data is incomplete in representing historical operation behavior data, then invalid operation behaviors will be added or deleted.

[0164] For example, in a nuclear power plant, water pumps are only started during the unit's power operation phase. If the pump's operating condition is not considered, the start-up or shutdown during routine maintenance and testing phases will also be identified as normal operating conditions. Therefore, an instruction is generated to supplement the pump's operating condition parameters (such as power level, average temperature, pressure, etc.) into the pump operation behavior identification range. If the associated parameters of the pump are selected incorrectly (such as the inlet pressure of pump 1 being associated with pump 2), an instruction is generated to delete the associated parameter.

[0165] Furthermore, if the second integrity detection data represents complete historical operational behavior data, then the behavioral feature logic rules and detector optimization parameters of the correction operational feature detector are generated.

[0166] The embodiments of this application shown in steps S601 to S603 form a dynamic adjustment and optimization mechanism through working state deviation detection, integrity check, and parameter optimization of reinforcement learning model. When the operation feature data and working condition feature data fail to match, this mechanism can automatically identify the cause of the deviation and adjust the detector parameters, thereby improving the accuracy and reliability of feature detection.

[0167] In some embodiments, step S102 specifically refers to the log of operational instructions, equipment operating status, and events recorded on the DSC system during the operation of the nuclear power plant.

[0168] For example, the work log information can record the operator's instructions for adjusting the reactor power at the current moment, as well as the instructions for opening and closing valves in the cooling system.

[0169] In this embodiment, by acquiring work log information, data support can be provided for the subsequent identification of the operating status and operational status of nuclear power plant equipment.

[0170] In some embodiments, step S103 specifically refers to the target operation behavior data, which refers to the specific action data performed by the current operating equipment in the specific operating scenario of nuclear power plant equipment.

[0171] Specifically, the operation behavior is identified from the work log information to obtain target operation behavior data that matches the work log information, including: identifying the operation device from the work log information to obtain target operation device that matches the work log information; and identifying the device operation action of the target operation device to obtain target operation behavior data that matches the work log information.

[0172] Furthermore, the target operating equipment refers to the operating equipment involved in the specific operating scenario of the current nuclear power plant equipment.

[0173] In this embodiment, by identifying the operation behavior of the work log information, target operation behavior data matching the work log information is obtained. This can transform unstructured operation records in the work log into structured operation behavior data, so that subsequent analysis of the device's working status is not limited to the device itself.

[0174] In other embodiments of the nuclear power plant operating status analysis method of this application, in addition to obtaining the operating log information of the target nuclear power plant, it may also include: obtaining target operating condition parameters that match the operating log information; performing operating condition feature detection on the target operating condition parameters using a pre-built operating condition feature detector to obtain target operating condition feature data; performing operation feature detection on the target operation behavior data using a pre-built operation feature detector to obtain target operation feature data; if the target operation feature data and the target operating condition feature data match the same candidate operating state, determining the candidate operating state as the target operating state; if the target operation feature data and the target operating condition feature data do not match the same candidate operating state, performing operating state deviation detection on the candidate operating state to obtain candidate state deviation data; if the candidate state deviation data represents the operating state deviation corresponding to the target operating condition feature data, then the target operating state is... The parameters are checked for operational integrity to obtain operational integrity check data. Based on the operational integrity check data, the pre-built reinforcement learning model is used to optimize the parameters of the operational feature detector. The process then returns to the step of obtaining the target operational parameters that match the work log information, until the target operation feature data and the target operational feature data match the same candidate working state. If the working state deviation data represents the working state deviation corresponding to the target operation feature data, then the target operation behavior data is checked for behavior integrity to obtain behavior integrity check data. Based on the behavior integrity check data, the reinforcement learning model is used to optimize the operation feature detector parameters. The process then returns to the step of identifying the operation behavior of the work log information to obtain the target operation behavior data that matches the work log information, until the target operation feature data and the target operational feature data match the same candidate working state.

[0175] In other embodiments of the nuclear power plant operating status analysis method of this application, the operating condition feature detector parameters are optimized based on the operating condition integrity detection data indicating the reinforcement learning model, including:

[0176] If the working condition integrity detection data indicates that the target working condition parameters are incomplete, then obtain the target working condition parameter update indication data corresponding to the target working condition parameters;

[0177] If the working condition integrity detection data indicates that the target working condition parameters are complete, then the target detector update indication data corresponding to the working condition feature detector is obtained;

[0178] The reinforcement learning model is instructed to update the parameters of the condition feature detector based on the target condition parameter update indication data and the target detector update indication data.

[0179] Furthermore, target operating condition parameters refer to the combination of operating parameters of various equipment and systems in the nuclear power plant during its current operation, used to reflect the current operating condition of the nuclear power plant. Target operating condition characteristic data refers to the current operating condition parameter index characteristics extracted from the target operating condition parameters. Target operational characteristic data refers to the operational characteristic vectors extracted from the target operational behavior data that can reflect the current operation of the nuclear power plant equipment. Candidate state deviation data refers to state deviation data where at least one of the target operational characteristic data or target operating condition characteristic data does not match a candidate operating state, reflecting the characteristic deviations that occur in the current operating condition characteristics or current operational behavior characteristics. Operating condition integrity check data is used to reflect whether there are missing, abnormal, or erroneous current operating condition parameters. Behavioral integrity check data is used to reflect whether the target operational behavior takes into account the current operating condition of the nuclear power plant equipment.

[0180] Furthermore, when the target operation feature data and the target operating condition feature data do not match the same candidate operating state, the target operation behavior data is added to the operation behavior sample library to achieve real-time updates of the operation sample library, further improve the operation sample library, and enable timely detection of operator errors or abnormal operation behaviors when operating nuclear power plant equipment, thus ensuring the safe operation of nuclear power plant equipment.

[0181] In this embodiment, by performing feature detection on the current operating parameters and operational behaviors of nuclear power plant equipment, and by detecting deviations in the current operating characteristics and operational features, performing integrity checks, and optimizing the parameters of the reinforcement learning model, a dynamic adjustment and optimization mechanism can be formed. When the target operational feature data and the target operating characteristic data fail to match, this mechanism can automatically identify the cause of the deviation and adjust the detector parameters, thereby improving the accuracy and reliability of the detection of current operational behaviors and current operating characteristics.

[0182] In some embodiments, step S104 specifically refers to hit operation data, which is historical operation behavior data that is most similar to the target operation behavior data.

[0183] Specifically, the comparison process can find the closest candidate operational behavior data by calculating the similarity or matching degree between the target operational behavior data and the candidate operational behavior data in the sample library.

[0184] For example, by comparing the sequence of operation instructions in the target operation behavior data with the sequence of operation instructions recorded in the sample library, the candidate operation behavior data with the highest matching degree can be found.

[0185] Specifically, the target operating state of the target nuclear power plant is determined based on the candidate operating states corresponding to the hit operation behavior data. The target operating state refers to the current operating state of the nuclear power plant equipment, including the normal operating state and the abnormal (such as fault, failure, etc.) operating state of the nuclear power plant equipment.

[0186] In this embodiment, by comparing the target operation behavior data with multiple candidate operation behavior data in the operation behavior sample library, the hit operation behavior data is obtained, which enables rapid location of historical operation behaviors similar to the current operation behavior. The candidate working state corresponding to the hit operation behavior data is determined as the target working state of the target nuclear power plant. This allows for analysis of the specific impact of the current operation behavior on the equipment working state, so as to accurately identify the working state of nuclear power plant equipment, thereby significantly improving the accuracy of nuclear power plant equipment safety assessment.

[0187] In other embodiments of the nuclear power plant operating status analysis method of this application, in the process of comparing the target operating behavior data with multiple candidate operating behavior data in the operating behavior sample library, the target operating condition parameters and the target operating behavior data can also be compared together with multiple candidate operating behavior data in the operating behavior sample library in the aforementioned embodiments to obtain the hit operating behavior data. Further, the candidate operating status matching the hit operating behavior data is determined from the operating behavior sample library.

[0188] Furthermore, the candidate operating states corresponding to the hit operation behavior data are determined as the target operating states of the target nuclear power plant.

[0189] In this embodiment, by comparing the target operating condition parameters and target operational behavior data together with multiple candidate operational behavior data in the operational behavior sample library, the hit operational behavior data is obtained. This not only allows for the analysis of the specific impact of the current operational behavior on the equipment's working status, but also, by combining the current operating condition parameters of the equipment and the operator, further determines the hit operational behavior data corresponding to the current operational behavior. This further accurately identifies the working status of nuclear power plant equipment and significantly improves the accuracy of nuclear power plant equipment safety assessment.

[0190] It should be noted that this application embodiment first obtains an operational behavior sample library; wherein, the operational behavior sample library includes multiple candidate operational behavior data and the candidate working state corresponding to each candidate operational behavior data, establishing a database containing the mapping relationship between operational behaviors and nuclear power plant equipment working states, rather than associating with equipment through simple event IDs, which can more effectively achieve the traceability of nuclear power plant equipment working states; secondly, it obtains the working log information of the target nuclear power plant and identifies operational behaviors in the working log information to obtain target operational behavior data matching the working log information, which can be used to analyze equipment working states not only from the equipment itself; finally, by comparing the target operational behavior data with multiple candidate operational behavior data in the operational behavior sample library, it obtains the matching operational behavior data, which can quickly locate historical operational behaviors similar to the current operational behavior, and determine the candidate working state corresponding to the matching operational behavior data as the target working state of the target nuclear power plant, enabling the analysis of the specific impact of the current operational behavior on the equipment working state. In this way, the accuracy of nuclear power plant equipment operation safety assessment can be improved.

[0191] Reference Figure 8 The nuclear power plant operating status analysis apparatus according to the second aspect of this application may include, but is not limited to:

[0192] The behavior sample library acquisition module 801 is used to acquire the operation behavior sample library; wherein, the operation behavior sample library includes multiple candidate operation behavior data and the candidate working status corresponding to each candidate operation behavior data;

[0193] The nuclear power plant log acquisition module 802 is used to acquire the work log information of the target nuclear power plant.

[0194] The operation behavior recognition module 803 is used to recognize the operation behavior of the work log information and obtain target operation behavior data that matches the work log information.

[0195] The operation behavior comparison module 804 is used to compare the target operation behavior data with multiple candidate operation behavior data in the operation behavior sample library, obtain the hit operation behavior data, and determine the candidate working state corresponding to the hit operation behavior data as the target working state of the target nuclear power plant.

[0196] It is evident that the content of the above-described nuclear power plant operating status analysis method embodiments is applicable to the embodiments of this nuclear power plant operating status analysis device. The specific functions implemented by this nuclear power plant operating status analysis device embodiment are the same as those of the above-described nuclear power plant operating status analysis method embodiments, and the beneficial effects achieved are also the same as those achieved by the above-described nuclear power plant operating status analysis method embodiments.

[0197] Reference Figure 9, Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0198] The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0199] The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and called and executed by the processor 901 using the nuclear power plant operating status analysis method of the embodiments of this application.

[0200] The input / output interface 903 is used to implement information input and output;

[0201] The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0202] Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904);

[0203] The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0204] This application also provides a computer program product, which includes a computer program. A processor of a computer device reads and executes the computer program, causing the computer device to perform the aforementioned nuclear power plant operating status analysis method.

[0205] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in this disclosure and the foregoing drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “including,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatuses.

[0206] It should be understood that in this disclosure, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, which may include, but is not limited to, any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0207] It should be understood that in the description of the embodiments of this application, "multiple" means two or more, "greater than", "less than", "exceeding" etc. are understood to exclude the number itself, and "above", "below", "within" etc. are understood to include the number itself.

[0208] In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0209] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0210] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0211] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and may include, but is not limited to, several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this disclosure. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0212] It should also be understood that the various implementation methods provided in this application can be combined arbitrarily to achieve different technical effects.

[0213] The above is a detailed description of the embodiments of this disclosure. However, this disclosure is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this disclosure. All such equivalent modifications or substitutions are included within the scope defined by the claims of this disclosure.

Claims

1. A method for analyzing the operating status of a nuclear power plant, characterized in that, include: Obtain an operational behavior sample library; wherein, the operational behavior sample library includes multiple candidate operational behavior data and a candidate working state corresponding to each candidate operational behavior data; Obtain the operational log information of the target nuclear power plant; The operation behavior is identified by performing operation behavior recognition on the work log information to obtain target operation behavior data that matches the work log information; The target operation behavior data is compared with multiple candidate operation behavior data in the operation behavior sample library to obtain the hit operation behavior data, and the candidate working state corresponding to the hit operation behavior data is determined as the target working state of the target nuclear power plant. The acquisition of the operation behavior sample library includes: Based on the historical operating status of the target nuclear power plant, historical log information and historical operating parameters corresponding to the historical operating status are obtained; wherein, the historical operating status corresponds to multiple historical operation behavior data. Operating condition feature detection is performed on the historical operating condition parameters to obtain operating condition feature data; Operation behavior identification is performed on the historical log information to obtain historical operation behavior data; Operation feature data is obtained by performing operation feature detection on the historical operation behavior data. When the operation feature data and the working condition feature data match the same historical working state, the historical working state is determined as the candidate working state, and the historical operation behavior data is determined as the candidate operation behavior data of the candidate working state. Based on the candidate working status and the candidate operation behavior data, construct the operation behavior sample library; The operation feature detection performed on the historical operation behavior data to obtain operation feature data includes: Based on the pre-constructed operational feature detector's behavioral feature logic rules, operational feature state detection is performed on each of the historical operational behavior data to obtain operational feature parsing data corresponding to each of the historical operational behavior data. For each historical operation behavior data, the operation feature data is obtained by fusing the operation feature parsing data.

2. The method according to claim 1, characterized in that, The historical working status corresponds to multiple historical working condition parameters; The step of performing operating condition feature detection on the historical operating condition parameters to obtain operating condition feature data includes: Based on the pre-constructed working condition feature detector, the working condition feature status detection is performed on each of the historical working condition parameters to obtain the working condition feature parsing data corresponding to each of the historical working condition parameters. For each of the historical operating condition parameters, the operating condition feature data is obtained by performing operating condition feature fusion on the corresponding operating condition feature parsing data.

3. The method according to claim 1, characterized in that, The step of identifying operational behavior from the historical log information to obtain historical operational behavior data includes: The historical log information is used to identify the operating device to obtain the historical operating device that matches the historical log information. The historical operation device is identified to obtain historical operation behavior data that matches the historical log information.

4. The method according to claim 1, characterized in that, Before the operational feature data and the working condition feature data match the same historical working state, the method further includes: If the operation feature data and the working condition feature data do not match the same historical working state, then a working state deviation detection is performed on the historical working state to obtain working state deviation data. If the working state deviation data represents the working state deviation corresponding to the working condition feature data, then a first integrity check is performed on the historical working condition parameters to obtain first integrity detection data. Based on the first integrity detection data, the pre-constructed reinforcement learning model is used to optimize the working condition feature detector parameters. Then, the process returns to the step of obtaining the historical log information and historical working condition parameters corresponding to the historical working state until the operation feature data and the working condition feature data match the same historical working state. If the working state deviation data represents the working state deviation corresponding to the operating feature data, then the historical operating behavior data is subjected to an integrity check to obtain second integrity check data. Based on the second integrity check data, the pre-built reinforcement learning model is used to optimize the operating feature detector parameters. The process is then repeated to perform the step of identifying the operating behavior of the historical log information to obtain historical operating behavior data, until the operating feature data and the working condition feature data match the same historical working state.

5. The method according to claim 4, characterized in that, The step of optimizing the working condition detector parameters of the pre-constructed reinforcement learning model based on the first integrity detection data includes: If the first integrity detection data indicates that the historical operating condition parameters are incomplete, then obtain the operating condition parameter update indication data corresponding to the historical operating condition parameters; If the first integrity detection data indicates that the historical operating condition parameters are complete, then obtain the detector update indication data corresponding to the operating condition feature detector; The reinforcement learning model is instructed to update the working condition detector parameters of the working condition feature detector according to the working condition parameter update indication data and the detector update indication data.

6. A nuclear power plant operating status analysis device, used to implement the nuclear power plant operating status analysis method according to any one of claims 1 to 5, characterized in that, include: The behavior sample library acquisition module is used to acquire an operation behavior sample library; wherein, the operation behavior sample library includes multiple candidate operation behavior data and a candidate working state corresponding to each candidate operation behavior data; The nuclear power plant log acquisition module is used to acquire the working log information of the target nuclear power plant. An operation behavior recognition module is used to recognize the operation behavior of the work log information and obtain target operation behavior data that matches the work log information. The operation behavior comparison module is used to compare the target operation behavior data with multiple candidate operation behavior data in the operation behavior sample library to obtain the hit operation behavior data, and to determine the candidate working state corresponding to the hit operation behavior data as the target working state of the target nuclear power plant.

7. An electronic device, characterized in that, include: The system includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the nuclear power plant operating status analysis method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The storage medium stores a program, which is executed by a processor to implement the nuclear power plant operating status analysis method as described in any one of claims 1 to 5.

Images