Nuclear power plant transient management method and system

Abstract

This invention relates to a method and system for transient management of nuclear power plants. The method includes: acquiring raw monitoring data; cleaning and filtering the raw monitoring data to obtain processed data; setting the start time of the current transient identification based on information from the previous automatic transient identification result, thereby obtaining a complete range of data to be identified; extracting data from the processed data according to the range of data to be identified to obtain the data to be identified; performing automatic transient identification on the data to be identified to obtain the automatic transient identification result; classifying and statistically analyzing the automatic transient identification result to obtain the classification and statistical results; performing over-limit analysis and transient consumption prediction based on the classification and statistical results to obtain the over-limit result and prediction result, and outputting the over-limit result and prediction result. This invention enables data-driven management of raw monitoring data related to transients in nuclear power plants.

Description

Technical Field

[0001] This invention relates to the field of nuclear power plant operation and management technology, and in particular to a method and system for transient management of nuclear power plants. Background Technology

[0002] During operation, parameters such as temperature, pressure, and coolant flow rate in the main loop of a nuclear power plant change with operating conditions; these changes are referred to as transients. Transients can cause fatigue damage to the mechanical equipment in the main loop. Therefore, identifying and statistically analyzing transients in the main loop is crucial for managing fatigue damage to primary loop equipment and ensuring the integrity of the primary loop's pressure boundaries.

[0003] Currently, transient management in nuclear power plants still largely relies on manual identification and statistics. On-site engineers periodically record and analyze transient monitoring data from the units. However, this management method suffers from drawbacks such as low efficiency and reliability in transient identification, significant influence of human factors on classification and statistical results, and a lack of data-driven management. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for transient management of nuclear power plants.

[0005] The technical solution adopted by this invention to solve its technical problem is: constructing a transient management method for nuclear power plants, comprising: Obtain raw monitoring data; The original monitoring data is cleaned and filtered to obtain the processed data; The start time of this transient recognition is set based on the information from the previous transient automatic recognition result, thereby obtaining the complete range of data to be recognized; data extraction is performed on the processed data based on the range of data to be recognized to obtain the data to be recognized; The data to be identified is subjected to automatic transient identification to obtain an automatic transient identification result; the automatic transient identification result includes remarks indicating whether the duration of the transient exceeds the trigger end time; The transient automatic identification results are then classified and statistically analyzed to obtain classification and statistical results; the classification and statistical results include transient classification results, verification results, and cumulative number of transient occurrences; Based on the classification and statistical results, exceedance analysis and transient consumption prediction are performed to obtain exceedance results and prediction results, and the exceedance results and prediction results are output.

[0006] Preferably, the cleaning and filtering of the raw monitoring data includes: The original monitoring data is subjected to outlier removal processing to obtain cleaned data; The data removed from the cleaned data is repaired using interpolation and / or adjacent value filling methods to obtain repaired data. The repaired data is filtered to obtain the processed data.

[0007] Preferably, the raw monitoring data includes monitoring data output from multiple different types of sensors; The automatic transient identification of the data to be identified includes: The identification process for each type of monitoring data in the data to be identified is performed based on the sensor type, including: determining a transient identification parameter threshold and a transient identification time threshold according to the sensor category and location of the monitoring data; determining whether the change or increment of the monitoring data within the transient identification time threshold is greater than the number of occurrences of the transient identification parameter threshold; if so, determining that the monitoring data has a transient change feature and recording the transient information of each occurrence of the transient change feature; otherwise, determining that the monitoring data has no transient change feature; wherein, the transient information includes the transient identification parameter threshold, the transient identification time threshold, the feature start time, the feature end time, the start value, the end value, the maximum change rate, and sensor description information.

[0008] Preferably, the transient classification and statistics of the transient automatic identification results include: The transient information from various monitoring data is used to classify and identify the design transients that occur, resulting in transient classification results. The types of design transients include primary loop temperature transients, primary loop auxiliary system nozzle transients, primary loop pressure transients, and steam generator secondary side pressure transients. The classification and identification process includes: determining whether a primary loop temperature transient has occurred based on primary loop cold section temperature monitoring data and hot section temperature monitoring data; determining whether a primary loop auxiliary system nozzle transient has occurred based on primary loop nozzle temperature monitoring data; determining whether a primary loop pressure transient has occurred based on primary loop pressure monitoring data; and determining whether a steam generator secondary side pressure transient has occurred based on steam generator secondary side pressure monitoring data. The transient classification results include the occurrence of the design transient, the transient start time, and the transient end time. The change amount and rate of change of each monitoring data are compared with the design transient limit to obtain the verification result; Based on the transient classification results, statistics are performed on each design transient to obtain the cumulative number of occurrences of each design transient.

[0009] Preferably, the step of performing transient classification and statistics on the transient automatic identification results further includes: If the automatic identification result for a certain transient states that the transient has not ended, the transient will not be classified for the time being.

[0010] Preferably, the classification and identification process further includes: Retrieve the operation record if running; The transient classification results are verified based on the operation records.

[0011] Preferably, the step of performing over-limit analysis and transient consumption prediction based on the classification and statistical results includes: The cumulative number of transient occurrences for each design transient is compared with the corresponding preset consumption limit to obtain the comparison results; The transient occurrence frequency is determined based on the historical cumulative number of occurrences of each of the design transients. Obtain the target prediction time, predict the cumulative number of transient occurrences at the target prediction time based on the transient occurrence frequency, and obtain the prediction result.

[0012] Preferably, the nuclear power plant transient management method further includes: Store the identification results, classification and statistical results, out-of-limit results and prediction results obtained each time the transient automatic identification process is triggered, and update the historical statistical data based on the identification results, classification and statistical results, out-of-limit results and prediction results; The consumption rate of each design transient is generated based on the cumulative number of transient occurrences, and the consumption rate ranking of each design transient is displayed.

[0013] Preferably, the nuclear power plant transient management method further includes: Generate one-to-one transient codes based on each of the described transient designs; The permissions for each user role are set according to a preset permission list; wherein, the user roles include system administrator, operator, advanced user, running user, and general user; Determine the current user's role; Obtain operation instructions, and perform at least one of the following operations based on the operation instructions and the permissions of the current user role: edit user role, edit the default extraction time of data extraction time, edit multiple transient codes corresponding one-to-one with each of the design transients, output the cumulative number of transient occurrences of the design transients corresponding to the transient codes, set the preset consumption limit of the design transients, query historical statistical data, query operation logs, enter transient data, query transient data, edit transient data, and verify transient data; wherein, the transient data includes raw monitoring data and processed data.

[0014] The present invention also constructs a transient management system for nuclear power plants, comprising: The acquisition module is used to acquire raw monitoring data; The filtering and cleaning module is used to clean and filter the original monitoring data to obtain processed data. The data extraction module is used to set the start time of the current transient recognition based on the information of the previous transient automatic recognition result, thereby obtaining the complete range of data to be recognized; and to extract data from the processed data according to the range of data to be recognized, to obtain the data to be recognized. The transient identification module is used to automatically identify transients in the data to be identified and obtain an automatic transient identification result; the automatic transient identification result includes remarks indicating whether the duration of the transient exceeds the trigger end time; The classification and statistics module is used to classify and statistically analyze the transient automatic identification results to obtain classification and statistics results; the classification and statistics results include transient classification results and the cumulative number of transient occurrences; The over-limit analysis and prediction module is used to perform over-limit analysis and transient consumption prediction based on the classification and statistical results, obtain over-limit results and prediction results, and output the over-limit results and prediction results.

[0015] Implementing this invention has the following beneficial effects: it enables data-driven management of raw monitoring data related to transients in nuclear power plants, improves the management efficiency of transient classification and statistics, reduces the risk of human error, and can also predict future transient situations, providing important reference data for equipment life extension, and helps improve the economy and reliability of nuclear power plants. Attached Figure Description

[0016] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings: Figure 1 This is a flowchart of a transient management method for nuclear power plants in some embodiments of the present invention; Figure 2 This is a schematic diagram of the structure of a nuclear power plant transient management system in some embodiments of the present invention. Detailed Implementation

[0017] To provide a clearer understanding of the technical features, objectives, and effects of the present invention, specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0018] It should be noted that the flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0019] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0020] Figure 1 This is a flowchart of a transient management method for nuclear power plants in some embodiments of the present invention. This transient management method can be applied to a processor, enabling data-driven management of raw monitoring data related to transients in nuclear power plants. It improves the efficiency of transient classification and statistical management, reduces the risk of human error, and can also predict future transient situations, providing important reference data for equipment life extension and contributing to improved economic efficiency and reliability of nuclear power plants.

[0021] like Figure 1 As shown, the transient management method for nuclear power plants may include steps S10, S20, S30, S40, S50 and S60.

[0022] Step S10 includes: acquiring raw monitoring data.

[0023] In some embodiments, the raw monitoring data includes monitoring data output by multiple different types of sensors, specifically including monitoring data output by multiple temperature sensors, multiple pressure sensors, multiple flow sensors, and multiple level sensors (the raw monitoring data of a certain nuclear power plant includes monitoring data output by more than 40 sensors). Each sensor is an existing sensor installed in different locations in the nuclear power plant, such as temperature and pressure sensors installed in the primary loop and auxiliary loop, temperature sensors installed at the nozzles, and pressure sensors installed on the secondary side of the steam generator.

[0024] In some embodiments, raw monitoring data can be obtained online or manually.

[0025] Raw monitoring data is typically acquired over a full day, from 00:00:00 to 24:00:00. After the raw monitoring data is imported into the system, the management system automatically begins the data cleaning, filtering, and transient automatic identification process, which are the subsequent steps.

[0026] Step S20 includes cleaning and filtering the raw monitoring data to obtain processed data. It should be noted that due to factors such as environmental noise, the raw monitoring data may contain anomalies such as missing data, out-of-range data, and abrupt data jumps. Missing data can cause timestamp shifts, affecting the determination of the duration, start time, and end time of transients. Out-of-range and abrupt data jumps can affect the accuracy of transient classification. This step of cleaning and filtering the raw monitoring data can eliminate noise signals (including out-of-range and abrupt data jumps) in the raw data, ensure data integrity, and play an important role in improving the confidence level of transient management.

[0027] In some embodiments, the cleaning and filtering process may include: removing outliers from the original monitoring data to obtain cleaned data; repairing the removed data in the cleaned data based on interpolation and / or adjacent value filling to obtain repaired data; and filtering the repaired data to obtain processed data.

[0028] Specifically, taking the monitoring data of a certain sensor as an example, outlier removal processing can include: performing a temporal continuity check on the monitoring data (i.e., determining whether the sampling timestamps are continuous) to determine whether there is missing data and to determine the location of the missing data; further, for each sample value in the monitoring data, determine whether the sample value exceeds the sensor's predetermined data range, and if so, determine that the sample value is out-of-range data; also determine whether the change in the sample value from the previous sample value is greater than a set threshold, and if so, determine that the sample value is jump data; when the sample value does not exceed the sensor's predetermined data range and the change in the sample value from the previous sample value is not greater than the set threshold, determine that the sample value is normal data; remove out-of-range data and jump data. Next, for multiple points of consecutively removed data in terms of timestamps, interpolation is preferentially used for data repair, which helps improve data reliability; for single points or a few (e.g., less than 3) of consecutively removed data in terms of timestamps, adjacent value filling is preferentially used for data repair, which helps reduce the processor's computational burden. Filtering can include low-pass filtering algorithms, median filtering algorithms, etc., to remove impulse noise superimposed on the repaired data and improve the signal-to-noise ratio of the data.

[0029] Step S30 includes: setting the start time of the current transient recognition based on the information of the previous transient automatic recognition result, thereby obtaining the complete range of data to be recognized; and extracting data from the processed data according to the range of data to be recognized to obtain the data to be recognized.

[0030] The remarks indicate whether the duration of the transient in the previously triggered automatic transient identification process has ended. Since there may be cases where the transient has not ended by the time the automatic transient identification process ends, this step can set the start time of the unfinished transient in the previous automatic transient identification process as the start time of the current transient identification, thereby ensuring the integrity of transient management.

[0031] In some embodiments, the data to be identified can be obtained by performing the following steps: If a transient identification parameter was marked as "transient not ended" at the end of the previous transient automatic identification process, then the start time of the current transient automatic identification process is the transient start time of that transient identification parameter in the previous transient identification result. For example, if the temperature sensor MT029 starts heating at 14:00 on day T0 and the heating has not ended by 24:00, the transient automatic identification result will be marked with the information "transient not ended". When the transient data of day T0+1 is imported into the system and after data cleaning and filtering, the system starts to perform transient automatic identification on the MT029 temperature monitoring data, and will automatically start the transient identification process from 14:00 on day T0 based on the annotation information of day T0. In addition, the end time of each transient identification can be a preset default end time.

[0032] Step S40 includes: performing automatic transient identification on the data to be identified to obtain the automatic transient identification result. The automatic transient identification result includes transient information and remarks. The transient information may include transient identification parameter thresholds, transient identification time thresholds, feature start time (representing the start of the transient), feature end time (representing the end of the transient), initial value (representing the sampled value at the start of the transient), final value (representing the sampled value at the end of the transient), difference (i.e., the difference between the final value and the initial value), maximum rate of change, and sensor description information (which may include the sensor's specific installation location, function, sensor model, etc.). The sensor description information includes the sensor's specific installation location and functional description.

[0033] In some embodiments, automatic transient identification can be performed by executing the following steps: Each type of monitoring data in the data to be identified is processed based on the sensor type. Further, the identification process may include: determining a transient identification parameter threshold and a transient identification time threshold based on the sensor category and location of the monitoring data; determining whether the change in the transient identification parameter within the transient identification time threshold is greater than the number of occurrences of the transient identification parameter threshold; if so, determining that the monitoring data exhibits transient change characteristics and recording the transient information for each occurrence of the transient change characteristic; otherwise, determining that the monitoring data does not exhibit transient change characteristics.

[0034] It should be noted that when the temperature sensor is located in the primary loop system, the monitored data is the temperature value; when the temperature sensor is located in the primary loop auxiliary system, the transient identification parameter is the "temperature difference". For pressure sensors, the monitored data is the pressure value.

[0035] For transient nozzle conditions in the primary loop auxiliary system, due to the combined influence of the primary loop coolant and the auxiliary system coolant, transient nozzle identification requires a "temperature difference" parameter. This means using the temperature difference between the auxiliary system nozzle position temperature sensor and the corresponding primary loop position temperature sensor as the parameter for transient identification. Typically, the parameter threshold for transient nozzle conditions is 20°C, and the time threshold is 1 hour. For example, for transient nozzle identification in a chemical and volumetric control system (RCV system), the identification parameters should be: ,in For RCV system nozzle position temperature sensor, This is a temperature sensor for the corresponding location in a primary loop system (RCP).

[0036] It should be noted that "change" includes both increases and decreases in monitored data. Taking a temperature sensor in a primary loop as an example, assuming the transient identification parameter threshold is 5℃ and the transient identification time threshold is 3 hours, since the temperature rise and fall in the primary loop is closely related to reactivity, it is necessary to monitor the change. If, based on the monitoring data of this temperature sensor, it is determined that the temperature rise or fall exceeds 5℃ within 3 hours during the data extraction time, it is judged that the monitoring data corresponding to this temperature sensor exhibits transient change characteristics.

[0037] Furthermore, the transient recognition parameter threshold and transient recognition time threshold can be different for different sensors, including the case of multiple sensors of the same type installed in different locations. For example, the transient recognition parameter threshold and transient recognition time threshold can be different for a primary-loop pressure sensor and a secondary-loop pressure sensor.

[0038] Step S50 includes: classifying and statistically analyzing the transient automatic identification results to obtain classification and statistical results. The classification and statistical results include transient classification results, verification results, and the cumulative number of transient occurrences.

[0039] Transient classification can categorize the results of automatic transient identification into one or several design transients, and compare and verify the relevant monitoring data (such as temperature difference, maximum temperature change rate, pressure difference, etc.) with the corresponding design transient limits. That is, the identification of each design transient may involve transient monitoring of multiple monitoring data (such as temperature, pressure, etc.).

[0040] Statistics refer to the counting of the number of times each design transient has occurred. Each nuclear power unit has a design transient inventory file, which defines several design transients, such as reactor startup transients and reactor power boost transients. The design file contains information on the expected number of times each design transient will occur within the design life, as well as the temperature change limits, temperature change rate limits, and pressure change limits for each design transient.

[0041] In some embodiments, transient classification and statistics can be performed by executing the following steps: classifying and identifying the design transients based on the transient information of each monitoring data to obtain transient classification results; automatically verifying each monitoring data by comparing the change amount and rate of change of each monitoring data with the design transient limit to obtain verification results; and statistically analyzing each design transient based on the transient classification results to obtain the cumulative occurrence count of each design transient. The transient classification results include the type of the design transient, the transient start time, and the transient end time. Furthermore, the transient duration can be calculated from the transient start time and transient end time.

[0042] The purpose of classification and identification processing is to determine what type of design transient occurred within a given time period. Automatic verification of each monitoring data point ensures that it falls within the design transient limits, improving transient classification accuracy. The verification results indicate whether the amount and rate of change of each monitoring data point exceed the limits. Furthermore, if the verification fails, a new design transient must be selected, or the relevant monitoring data must be recorded as an "unclassifiable transient."

[0043] In some embodiments, the type of design transient in the transient automatic identification result may include primary loop temperature transient, primary loop auxiliary system nozzle transient, primary loop pressure transient, and steam generator secondary side pressure transient. Accordingly, the classification and identification process may include: determining whether a primary loop temperature transient has occurred based on primary loop cold section temperature monitoring data and hot section temperature monitoring data; determining whether a primary loop auxiliary system nozzle transient has occurred based on primary loop nozzle temperature monitoring data; determining whether a primary loop pressure transient has occurred based on primary loop pressure monitoring data; and determining whether a steam generator secondary side pressure transient has occurred based on steam generator secondary side pressure monitoring data.

[0044] In addition, when the note information of a transient automatic identification result is "transient has not ended", it can be temporarily left unclassified and identified and classified after subsequent data is imported into the system.

[0045] In this embodiment, the temperature monitoring data for the primary loop cold and hot sections includes the monitoring data output by temperature sensors installed in the primary loop cold and hot sections; the primary loop pressure monitoring data includes the monitoring data output by pressure sensors installed in the primary loop; the primary loop nozzle temperature monitoring data includes the monitoring data output by temperature sensors installed in the primary loop nozzles; and the steam generator secondary side pressure monitoring data includes the monitoring data output by pressure sensors installed on the secondary side of the steam generator. Understandably, taking a primary loop temperature transient as an example, when a transient change is observed in the monitoring data output by a temperature sensor in a primary loop cold or hot section, a primary loop temperature transient can be identified. Furthermore, different types of design transients may occur simultaneously within the same transient automatic identification process, and the same design transient may occur multiple times within the same transient automatic identification process. This embodiment can classify and statistically analyze several types of design transients occurring within the analysis time.

[0046] Because there are time differences in the responses of different sensors when a design transient occurs, transients can be categorized and their initial and final times determined as follows: The initial and final times of the transient are determined based on the characteristic start and end times of each transient change feature during the transient event; and the design transient is selected based on the operation. Specifically, since multiple sensors may be involved in transient change features when each design transient occurs, the characteristic start and end times of each sensor's transient change feature can be displayed in a table format through a human-computer interaction module (which may include a monitor, mouse, keyboard, etc.). Furthermore, the table can also display information such as the amount of change, rate of change, transient identification parameter threshold, transient identification time threshold, and verification results for each transient change feature, so that staff can access relevant information.

[0047] In one specific embodiment, if the temperature sensor MT029 exhibits transient change characteristics between "2:10" and "3:40" and between "4:00" and "5:00", respectively, and the pressure sensor MP037 exhibits transient change characteristics between "1:00" and "2:00", the operator can determine that a certain design transient has occurred based on engineering experience and the unit's operating information for the day. Therefore, the operator can select the design transient through the human-machine interface module (as shown in the drop-down menu) and simultaneously input the transient start time and transient end time. It should be noted that the transient start time and transient end time usually encompass the duration of all transient change characteristics. For example, in this embodiment, the transient start time can be set to "1:00" (i.e., the earliest characteristic start time), and the transient end time can be set to a time later than the latest characteristic end time among all transient change characteristics, such as "5:00", "6:00", and "7:00", etc.

[0048] Alternatively, in other embodiments, transient classification and determination of transient start and end times can be achieved by employing machine learning techniques (such as neural network algorithms) to construct a classification model that can automatically classify transients and determine their start and end times based on the transient identification results. Understandably, this embodiment can improve recognition efficiency.

[0049] Furthermore, the training process of the classification model may include: acquiring training data (including multiple transient automatic identification results and the design transients corresponding to each transient automatic identification result); constructing an initial model based on a neural network algorithm; training the initial model using the training data, and correcting it according to the output results of the initial model during the training process (correcting the output results when they are incorrect, such as classification errors, errors in determining the transient end time, etc.); iterating the training until the accuracy of the output results of the initial model reaches a set accuracy (e.g., 90%), and the training is completed, thus obtaining the classification model.

[0050] In some embodiments, the classification and identification process may further include: acquiring operation records; and verifying the transient classification results based on the operation records. Operation records may include valve operation records, mode switching records, power control records, etc. Operation records are closely related to transient occurrences. For example, during reactor start-up transients, the opening and closing of certain valves may lead to primary loop pressure transients. Therefore, this embodiment can combine the status data of the set valves and the unit status to verify the accuracy of the transient classification results. Taking valve operation records as an example, valve operation records may include status switching records of several set valves, which may include valves installed in the primary and secondary loops. For example, when a primary loop pressure transient is determined to occur, the status switching records of the valves in the primary loop can determine that these valves have actions to increase or decrease their opening, thus determining that the occurrence of a primary loop pressure transient is a normal situation. If the status switching records of the valves in the primary loop determine that the opening of these valves remains unchanged during the data extraction time, it indicates that the cause of the primary loop pressure transient needs further investigation, and an alert signal can be output to prompt personnel to analyze the cause of the primary loop pressure transient more deeply in subsequent processing.

[0051] The following steps can be used to automatically verify each monitoring data point: For each monitoring data point, the following steps are performed: 1. Obtain the relevant change limit based on the selected design transient; 2. Determine if the monitoring data is less than the change limit design; if so, the monitoring data meets the change verification requirements; otherwise, the monitoring data does not meet the change verification requirements; 3. Determine if the rate of change of the monitoring data is less than the rate of change design limit; if so, the rate of change of the monitoring data meets the rate of change verification requirements; otherwise, the rate of change of the monitoring data does not meet the rate of change verification requirements; 4. Generate sub-verification results corresponding to the monitoring data based on the above determination results. The verification result is composed of the sub-verification results corresponding to each monitoring data point.

[0052] It should be noted that "relevant change limits" include the change limit and rate of change design limits corresponding to several types of monitoring data encompassed by the selected design transient. For example, if a design transient identifies the temperature of the first set target and the pressure of the second set target, then the "relevant change limits" include the temperature change limit and the rate of temperature change design limit for the first set target, as well as the pressure change limit and the rate of pressure change design limit for the second set target.

[0053] Step S60 includes: performing over-limit analysis and transient consumption prediction based on the classification and statistical results, obtaining over-limit results and prediction results, and outputting the over-limit results and prediction results.

[0054] In this step, the exceedance results and prediction results can be combined to form a management report, which can be output to a display device for display. The exceedance results can include the judgment result of whether the cumulative number of transient occurrences for each design transient exceeds the preset consumption limit. The prediction results can include the curve (or trend) of the cumulative number of occurrences of each design transient in the future.

[0055] In some embodiments, over-limit analysis and transient consumption prediction can be performed by performing the following steps: comparing the cumulative number of transient occurrences for each design transient with the corresponding preset consumption limit to obtain the comparison result; determining the transient occurrence frequency based on the historical cumulative number of transient occurrences for each design transient; obtaining the target prediction time, and predicting the cumulative number of transient occurrences at the target prediction time based on the transient occurrence frequency to obtain the prediction result.

[0056] Specifically, the preset consumption limit for each design transient can be given in the technical specifications and set in advance by the staff. When the cumulative number of transient occurrences for a certain design transient exceeds its corresponding preset consumption limit, the comparison result is set as the design transient exceeding the limit; otherwise, the comparison result is set as the design transient not exceeding the limit. The comparison results of each design transient constitute the aforementioned exceedance result. The historical cumulative number of transient occurrences includes the cumulative number of transient occurrences based on previous transient classification results. Taking a certain design transient as an example, the occurrence frequency (e.g., X times / year or X times / fuel cycle) can be calculated based on the historical cumulative number of transient occurrences of the design transient. The target prediction time (e.g., Y years or the Zth fuel cycle, where Z is a positive integer greater than the number of fuel cycles completed by the unit) is multiplied by the occurrence frequency to obtain the predicted cumulative number of transient occurrences (i.e., the prediction result). In addition, the fuel cycle is relatively fixed for the unit, such as 12 months or 18 months.

[0057] Because the frequency of transients is relatively high during the commissioning phase of the unit, in order to improve the confidence of the prediction results, in some embodiments, the steps of performing over-limit analysis and transient consumption prediction may further include: obtaining the unit commissioning start time and unit commissioning end time; removing the cumulative transient occurrences from the unit commissioning start time to the unit commissioning end time from the historical cumulative transient occurrences to form the historical cumulative transient occurrences during normal unit operation; and performing curve fitting based on the historical cumulative transient occurrences during normal unit operation for the design transient to obtain the transient cumulative occurrences change curve. In some embodiments, the nuclear power plant transient management method may further include the following steps: storing the transient automatic identification results, classification and statistical results, over-limit results, and prediction results obtained each time the transient automatic identification process is triggered, and updating the historical statistical data based on the transient automatic identification results, classification and statistical results, over-limit results, and prediction results; and / or generating the consumption rate of each design transient based on the cumulative transient occurrences of each design transient to display the consumption rate ranking of each design transient (e.g., the top 10 ranking).

[0058] In this embodiment, historical statistical data includes all transient automatic identification results, classification and statistical results, limit exceedance results, and prediction results obtained from previous triggering of the transient automatic identification process, so that staff can review management records. Taking one type of design transient as an example, the consumption rate can be equal to the quotient of the current cumulative number of transient occurrences of the design transient divided by its preset consumption limit. The consumption rate can more intuitively represent the remaining consumption limit of the design transient. For example, when the consumption rate of the design transient is as high as 80%, staff need to prepare for safety assessment, repair, or replacement of the relevant equipment (i.e., the equipment affected by the design transient). At the same time, it can also warn staff that the relevant equipment does not meet the life extension conditions.

[0059] In some embodiments, the nuclear power plant transient management method may further include the following steps: generating a one-to-one transient code based on each design transient; setting permissions for each user role according to a preset permission list; determining the current user role based on login information; obtaining operation instructions, and performing at least one of the following operations based on the operation instructions and the permissions of the current user role: editing user roles, setting the default extraction time for data extraction, editing management reports, querying management reports, verifying management reports, archiving management reports, editing multiple transient codes corresponding one-to-one with each design transient, outputting the cumulative number of transient occurrences of the design transient corresponding to the transient code, setting preset consumption limits for design transients, querying historical statistical data, querying operation logs, entering transient data, querying transient data, editing transient data, and verifying transient data. The user roles include system administrators, operators, advanced users, running users, and general users, and the transient data includes raw monitoring data and processed data.

[0060] In this embodiment, different user roles have different permissions. The system administrator's permissions include editing user roles, editing transient codes, entering transient data, and querying operation logs. The operator's permissions include tracking the cumulative occurrence count of the design transient corresponding to the output transient code, querying historical statistics, querying transient data, entering transient data, editing transient data, editing the default extraction time for data extraction, verifying transient data (i.e., determining the correctness of transient data), querying transient data, querying management reports, editing management reports, verifying management reports, and archiving management reports. The advanced user's permissions include tracking the cumulative occurrence count of the design transient corresponding to the output transient code, querying historical statistics, querying management reports, querying transient data, entering transient data, and verifying transient data. The running user's permissions include tracking the cumulative occurrence count of the design transient corresponding to the output transient code, querying management reports, querying transient data, setting preset consumption limits for design transients, and querying operation logs. The general user's permissions include querying transient data and querying management reports. In addition, the transient code is used to number the design transients. For example, the reactor shutdown transient is numbered as transient 2.0. By entering the transient code, users can directly query the cumulative number of transient occurrences, transient data, and other data of the corresponding design transient. This realizes the integrated query function of transient statistical data and actual transient data, which has the advantages of convenience and speed.

[0061] This invention also provides a transient management system for nuclear power plants. For example... Figure 2 As shown, the transient management system of the nuclear power plant may include an acquisition module 1, a filtering and cleaning module 2, a data extraction module 3, a transient identification module 4, a classification and statistics module 5, and an over-limit analysis and prediction module 6.

[0062] Module 1 is used to acquire raw monitoring data.

[0063] The filtering and cleaning module 2 is used to clean and filter the raw monitoring data to obtain processed data. It should be noted that the specific process of cleaning and filtering can be found above and will not be repeated here.

[0064] The data extraction module 3 is used to set the start time of the current transient recognition based on the information of the previous transient automatic recognition result, so as to obtain the complete range of data to be recognized; and to extract data from the processed data according to the range of data to be recognized, so as to obtain the data to be recognized.

[0065] The transient recognition module 4 is used to automatically recognize transients in the data to be recognized, and obtain the automatic transient recognition result. The automatic transient recognition result may include remarks indicating whether the transient duration exceeds the trigger end time. It should be noted that the specific process of transient recognition can be referred to above, and will not be repeated here.

[0066] The classification and statistics module 5 is used to classify and statistically analyze the transient automatic identification results, obtaining classification and statistical results. These results include transient classification results and the cumulative number of transient occurrences. It should be noted that the specific process of transient classification and statistics can be found above and will not be repeated here.

[0067] The out-of-limit analysis and prediction module 6 is used to perform out-of-limit analysis and transient consumption prediction based on the classification and statistical results, obtain the out-of-limit results and prediction results, and output the out-of-limit results and prediction results. It should be noted that the specific process of out-of-limit analysis and transient consumption prediction can be referred to above, and will not be repeated here.

[0068] In some embodiments, such as Figure 2 As shown, the transient management system of the nuclear power plant may also include a storage module, a consumption rate management module, a design transient limit generation module, a permission setting module, and a human-machine interaction module.

[0069] The storage module is used to store the transient automatic identification results, classification and statistical results, out-of-limit results and prediction results obtained each time the transient automatic identification process is triggered, and to update the historical statistical data based on the transient automatic identification results, classification and statistical results, out-of-limit results and prediction results.

[0070] The consumption rate management module is used to generate the consumption rate of each design transient based on the cumulative number of transient occurrences, display the consumption rate ranking of each design transient, and transmit the ranking results to the human-computer interaction module.

[0071] The transient limit generation module is used to set the preset consumption limits for each design transient, as well as the design limits for the amount of change and the rate of change for each monitoring data.

[0072] The permission settings module is used to set permissions for each user role according to a preset permission list and to determine the current user role based on login information. User roles include system administrator, operator, advanced user, running user, and general user.

[0073] The human-computer interaction module is used to perform at least one of the following operations based on the operation instructions and the permissions of the current user role: editing user roles, editing the default extraction time for data extraction, editing multiple transient codes corresponding one-to-one with each design transient, outputting the cumulative occurrence count of the design transient corresponding to the transient code, setting the preset consumption limit for the design transient, querying historical statistical data, querying operation logs, entering transient data, querying transient data, editing transient data, and verifying transient data. The human-computer interaction module is also used to perform display tasks when querying relevant data, including displaying transient data, displaying the consumption rate ranking of each design transient, displaying operation logs, and displaying historical statistical data.

[0074] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0075] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0076] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0077] It is understood that the above embodiments only illustrate preferred embodiments of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can freely combine the above technical features without departing from the concept of the present invention, and can also make several modifications and improvements, all of which fall within the protection scope of the present invention. Therefore, all equivalent transformations and modifications made with respect to the scope of the claims of the present invention should fall within the scope of the claims of the present invention.

Claims

1. A transient management method for nuclear power plants, characterized in that, include: Obtain raw monitoring data; The original monitoring data is cleaned and filtered to obtain the processed data; The start time of this transient recognition is set based on the information from the previous transient automatic recognition result, thereby obtaining the complete range of data to be recognized; data extraction is performed on the processed data based on the range of data to be recognized to obtain the data to be recognized; The data to be identified is subjected to automatic transient identification to obtain an automatic transient identification result; the automatic transient identification result includes remarks indicating whether the duration of the transient exceeds the trigger end time; The transient automatic identification results are then classified and statistically analyzed to obtain classification and statistical results; the classification and statistical results include transient classification results, verification results, and cumulative number of transient occurrences; Based on the classification and statistical results, exceedance analysis and transient consumption prediction are performed to obtain exceedance results and prediction results, and the exceedance results and prediction results are output.

2. The transient management method for nuclear power plants according to claim 1, characterized in that, The cleaning and filtering process for the raw monitoring data includes: The original monitoring data is subjected to outlier removal processing to obtain cleaned data; The data removed from the cleaned data is repaired using interpolation and / or adjacent value filling methods to obtain repaired data. The repaired data is filtered to obtain the processed data.

3. The transient management method for nuclear power plants according to claim 1, characterized in that, The raw monitoring data includes monitoring data output from multiple different types of sensors; The automatic transient identification of the data to be identified includes: The identification process for each type of monitoring data in the data to be identified is performed based on the sensor type, including: determining a transient identification parameter threshold and a transient identification time threshold according to the sensor category and location of the monitoring data; determining whether the change or increment of the monitoring data within the transient identification time threshold is greater than the number of occurrences of the transient identification parameter threshold; if so, determining that the monitoring data has a transient change feature and recording the transient information of each occurrence of the transient change feature; otherwise, determining that the monitoring data has no transient change feature; wherein, the transient information includes the transient identification parameter threshold, the transient identification time threshold, the feature start time, the feature end time, the start value, the end value, the maximum change rate, and sensor description information.

4. The nuclear power plant transient management method according to claim 3, characterized in that, The transient classification and statistics of the transient automatic identification results include: The transient information from various monitoring data is used to classify and identify the design transients that occur, resulting in transient classification results. The types of design transients include primary loop temperature transients, primary loop auxiliary system nozzle transients, primary loop pressure transients, and steam generator secondary side pressure transients. The classification and identification process includes: determining whether a primary loop temperature transient has occurred based on primary loop cold section temperature monitoring data and hot section temperature monitoring data; determining whether a primary loop auxiliary system nozzle transient has occurred based on primary loop nozzle temperature monitoring data; determining whether a primary loop pressure transient has occurred based on primary loop pressure monitoring data; and determining whether a steam generator secondary side pressure transient has occurred based on steam generator secondary side pressure monitoring data. The transient classification results include the occurrence of the design transient, the transient start time, and the transient end time. The change amount and rate of change of each monitoring data are compared with the design transient limit to obtain the verification result; Based on the transient classification results, statistics are performed on each design transient to obtain the cumulative number of occurrences of each design transient.

5. The nuclear power plant transient management method according to claim 4, characterized in that, The transient classification and statistics of the transient automatic identification results also include: If the automatic identification result for a certain transient states that the transient has not ended, the transient will not be classified for the time being.

6. The nuclear power plant transient management method according to claim 4, characterized in that, The classification and identification process also includes: Retrieve the operation record if running; The transient classification results are verified based on the operation records.

7. The transient management method for nuclear power plants according to claim 5, characterized in that, The step of performing over-limit analysis and transient consumption prediction based on the classification and statistical results includes: The cumulative number of transient occurrences for each design transient is compared with the corresponding preset consumption limit to obtain the comparison results; The transient occurrence frequency is determined based on the historical cumulative number of occurrences of each of the design transients. Obtain the target prediction time, predict the cumulative number of transient occurrences at the target prediction time based on the transient occurrence frequency, and obtain the prediction result.

8. The transient management method for nuclear power plants according to claim 7, characterized in that, The transient management method for nuclear power plants also includes: Store the identification results, classification and statistical results, out-of-limit results and prediction results obtained each time the transient automatic identification process is triggered, and update the historical statistical data based on the identification results, classification and statistical results, out-of-limit results and prediction results; The consumption rate of each design transient is generated based on the cumulative number of transient occurrences, and the consumption rate ranking of each design transient is displayed.

9. The transient management method for nuclear power plants according to claim 8, characterized in that, The transient management method for nuclear power plants also includes: Generate one-to-one transient codes based on each of the described transient designs; The permissions for each user role are set according to a preset permission list; wherein, the user roles include system administrator, operator, advanced user, running user, and general user; Determine the current user's role; Obtain operation instructions, and perform at least one of the following operations based on the operation instructions and the permissions of the current user role: edit user role, edit the default extraction time of data extraction time, edit multiple transient codes corresponding one-to-one with each of the design transients, output the cumulative number of transient occurrences of the design transients corresponding to the transient codes, set the preset consumption limit of the design transients, query historical statistical data, query operation logs, enter transient data, query transient data, edit transient data, and verify transient data; wherein, the transient data includes raw monitoring data and processed data.

10. A transient management system for a nuclear power plant, characterized in that, include: The acquisition module is used to acquire raw monitoring data; The filtering and cleaning module is used to clean and filter the original monitoring data to obtain processed data. The data extraction module is used to set the start time of the current transient recognition based on the information of the previous transient automatic recognition result, thereby obtaining the complete range of data to be recognized; and to extract data from the processed data according to the range of data to be recognized, to obtain the data to be recognized. The transient identification module is used to automatically identify transients in the data to be identified and obtain an automatic transient identification result; the automatic transient identification result includes remarks indicating whether the duration of the transient exceeds the trigger end time; The classification and statistics module is used to classify and statistically analyze the transient automatic identification results to obtain classification and statistics results; the classification and statistics results include transient classification results and the cumulative number of transient occurrences; The over-limit analysis and prediction module is used to perform over-limit analysis and transient consumption prediction based on the classification and statistical results, obtain over-limit results and prediction results, and output the over-limit results and prediction results.

Images