Nuclear power operation optimization method based on atlas driving

Abstract

The present application relates to the technical field of intelligent operation and maintenance, in particular to a nuclear energy operation and maintenance optimization method based on graph driving, comprising the following steps: obtaining equipment data and maintenance records, marking state matching, screening maintenance strategies, combining semantic reasoning to extract fault paths, deviation classification to generate adaptability labels, screening non-interference tasks to extract work order mapping distribution to judge execution imbalance, calculating resource and task ratio record period difference, and generating operation and maintenance progress monitoring structure indicators.In the present application, the mapping relationship between equipment and working conditions is constructed through operation data and maintenance records, precise health state evaluation is realized, the fault path and deviation degree are identified by combining semantic reasoning, the adaptability of maintenance strategies and working conditions is improved, the risk of task interference is avoided, load fluctuation is identified by means of work order execution data, resource and task quantity comparison is combined, a resource input benefit evaluation mechanism is constructed, thereby improving fault prediction accuracy, task execution coordination and resource allocation rationality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent operation and maintenance, and in particular to a nuclear power operation and maintenance optimization method based on graph driving. BACKGROUND

[0002] The technical field of intelligent operation and maintenance mainly involves the use of modern information technology, automation technology and artificial intelligence to intelligently manage and optimize industrial equipment, production processes and the entire production environment. Its core tasks include equipment health management, predictive maintenance, fault diagnosis and repair, and production efficiency improvement. Intelligent operation and maintenance relies on technologies such as big data, cloud computing and the Internet of Things, and provides intelligent decision support for manufacturing enterprises through real-time monitoring, data collection and analysis, thereby achieving automation and self-optimization of production systems. Intelligent operation and maintenance technology not only reduces equipment failure rates and extends equipment life, but also identifies problems and makes predictive adjustments in the production process, thereby improving the overall operational efficiency and resource utilization of enterprises. The traditional nuclear power operation and maintenance optimization method refers to the operation and maintenance management of nuclear power facilities through conventional maintenance processes based on existing equipment. The traditional method relies on manual inspection, regular maintenance and equipment state monitoring, with the goal of ensuring the safety and stability of nuclear power facilities. Traditional operation and maintenance methods have limitations, relying on experience-based judgments, making it difficult to accurately predict equipment failure times and causes, and maintenance and repair work has strong timeliness requirements, making it impossible to achieve optimal resource allocation and optimization.

[0003] Existing technologies rely on manual inspection and regular maintenance, making it difficult to capture abnormal signs in time when the operating state of nuclear power equipment changes suddenly or external disturbances occur frequently. Equipment state recognition is based on experience-based judgments, and there is a lack of quantitative evaluation methods for health status, making it difficult to accurately match maintenance strategies to actual working conditions. The data collected by sensors cannot be effectively associated with specific task sections, and resource duplication or execution imbalance may occur during operation and maintenance task scheduling, such as when abnormal equipment operation data is not discovered in time, related maintenance tasks are still executed as usual, which may lead to task overlap, resource waste and schedule deviation problems, and overall limits the response capability of the operation and maintenance system to complex state changes and resource utilization efficiency. SUMMARY

[0004] The purpose of the present application is to solve the shortcomings in the prior art, and a nuclear power operation and maintenance optimization method based on graph driving is proposed.

[0005] In order to achieve the above-mentioned purpose, the present application adopts the following technical solution: a nuclear power operation and maintenance optimization method based on graph driving, comprising the following steps:

[0006] S1: Obtain nuclear energy equipment operation data and original maintenance records, extract equipment nodes and their associations, construct an initial knowledge graph, mark the matching between equipment status and operating conditions, and generate an equipment health status assessment list;

[0007] S2: Based on the equipment health status assessment list, select maintenance strategies that are suitable for the current working conditions, extract fault mode paths by combining semantic reasoning algorithms, and perform deviation calculation and classification processing with the benchmark working conditions to obtain maintenance strategy adaptability labels.

[0008] S3: Call the maintenance strategy adaptability tag, extract the fault mode number, identify the range of sensor data fluctuation within the section, compare the radiation sensor monitoring period with the fault mode section, record the number of overlapping time periods, and generate a list of radiation sensor abnormal impact sections.

[0009] S4: Based on the list of abnormally affected sections of the radiation sensor, filter out maintenance task nodes that are not disturbed, extract work order segment records and operation data, map task allocation and operation time distribution, determine whether there is an execution imbalance of tasks, and obtain work order task execution fluctuation groups.

[0010] As a further aspect of the present invention, the equipment health status assessment list includes equipment number, status label, operating condition deviation, and maintenance classification; the maintenance strategy adaptability label includes adaptability level, fault type, benchmark comparison result, and task association number; the radiation sensor abnormality impact zone list includes equipment type, impact time zone, number of overlapping time periods, and affected task number; and the work order task execution fluctuation group includes task distribution unevenness number, operation duration record, task completion deviation, and operation matching degree.

[0011] As a further aspect of the present invention, the steps for obtaining the equipment health status assessment list are as follows:

[0012] S111: Acquire nuclear energy equipment operation data and original maintenance records, extract equipment nodes and their associations, match equipment status acquisition time with operating condition requirement time, compare time range with status requirements, and generate partition node operation record time periods;

[0013] S112: Based on the time period of the partition node operation record, extract the overlapping time period between the equipment status and the working condition demand time interval, calculate the ratio of the overlapping time to the total working condition demand time, calculate the overlap ratio value, filter nodes with an overlap ratio lower than the benchmark value, and obtain the partition node status coverage deviation rate according to the number of equipment status labels.

[0014] S113: According to the partition node state coverage deviation rate, the node number is judged in a deviation state, the node number whose deviation rate exceeds the node synchronization threshold is identified, the node number, the state coverage information and the deviation rate value are integrated, and the equipment health state evaluation list is generated.

[0015] As a further scheme of the present application, the obtaining step of the maintenance strategy adaptability label is specifically:

[0016] S211: Based on the equipment health state evaluation list, identify the maintenance strategy and fault mode path that adapt to the current working condition requirement, extract the real-time sensor start and end fluctuation interval, calculate the start and end difference value of the fluctuation section, compare with the reference fluctuation interval, and get the fluctuation deviation value;

[0017] S212: Call the fluctuation deviation value, combine section distribution, fluctuation trend and adjustment frequency, integrate maintenance strategy deviation data, identify and calculate adaptability deviation degree according to section number, judge fluctuation direction according to adjustment frequency, and get maintenance strategy adaptability label.

[0018] As a further scheme of the present application, the obtaining step of the radiation sensor abnormal influence section list is specifically:

[0019] S311: Call the maintenance strategy adaptability label, screen the fluctuation deviation task section number, extract the fluctuation time period according to the node association table, process the section fluctuation time period according to the time dimension, identify the fluctuation time period index table, and get the fluctuation task time period set;

[0020] S312: According to the fluctuation task time period set, collect the sensor data fluctuation range of the same period section, identify the radiation sensor influence table, judge the daily sensor interference according to the interference threshold, match with the fluctuation task time period, judge whether there is fluctuation abnormal association, and generate the radiation sensor abnormal influence section list.

[0021] As a further scheme of the present application, the obtaining step of the work order task execution fluctuation group is specifically:

[0022] S411: Based on the radiation sensor abnormal influence section list, screen the maintenance task node, extract the task list, and get the node task set not affected by the radiation sensor interference;

[0023] S412: Call the node task set not affected by the radiation sensor interference, match the work order daily segmented record and operation data, extract the planned task quantity according to the task number, count the number of operators and real-time operation period, and generate the work order cooperation execution situation matching data set;

[0024] S413: According to the work order cooperation execution situation matching data set, the matching degree of task execution efficiency and operation distribution is evaluated, the efficiency fluctuation node is identified, the task whose fluctuation exceeds the benchmark value is marked as an abnormal node, the work order task execution matching deviation is analyzed, and a work order task execution fluctuation group is obtained.

[0025] As a further scheme of the present application, the method further comprises a step S5:

[0026] S5: The work order task execution fluctuation group is called, the abnormal fluctuation task group is extracted, the ratio of resource input to task quantity in the operation and maintenance model is calculated, the difference distribution of resource deployment period and task execution period is recorded, and an operation and maintenance progress monitoring structure index is generated.

[0027] The operation and maintenance progress monitoring structure index comprises a resource configuration ratio, a task intensity level, an execution period difference, and an operation and maintenance efficiency index.

[0028] As a further scheme of the present application, the operation and maintenance progress monitoring structure index is obtained by:

[0029] S511: The work order task execution fluctuation group is called, the nodes exceeding the threshold value are screened, the time interval and the task quantity change amplitude are recorded, and a progress fluctuation abnormality identification set is obtained.

[0030] S512: Based on the operation and maintenance model resources corresponding to the nodes in the progress fluctuation abnormality identification set, a node resource input ratio sequence is identified, an abnormal distribution interval is extracted and compared with a critical coefficient, a ratio deviation direction and a node number are recorded, and an operation and maintenance resource matching deviation index group is formed.

[0031] S513: According to the operation and maintenance resource matching deviation index group, the operation and maintenance model resource deployment and task execution time period are extracted, the difference between the resource deployment period and the operation period is identified, and the difference is sorted and labeled according to the progress benchmark, and an operation and maintenance progress monitoring structure index is generated.

[0032] Compared with the prior art, the present application has the advantages and positive effects that:

[0033] In the present application, by analyzing the nuclear power equipment operation data and maintenance records, the mapping relationship between equipment nodes and working condition requirements is formed, and then the fine characterization of the equipment health state is realized, combined with semantic reasoning to extract the fault path and quantify the deviation degree from the benchmark state, which can improve the adaptation accuracy between the maintenance strategy and the actual demand, relying on the sensor data fluctuation to identify the abnormal influence section, which can accurately locate the potential risk points in the unstable area, and then avoid interference factors in task allocation, using the work order execution record to build a task execution dynamic distribution model, which can effectively identify the task load fluctuation trend, further combined with the dynamic comparison of resources and task quantity, realize the structured evaluation of the efficiency of operation and maintenance resource investment, so as to promote the overall improvement of fault prediction accuracy, task coordination efficiency and resource allocation rationality. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 It is the main step schematic diagram of the present application;

[0035] Figure 2 It is the acquisition flow chart of equipment health state evaluation list in the present application;

[0036] Figure 3 It is the acquisition flow chart of maintenance strategy adaptability label in the present application;

[0037] Figure 4 It is the acquisition flow chart of radiation sensor abnormal influence section list in the present application;

[0038] Figure 5 It is the acquisition flow chart of work order task execution fluctuation group in the present application;

[0039] Figure 6 It is the acquisition flow chart of operation progress monitoring structure index in the present application. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below combined with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application, and are not used to limit the present application.

[0041] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0042] Embodiment one

[0043] Please refer to Figure 1 The present application provides a technical solution: a nuclear power operation and maintenance optimization method based on atlas driving, comprising the following steps:

[0044] S1: Obtain nuclear power equipment operation data and original maintenance records, extract equipment nodes and their associations, construct an initial knowledge graph, mark the matching of equipment state and working condition demand, and generate an equipment health state evaluation list;

[0045] S2: Based on the equipment health state evaluation list, filter the maintenance strategies that adapt to the current working condition demand, extract the fault mode path combined with the semantic reasoning algorithm, and perform deviation calculation and classification processing with the benchmark working condition to obtain a maintenance strategy adaptability label;

[0046] S3: Call the maintenance strategy adaptability label, extract the fault mode number, identify the sensor data fluctuation range in the section, compare the radiation sensor monitoring period with the fault mode section, record the number of coincidence time periods, and generate a radiation sensor abnormal influence section list;

[0047] S4: Based on the radiation sensor abnormal influence section list, filter the maintenance task nodes that are not disturbed, extract the work order section record and operation data, map the task allocation amount and operation period distribution, judge whether the task exists execution imbalance, and obtain a work order task execution fluctuation group;

[0048] S5: Call the work order task execution fluctuation group, extract the abnormal fluctuation task group, calculate the ratio of resource input amount to task amount in the operation and maintenance model, record the difference distribution of resource deployment period and task execution period, and generate an operation and maintenance progress monitoring structure index.

[0049] The device health state evaluation list includes device number, state label, working condition deviation, maintenance classification, maintenance strategy adaptability label including adaptability level, fault type, benchmark comparison result, task association number, radiation sensor abnormality influence section list including device type, influence time section, coincidence period number, affected task number, work order task execution fluctuation group including task distribution uneven number, operation time length record, task completion deviation, operation matching degree, operation and maintenance progress monitoring structure index including resource configuration ratio, task intensity level, execution cycle difference, operation and maintenance efficiency index.

[0050] Please refer to Figure 2 The acquisition step of the device health state evaluation list is specifically:

[0051] S111: Obtain nuclear power device operation data and original maintenance records, extract device nodes and their associations, match device state collection time and working condition demand time, and compare time range and state demand to generate partition node operation record period;

[0052] The operation data and original maintenance records of the nuclear power equipment are acquired, and the key operation parameters, state parameters and historical maintenance activity data of the nuclear power equipment are collected, for example, the real-time data of the vibration sensor, bearing temperature data, current data and other operation parameters of a reactor coolant pump (number: RCP001), and the original maintenance records such as the periodic inspection records, fault repair records, component replacement records of the pump. From the acquired data, each independent functional unit or monitoring point in the equipment, i.e. the equipment node, is accurately identified, and the mutual dependence relationship and logical connection between the equipment nodes, i.e. the relevance, are also determined, for example, the RCP001 pump body is the main node, and the motor, bearing and impeller inside the pump body are the sub-nodes, and there is a direct correlation between the bearing temperature and the motor current. In the management of the nuclear power equipment, the time stamp of the collected equipment state data is strictly matched with the standard working condition operation time stamp required by the nuclear power unit or the specific equipment unit, for example, the sensor data acquisition time period of the RCP001 pump on October 26 is 08:00 to 17:00, and the specified working condition requirement operation time period of the pump on that day is 07:00 to 18:00. Then, the matched time range and the preset equipment state requirement are compared one by one, for example, it is checked whether the data from 08:00 to 17:00 fully covers the key operation state information from 07:00 to 18:00. If there is a part missing or redundancy, the corresponding trimming or supplement is carried out. On this basis, the above-mentioned nuclear power equipment operation data, original maintenance records and the results of time matching and comparison are integrated, and a record containing all the key operation states and related events of each partition node in the time period is generated, for example, the record time period of the RCP001 pump on October 26 is 08:00 to 17:00, which contains the vibration data, temperature data and corresponding maintenance event records during this period.

[0053] S112: Based on the partition node operation record time period, the overlapping time period of the equipment state and the working condition requirement time interval is extracted, and the ratio of the overlapping time and the total length of the working condition requirement is calculated, using the formula:

[0054] ;

[0055] The overlapping ratio value is calculated, the nodes with an overlapping ratio lower than the reference value are screened, and the partition node state coverage deviation rate is obtained according to the number of equipment state annotations.

[0056] Wherein, represents the overlapping ratio value, represents the time interval overlapping length of the equipment state and the working condition requirement in the i-th record period, represents the normalized adjustment coefficient of the number of state annotations in the i-th record period, represents the equipment state length in the i-th record period, This represents the total duration of the operating condition within the i-th recording period. This indicates the total number of record periods involved in the calculation;

[0057] Based on the operating time periods of the partitioned nodes of nuclear energy equipment under specific operating conditions, the overlapping time periods of the equipment status data collection time interval and the corresponding operating condition demand time interval for each equipment node are accurately identified and extracted. For example, for nuclear energy equipment node RCP001, its equipment status data collection time is from 08:00 to 17:00 on the same day, and the operating condition demand time is from 07:00 to 18:00 on the same day. Then, the overlapping time period is from 08:00 to 17:00, which is 9 hours. Next, the ratio of the overlapping time period to the total operating condition demand time is calculated using the following formula, which is the overlap ratio value:

[0058] ,in, This represents the overlap ratio, which indicates the extent to which the equipment status data covers the operating requirements. Its absolute value ensures that the result is positive. Representing the The time interval between the equipment status and operating requirements within each recording period overlaps, in hours. This measure indicates the duration of actual effective data coverage. Representing the The normalized adjustment coefficient for the number of status labels within a recording period is used to measure the richness of human or labeled information in the device status data. It is calculated by comparing the number of status labels within that period to a preset maximum number of labels. For example, if there are 25 status labels in a period, and the maximum number that period can accommodate is 50, then... ; Representing the The device status duration within each recording period, i.e. the actual duration for which the device outputs data, is expressed in hours. This item represents the actual running time of data acquisition. Representing the The total operating time required within a recording period, that is, the total operating time that the equipment should theoretically meet within that period, in hours. This item represents the theoretical working time of the equipment under specific operating conditions. This represents the total number of recording periods involved in the calculation; it is the summation symbol in the formula. The upper limit represents the number of data samples included in the calculation, and the formula is obtained through... The difference between the calculated state duration and the required duration is multiplied by an adjustment factor. The duration of overlap Add them together to form the numerator, which aims to comprehensively consider data coverage, data volume, and demand satisfaction. The denominator is... The square sum of the total length of the working condition demand is considered, and the square root of 1 is taken for normalization processing of the numerator, to prevent the denominator from being too small, causing the ratio value to abnormally increase, and to give the ratio value a stable scale, so that the coincidence ratio value can objectively reflect the comprehensive coverage degree of equipment state data to working condition demand, for example, the data of RCP001 pump in three consecutive recording periods are selected for calculation, as shown in the following table:

[0059] Table 1: Nuclear power equipment node RCP001 running data statistics table

[0060]

[0061] Assuming that the preset maximum state label number is 50, the normalization adjustment coefficient of each period is respectively: , , ;

[0062] The above data is substituted into the formula to calculate value:

[0063] ;

[0064] The coincidence ratio value indicates that the data coverage and state recording of the nuclear power equipment in the selected period are good, and the coincidence ratio value is compared with the preset reference value, for example, the reference value is set to 0.8, if the calculated coincidence ratio value is lower than the reference value, the data coverage degree of the equipment node is determined to be insufficient, and further analysis is needed, for example, if the calculated coincidence ratio of a node is 0.75, which is lower than the reference value of 0.8, it is screened out, and according to the number of state labels corresponding to the screened equipment node, and combining the working condition demand, the equipment state coverage deviation rate of each node is calculated, the calculation method of the equipment state coverage deviation rate is: 1-(actual state label number / expected state label number), the expected state label number is set according to the equipment type, running condition and historical data quality requirement, for example, for RCP001 pump, if the coincidence ratio is lower than 0.8 and is screened out, and the actual state label number in a recording period is 10, and the expected state label number is 40, then the state coverage deviation rate is , the partition node state coverage deviation rate is obtained.

[0065] S113: According to the partition node state coverage deviation rate, the node number is judged in deviation state, the node number whose deviation rate exceeds the node synchronization threshold value is identified, the node number, state coverage information and deviation rate value are integrated, and a device health state evaluation list is generated; ​​

[0066] According to the partition node state coverage deviation rate, for example, for the device with node number RCP001, the state coverage deviation rate is 0.75, compare this deviation rate with the preset node synchronization threshold, for example, the node synchronization threshold is set to 0.50, which is determined based on long-term experience data and risk assessment of nuclear power plant operation, and represents the acceptable data coverage deviation degree, any deviation rate exceeding this threshold is considered as a state abnormality that needs attention, in this determination process, if the deviation rate of a node exceeds the threshold, for example, 0.75 is significantly higher than 0.50, the node number is identified as the node number with deviation rate exceeding the node synchronization threshold, which means that the data coverage quality or state synchronization of the node has a problem, then the identified node number, its corresponding state coverage information (for example, coincidence rate 1.2378 and actual state label number 10), and specific deviation rate value (for example, 0.75) are integrated to form a structured data set, for example, a record with an entry of {node number: RCP001, state coverage information: {coincidence rate: 1.2378, actual label number: 10}, deviation rate: 0.75}, the integrated information is organized into a comprehensive device health state evaluation list, which provides basic data for subsequent maintenance strategy formulation and failure mode analysis, and generates a device health state evaluation list.

[0067] Please refer to Figure 3 The acquisition step of the maintenance strategy adaptability label is specifically:

[0068] S211: Based on the device health state evaluation list, identify the maintenance strategy and failure mode path that adapt to the current working condition demand, extract the real-time sensor start and end fluctuation interval, and use the formula:

[0069] ;

[0070] Calculate the start and end difference value of the fluctuation section, compare it with the reference fluctuation interval, and get the fluctuation deviation value;

[0071] Wherein, represents the fluctuation difference characteristic value, represents the end sensor value of the jth fluctuation section, represents the start sensor value of the jth fluctuation section, represents the normalized coefficient of the number of failure mode paths corresponding to the sensor in the jth fluctuation section, represents the expected fluctuation value in the jth fluctuation section in the device health state evaluation list that matches the current working condition demand, represents the number of fluctuation sections participating in the calculation;

[0072] Based on the equipment health status assessment checklist, each equipment node in the checklist is analyzed to identify and match the most suitable maintenance strategy and potential failure mode paths under the current nuclear power operating conditions. For example, for the RCP001 pump, which is marked as having poor health status in the assessment checklist, strategies such as "condition-based predictive maintenance" or "fault diagnosis-based repair" are identified from the preset maintenance strategy library based on its current operating parameters (such as vibration data and bearing temperature) and operating conditions (such as full-load operation and startup phase), and associated with failure mode paths such as "bearing wear" and "impeller imbalance". At the same time, the starting and ending sensor values ​​of the equipment fluctuation range are extracted from real-time sensor data. For example, for the vibration sensor of the RCP001 pump, the starting value of a certain fluctuation range is... The termination value is The starting and ending difference of the fluctuation range is calculated using the following formula and compared with the preset benchmark fluctuation range to obtain the fluctuation deviation value: ,in, This represents the characteristic value of fluctuation difference, which is used to quantify the degree of fluctuation in sensor data and its deviation from the expected value; Representing the The termination sensor value of a fluctuation segment, for example, in vibration sensor monitoring, the vibration amplitude at the end of a certain monitoring period, in mm / s; Representing the The initial sensor value of each fluctuation segment, that is, the vibration amplitude at the beginning of the monitoring period, in mm / s; Representing the The normalized coefficient for the number of fault mode paths corresponding to a sensor within a fluctuation range is calculated by comparing the number of fault mode paths associated with that fluctuation range to the maximum number of fault mode paths associated with that type of sensor. For example, if a vibration sensor's data fluctuation is associated with 3 fault modes (such as bearing wear, rotor imbalance, pump cavitation), and that type of sensor can be associated with a maximum of 5 typical fault modes, then... ; Representing the The expected fluctuation value in the equipment health status assessment list within each fluctuation range matches the current operating conditions. This value is set based on the equipment's historical health data and standard operating specifications. For example, for the RCP001 pump in a healthy state, its expected vibration fluctuation value is 0.05 mm / s. This represents the number of fluctuation segments involved in the calculation, and is the summation symbol in the formula. The upper limit represents the number of sensor data fluctuation sample segments included in the calculation, as shown in the formula. The term calculates the squared difference within the fluctuation range, reflecting the intensity of the fluctuation itself, while The item combines the difference between the fluctuation termination value and the expected value, and considers the complexity of the failure mode, and the average of the two is taken, so that The value comprehensively evaluates the fluctuation characteristics of the sensor data and the deviation from the expected value, for example, the values of the RCP001 pump vibration sensor in three consecutive fluctuation sections are collected for calculation, as shown in Table 2:

[0073] Table 2: Nuclear power plant vibration sensor fluctuation data

[0074]

[0075] Assuming that the maximum number of associated failure modes of such sensors is 5, the normalization coefficients of each section are respectively: , , Substitute the above data into the formula to calculate the value:

[0076] ;

[0077] The fluctuation difference characteristic value indicates that the vibration sensor data of the RCP001 pump in the monitoring section has a certain fluctuation, and there is a slight deviation from the expected value. Compare the calculated fluctuation difference characteristic value with the preset reference fluctuation interval, for example, the preset reference fluctuation interval is 0.01 to 0.05 mm / s, if the value exceeds this range, it is determined that there is a fluctuation deviation, for example, 0.05856 exceeds 0.05, and this comparison result is taken as the fluctuation deviation value, and the fluctuation deviation value is obtained.

[0078] S212: Call the fluctuation deviation value, combine the section distribution, fluctuation trend and adjustment frequency, and uniformly collect and maintain the strategy deviation data, identify and calculate the adaptability deviation degree according to the section number, judge the fluctuation direction according to the adjustment frequency, and obtain the maintenance strategy adaptability label;

[0079] The fluctuation deviation value is called, and the value is comprehensively considered with the section distribution of the device operation, the fluctuation trend of the sensor, and the adjustment frequency of the maintenance strategy. For example, for the RCP001 pump, the fluctuation deviation value is 0.05856, and the fluctuation deviation value is combined with the running section (for example, frequently occurs in the starting stage, and occasionally occurs in the steady state running stage) of the deviation value, the fluctuation deviation value with the change trend over time (for example, the vibration deviation value shows a slow upward trend), and the maintenance strategy adjustment frequency for the pump (for example, once a month for preventive maintenance strategy adjustment, or once a quarter for overhaul strategy adjustment). On this basis, all related data are uniformly collected to form maintenance strategy deviation data, the deviation data are identified according to the section number of the device, and the adaptability deviation degree of each section is calculated. The adaptability deviation degree quantifies the effectiveness of the current maintenance strategy for a specific fluctuation section. The size, duration and frequency of the fluctuation deviation value are considered in the calculation. For example, if the vibration deviation value of the RCP001 pump in the starting section is high and the adjustment frequency is low, the adaptability deviation degree will be calculated as high. According to the adjustment frequency of the maintenance strategy, the fluctuation direction of the device is determined. If the adjustment frequency is high, for example, the parameters are adjusted every week, which indicates that the fluctuation is quickly responded and the fluctuation direction tends to be stable or controlled. If the adjustment frequency is low, for example, the overhaul is performed once a year, and the fluctuation deviation continues to increase, which indicates that the fluctuation direction tends to deteriorate or lose control. Combined with the analysis result, the maintenance strategy adaptability label is finally obtained.

[0080] Please refer to Figure 4 The acquisition step of the abnormal influence section list of the radiation sensor is specifically as follows:

[0081] S311: Call the maintenance strategy adaptability label, filter the fluctuation deviation task section number, extract the fluctuation time period according to the node association table, process the section fluctuation time period according to the time dimension, identify the fluctuation time period index table, and obtain the fluctuation task time period set;

[0082] The maintenance strategy adaptability label is called to accurately screen all task section numbers with significant fluctuation deviation or low maintenance strategy adaptability, for example, if the "start" running section of RCP001 pump is marked as low adaptability, the section number is selected, then the fluctuation time period associated with the task section number is extracted according to the pre-established device node association table, which records each device node, sensor data type and corresponding historical fluctuation time, for example, the "start" section of RCP001 pump is obtained through the node association table. All vibration data of the pump in the past month is outside the normal range, such as "October 27, 07:00-07:30", then the extracted section fluctuation period is finely processed in the time dimension, including merging time overlapping sections, filling time gap short sections or filtering according to the preset minimum fluctuation duration, for example, if "07:00-07:10" and "07:15-07:30" are components of the same fluctuation event, and the interval is less than 10 minutes, they are merged into "07:00-07:30", after completing the time dimension processing, a fluctuation time period index table is identified and generated, which details the final fluctuation time period of each selected task section and its unique identifier, for example, {task section number: RCP001-start, fluctuation time period: [10-2707:00-07:30, 11-0306:45-07:15]}, all fluctuation time periods in the fluctuation time period index table are collected to obtain the fluctuation task period set.

[0083] S312: According to the fluctuation task period set, the sensor data fluctuation range of the same period section is collected, the radiation sensor influence table is identified, the daily sensor interference is judged according to the interference threshold, and the fluctuation task period is matched to judge whether there is a fluctuation abnormal association, and generate a radiation sensor abnormal influence section list;

[0084] According to the fluctuation task period set, the fluctuation range of sensor data of all sections at the same time is collected and obtained in a specific time period, for example, for the time period "10:00-10:30" of RCP001 pump in the fluctuation task period set, the actual measurement values of all sensors (not limited to vibration sensors, including temperature, pressure, etc.) in this time period are collected, and the fluctuation amplitude is calculated, for example, the vibration fluctuation range of 0.05mm / s to 0.15mm / s is obtained, at the same time, the preset radiation sensor influence table is referred to and identified, which records the known influence of different radiation levels in the nuclear energy environment on the readings of various sensors, for example, the table lists "when the gamma ray intensity is higher than 100nGy / h, the readings of some temperature sensors produce ±2% error", according to the preset interference threshold to judge whether the sensor is interfered by radiation every day, for example, set the gamma ray interference threshold to 150nGy / h, if the radiation sensor reading is higher than this threshold continuously, it is determined that there is radiation interference, the setting of this threshold is based on the experimental data and industry standard of the equipment's radiation resistance, and is accurately matched with the fluctuation task period, for example, if RCP001 pump in the fluctuation task period "10:00-10:30" on October 27, synchronously monitors the nearby radiation sensor reading of 200nGy / h, which exceeds the interference threshold of 150nGy / h, further judges whether there is fluctuation abnormal association in this fluctuation task period, that is, whether the fluctuation of sensor data is causally related or strongly correlated with radiation interference, for example, by comparing the synchronism of radiation intensity curve and sensor fluctuation curve, if they are highly consistent in time and have consistent amplitude change, it is determined that there is abnormal association, on this basis, all the identified section information affected by radiation anomaly is integrated to generate a radiation sensor abnormal influence section list.

[0085] Please refer to Figure 5 The acquisition step of the work order task execution fluctuation group is specifically:

[0086] S411: Based on the radiation sensor abnormal influence section list, filter the maintenance task nodes, extract the task list, and obtain the node task set not affected by the radiation sensor interference;

[0087] Based on the radiation sensor abnormal influence section list, first, the maintenance task nodes contained therein are accurately screened, for example, all maintenance tasks related to the RCP001 pump are identified from the list, and the corresponding task list is extracted from the nuclear power plant maintenance overall plan, which contains all planned maintenance activities, execution time, expected resources, etc. Information, by comparing the maintenance task nodes with the radiation sensor abnormal influence section list, those node tasks in the radiation sensor abnormal influence section list are excluded from the total task list, for example, if a certain maintenance task (for example: bearing check) of the RCP001 pump is listed in the radiation sensor abnormal influence section list, the task will not be included in this execution range for the time being, to ensure the accuracy of subsequent operations, and finally obtain the node task set not affected by the radiation sensor interference.

[0088] S412: Call the node task set not affected by the radiation sensor interference, match the work order daily segment record and the operation data, extract the planned task quantity according to the task number, count the number of operators and the real-time operation period, and generate the work order cooperation execution situation matching data set;

[0089] Call the node task set not affected by the radiation sensor interference, and accurately match each task in the task set with the daily segment record and the actual operation data recorded in the daily work order management, for example, for the daily inspection task (task number: RCP_DAILY_CHK_001) of the RCP001 pump, match its work order record on October 28, including the actual execution time period, the operator, etc. Information, then, according to the task number, extract the planned task quantity of the task from the matched work order record, for example, the planned task quantity of the inspection task is "check 20 measuring points", and simultaneously count the number of operators and the real-time operation period during the actual operation of the task, for example, the actual number of operators is 2, and the actual operation period is 09:00-10:00. Integrate the matching, extraction and statistics results, including task number, planned task quantity, actual number of operators, actual operation period and deviation of planned operation, etc., to form the work order cooperation execution situation matching data set.

[0090] S413: According to the work order cooperation execution situation matching data set, evaluate the matching degree of task execution efficiency and operation distribution, identify efficiency fluctuation nodes, mark tasks with fluctuation exceeding the benchmark value as abnormal nodes, analyze the matching deviation of work order task execution, and obtain the work order task execution fluctuation group;

[0091] According to the work order cooperation execution matching dataset, the execution efficiency of each task and the matching degree of operation distribution are evaluated. For example, for the inspection task with task number RCP_DAILY_CHK_001, the planned task amount is "check 20 measuring points", the actual number of operators is 2, the actual operation period is 09:00-10:00, and if the actual number of completed measuring points is 18, the execution efficiency is 18 / 20=0.9, and the matching degree of operation distribution is evaluated. Based on the evaluation result, the efficiency fluctuation node is identified, that is, the task node whose execution efficiency or operation distribution deviates from the expectation, for example, if the execution efficiency is lower than 0.95 or higher than 1.05 (i.e. the efficiency deviation rate exceeds 5%), it is identified as an efficiency fluctuation node, and the efficiency deviation rate is calculated as |actual efficiency-1|, and those tasks whose fluctuations exceed the preset reference value are marked as abnormal nodes, for example, if the reference value of the efficiency deviation rate is set to 0.10 (i.e. the efficiency fluctuation exceeding 10% is regarded as abnormal), if the efficiency deviation rate of a task is 0.12, the task is marked as an abnormal node, and the reference value is set according to historical task execution data and best practices in the nuclear power industry. Through further analysis of abnormal nodes, the execution matching deviation of work order tasks is evaluated in depth, for example, analyzing whether the abnormal deviation rate 0.12 is due to insufficient personnel, non-standard operation process, or external environmental interference, and the tasks evaluated and analyzed are classified and integrated to obtain the work order task execution fluctuation group.

[0092] Please refer to Figure 6 The acquisition steps of the operation progress monitoring structure index are as follows:

[0093] S511: Call the work order task execution fluctuation group, filter the nodes exceeding the threshold, record the time interval and task quantity change amplitude, and obtain the progress fluctuation abnormality identification set;

[0094] Call the work order task execution fluctuation group, first accurately filter all task nodes in it, identify and extract those nodes whose execution efficiency or operation distribution fluctuation exceeds the preset threshold, for example, from the work order task execution fluctuation group, filter a certain maintenance task of RCP001 pump, whose efficiency fluctuation rate is 0.12, which exceeds the set fluctuation threshold 0.10. For the filtered nodes, accurately record the time interval of task execution, for example, 09:00-10:00 on October 28, and record the specific change amplitude of task quantity in the time interval, for example, the planned inspection of 20 measuring points, the actual completion of 18 measuring points, the task quantity change amplitude is 2 measuring points or 10% of the uncompleted quantity. Organize and identify the recorded time interval and task quantity change amplitude information to form the progress fluctuation abnormality identification set.

[0095] S512: Identify the operation and maintenance model resources corresponding to the nodes in the progress fluctuation anomaly identification set, identify the node resource input ratio sequence, extract the abnormal distribution interval and compare the critical coefficient, record the ratio deviation direction and node number, and form the operation and maintenance resource matching deviation index group;

[0096] Based on the nodes identified by the progress fluctuation anomaly identification set, the operation and maintenance model resources corresponding to the nodes are first called. The operation and maintenance model resources include standard maintenance processes, required manpower, material resources, time, and other resource configuration information for this type of equipment. For example, for the RCP001 pump maintenance task identified as abnormal, the operation and maintenance model specifies that the standard resource input is 2 senior engineers, and the time consumption is 2 hours. The resource input ratio sequence of the node is identified and calculated, i.e., the ratio of actual resource input to operation and maintenance model resource input. For example, if the task actually inputs 3 senior engineers and consumes 2.5 hours, the manpower ratio is 3 / 2 = 1.5, and the time ratio is 2.5 / 2 = 1.25. Further, the abnormal distribution interval is extracted from the resource input ratio sequence. For example, if the normal ratio range is between 0.8 and 1.2, then 1.5 and 1.25 both fall within the abnormal distribution interval. The abnormal distribution interval is compared with the preset critical coefficient. The critical coefficient is a threshold value used to judge the degree of resource input abnormality. For example, the critical coefficient is set to 1.3, indicating that if the ratio exceeds 1.3, it is considered that the resource input deviates significantly. This coefficient is set based on historical operation and maintenance data and risk assessment. After comparison, the direction of each abnormal ratio deviation (e.g., positive deviation if higher than 1.3, negative deviation if lower than 0.7) and the corresponding node number are recorded. For example, the manpower ratio 1.5 of the RCP001 pump task is a positive deviation. The information including the deviation direction and node number is integrated to form the operation and maintenance resource matching deviation index group.

[0097] S513: According to the operation and maintenance resource matching deviation index group, extract the operation and maintenance model resource input and task execution time period, identify the difference between the resource input period and the operation period, and sort and label according to the progress benchmark to generate the operation and maintenance progress monitoring structure index;

[0098] According to the operation and maintenance resource matching offset index group, the operation and maintenance model resource allocation information (for example, the planned resource input amount and time) corresponding to each task and the actual execution time period of the task are accurately extracted. For example, the operation and maintenance model resource allocation plan of a certain task is 4 hours, and the actual execution time period is 08:00 to 13:00 (that is, 5 hours). Further, the difference between the resource allocation period and the operation period, that is, the deviation in time between the plan and the actual, is identified. For example, the planned 4 hours and the actual 5 hours differ by 1 hour. At the same time, the difference information is sorted and labeled with a preset progress benchmark. The progress benchmark is a standard for measuring whether the task completion progress meets expectations. For example, the progress benchmark can be set as "completed on time (difference ≤ 0)", "slight delay (0 < difference ≤ 1 hour)", "moderate delay (1 hour < difference ≤ 3 hours)", or "serious delay (difference > 3 hours)". Based on the benchmark, the progress of each task is sorted and labeled. For example, the 1-hour difference of the above task will be labeled as "slight delay". The information including the difference between the resource allocation and operation periods and the progress benchmark sorting and labeling is organized to generate an operation and maintenance progress monitoring structure index.

[0099] The above is only a preferred embodiment of the present application, and does not limit the present application in other forms. Any skilled person in the art can modify or change the above disclosed technical content to equivalent embodiments applied to other fields, but any simple modification, equivalent change and modification of the above embodiments without departing from the technical solution of the present application, according to the technical essence of the present application, still belongs to the protection scope of the present application.

Claims

1. A method for nuclear power operation optimization based on atlas driving, characterized in that, The method comprises the following steps: S1: obtaining nuclear power equipment operation data and original maintenance records, extracting equipment nodes and their associations, constructing an initial knowledge graph, marking the matching of equipment state and working condition demand, and generating an equipment health state evaluation list; S2: based on the equipment health state evaluation list, screening maintenance strategies suitable for the current working condition demand, extracting fault mode paths combined with semantic reasoning algorithms, and calculating and classifying deviations from the reference working condition to obtain a maintenance strategy adaptability label; S3: calling the maintenance strategy adaptability label, extracting fault mode numbers, identifying the fluctuation range of sensor data in the section, comparing the radiation sensor monitoring period with the fault mode section, recording the number of coincidence time periods, and generating a radiation sensor abnormal influence section list; The acquisition step of the radiation sensor abnormal influence section list is specifically: S311: calling the maintenance strategy adaptability label, screening fluctuation deviation task section numbers, extracting fluctuation time periods according to the node association table, processing section fluctuation time periods according to the time dimension, identifying the fluctuation time period index table, and obtaining a fluctuation task time period set; S312: according to the fluctuation task time period set, collecting the sensor data fluctuation range of the same period section, identifying the radiation sensor influence table, judging the daily sensor interference according to the interference threshold, matching with the fluctuation task time period, judging whether there is a fluctuation abnormal association, and generating a radiation sensor abnormal influence section list; S4: based on the radiation sensor abnormal influence section list, screening maintenance task nodes not disturbed, extracting work order section records and operation data, mapping task allocation and operation time period distribution, judging whether the task exists execution imbalance, and obtaining a work order task execution fluctuation group.

2. The atlas-driven nuclear energy operation optimization method according to claim 1, characterized in that, The equipment health state evaluation list includes equipment number, state label, working condition deviation amount, and maintenance classification. The maintenance strategy adaptability label includes adaptability level, fault type, reference comparison result, and task association number. The radiation sensor abnormal influence section list includes equipment type, influence time section, coincidence time period number, and affected task number. The work order task execution fluctuation group includes task distribution uneven number, operation time length record, task completion deviation amount, and operation matching degree.

3. The atlas-driven nuclear energy operation optimization method according to claim 1, characterized in that, The acquisition step of the equipment health state evaluation list is specifically: S111: obtaining nuclear power equipment operation data and original maintenance records, extracting equipment nodes and their associations, matching equipment state collection time and working condition demand time, and comparing time range and state demand to generate a partition node running record time period; S112: based on the partition node running record time period, extracting the coincidence time period of the equipment state and working condition demand time interval, calculating the ratio of the coincidence time to the total length of the working condition demand, calculating the coincidence ratio value, screening nodes with a coincidence ratio lower than the reference value, and obtaining the partition node state coverage deviation rate according to the number of equipment state labels; S113: according to the partition node state coverage deviation rate, making a deviation state judgment on the node number, identifying the node number whose deviation rate exceeds the node synchronization threshold, integrating the node number, state coverage information and deviation rate value, and generating an equipment health state evaluation list.

4. The atlas-driven nuclear energy operation optimization method according to claim 3, characterized in that, The obtaining step of the maintenance strategy adaptability label is specifically: S211: Based on the equipment health state evaluation list, identify the maintenance strategy and fault mode path that adapt to the current working condition demand, extract the real-time sensor start and end fluctuation interval, calculate the start and end difference value of the fluctuation section, compare with the reference fluctuation interval, and obtain the fluctuation deviation value; S212: Call the fluctuation deviation value, combine the section distribution, fluctuation trend and adjustment frequency, unify the maintenance strategy deviation data, identify and calculate the adaptability deviation degree according to the section number, judge the fluctuation direction according to the adjustment frequency, and obtain the maintenance strategy adaptability label.

5. The atlas-driven nuclear energy operation optimization method according to claim 1, wherein, The obtaining step of the work order task execution fluctuation group is specifically: S411: Based on the radiation sensor abnormal influence section list, screen the maintenance task node, extract the task list, and obtain the node task set not affected by the radiation sensor interference; S412: Call the node task set not affected by the radiation sensor interference, match the work order daily section record and operation data, extract the planned task quantity according to the task number, count the number of operators and real-time operation period, and generate the work order cooperation execution situation matching data set; S413: According to the work order cooperation execution situation matching data set, evaluate the matching degree of task execution efficiency and operation distribution, identify efficiency fluctuation nodes, mark tasks with fluctuation exceeding the reference value as abnormal nodes, analyze the work order task execution matching deviation, and obtain the work order task execution fluctuation group.

6. The atlas-driven nuclear energy operation optimization method according to claim 1, wherein, The method further comprises the S5 step: S5: Call the work order task execution fluctuation group, extract the abnormal fluctuation task group, calculate the resource input quantity and task quantity ratio in the operation and maintenance model, record the difference distribution of resource deployment period and task execution period, and generate the operation and maintenance progress monitoring structure index; The operation and maintenance progress monitoring structure index includes resource configuration ratio, task intensity level, execution period difference, and operation and maintenance efficiency index.

7. The atlas-driven nuclear energy operation optimization method according to claim 6, characterized in that, The obtaining step of the operation and maintenance progress monitoring structure index is specifically: S511: Call the work order task execution fluctuation group, screen nodes exceeding the threshold value, record the time interval and task quantity change amplitude, and obtain the progress fluctuation abnormality identification set; S512: Based on the operation and maintenance model resources corresponding to the nodes in the progress fluctuation abnormality identification set, identify the node resource input ratio sequence, extract the abnormal distribution interval and compare the critical coefficient, record the ratio deviation direction and node number, and form the operation and maintenance resource matching deviation index group; S513: According to the operation and maintenance resource matching deviation index group, extract the operation and maintenance model resource deployment and task execution time period, identify the difference between the resource deployment period and the operation period, and sort and mark according to the progress reference, and generate the operation and maintenance progress monitoring structure index.

Images