A method and system for intelligent examination and evaluation and hidden danger closed-loop processing of a nuclear power plant

Abstract

The application discloses a kind of nuclear power plant intelligent examination evaluation and hidden danger closed loop processing method and system, comprising: in response to the creation request of examination evaluation task, obtain first identification, for representing evaluation object;First data is obtained from the first database based on the first identification;In response to the association completion of evaluation standard, corresponding second data is obtained from the associated business system based on the first identification;Second data and third data in second database are matched, and first matching result is obtained;In response to the completion of matching, generate first record, for representing identified hidden danger information;Second record is generated based on first record, for representing task information needing rectification;The processing procedure of execution mechanism is triggered based on second record, and the state information of processing procedure is obtained;First report is generated based on first data, first matching result and state information, for representing examination evaluation result. It can improve the standardization, accuracy and execution efficiency of examination evaluation work.

Description

Technical Field

[0001] This invention relates to the technical field of intelligent production management in nuclear power plants, and in particular to a method and system for intelligent assessment and evaluation and closed-loop handling of potential hazards in nuclear power plants. Background Technology

[0002] Nuclear power plants need to continuously conduct safety management evaluations, performance evaluations, special supervision evaluations, and hazard investigation and rectification during production and operation to ensure the safe and stable operation of the units. At present, most nuclear power plants rely mainly on manual management for their assessment and evaluation work. Evaluation standards are scattered across various institutional documents, management procedures, and business systems. The evaluation process requires manual data collection, statistical analysis, and the generation of evaluation reports.

[0003] In practical applications, existing technologies mainly suffer from the following problems: Different departments use varying evaluation standards, scoring rules, and assessment criteria, leading to inconsistent evaluation results and hindering unified management and cross-sectional comparative analysis. Staff need to extract data from multiple business systems and manually summarize it, which can easily result in omissions, duplications, or input errors, affecting the accuracy of evaluation results and increasing management costs. Most existing evaluation systems remain at the level of result statistics, failing to automatically transform identified problems into rectification tasks and thus failing to form a complete closed-loop management mechanism. Due to the lack of a unified risk identification mechanism and knowledge accumulation platform, different personnel may have different risk level judgments for the same problem, affecting the accuracy and consistency of hazard identification. When nuclear safety regulations, technical standards, or operating conditions change, assessment indicators and evaluation standards are difficult to adjust in a timely manner, affecting the adaptability and effectiveness of the evaluation system. Therefore, it is necessary to provide a nuclear power plant evaluation management method to achieve unified management of evaluation standards, automated execution of the evaluation process, intelligent risk identification, and closed-loop management of the entire rectification process. Summary of the Invention

[0004] In view of the aforementioned existing problems, this invention is proposed. Therefore, this invention provides a method and system for intelligent assessment and evaluation and closed-loop handling of potential hazards in nuclear power plants, addressing the problems of inconsistent evaluation standards, high reliance on manual labor, insufficient risk identification capabilities, and imperfect closed-loop management of rectification in existing technologies.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, embodiments of the present invention provide a method for intelligent assessment and evaluation and closed-loop handling of potential hazards in nuclear power plants, including: In response to the request to create an assessment task, a first identifier is obtained, which is used to characterize the assessment object; Based on the first identifier, first data is obtained from the first database, the first database is used to store evaluation criteria, and the first data contains at least one evaluation criterion; In response to the completion of the association of the evaluation criteria, the corresponding second data is obtained from the associated business system based on the first identifier. The second data is used to characterize the operating status of the evaluation object. The second data is matched with the third data in the second database to obtain a first matching result. The second database is used to store risk features, and the third data contains at least one risk feature record. In response to the completion of the matching, a first record is generated, which is used to characterize the identified hazard information; A second record is generated based on the first record, and the second record is used to represent the task information that needs to be rectified. The second record triggers the execution mechanism's processing flow, and the status information of the processing flow is obtained; Based on the first data, the first matching result, and the status information, a first report is generated, which is used to characterize the assessment and evaluation results.

[0006] As a preferred embodiment of the intelligent assessment and closed-loop handling method for hidden dangers in nuclear power plants described in this invention, the step of obtaining first data from a first database based on the first identifier includes: Obtain the set of evaluation criteria from the first database, wherein each record in the set of evaluation criteria contains at least a feature field and a weight field; The corresponding set of elements is determined based on the first identifier, and the set of elements is matched with the element fields in the set of evaluation criteria. Select the records that successfully match the evaluation criteria as the first candidate data; Based on the cycle type of the assessment task, the corresponding evaluation standard records are selected from the first candidate data to obtain the first data.

[0007] As a preferred embodiment of the intelligent assessment and closed-loop handling method for hidden dangers in nuclear power plants described in this invention, the step of matching the second data with the third data in the second database to obtain a first matching result includes: The second data is preprocessed to obtain the processed dataset; The processed dataset is compared with the threshold condition field and case feature field in the third dataset; Data that meets the preset anomaly conditions is selected as the second candidate data; Based on the second candidate data and the risk level determination rules, the corresponding risk level is determined; The second candidate data, the corresponding risk level, and the matched risk characteristics are recorded as the first matching result.

[0008] As a preferred embodiment of the intelligent assessment and closed-loop handling method for hidden dangers in nuclear power plants described in this invention, the step of generating a first record upon completion of matching includes: Based on the risk feature records in the first matching result, the corresponding risk description template is obtained from the second database; The device information, parameter deviations, and risk levels from the second candidate data are filled into the risk description template to generate the first description information; The first description information, risk level, scope of impact, and rectification suggestions are encapsulated into the first record.

[0009] As a preferred embodiment of the intelligent assessment and closed-loop hazard handling method for nuclear power plants described in this invention, the step of generating a second record based on the first record includes: Read the risk level field from the first record and map it to the processing priority; Based on the device code in the first record, obtain the first spatial coordinates of the corresponding device from the 3D model database; Based on the measurement input information, the second spatial coordinates of the defect location are calculated, where the measurement input information represents the distance of the defect relative to the reference point of the equipment. The second spatial coordinates are calibrated to obtain the target defect location coordinates; Write the target defect location coordinates, risk level, and rectification suggestions into the second record.

[0010] As a preferred embodiment of the intelligent assessment and closed-loop handling method for hidden dangers in nuclear power plants described in this invention, the step of triggering the execution mechanism based on the second record and obtaining the status information of the processing flow includes: Based on the device category and risk level in the second record, generate processing task instructions; The processing task instructions are sent to the corresponding execution mechanism system, and the task execution status is monitored; Obtain progress information, verification results, and completion status from the actuator system; The progress information, verification results, and completion status are used as the status information.

[0011] As a preferred embodiment of the intelligent assessment and closed-loop handling method for hidden dangers in nuclear power plants described in this invention, the step of generating a first report based on the first data, the first matching result, and the status information includes: Based on the weight configuration and scores of each indicator in the first data, a weighted average is performed to obtain a comprehensive evaluation score. The evaluation level is determined based on the comprehensive evaluation score and the preset grading rules; The first matching result and the status information are statistically analyzed to generate hidden danger statistics results and rectification progress results; Based on the historical evaluation score sequence, trend analysis results are generated; The evaluation level, hazard statistics, rectification progress, and trend analysis results are written into the first report.

[0012] As a preferred embodiment of the intelligent assessment and closed-loop management method for hidden dangers in nuclear power plants described in this invention, it further includes: In response to the completion of the rectification task, rectification completion data is obtained, which includes the final processing plan and effect verification results; Based on the rectification completion data, update the third data and risk level determination rules in the second database.

[0013] As a preferred embodiment of the intelligent assessment and closed-loop management method for hidden dangers in nuclear power plants described in this invention, the step of updating the third data and risk level determination rules in the second database based on the rectification completion data includes: The data obtained after rectification is added as new samples to the sample set of the second database. Based on the updated sample set, adjust the parameters of risk feature records and matching conditions; The adjusted parameters are written into the second database, and the corresponding version identifier is updated.

[0014] Secondly, the present invention provides a nuclear power plant intelligent assessment and evaluation and hidden danger closed-loop handling system, comprising: The first acquisition module is used to acquire a first identifier in response to the creation request of the assessment task, wherein the first identifier is used to characterize the assessment object; A first processing module is configured to retrieve first data from a first database based on the first identifier, the first database being used to store evaluation criteria, and the first data containing at least one evaluation criterion. The second acquisition module is used to obtain corresponding second data from the associated business system based on the first identifier in response to the completion of the association of the evaluation criteria. The second data is used to characterize the operating status of the evaluation object. A matching module is used to match the second data with the third data in the second database to obtain a first matching result. The second database is used to store risk features, and the third data contains at least one risk feature record. The first generation module is used to generate a first record in response to the completion of matching, and the first record is used to characterize the identified hidden danger information; The second generation module is used to generate a second record based on the first record, and the second record is used to represent the task information that needs to be rectified. The triggering module is used to trigger the processing flow of the actuator based on the second record and to obtain the status information of the processing flow; The third generation module is used to generate a first report based on the first data, the first matching result, and the status information. The first report is used to characterize the assessment and evaluation results.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention establishes a unified rating standard library, enabling centralized configuration and unified management of assessment indicators, scoring rules, and evaluation levels. This solves the problem of inconsistent evaluation standards across different departments, improving the consistency and comparability of evaluation results. This invention automates the processes of rating standard configuration, evaluation task creation, evaluation result calculation, and report generation, reducing manual intervention, minimizing human error, and improving evaluation efficiency and data accuracy. This invention constructs a risk identification library and combines it with machine learning models trained on historical hazard data to achieve automatic identification of risk characteristics and automatic determination of risk levels, improving hazard detection capabilities and the accuracy of risk assessment.

[0016] This invention links assessment results with the hazard management process, enabling comprehensive management of the entire process from hazard discovery, reporting, work application, rectification execution, status tracking, and effect verification, thereby improving the efficiency of hazard management. This invention generates 3D coordinates of defect locations by combining equipment 3D models with on-site measurement data, enabling visualized display of hazard locations and facilitating rapid defect location and handling by staff. This invention establishes a dynamic update mechanism, continuously optimizing the rating standard library and risk identification library based on new hazard data, changes in operating conditions, and updates to regulations and standards, improving system adaptability and long-term application value. Through standardized evaluation, intelligent identification, and a closed-loop rectification mechanism, this invention achieves deep integration of assessment and safety management, providing effective data support and decision-making basis for nuclear power plant operation and management, and improving the safety management level and operational management capabilities of nuclear power plants. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1This is a schematic diagram of the process flow of a method for intelligent assessment and evaluation and closed-loop handling of potential hazards in a nuclear power plant, as described in one embodiment of the present invention. Detailed Implementation

[0018] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0019] Example 1, referring to Figure 1 As one embodiment of the present invention, this embodiment provides a method for intelligent assessment and evaluation and closed-loop handling of potential hazards in nuclear power plants, including: S100: In response to the request to create an assessment task, obtain the first identifier, which is used to characterize the assessment object; S200: Based on the first identifier, obtain first data from the first database, the first database being used to store evaluation criteria, and the first data containing at least one evaluation criterion; S300: In response to the completion of the association of the evaluation criteria, the corresponding second data is obtained from the associated business system based on the first identifier. The second data is used to characterize the operating status of the evaluation object. S400: Match the second data with the third data in the second database to obtain a first matching result. The second database is used to store risk features, and the third data contains at least one risk feature record. S500: In response to the completion of the matching, a first record is generated. The first record is used to characterize the identified hazard information. S600: Generate a second record based on the first record. The second record is used to characterize the task information that needs to be rectified. S700: Trigger the processing flow of the actuator based on the second record, and obtain the status information of the processing flow; S800: Based on the first data, the first matching result, and the status information, generate the first report, which is used to characterize the assessment and evaluation results.

[0020] It should be noted that, addressing the problems of inconsistent evaluation standards, high reliance on manual labor, insufficient risk identification capabilities, and imperfect closed-loop management of rectification in existing technologies, this invention constructs a rating standard library and a risk identification library, combined with an assessment and evaluation process management mechanism, to achieve full-process management of assessment standard configuration, assessment task creation, risk identification, hazard management, rectification tracking, and result statistics. Furthermore, through rating standard element configuration; inputting rating standard library data; creating assessment and evaluation tasks; selecting assessment standard libraries; creating hazard lists; creating work applications; creating status reports; and comprehensively statistically analyzing evaluation results, this achieves standardized configuration, automated execution, intelligent risk identification, and closed-loop management of nuclear power plant assessment and evaluation work, improving the standardization, accuracy, and efficiency of assessment and evaluation work.

[0021] Furthermore, based on the first identifier, the first data is obtained from the first database, including: Obtain the set of evaluation criteria from the first database. Each record in the set of evaluation criteria must contain at least a feature field and a weight field. The corresponding set of elements is determined based on the first identifier, and the set of elements is matched with the element fields in the set of evaluation criteria. Select the records that successfully match the evaluation criteria as the first candidate data; Based on the cycle type of the assessment task, the corresponding evaluation standard records are selected from the first candidate data to obtain the first data.

[0022] It should be noted that the first database can be a relational database (such as MySQL or Oracle) to store structured evaluation criteria records; it can also be a NoSQL database (such as MongoDB) to store semi-structured evaluation criteria documents; or it can be a distributed file system to store evaluation criteria files defined in JSON or XML format.

[0023] Furthermore, the second data is matched with the third data in the second database to obtain the first matching result, including: The second set of data is preprocessed to obtain the processed dataset. The processed dataset is compared with the threshold condition field and case feature field in the third dataset; Data that meets the preset anomaly conditions is selected as the second candidate data; Based on the second candidate data and the risk level determination rules, the corresponding risk level is determined; The second candidate data, the corresponding risk level, and the matching risk characteristics are recorded as the first matching result.

[0024] It should be noted that, in the embodiments of the present invention, the second data can be a real-time data stream, which is obtained in real time from a SCADA system, DCS system or radiation monitoring system via API; it can also be a historical data record, which is obtained by querying from a relational database, time series database or log file; or it can be an offline data file that is manually entered or uploaded.

[0025] It should be noted that, in this embodiment of the invention, the core element of nuclear safety has a weight of 45%, the core element of equipment operation and maintenance has a weight of 25%, the core element of personnel operation has a weight of 20%, and the core element of process compliance has a weight of 10%. Each secondary and tertiary element is further weighted within the scope of its respective core element to form a complete evaluation index system.

[0026] Furthermore, in response to a complete match, a first record is generated, including: Based on the risk feature records in the first matching result, the corresponding risk description template is obtained from the second database; Fill the risk description template with the equipment information, parameter deviations and risk levels from the second candidate data to generate the first description information; The first description information, risk level, scope of impact, and rectification suggestions are packaged into the first record.

[0027] It should be noted that, in the embodiments of the present invention, the first matching result may be a structured data object containing fields such as the matched risk feature ID, risk level, and similarity score; it may also be a list listing all successfully matched risk features and their attributes; or it may be a data source for a visual chart used to display the risk distribution on the interface.

[0028] It should also be noted that the first record can be a database record stored in the hazard management database; it can also be an electronic document object that flows in the workflow engine; or it can be a message object that is sent to the message queue for other systems to consume.

[0029] Furthermore, a second record is generated based on the first record, including: Read the risk level field from the first record and map it to the processing priority; Based on the device code in the first record, obtain the first spatial coordinates of the corresponding device from the 3D model database; Based on the measurement input information, the second spatial coordinates of the defect location are calculated, and the measurement input information represents the distance of the defect relative to the reference point of the equipment. The second spatial coordinates are calibrated to obtain the coordinates of the target defect location; Write the target defect location coordinates, risk level, and rectification suggestions into the second record.

[0030] It should be noted that, in this embodiment of the invention, the first spatial coordinates can be two-dimensional planar coordinates based on the overall layout of the nuclear power plant; or three-dimensional coordinates based on a three-dimensional digital twin model; or coordinates including latitude and longitude information from a geographic information system. The measurement input information can be distance values ​​entered by inspection personnel via a handheld terminal; or it can be measurement data automatically uploaded by a laser rangefinder. Furthermore, the execution mechanism's processing flow is triggered based on the second record, and the status information of the processing flow is obtained, including: Based on the device category and risk level in the second record, generate processing task instructions; The task processing instructions are sent to the corresponding execution mechanism system, and the task execution status is monitored; Obtain progress information, verification results, and completion status from the implementing agency system; Progress information, verification results, and completion status are used as status information.

[0031] It should be noted that, in this embodiment of the invention, the actuator system can be a maintenance management system (such as SAP PM, Maximo) for creating maintenance work orders; it can also be an in-service inspection management system for scheduling inspection plans; or it can be an operation management system for generating operation instructions. Processing task instructions can be electronic messages conforming to a specific protocol (such as SOAP, RESTful); they can also be records directly written to the actuator system database; or they can be signals that trigger the workflow engine to start a specific process.

[0032] Furthermore, based on the first data, the first matching result, and the status information, a first report is generated, including: Based on the weight configuration and scores of each indicator in the first data, a weighted average is performed to obtain a comprehensive evaluation score. The evaluation level is determined based on the comprehensive evaluation score and the preset grading rules; The first matching result and status information are statistically analyzed to generate hidden danger statistics and rectification progress results; Based on the historical evaluation score sequence, trend analysis results are generated; The evaluation level, hazard statistics, rectification progress, and trend analysis results will be included in the first report.

[0033] It should be noted that, in this embodiment of the invention, the rectification completion data can be a closed-loop report of a maintenance work order; it can also be a verification result file of an inspection task; or it can be equipment operating parameters collected by sensors, which have been verified to have returned to the normal range. The first report can be a comprehensive evaluation report document in PDF format; it can also be an interactive dashboard page; or it can be a structured data package sent to the management system for subsequent trend analysis and decision support.

[0034] Furthermore, this also includes: In response to the completion of rectification tasks, obtain rectification completion data, which includes the final treatment plan and effect verification results; Based on the data from the completion of rectification, the third data and risk level determination rules in the second database are updated.

[0035] Furthermore, based on the data from the completion of rectification, the third data in the second database and the risk level determination rules are updated, including: The data from the completed rectification will be added as new samples to the sample set of the second database; Based on the updated sample set, adjust the parameters of risk feature records and matching conditions; Write the adjusted parameters into the second database and update the corresponding version identifier.

[0036] Example 2 illustrates a schematic scheme for a method of intelligent assessment and closed-loop management of potential hazards in nuclear power plants. It should be noted that the technical solution of this intelligent assessment and closed-loop management system for nuclear power plants is based on the same concept as the aforementioned method. Details not described in detail in this example can be found in the description of the aforementioned method.

[0037] This embodiment describes a nuclear power plant intelligent assessment and closed-loop hazard handling system, comprising: The first acquisition module is used to acquire the first identifier in response to the creation request of the assessment task. The first identifier is used to characterize the assessment object. The first processing module is used to obtain first data from the first database based on the first identifier. The first database is used to store evaluation criteria, and the first data contains at least one evaluation criterion. The second acquisition module is used to obtain the corresponding second data from the associated business system based on the first identifier in response to the completion of the association of the evaluation criteria. The second data is used to characterize the operating status of the evaluation object. The matching module is used to match the second data with the third data in the second database to obtain the first matching result. The second database is used to store risk features, and the third data contains at least one risk feature record. The first generation module is used to generate a first record in response to the completion of the matching. The first record is used to characterize the identified hazard information. The second generation module is used to generate a second record based on the first record. The second record is used to represent the task information that needs to be rectified. The triggering module is used to trigger the processing flow of the actuator based on the second record and to obtain the status information of the processing flow; The third generation module is used to generate a first report based on the first data, the first matching result, and the status information. The first report is used to characterize the assessment and evaluation results.

[0038] This embodiment also provides an electronic device applicable to the intelligent assessment and evaluation and hazard closed-loop handling method for nuclear power plants, including: The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement the intelligent assessment and closed-loop management method for potential hazards in nuclear power plants, as proposed in the above embodiments.

[0039] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the method for intelligent assessment and evaluation and closed-loop handling of potential hazards in nuclear power plants as proposed in the above embodiments.

[0040] The storage medium proposed in this embodiment belongs to the same inventive concept as the method for realizing intelligent assessment and evaluation and closed-loop handling of hidden dangers in nuclear power plants proposed in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0041] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0042] Example 3 is an embodiment of the present invention. This embodiment is based on the assessment and evaluation implementation process and has verified the effectiveness of the present invention.

[0043] The nuclear power plant assessment and evaluation standard system established in this embodiment includes the following rating standard elements: core elements; secondary elements; tertiary elements; element properties; standard scores; responsible departments; assessment content; and scoring criteria. Specifically, core elements define the primary classification of the assessment and evaluation; secondary and tertiary elements refine the assessment content at each level; element properties identify the management attributes of corresponding indicators; standard scores define the maximum score for each indicator; responsible departments determine the unit to which the indicator belongs; assessment content describes the specific assessment object; and scoring criteria define the scoring basis, deduction rules, and bonus rules for each indicator.

[0044] To ensure continuous optimization of the evaluation process, assessment nodes are set up at each process stage. The system collects process execution data in real time and judges the execution status based on preset assessment rules. When a process timeout, missing data, rule conflict, or abnormal operation is detected, the system automatically generates an early warning message and pushes it to the corresponding responsible personnel. At the same time, the system records the execution results of each process node and automatically generates process optimization suggestions based on statistical analysis results, realizing continuous improvement of the assessment process.

[0045] Furthermore, to achieve unified management of evaluation results, this invention divides nuclear power safety evaluations into four levels: Excellent, Qualified, Basically Qualified, and Unqualified. Excellent level: Weighted total score greater than or equal to 90 points, with no major hidden dangers, and all core nuclear safety indicators meet the requirements; Qualified level: Weighted total score greater than or equal to 75 points and less than 90 points, with no major hidden dangers; Basically Qualified level: Weighted total score greater than or equal to 60 points and less than 75 points; Unqualified level: Weighted total score less than 60 points, or the existence of major hidden dangers, major violations of regulations, or serious exceedances of core nuclear safety indicators.

[0046] Furthermore, to ensure the scientific rigor and objectivity of the evaluation results, this embodiment employs the Analytic Hierarchy Process (AHP) to determine the weights of each evaluation indicator. First, a hierarchical model is established, consisting of a target layer, a criterion layer, and an indicator layer. The target layer represents the total score for the nuclear power plant assessment, the criterion layer represents the core elements, and the indicator layer represents the secondary and tertiary elements. Subsequently, an expert group uses a 1-9 scale to compare each evaluation indicator pairwise, forming a judgment matrix. The system calculates the weight vector based on the judgment matrix and performs a consistency check. When the consistency ratio (CR) meets the preset threshold, the final weights are generated and written into the rating standard library; when the consistency ratio (CR) does not meet the requirements, a new expert evaluation is conducted.

[0047] In this embodiment, the core element of nuclear safety has a weight of 45%, the core element of equipment operation and maintenance has a weight of 25%, the core element of personnel operation has a weight of 20%, and the core element of process compliance has a weight of 10%. Each secondary and tertiary element is further weighted within the scope of its respective core element to form a complete evaluation index system.

[0048] Furthermore, to achieve standardized management of performance evaluation indicators, this embodiment adopts a hierarchical structure of "core elements - secondary elements - tertiary elements" to construct the evaluation indicator system. Specifically: core elements are used to define evaluation dimensions; secondary elements are used to classify core elements according to their business functions; and tertiary elements are used to form quantifiable evaluation indicators.

[0049] In this embodiment, the assessment indicator system includes: core nuclear safety elements, used to evaluate the level of nuclear safety-related management, with a weight of 45%. The core nuclear safety elements include: radiation protection; emergency management; and safety monitoring. Radiation protection includes three levels of elements: radiation dose monitoring, the integrity rate of protective equipment, and radiation area control. The corresponding data comes from the radiation monitoring system, equipment inspection system, and on-site supervision records.

[0050] The core elements of equipment operation and maintenance (O&M) are used to evaluate the equipment management status, with a weight of 25%. These core elements include: equipment operational stability; timeliness of maintenance; and defect handling status. The corresponding data comes from the equipment management system, maintenance management system, and equipment operation database.

[0051] The core elements of personnel operation are used to evaluate personnel performance, with a weight of 20%. These core elements include operational compliance, professional competence, and emergency response capabilities. The corresponding data comes from the training management system, operation record system, and emergency drill records.

[0052] The core elements of process compliance are used to evaluate and assess process execution, with a weight of 10%. These core elements include process standardization; timeliness of data reporting; and document completeness. The corresponding data comes from the process management system and the business approval system. This hierarchical indicator system enables structured management and quantitative evaluation of the assessment indicators.

[0053] Furthermore, to improve the accuracy of risk identification, a risk identification database is constructed. The risk identification database includes: a hazard characteristic database; a description template database; and a risk level determination database.

[0054] The risk identification database construction process includes: collecting historical hazard records, equipment defect records, operational event reports, experience feedback information, and nuclear safety regulatory requirements from nuclear power plants to establish an initial dataset. This dataset is then categorized and labeled according to dimensions such as hazard type, equipment category, risk level, impact scope, and rectification measures, forming standardized sample data. Feature information such as equipment codes, equipment categories, operating parameter deviations, defect manifestations, operating conditions, and historical processing results are extracted from the sample data. A risk identification model is then built using the random forest algorithm. Specifically, the sample data is cleaned; a training dataset is established; training, validation, and test sets are created; the random forest algorithm is used for training; the model parameters are optimized using the validation set; and the risk identification model is generated. Based on the trained risk identification model, a hazard feature library, a description template library, and a risk level determination library are constructed. The system periodically collects new hazard data and operational data to incrementally train the risk identification model and synchronously update the risk identification database.

[0055] The system automatically generates standardized hazard descriptions based on the evaluation object. It acquires relevant data about the evaluation object, including equipment codes, real-time operating parameters, inspection records, historical defect information, and operating logs. It then calls upon the hazard feature library in the risk identification database. Through equipment category matching, parameter threshold comparison, and historical case similarity analysis, it determines the corresponding risk characteristics. Next, it calls upon the risk level determination library and automatically determines the risk level based on the matching results. Finally, it calls upon the description template library and matches the corresponding template based on the risk level and risk category.

[0056] Equipment information, parameter deviations, risk levels, impact ranges, and rectification suggestions are automatically populated into a template to form a standardized hazard description. The risk level, hazard description, impact range, responsible department, and rectification suggestions are encapsulated into a hazard data object. This hazard data object serves as the data source for subsequent hazard record creation. After hazard rectification is completed, the rectification results are fed back into the risk identification database for subsequent model training and case accumulation. To achieve precise hazard location, this invention uses a combination of equipment 3D model positioning and on-site measurement to generate 3D coordinates.

[0057] For example, a 3D model of nuclear power plant equipment is imported into the system, and a unified 3D coordinate system is established. Each piece of equipment and its components has unique spatial coordinate information. After discovering a potential hazard, personnel select the corresponding equipment and defect location using a mobile inspection terminal. The system reads the reference coordinate information from the equipment's 3D model. The mobile inspection terminal is used to obtain the distance information of the defect location relative to the equipment's reference point. The system combines the equipment's 3D model coordinates with on-site measurement data to calculate the defect location coordinates. The system performs calibration processing by combining historical defect records, in-service inspection records, and equipment operation and maintenance records. The calibrated 3D coordinates are automatically written into the hazard report and associated with the equipment's 3D model, enabling a visual display of the defect location.

[0058] Furthermore, the system will uniformly input the configured grading rules, weighting coefficients, and assessment indicator elements into the rating standard library. Simultaneously, it will establish data associations with historical hazard data, equipment operation and maintenance data, and historical evaluation records. The rating standard library serves as the data foundation for subsequent assessment and evaluation task creation and the retrieval of evaluation standards.

[0059] Furthermore, evaluation tasks are created based on the user-selected evaluation objects, evaluation periods, and evaluation scope. Evaluation objects include departments, positions, systems, or equipment. Evaluation periods include real-time evaluation, daily evaluation, weekly evaluation, and monthly evaluation. After creation, a unique task number is generated and linked to the corresponding rating standard library.

[0060] Furthermore, the system acquires information about the created assessment task, including the assessment object, assessment scope, assessment cycle, and relevant business area. The system then filters assessment standards from the rating standard library to find those that meet the criteria and establishes a mapping relationship between the assessment task and the assessment standards. After selecting the assessment standards, the system automatically acquires relevant business data about the assessment object, including equipment operating parameters, inspection records, historical defect records, personnel operation records, and process execution records.

[0061] Furthermore, the system matches the acquired data with the hazard feature library in the risk identification database, identifying potential risks through equipment category matching, parameter threshold comparison, and historical case similarity analysis. The risk level determination library outputs the corresponding risk level based on the matching results. The description template library automatically generates standardized hazard descriptions based on the risk category. The system encapsulates information such as risk level, hazard description, impact scope, and rectification suggestions into a hazard data object, providing basic data for subsequent hazard order creation.

[0062] Furthermore, the system reads the generated hazard data objects and automatically associates them with equipment information, responsible departments, historical maintenance records, and equipment 3D model information.

[0063] The system automatically determines the handling priority based on the hazard level. Specifically: major risks correspond to Level 1 priority; significant risks to Level 2 priority; general risks to Level 3 priority; and low risks to Level 4 priority. The system automatically generates an electronic hazard report according to preset rules. A hazard report must include at least: hazard number; equipment code; equipment name; hazard description; risk level; scope of impact; three-dimensional coordinates of the defect location; responsible department; rectification deadline; and rectification suggestions. Once generated, the hazard report automatically enters the hazard management process and sends a handling notification to the corresponding responsible department.

[0064] Furthermore, the system automatically generates corresponding work applications based on the content of the hazard report. The work application includes: work application number; associated hazard number; equipment information; work content; risk level; planned start time; planned end time; responsible personnel; and approval status. The system automatically matches the corresponding professional department based on equipment category and hazard type. When equipment maintenance is involved, the system automatically interacts with the maintenance work order system. When in-service inspection is involved, the system automatically links with the in-service inspection management system. When operational operations are involved, the system automatically links with the operation management system. Once the work application is approved, it enters the execution state. The system records various status changes in real time during the processing, creating a complete process tracking record.

[0065] Furthermore, the system continuously collects status data during the execution of work applications. Status data includes: improvement progress information; equipment retest results; verification results; responsible personnel handling records; and approval records. The system automatically generates status reports based on the collected data. Status reports include: overall hazard statistics; risk level distribution; rectification progress statistics; overdue task statistics; rectification completion rate statistics; and risk change trend analysis. The system also uses visualization methods to display statistical results, including but not limited to: bar charts; line charts; pie charts; and trend analysis charts. Managers can use status reports to monitor the implementation of performance evaluations and the progress of hazard rectification in real time.

[0066] Furthermore, the system automatically calculates the scores for each evaluation indicator based on the weighting rules in the rating standard library. After the scores for each indicator are calculated, a weighted average is performed according to their corresponding weights. The formula for calculating the weighted total score is as follows: P=Σ(W i ×S i ); Where P represents the total evaluation score; W i S represents the weight of the i-th indicator; i This represents the score of the i-th indicator.

[0067] The system automatically determines the evaluation level based on the final score. Simultaneously, the system generates a comprehensive evaluation report. The comprehensive evaluation report includes: basic information about the evaluated object; scores for each indicator; evaluation level; statistical results of potential hazards; rectification completion status; trend analysis results; and improvement suggestions. The system stores the evaluation results in a historical database, serving as a crucial data source for subsequent assessments, risk identification model training, and standard optimization, forming a complete closed-loop management process.

[0068] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for intelligent assessment and closed-loop handling of potential hazards in nuclear power plants, characterized in that, include: In response to the request to create an assessment task, a first identifier is obtained, which is used to characterize the assessment object; Based on the first identifier, first data is obtained from the first database, the first database is used to store evaluation criteria, and the first data contains at least one evaluation criterion; In response to the completion of the association of the evaluation criteria, the corresponding second data is obtained from the associated business system based on the first identifier. The second data is used to characterize the operating status of the evaluation object. The second data is matched with the third data in the second database to obtain a first matching result. The second database is used to store risk features, and the third data contains at least one risk feature record. In response to the completion of the matching, a first record is generated, which is used to characterize the identified hazard information; A second record is generated based on the first record, and the second record is used to represent the task information that needs to be rectified. The second record triggers the execution mechanism's processing flow, and the status information of the processing flow is obtained; Based on the first data, the first matching result, and the status information, a first report is generated, which is used to characterize the assessment and evaluation results.

2. The method for intelligent assessment and closed-loop handling of potential hazards in nuclear power plants as described in claim 1, characterized in that, The step of obtaining the first data from the first database based on the first identifier includes: Obtain the set of evaluation criteria from the first database, wherein each record in the set of evaluation criteria contains at least a feature field and a weight field; The corresponding set of elements is determined based on the first identifier, and the set of elements is matched with the element fields in the set of evaluation criteria. Select the records that successfully match the evaluation criteria as the first candidate data; Based on the cycle type of the assessment task, the corresponding evaluation standard records are selected from the first candidate data to obtain the first data.

3. The intelligent assessment and evaluation method for nuclear power plants and the closed-loop handling method for potential hazards as described in claim 2, characterized in that, The step of matching the second data with the third data in the second database to obtain a first matching result includes: The second data is preprocessed to obtain the processed dataset; The processed dataset is compared with the threshold condition field and case feature field in the third dataset; Data that meets the preset anomaly conditions is selected as the second candidate data; Based on the second candidate data and the risk level determination rules, the corresponding risk level is determined; The second candidate data, the corresponding risk level, and the matched risk characteristics are recorded as the first matching result.

4. The method for intelligent assessment and closed-loop handling of potential hazards in nuclear power plants as described in claim 3, characterized in that, The response to the completion of the matching, generating a first record, includes: Based on the risk feature records in the first matching result, the corresponding risk description template is obtained from the second database; The device information, parameter deviations, and risk levels from the second candidate data are filled into the risk description template to generate the first description information; The first description information, risk level, scope of impact, and rectification suggestions are encapsulated into the first record.

5. The method for intelligent assessment and closed-loop handling of potential hazards in nuclear power plants as described in claim 4, characterized in that, The generation of the second record based on the first record includes: Read the risk level field from the first record and map it to the processing priority; Based on the device code in the first record, obtain the first spatial coordinates of the corresponding device from the 3D model database; Based on the measurement input information, the second spatial coordinates of the defect location are calculated, where the measurement input information represents the distance of the defect relative to the reference point of the equipment. The second spatial coordinates are calibrated to obtain the target defect location coordinates; Write the target defect location coordinates, risk level, and rectification suggestions into the second record.

6. The method for intelligent assessment and closed-loop handling of potential hazards in nuclear power plants as described in claim 5, characterized in that, The process of triggering the execution mechanism based on the second record and obtaining the status information of the processing process includes: Based on the device category and risk level in the second record, generate processing task instructions; The processing task instructions are sent to the corresponding execution mechanism system, and the task execution status is monitored; Obtain progress information, verification results, and completion status from the actuator system; The progress information, verification results, and completion status are used as the status information.

7. The method for intelligent assessment and closed-loop handling of potential hazards in nuclear power plants as described in claim 6, characterized in that, The step of generating a first report based on the first data, the first matching result, and the status information includes: Based on the weight configuration and scores of each indicator in the first data, a weighted average is performed to obtain a comprehensive evaluation score. The evaluation level is determined based on the comprehensive evaluation score and the preset grading rules; The first matching result and the status information are statistically analyzed to generate hidden danger statistics results and rectification progress results; Based on the historical evaluation score sequence, trend analysis results are generated; The evaluation level, hazard statistics, rectification progress, and trend analysis results are written into the first report.

8. The method for intelligent assessment and closed-loop handling of potential hazards in nuclear power plants as described in claim 7, characterized in that, Also includes: In response to the completion of the rectification task, rectification completion data is obtained, which includes the final processing plan and effect verification results; Based on the rectification completion data, update the third data and risk level determination rules in the second database.

9. The method for intelligent assessment and closed-loop handling of potential hazards in nuclear power plants as described in claim 8, characterized in that, The step of updating the third data and risk level determination rules in the second database based on the rectification completion data includes: The data obtained after rectification is added as new samples to the sample set of the second database. Based on the updated sample set, adjust the parameters of risk feature records and matching conditions; The adjusted parameters are written into the second database, and the corresponding version identifier is updated.

10. A nuclear power plant intelligent assessment and closed-loop hazard handling system, applied to the method described in any one of claims 1-7, characterized in that, include: The first acquisition module is used to acquire a first identifier in response to the creation request of the assessment task, wherein the first identifier is used to characterize the assessment object; A first processing module is configured to retrieve first data from a first database based on the first identifier, the first database being used to store evaluation criteria, and the first data containing at least one evaluation criterion. The second acquisition module is used to obtain corresponding second data from the associated business system based on the first identifier in response to the completion of the association of the evaluation criteria. The second data is used to characterize the operating status of the evaluation object. A matching module is used to match the second data with the third data in the second database to obtain a first matching result. The second database is used to store risk features, and the third data contains at least one risk feature record. The first generation module is used to generate a first record in response to the completion of matching, and the first record is used to characterize the identified hidden danger information; The second generation module is used to generate a second record based on the first record, and the second record is used to represent the task information that needs to be rectified. The triggering module is used to trigger the processing flow of the actuator based on the second record and to obtain the status information of the processing flow; The third generation module is used to generate a first report based on the first data, the first matching result, and the status information. The first report is used to characterize the assessment and evaluation results.

Images