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

Abstract

The invention 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; wherein 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; acquiring work log information of the target nuclear power plant; performing operation behavior recognition on the work log information to obtain target operation behavior data matched with the work log information, and comparing the target operation behavior data with multiple candidate operation behavior data in an operation behavior sample library to obtain hit operation behavior data; and determining the candidate working state corresponding to the hit operation behavior data as the target working state of the target nuclear power plant. Therefore, the accuracy of nuclear power plant equipment operation safety assessment can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of nuclear power plants, and in particular to a method for analyzing the working status of a nuclear power plant, a device thereof, electronic equipment, and a storage medium. Background Art

[0002] Since nuclear power plant equipment control is now universally integrated into the Digital Control System (DCS), nuclear power plant personnel can control nuclear power equipment through the system's 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 for nuclear power equipment and the increase in equipment control steps requiring human intervention, the nuclear power plant process execution process has become increasingly complex, increasing the workload of the main control room operators. This makes it easy for human errors to cause abnormal operating status of nuclear power plant equipment, leading to operational safety issues for nuclear power plant equipment.

[0003] To address this issue, the platform logs and operating system logs of non-safety-level DCS systems are typically collected in real time, comprehensively analyzed and processed at the aggregation end, and statistical results are generated. Finally, these are visualized on the display end, enabling analysis of the operating system log information during DCS system operation to ensure stable system operation. However, this method only analyzes the system's own equipment and status, and when analyzing logs, it is necessary to associate them with the system's own equipment based on preset event types (such as event ID representations). This results in a relatively single object for the equipment status analysis process and an inability to effectively detect the actual operating status of the equipment. This leads to low accuracy in equipment operation safety assessments during the actual operation of nuclear power plants. Therefore, improving the accuracy of nuclear power plant equipment operation safety assessments remains a difficult problem that needs to be solved urgently in the industry. Summary of the Invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a nuclear power plant operating status analysis method and its device, electronic equipment, and storage medium, which can improve the accuracy of nuclear power plant equipment operation safety assessment.

[0005] A method for analyzing the operating status of a nuclear power plant according to an embodiment of the first aspect of the present application includes:

[0006] Acquire an operation behavior sample library; wherein the operation behavior sample library includes a plurality of candidate operation behavior data and a candidate working state corresponding to each candidate operation behavior data;

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

[0008] Performing operation behavior recognition on the work log information to obtain target operation behavior data matching the work log information;

[0009] The target operation behavior data is compared with a plurality of candidate operation behavior data in the operation behavior sample library to obtain 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 the present application, obtaining an operation behavior sample library includes:

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

[0012] Performing operating condition characteristic detection on the historical operating condition parameters to obtain operating condition characteristic data;

[0013] Performing operation behavior identification on the historical log information to obtain historical operation behavior data;

[0014] Performing operation feature detection on the historical operation behavior data to obtain operation feature data;

[0015] In a case where the operation characteristic data and the working condition characteristic data match the same historical working state, determining the historical working state as the candidate working state, and determining the historical operation behavior data as the candidate operation behavior data of the candidate working state;

[0016] The operation behavior sample library is constructed according to the candidate working states and the candidate operation behavior data.

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

[0018] The operating condition characteristic detection is performed on the historical operating condition parameters to obtain operating condition characteristic data, including:

[0019] Performing an operating condition characteristic state detection on each of the historical operating condition parameters according to a pre-built operating condition characteristic detector to obtain operating condition characteristic analysis data corresponding to each of the historical operating condition parameters;

[0020] The operating condition characteristic fusion is performed on the operating condition characteristic analysis data corresponding to each of the historical operating condition parameters to obtain the operating condition characteristic data.

[0021] According to some embodiments of the present application, performing operation behavior identification on the historical log information to obtain historical operation behavior data includes:

[0022] Performing operation device identification on the historical log information to obtain a historical operation device that matches the historical log information;

[0023] Device operation actions are identified on the historical operation device to obtain the historical operation behavior data that matches the historical log information.

[0024] According to some embodiments of the present application, the historical working status corresponds to a plurality of historical operation behavior data;

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

[0026] Performing an operation feature state detection on each of the historical operation behavior data according to the behavior feature logic rules of the pre-built operation feature detector to obtain operation feature analysis data corresponding to each of the historical operation behavior data;

[0027] Behavior feature fusion is performed on the operation feature analysis data corresponding to each of the historical operation behavior data to obtain the operation feature data.

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

[0029] In the case that the operation characteristic data and the working condition characteristic data do not match the same historical working state, performing working state deviation detection 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 characteristic data, a first integrity check is performed on the historical working condition parameters to obtain first integrity check data, and a pre-built reinforcement learning model is instructed by the first integrity check data to optimize working condition detector parameters for the working condition characteristic detector, and the step of obtaining historical log information and historical working condition parameters corresponding to the historical working state is returned to execution until the operation characteristic data and the working condition characteristic data match the same historical working state;

[0031] If the working state deviation data represents the working state deviation corresponding to the operation feature data, an integrity check is performed on the historical operation behavior data to obtain second integrity check data, and the operation detector parameters of the operation feature detector are optimized according to the pre-built reinforcement learning model indicated by the second integrity check data, and the step of performing operation behavior identification on the historical log information to obtain historical operation behavior data is returned to, until the operation feature data and the working condition feature data match the same historical working state.

[0032] According to some embodiments of the present application, performing operating condition detector parameter optimization on the operating condition feature detector using a pre-built reinforcement learning model indicated by the first integrity detection data includes:

[0033] If the first integrity detection data indicates that the historical operating condition parameters are incomplete, obtaining 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, obtaining detector update indication data corresponding to the operating condition feature detector;

[0035] Instruct the reinforcement learning model 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.

[0036] According to the second embodiment of the present application, a nuclear power plant operating status analysis device includes:

[0037] A behavior sample library acquisition module is used to acquire an operation behavior sample library; wherein the operation behavior sample library includes a plurality of 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 obtain the work log information of the target nuclear power plant;

[0039] An operation behavior recognition module, configured to perform operation behavior recognition on the work log information to obtain target operation behavior data matching 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 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.

[0041] In a third aspect, an embodiment of the present application provides an electronic device comprising: a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the nuclear power plant working status analysis method as described in any one of the embodiments of the first aspect of the present application.

[0042] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement a nuclear power plant operating status analysis method as described in any one of the embodiments of the first aspect of the present application.

[0043] According to the nuclear power plant working state analysis method and its device, electronic device, and storage medium of the embodiment of the present application, there are at least the following beneficial effects: first, by obtaining an operation behavior sample library; wherein the operation behavior sample library includes multiple candidate operation behavior data and the candidate working state corresponding to each candidate operation behavior data, a database containing the mapping relationship between operation behavior and nuclear power plant equipment working state is established, rather than simply associating event IDs with equipment, which can more effectively realize the tracing of nuclear power plant equipment working state; second, obtaining the work log information of the target nuclear power plant, and identifying the operation behavior of the work log information to obtain the target operation behavior data matching the work log information, which can not only be limited to the equipment itself in the subsequent equipment working state analysis; finally, 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 can quickly locate the historical operation behavior similar to the current operation behavior, and determine the candidate working state corresponding to the hit operation behavior data as the target working state of the target nuclear power plant, which can analyze the specific impact of the current operation behavior on the equipment working state. In this way, the accuracy of the nuclear power plant equipment operation safety assessment can be improved.

[0044] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0046] Figure 1 A schematic diagram of a process for analyzing the operating status of a nuclear power plant provided in an embodiment of the present application;

[0047] Figure 2 for Figure 1 Flowchart of step S101 in FIG.

[0048] Figure 3 for Figure 2Flowchart of step S202 in FIG.

[0049] Figure 4 for Figure 2 Flowchart of step S203 in FIG.

[0050] Figure 5 for Figure 2 Flowchart of step S204 in FIG.

[0051] Figure 6 Another schematic diagram of a process for analyzing the operating status of a nuclear power plant provided in an embodiment of the present application;

[0052] Figure 7 for Figure 6 Flowchart of step S602 in FIG.

[0053] Figure 8 Schematic diagram of the structure of the nuclear power plant working status analysis device provided in an embodiment of the present application;

[0054] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

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

[0056] In the description of this application, "several" means one or more, "many" means more than two, "greater than," "less than," and "exceed" are understood to exclude the number itself, while "above," "below," and "within" are understood to include the number itself. The terms "first" and "second" are used solely to distinguish technical features and are not to be construed as indicating or implying relative importance, or as implicitly specifying the number or order of the technical features indicated.

[0057] In the description of this application, it should be understood that descriptions involving orientations, such as up, down, left, right, front, and back, etc., indicating orientations or positional relationships, are based on the orientations or positional relationships 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, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on this application.

[0058] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any 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 "set," "install," and "connect" should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in this application based on the specific content of the technical solution. In addition, the identification of specific steps below does not represent a limitation on the order of steps and execution logic. The execution order and execution logic between each step should be understood and inferred with reference to the content described in the embodiments.

[0060] As the control requirements for nuclear power equipment increase and the equipment control steps requiring human intervention also increase, the process execution of nuclear power plants becomes increasingly complex, which increases the workload of the operating personnel in the main control room. It is easy to make mistakes due to human operation, causing abnormal working conditions of nuclear power plant equipment, thereby leading to operational safety problems of nuclear power plant equipment.

[0061] To address this issue, the platform logs and operating system logs of non-safety-level DCS systems are typically collected in real time, comprehensively analyzed and processed at the aggregation end, and statistical results are generated. Finally, these are visualized on the display end, enabling analysis of the operating system log information during DCS system operation to ensure stable system operation. However, this method only analyzes the equipment and status of the system itself, and when analyzing the logs, it is necessary to associate them with the system's own equipment based on preset event types (such as fixed ID representations). It cannot be associated with the specific operational behavior of operation and maintenance personnel or the specific operating scenarios of nuclear power plant equipment, resulting in low accuracy in equipment operation safety assessments during actual operation of nuclear power plant equipment. Therefore, how to improve the accuracy of nuclear power plant equipment operation safety assessments remains a difficult problem that needs to be solved urgently in the industry.

[0062] Therefore, firstly, by constructing a database containing historical operating behaviors and their corresponding equipment working states, the association between operating behaviors and equipment operating states is achieved, thereby realizing the traceability of the working states of nuclear power plant equipment; secondly, by obtaining the work logs of the target nuclear power plant and extracting the current operating behaviors, the equipment working state analysis can be not limited to the equipment information of the system itself; finally, by matching the operating behaviors with the candidate operating behaviors in the database, the optimal matching historical operating mode can be automatically associated to determine the equipment working state corresponding to the current operating behavior, breaking through the limitation of traditional log analysis that only focuses on the equipment itself, and significantly improving the accuracy of the safety assessment of the working state of nuclear power equipment.

[0063] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a nuclear power plant operating status analysis method and its device, electronic equipment, and storage medium, which can improve the accuracy of nuclear power plant equipment operation safety assessment.

[0064] The following is a further explanation based on the accompanying drawings:

[0065] Reference Figure 1 The method for analyzing the working status of a nuclear power plant according to an embodiment of the present application may include, but is not limited to:

[0066] Step S101: Acquire an operation behavior sample library; wherein the operation behavior sample library includes a plurality of candidate operation behavior data and a candidate working state corresponding to each candidate operation behavior data;

[0067] Step S102, obtaining work log information of the target nuclear power plant;

[0068] Step S103: performing operation behavior recognition on the work log information to obtain target operation behavior data matching the work log information;

[0069] Step S104 , comparing the target operation behavior data with multiple candidate operation behavior data in the operation behavior sample library to obtain hit operation behavior data, and determining 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 working state analysis method shown in steps S101 to S104 of the embodiment of the present application requires obtaining an operation behavior sample library; wherein the operation behavior sample library includes multiple candidate operation behavior data and candidate working states corresponding to each candidate operation behavior data, and establishing a database containing the mapping relationship between operation behavior and nuclear power plant equipment working state, rather than simply associating the event ID with the equipment, which can more effectively realize the tracing of the working state of the nuclear power plant equipment; secondly, obtaining the work log information of the target nuclear power plant, and performing operation behavior identification on the work log information to obtain target operation behavior data matching the work log information, which can not only be limited to the equipment itself in the subsequent equipment working state analysis; finally, by comparing the target operation behavior data with multiple candidate operation behavior data in the operation behavior sample library, obtaining the hit operation behavior data, which can quickly locate the historical operation behavior similar to the current operation behavior, and determine the candidate working state corresponding to the hit operation behavior data as the target working state of the target nuclear power plant, which can analyze the specific impact of the current operation behavior on the equipment working state. In this way, the accuracy of the nuclear power plant equipment operation safety assessment can be improved.

[0071] Reference Figure 2 According to some embodiments of the present application, step S101 of obtaining an operation 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, obtaining historical log information and historical operating parameters corresponding to the historical operating status;

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

[0074] Step S203: identify the operation behavior of the historical log information to obtain historical operation behavior data;

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

[0076] Step S205 , when the operation characteristic data and the working condition characteristic data match the same historical working state, determining the historical working state as a candidate working state, and determining the historical operation behavior data as candidate operation behavior data for the candidate working state;

[0077] Step S206: construct an operation behavior sample library based on the candidate working states and the candidate operation behavior data.

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

[0079] For example, a nuclear power plant may experience a normal water pump startup state or an abnormal water pump startup failure state in a water pump startup scenario.

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

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

[0082] For example, the core power, temperature, and pressure, the steam generator temperature, pressure, and flow rate, the power, speed, and frequency of the steam turbine generator set, etc.

[0083] In this embodiment, by obtaining historical log information and historical operating parameters corresponding to historical working status, rich data support can be provided for subsequent operating condition and behavior feature detection and sample library construction, thereby providing data support for the analysis of the operating status of the nuclear power plant.

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

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

[0086] In this embodiment, operating condition feature detection is performed on historical operating condition parameters to obtain operating condition feature data, which can simplify complex operating condition parameters into more representative feature data, provide data support for the matching of subsequent operating behaviors and working states, and thus improve the accuracy of the construction of subsequent operating behavior sample library.

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

[0088] Step S301: Performing an operating condition characteristic state detection on each historical operating condition parameter according to a pre-built operating condition characteristic detector to obtain operating condition characteristic analysis data corresponding to each historical operating condition parameter;

[0089] Step S302 : performing operating condition feature fusion on the operating condition feature analysis data corresponding to each historical operating condition parameter to obtain operating condition feature data.

[0090] In step S301 of some embodiments, specifically, the operating condition feature detector is a detection network based on which operating condition parameter thresholds are configured by nuclear power business experts through empirical knowledge. The output of the operating condition feature detector is a 0 / 1 logical result, which is used to analyze and count the operating condition features in historical operating condition parameters.

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

[0092] For example, the stable operating parameter thresholds of a nuclear power plant in a full-power operation scenario may be that the average temperature of a single circuit should be 310°C, the fluctuation range of the average temperature is ±0.5°C, and the temperature change rate does not exceed 28°C / h. The operating condition characteristic detector analyzes the average temperature of a single circuit in the full-power operation scenario and obtains 305°C, which is lower than the threshold of 309.5°C, indicating that the operating condition characteristic analysis data does not meet the stable operating parameter thresholds.

[0093] In this embodiment, the operating condition feature status detection is performed on each historical operating condition parameter based on the pre-built operating condition feature detector, which can reduce the high-dimensional operating condition parameters into interpretable operating condition features, and help to understand whether the operating condition of the equipment itself is abnormal when no operating behavior intervenes.

[0094] In step S302 of some embodiments, specifically, the operating condition characteristic data refers to a feature vector extracted from the operating condition parameters that can reflect the operating condition of the nuclear power plant equipment, and the feature vector is used to represent compliance with or non-compliance with the operating condition.

[0095] For example, when a nuclear power plant is operating at full power and in stable conditions, the operating parameters such as primary circuit power, temperature, pressure, and flow can only be determined to be at full power and stable conditions if they all meet the operating parameter thresholds for full power operation.

[0096] Specifically, the operating condition characteristic analysis data corresponding to each historical operating condition parameter is spliced with 0 / 1 logic results to obtain a set of fused operating condition characteristic vectors.

[0097] In this embodiment, the operating condition characteristics are fused for the operating condition characteristic analysis data corresponding to each historical operating condition parameter, which can eliminate the limitations of single operating condition parameter detection. By associating all the operating condition parameters involved in the equipment operation scenario, the actual operating status of the nuclear power equipment can be accurately represented.

[0098] The embodiment of the present application shown through steps S301 to S302 can accurately extract key features reflecting the operating conditions of a nuclear power plant. Combined with the operating condition feature fusion step, it can also integrate multiple related operating condition feature analysis data to generate more representative and comprehensive operating condition feature data. It not only takes into account the characteristics of each operating condition parameter, but also takes into account the global operating condition parameter characteristics to eliminate the limitations of single operating condition parameter detection and more accurately represent the true operating status of nuclear power equipment.

[0099] Reference Figure 4 According to some embodiments of the present application, step S203 performs operation behavior identification on historical log information, and the obtained historical operation behavior data may include, but is not limited to:

[0100] Step S401: identify the operation device of the historical log information to obtain the historical operation device that matches the historical log information;

[0101] Step S402: performing device operation action recognition on 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 device refers to the operating device involved in the specific operation scenario of the nuclear power plant equipment in the historical period.

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

[0104] Specifically, the device operation action recognition can be performed by parsing the logged device operation instructions in the historical log information to parse out the specific devices involved in the device operation process.

[0105] For example, if the historical log information records the operator's operation to start the water pump, by analyzing the operator's operation instructions for starting the water pump, 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 device of historical log information, the historical operating device that matches the historical log information is obtained, and the readable representation of the operating instructions can be achieved to quickly locate other devices or device components associated with different devices in the operating scenarios, providing a clear analysis device object for subsequent operating behavior analysis.

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

[0108] For example, in the startup scenario of a water pump in a nuclear power plant, the operation behavior of the lubricating oil pump can be shutdown or startup, and the operation behavior of the water inlet valve and the water outlet valve can be open or closed, etc.

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

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

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

[0112] The embodiment of the present application shown through steps S401 to S402 can convert the unstructured equipment operation records in the historical log information into structured operation behavior data, which 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 promptly analyze the impact of operation behavior errors or abnormal operation behaviors on the safe operation of nuclear power equipment.

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

[0114] Step S501: Performing an operation feature state detection on each historical operation behavior data according to the behavior feature logic rules of the pre-built operation feature detector to obtain operation feature analysis data corresponding to each historical operation behavior data;

[0115] Step S502 : performing behavior feature fusion on the operation feature analysis data corresponding to each historical operation behavior data to obtain operation feature data.

[0116] In step S501 of some embodiments, specifically, the operation feature detector is an operation behavior detection network constructed based on a behavior feature logic rule engine. The output of the operation feature detector is a 0 / 1 logical result, which is used to analyze and compile statistics on the operation features in historical operation behaviors. The behavior feature logic rules include, but are not limited to, behavior timing constraints (such as the minimum interval between two operations), behavior causal relationships (such as the need to "disconnect the external power grid" before "starting the emergency diesel engine"), behavior sequence relationships (such as the water pump's inlet valve opening and the water outlet valve closing), and behavior parameter rationality (such as the outlet pressure adjustment range).

[0117] Specifically, the operation characteristic analysis data refers to the operation behavior characteristics represented by the logical result of 0 / 1, which is used to reflect the specific operation characteristics of nuclear power plant equipment in different operation scenarios.

[0118] For example, in the scenario of starting a water pump in a nuclear power plant, the operation characteristic analysis data can be represented by a 1 logical result, which means that the lubricating oil pump starts from being shut down, the water inlet valve is open, the water outlet valve changes from closed to open, the water inlet pressure must not be lower than the limit value allowed for startup, and the water outlet pressure changes from low to high.

[0119] In this embodiment, operation feature state detection is performed on each historical operation behavior data based on the behavior feature logic rules of the pre-built operation feature detector, which can reduce the high-dimensional operation behavior into operation features with clear meanings.

[0120] In step S502 of some embodiments, specifically, the operation characteristic data refers to an operation characteristic vector extracted from historical operation behaviors that can reflect the historical operation of nuclear power plant equipment. The operation characteristic vector is used to characterize a set of operation behaviors that meet or do not meet the requirements of 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 operation sets are met: the lubricating oil pump is started from shutdown, the water inlet valve is open, the water outlet valve is turned from closed to open, the water inlet pressure must be no lower than the limit allowed for startup, and the water outlet pressure changes from low to high.

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

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

[0124] The embodiment of the present application provided through steps S501 to S502 can extract key information from historical operating behavior data and integrate it into operating feature data with clear meaning. It can also help technicians more efficiently identify and analyze potential problems or abnormal patterns in operating behaviors, thereby achieving that in the safety assessment of nuclear power plant equipment, it is not only limited to the consideration of the equipment itself information, but also combines the impact of the operator's behavior on the equipment's working status, which helps to analyze whether there is a risk of equipment working status failure due to operating errors in the operating behavior, and facilitates the subsequent improvement of the accuracy of the safety assessment of nuclear power plant equipment.

[0125] Reference Figure 6 According to some embodiments of the present application, before step S205 in which the operation characteristic data and the 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 characteristic data and the working condition characteristic data do not match the same historical working state, a working state deviation detection is performed on the historical working state to obtain working state deviation data;

[0127] Step S602: If the working state deviation data represents a working state deviation corresponding to the working condition characteristic data, a first integrity check is performed on the historical working condition parameters to obtain first integrity check data, and a pre-built reinforcement learning model is instructed by the first integrity check data to optimize working condition detector parameters for the working condition characteristic detector. The process then returns to the step of obtaining historical log information and historical working condition parameters corresponding to the historical working state until the operation characteristic data and the working condition characteristic data match the same historical working state.

[0128] Step S603: If the working state deviation data represents the working state deviation corresponding to the operation feature data, an integrity check is performed on the historical operation behavior data to obtain second integrity check data. The operation detector parameters are optimized for the operation feature detector according to the pre-built reinforcement learning model indicated by the second integrity check data, and the step of performing operation behavior identification on the historical log information to obtain historical operation behavior data is returned until the operation feature data and the working condition feature data match the same historical working state.

[0129] In step S601 of some embodiments, specifically, the working state deviation data refers to state deviation data in which at least one of the operation characteristic data or the working condition characteristic data does not match the historical working state, and 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 operation characteristic data.

[0130] For example, in a nuclear power plant, when the operation behavior is to start the emergency feed water pump, and the operating parameters do not show the expected characteristics of the steam generator water level rising, it means that the operation characteristic data and the operating characteristic data do not match the same historical working state.

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

[0132] For example, the historical working state is the normal starting state of the water pump, the first working state is the normal starting state of the water pump, and the second working state is that after the water pump is started, the cooling water flow rate does not reach the set value (such as 1000m 3 / h), and the water pump outlet pressure is not stable in the water pump startup fault state of 2MPa, indicating that the second working state does not match the historical working state, and the working state deviation data is due to the working state deviation caused by the error in the recognition of the working condition characteristic data.

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

[0134] In step S602 of some embodiments of the present application, specifically, the first integrity check data can be used to characterize that the historical operating condition parameters are incomplete, and then determine that there are invalid parameters in the historical operating condition parameters, or to characterize that the historical operating condition parameters are complete, and then determine that the operating condition parameters are due to problems in the parameters or detection rules of the operating condition feature detector during the detection process.

[0135] Specifically, the first integrity check is to check whether these historical operating condition 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 the pre-built reinforcement learning model, and the steps of obtaining historical log information and historical operating condition parameters corresponding to the historical working state can be returned to execute until the operation feature data and the operating condition feature data match the same historical working state. The detector parameters can be automatically adjusted to improve the detection accuracy of the operating condition feature detector for the operating condition features, thereby improving the accuracy of identifying the working state of nuclear power plant equipment.

[0137] Reference Figure 7 According to some embodiments of the present application, step S602 of optimizing the parameters of the operating condition detector using the pre-built reinforcement learning model according to 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, obtaining 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 obtaining detector update indication data corresponding to the operating condition characteristic detector;

[0140] Step S703 : instructing the reinforcement learning model 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.

[0141] In step S701 of some embodiments, specifically, the reinforcement learning model is an algorithm 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, indicating that invalid operating condition parameters exist in the historical operating condition parameters, indication data for supplementing or deleting the invalid operating condition parameters may be generated.

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

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

[0146] In step S702 of some embodiments, specifically, the detector update indication data is used to instruct the reinforcement learning model to update parameters of the operating 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, and the reason for the inaccurate operating condition feature detection is the rules or detector parameters set in the operating condition feature detector, then indication information can be generated to indicate that the parameters of the operating condition feature detector should be optimized.

[0148] For example, if the operating condition characteristic detector has a delay in detecting a change in reactor coolant pressure, the detector update indication data may generate indication information for adjusting a time window parameter of the detector to respond to the pressure change more quickly.

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

[0150] In step S703 of some embodiments, specifically, the input working condition parameter update indication data and detector update indication data can be updated through a reinforcement learning model, the performance of the current working condition feature detector and the integrity of the working condition parameters can be analyzed, and the working condition feature detector parameters can be adjusted based on the internal strategy and reward function of the reinforcement learning model (such as correcting the equipment working condition threshold or optimizing the feature extraction algorithm), and these adjustments are applied to the working condition feature detector to update the parameter settings of the working condition feature detector, and the updated working condition feature detector re-detects the working condition features. The reinforcement learning optimization model further optimizes the reward function according to the new working condition feature detection results and reward feedback until the performance of the working condition feature detector reaches the optimal level, thereby ensuring the accuracy and reliability of the working condition feature detection.

[0151] The embodiment of the present application shown in steps S701 to S703 can timely supplement or correct incomplete operating 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 identifying working equipment in nuclear power plants.

[0152] In step S205 of some embodiments, specifically, by analyzing the correlation between the operation characteristic data and the working condition characteristic data and the historical working status in the actual operation scenario of the nuclear power plant, the historical working status and operation behavior data as candidate samples can be determined.

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

[0154] In an embodiment of the present application, by determining the historical working state as a candidate working state when the operation characteristic data and the working condition characteristic data match the same historical working state, and determining the historical operation behavior data as candidate operation behavior data of the candidate working state, representative operation behavior sample data can be screened out, providing an accurate sample basis for subsequent sample library construction, thereby improving the quality and practicality of the sample library.

[0155] In step S206 of some embodiments, specifically, the operation behavior sample library is a set including a plurality of candidate operation behavior data and their corresponding candidate working states.

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

[0157] In this embodiment, an operation behavior sample library is constructed based on candidate working states and candidate operation behavior data, which can provide an important reference basis for the identification and analysis of the working state of the nuclear power plant, and facilitate the subsequent comparison and analysis of the current operation behavior and the behavior data in the sample library, so as to realize the rapid identification and judgment of the current working state of the nuclear power plant.

[0158] The embodiment of the present application shown in steps S201 to S206 can make full use of the historical equipment operation data of the nuclear power plant, and screen out representative sample data through working condition and operation feature detection and matching, providing a high-quality reference basis for the subsequent identification and analysis of the working status of the nuclear power plant. Furthermore, by constructing an operation behavior sample library, it is possible to achieve subsequent rapid and accurate identification of the current working status of the nuclear power plant, providing strong data support for the safe operation of the nuclear power plant.

[0159] In step S603 of some embodiments, specifically, the second integrity check data can be used to characterize that if the historical operation behavior data is incomplete, then it is determined that there is invalid behavior in the historical operation behavior, or to characterize that the historical operation behavior data is complete, then it is determined that the operation parameters in the detection process are due to problems with the parameters of the operation feature detector or the behavior feature logic rules.

[0160] Specifically, the second integrity check is to check whether these historical operating behaviors take into account the operating conditions of nuclear power plant equipment, etc.

[0161] Specifically, based on the second integrity check data, the parameters of the operation feature detector can be optimized through the pre-built reinforcement learning model, and the steps of performing operation behavior identification on historical log information to obtain historical operation behavior data are returned until the operation feature data and the operating condition feature data match the same historical working state. The operation feature detector parameters can be automatically adjusted to improve the detection accuracy of the operation feature detector for the operation feature, thereby improving the accuracy of identifying the working state of nuclear power plant equipment.

[0162] Furthermore, the operation feature detector is optimized based on the pre-built reinforcement learning model indicated by 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 behavior operation 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 reinforcement learning model is instructed to update the operation detector parameters of the operation feature detector based on the operation behavior update indication data and the operation logic update indication data.

[0163] Specifically, if the second integrity detection data indicates that the historical operation behavior data is incomplete, invalid operation behaviors are added or deleted.

[0164] For example, in a nuclear power plant, the operation of the water pump is only started during the power operation phase of the unit. If the water pump operating condition is not taken into consideration, the start or stop during the normal maintenance and testing phase will also be identified as a normal operating condition. Therefore, an indication information is generated to add the parameters of the water pump operating condition (such as power level, average temperature, pressure and other parameters) to the water pump operation behavior identification range; if the associated parameters of the water pump are incorrectly selected (such as the inlet pressure of pump No. 1 is associated with pump No. 2), an indication information is generated to delete the associated parameters.

[0165] Furthermore, if the second integrity detection data indicates that the historical operation behavior data is complete, behavior feature logic rules and detector optimization parameters for correcting the operation feature detector are generated.

[0166] The embodiment of the present application shown in steps S601 to S603 forms a dynamic adjustment and optimization mechanism through working state deviation detection, integrity check and parameter optimization of the reinforcement learning model. When the operation feature data and the 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 step S102 of some embodiments, specifically, the work log information refers to a log of operation behavior instructions, equipment operating status, and events recorded on the DSC system during the operation of the current nuclear power plant.

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

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

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

[0171] Specifically, the operation behavior of the work log information is identified to obtain target operation behavior data that matches the work log information, including: identifying the operation device of the work log information to obtain the target operation device that matches the work log information; 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 scenario of the current nuclear power plant equipment operation.

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

[0174] In some other embodiments of the present application, in addition to obtaining the work log information of the target nuclear power plant, the nuclear power plant working state analysis method may also include: obtaining target operating condition parameters that match the work log information; using a pre-built operating condition feature detector to perform operating condition feature detection on the target operating condition parameters to obtain target operating condition feature data; using a pre-built operation feature detector to perform operation feature detection on the target operation behavior data to obtain target operation feature data; when the target operation feature data and the target operating condition feature data match the same candidate working state, the candidate working state is determined as the target working state; when the target operation feature data and the target operating condition feature data do not match the same candidate working state, the candidate working state is detected for a working state deviation to obtain candidate state deviation data; if the candidate state deviation data represents the working state deviation corresponding to the target operating condition feature data, the target working state is detected. The parameters are checked for working condition integrity to obtain working condition integrity check data, and the working condition feature detector is optimized by a pre-built reinforcement learning model according to the working condition integrity check data, and the step of obtaining the target working condition parameters that match the work log information is returned to execute until the target operation feature data and the target working condition 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, the target operation behavior data is checked for behavior integrity to obtain behavior integrity check data, and the operation feature detector is optimized by the reinforcement learning model according to the behavior integrity check data, and the step of identifying the operation behavior on the work log information and obtaining the target operation behavior data that matches the work log information is returned to execute until the target operation feature data and the target working condition feature data match the same candidate working state.

[0175] In other embodiments of the present application, the nuclear power plant operating state analysis method optimizes the operating condition detector parameters of the operating condition feature detector according to the operating condition integrity detection data indicating the reinforcement learning model, including:

[0176] If the operating condition integrity detection data indicates that the target operating condition parameter is incomplete, obtaining target operating condition parameter update indication data corresponding to the target operating condition parameter;

[0177] If the operating condition integrity detection data indicates that the target operating condition parameters are complete, obtaining target detector update indication data corresponding to the operating condition feature detector;

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

[0179] Furthermore, the target operating condition parameters refer to the combination of operating parameters of various equipment and systems in the current operation process of the nuclear power plant, which are used to reflect the current operating conditions of the nuclear power plant. The target operating condition characteristic data refer to the current operating condition parameter index characteristics extracted from the target operating condition parameters. The target operation characteristic data refer to the operation characteristic vector that can reflect the current operation of the nuclear power plant equipment extracted from the target operation behavior data. The candidate state deviation data refers to the state deviation data of at least one of the target operation characteristic data or the target operating condition characteristic data that does not match the candidate working state, which can reflect the characteristic deviation of the current operating condition characteristics or the current operation behavior characteristics. The operating condition integrity check data is used to reflect whether the current operating condition parameters are missing, abnormal or erroneous. The behavior integrity check data is used to reflect whether the target operation behavior takes into account the current nuclear power plant equipment conditions.

[0180] Furthermore, when the target operation characteristic data and the target operating condition characteristic data do not match the same candidate working state, the target operation behavior data is added to the operation behavior sample library to realize real-time updating of the operation sample library, further improve the operation sample library, and be able to timely detect the operator's erroneous operation behavior or abnormal operation behavior when operating nuclear power plant equipment, thereby ensuring the safe operation of nuclear power plant equipment.

[0181] In this embodiment, by performing feature detection on the operating parameters and operating behaviors of the current nuclear power plant equipment, and by detecting the working state deviation of the current operating characteristics and current operating characteristics, checking the integrity, and optimizing the parameters of the reinforcement learning model, a set of dynamic adjustment and optimization mechanisms can be formed. When the target operating characteristic 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 the current operating behavior and the current operating characteristics.

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

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

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

[0185] Specifically, the target operating state of the target nuclear power plant is determined based on the candidate operating state 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 of the nuclear power plant equipment and the abnormal operating state (such as fault, failure, etc.) 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, and the historical operation behavior similar to the current operation behavior is quickly located. 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 specific impact of the current operation behavior on the working state of the equipment can be analyzed to accurately identify the working state of the nuclear power plant equipment, thereby significantly improving the accuracy of the safety assessment of the nuclear power plant equipment.

[0187] In the nuclear power plant operating state analysis method of other embodiments of the present application, in the process of comparing the target operating behavior data with a plurality of candidate operating behavior data in the operating behavior sample library, it is also possible to compare the target operating condition parameters and the target operating behavior data together with a plurality of candidate operating behavior data in the operating behavior sample library in some of the aforementioned embodiments to obtain hit operating behavior data, and further determine the candidate operating state matching the hit operating behavior data from the operating behavior sample library;

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

[0189] In this embodiment, by comparing the target operating parameters and target operation behavior data with multiple candidate operation behavior data in the operation behavior sample library, the hit operation behavior data is obtained. This not only analyzes the specific impact of the current operation behavior on the working status of the equipment, but also combines the current operating parameters of the equipment and the operator to further determine the hit operation behavior data corresponding to the current operation behavior, further accurately identify the working status of the nuclear power plant equipment, and significantly improve the accuracy of the safety assessment of nuclear power plant equipment.

[0190] It should be noted that the embodiment of the present application first obtains an operation behavior sample library; wherein the operation behavior sample library includes multiple candidate operation behavior data and candidate working states corresponding to each candidate operation behavior data, and establishes a database containing the mapping relationship between operation behavior and nuclear power plant equipment working state, rather than simply associating the event ID with the equipment, which can more effectively realize the tracing of the working state of the nuclear power plant equipment; secondly, the work log information of the target nuclear power plant is obtained, and the operation behavior is identified in the work log information to obtain the target operation behavior data that matches the work log information, so that the subsequent equipment working state analysis is not limited to the equipment itself; finally, 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 can quickly locate the historical operation behavior similar to the current operation behavior, and determine the candidate working state corresponding to the hit operation behavior data as the target working state of the target nuclear power plant, so as to analyze the specific impact of the current operation behavior on the equipment working state. In this way, the accuracy of the nuclear power plant equipment operation safety assessment can be improved.

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

[0192] The behavior sample library acquisition module 801 is used to acquire an operation behavior sample library; wherein the operation behavior sample library includes a plurality of candidate operation behavior data and a candidate working state corresponding to each candidate operation behavior data;

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

[0194] The operation behavior identification module 803 is used to identify 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 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.

[0196] It can be seen that the contents of the above-mentioned nuclear power plant working status analysis method embodiment are all applicable to the embodiment of the present nuclear power plant working status analysis device. The functions specifically implemented by the embodiment of the present nuclear power plant working status analysis device are the same as those in the above-mentioned nuclear power plant working status analysis method embodiment, and the beneficial effects achieved are also the same as those achieved by the above-mentioned nuclear power plant working status analysis method embodiment.

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

[0198] The processor 901 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an 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 the present application;

[0199] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an 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 codes are stored in the memory 902 and are called by the processor 901 to execute the nuclear power plant working status analysis method of the embodiments of this application.

[0200] Input / output interface 903, used to implement information input and output;

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

[0202] Bus 905 , which 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 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0204] The present application also provides a computer program product, which includes a computer program. A processor of a computer device reads and executes the computer program, so that the computer device implements the above-mentioned nuclear power plant operating status analysis method.

[0205] The terms "first," "second," "third," "fourth," and the like (if any) in the specification of the present disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present disclosure described herein, for example, can be implemented in orders other than those illustrated or described herein. In addition, the terms "comprises" and "comprising," and any variations thereof, are intended to cover non-exclusive inclusions, e.g., a process, method, system, product, or apparatus comprising 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 process, method, product, or apparatus.

[0206] It should be understood that in the present disclosure, "at least one (item)" refers to one or more, and "plurality" refers to two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can represent: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, and may include, but is not limited to, any combination of single items or plural items. For example, at least one 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, c can be single or multiple.

[0207] It should be understood that in the description of the embodiments of the present application, multiple (or multiple items) means more than two, greater than, less than, exceed, 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 the present disclosure, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0209] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0210] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0211] If the integrated unit is implemented in the form of 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 the present disclosure is essentially 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. The computer software product is stored in a storage medium and may include, but is not limited to, a number of instructions for 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 various embodiments of the present disclosure. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

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

[0213] The above is a specific description of the implementation methods of the present disclosure, but the present disclosure is not limited to the above implementation methods. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present disclosure. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present disclosure.

Claims

1. A method for analyzing the working status of a nuclear power plant, characterized in that: include: Acquire an operation behavior sample library; wherein the operation behavior sample library includes a plurality of candidate operation behavior data and a candidate working state corresponding to each candidate operation behavior data; Obtain work log information of the target nuclear power plant; Performing operation behavior recognition on the work log information to obtain target operation behavior data matching the work log information; The target operation behavior data is compared with a plurality of candidate operation behavior data in the operation behavior sample library to obtain 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.

2. The method according to claim 1, characterized in that The obtaining of the operation behavior sample library includes: Based on the historical operating status of the target nuclear power plant, obtaining historical log information and historical operating condition parameters corresponding to the historical operating status; Performing operating condition characteristic detection on the historical operating condition parameters to obtain operating condition characteristic data; Performing operation behavior identification on the historical log information to obtain historical operation behavior data; Performing operation feature detection on the historical operation behavior data to obtain operation feature data; In a case where the operation characteristic data and the working condition characteristic data match the same historical working state, determining the historical working state as the candidate working state, and determining the historical operation behavior data as the candidate operation behavior data of the candidate working state; The operation behavior sample library is constructed according to the candidate working states and the candidate operation behavior data.

3. The method according to claim 2, characterized in that The historical working state corresponds to a plurality of historical working condition parameters; The operating condition characteristic detection is performed on the historical operating condition parameters to obtain operating condition characteristic data, including: Performing an operating condition characteristic state detection on each of the historical operating condition parameters according to a pre-built operating condition characteristic detector to obtain operating condition characteristic analysis data corresponding to each of the historical operating condition parameters; The operating condition characteristic fusion is performed on the operating condition characteristic analysis data corresponding to each of the historical operating condition parameters to obtain the operating condition characteristic data.

4. The method according to claim 2, characterized in that The performing operation behavior identification on the historical log information to obtain historical operation behavior data includes: Performing operation device identification on the historical log information to obtain a historical operation device that matches the historical log information; Device operation actions are identified on the historical operation device to obtain the historical operation behavior data that matches the historical log information.

5. The method according to claim 2, characterized in that The historical working status corresponds to a plurality of historical operation behavior data; The performing operation feature detection on the historical operation behavior data to obtain operation feature data includes: Performing an operation feature state detection on each of the historical operation behavior data according to the behavior feature logic rules of the pre-built operation feature detector to obtain operation feature analysis data corresponding to each of the historical operation behavior data; Behavior feature fusion is performed on the operation feature analysis data corresponding to each of the historical operation behavior data to obtain the operation feature data.

6. The method according to claim 5, characterized in that Before the operation characteristic data and the working condition characteristic data match the same historical working state, the method further includes: In the case that the operation characteristic data and the working condition characteristic data do not match the same historical working state, performing working state deviation detection 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 characteristic data, a first integrity check is performed on the historical working condition parameters to obtain first integrity check data, and a pre-built reinforcement learning model is instructed by the first integrity check data to optimize working condition detector parameters for the working condition characteristic detector, and the step of obtaining historical log information and historical working condition parameters corresponding to the historical working state is returned to execution until the operation characteristic data and the working condition characteristic data match the same historical working state; If the working state deviation data represents the working state deviation corresponding to the operation feature data, an integrity check is performed on the historical operation behavior data to obtain second integrity check data, and the operation detector parameters of the operation feature detector are optimized according to the pre-built reinforcement learning model indicated by the second integrity check data, and the step of performing operation behavior identification on the historical log information to obtain historical operation behavior data is returned to, until the operation feature data and the working condition feature data match the same historical working state.

7. The method according to claim 6, characterized in that The step of optimizing parameters of the operating condition detector for the operating condition feature detector using a pre-built reinforcement learning model indicated by the first integrity detection data includes: If the first integrity detection data indicates that the historical operating condition parameters are incomplete, obtaining 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, obtaining detector update indication data corresponding to the operating condition feature detector; The reinforcement learning model is instructed to update the operating condition detector parameters of the operating condition feature detector according to the operating condition parameter update indication data and the detector update indication data.

8. A nuclear power plant operating status analysis device, characterized in that: include: A behavior sample library acquisition module is used to acquire an operation behavior sample library; wherein the operation behavior sample library includes a plurality of 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 obtain the work log information of the target nuclear power plant; An operation behavior recognition module, configured to perform operation behavior recognition on the work log information to obtain target operation behavior data matching 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 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.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for analyzing the working status of a nuclear power plant according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The storage medium stores a program, and the program is executed by a processor to implement the nuclear power plant operating status analysis method according to any one of claims 1 to 7.

Images