A method and system for monitoring initial loading of a reactor

Abstract

This application discloses a method and system for monitoring the initial fuel loading of a nuclear reactor, relating to the field of nuclear reactions. The method includes: compensating the original count rate of at least one detector based on environmental parameters to obtain a compensated count rate for at least one detector; preprocessing the compensated count rate of the at least one detector to obtain preprocessed detector data; performing data fusion processing on the preprocessed detector data to obtain overall core parameter data; obtaining prediction results based on a time series model using the overall core parameter data and historical overall core parameter data, the prediction results including predicted neutron flux, doubling time, and time to reach an alarm threshold; and determining the final monitoring result based on the prediction results and a dynamic alarm threshold. This application achieves end-to-end optimization from raw signals to intelligent decision-making through a complete data flow processing chain, providing a safe, reliable, and intelligent monitoring guarantee for the initial fuel loading of a nuclear reactor.

Description

Technical Field

[0001] This application relates to the field of nuclear reactions, and in particular to a method and system for monitoring the initial fuel loading of a reactor. Background Technology

[0002] The initial fuel loading monitoring system of a nuclear power plant plays a crucial role in real-time monitoring and assessment of the neutron flux in the reactor core during the initial fuel loading process. At this stage, the neutron flux spontaneously released from the fuel assemblies is extremely low, and the nuclear measurement systems located on the periphery of the core are at a certain distance from the core, making it difficult to accurately capture subtle changes within the core. To accurately grasp the core status and prevent the risk of accidental criticality or supercriticality during the fuel loading process, a temporary neutron detector must be introduced inside the core. This is a core technical means to ensure the safe conduct of the initial fuel loading operation.

[0003] Currently, the industry commonly uses monitoring systems with He proportional counters as the core detection element. However, this existing technology suffers from several drawbacks: the system's self-test function is highly dependent on manual operation, making it impossible to achieve comprehensive, automated diagnostics on a regular basis; multiple detectors typically operate independently, lacking system-level data fusion and collaborative analysis, resulting in insufficient overall early warning capabilities; furthermore, the system is susceptible to environmental interference, affecting the accuracy and reliability of monitoring data, which may lead to false alarms or missed alarms, posing safety hazards during the material loading process. Summary of the Invention

[0004] The purpose of this application is to address at least one of the aforementioned technical deficiencies.

[0005] On one hand, embodiments of this application provide a method for monitoring the initial fuel loading of a reactor, the method comprising: Obtain the raw count rate and environmental parameters of at least one detector, and compensate the raw count rate of at least one detector based on the environmental parameters to obtain the compensated count rate of at least one detector; At least one detector compensation count rate is preprocessed to obtain at least one preprocessed detector data, and the at least one preprocessed detector data is fused to obtain the overall core parameter data. Historical core overall parameter data is obtained, and prediction results are obtained based on the core overall parameter data and historical core overall parameter data using a time series model. The prediction results include predicted neutron flux, doubling time, and time to reach alarm threshold. Obtain the dynamic alarm threshold and determine the final monitoring result based on the relationship between the prediction result and the dynamic alarm threshold.

[0006] Optionally, the raw count rate for each detector is obtained in the following way: The neutron flux rate in the reactor core is obtained, and an electrical pulse signal is obtained based on the neutron flux rate in the reactor core. The electrical pulse signal is then amplified to obtain an amplified electrical pulse signal. The amplified electrical pulse signal is filtered to obtain a square wave pulse, and the original count rate of each detector is calculated based on the square wave pulse.

[0007] Optionally, environmental parameters include temperature and pressure data. The original count rate of at least one detector is compensated based on these environmental parameters to obtain a compensated count rate for at least one detector, including: Obtain the compensation model pre-established based on experimental data, input the temperature and pressure data into the compensation model, and obtain the compensation coefficients; The compensated count rate for each detector is obtained by multiplying the original count rate of each detector by the compensation coefficient.

[0008] Optionally, data preprocessing is performed on at least one detector's compensated count rate to obtain at least one preprocessed detector data, including: Align at least one detector compensation count rate to a unified timestamp to obtain the aligned detector compensation count rates. The compensated count rates of each aligned detector are filtered to obtain the filtered compensated count rates of each detector. The data missing of each filtered detector is filled by interpolation algorithm to obtain at least one preprocessed detector data.

[0009] Optionally, at least one preprocessed detector data is subjected to data fusion processing to obtain overall core parameter data, including: The location information of the detector corresponding to each preprocessed detector data is obtained, and the three-dimensional neutron fluence distribution is obtained through a data fusion algorithm based on each preprocessed detector data and the location information of each detector. The overall core parameters characterizing the overall state of the reactor core are calculated based on the three-dimensional neutron flux distribution.

[0010] Optionally, the overall core parameter data includes total core power, power peak factor, and flux tilt. The overall core parameter data characterizing the overall core state, calculated based on the three-dimensional neutron flux rate distribution, includes: The total core power was obtained by integrating the three-dimensional neutron flux rate distribution. The local maximum fluence rate and the average fluence rate are determined based on the three-dimensional neutron fluence rate distribution, and the ratio of the local maximum fluence rate to the average fluence rate is used as the power peak factor. The core axial power and core radial power are obtained, and the tilt angle is obtained based on the core axial power and core radial power.

[0011] Optionally, prediction results are obtained based on a time series model using overall core parameter data and historical overall core parameter data, including: Input the overall core parameter data and historical overall core parameter data into the time series model to obtain the predicted neutron flux; The flux exponential growth rate is calculated based on the neutron flux distribution in the reactor core, and the doubling time is calculated based on the flux exponential growth rate. Obtain the preset alarm neutron flux threshold, and determine the alarm threshold time based on the relationship between the predicted neutron flux and the alarm neutron flux threshold.

[0012] Optionally, obtain dynamic alarm thresholds, including: Obtain the alarm threshold, current loading stage, and current operation step for each loading stage; The alarm threshold corresponding to the current loading stage is dynamically adjusted based on the current operation steps to obtain the dynamic alarm threshold.

[0013] Optionally, the final monitoring results include risk assessment results and alarm levels. The final monitoring results are determined based on the relationship between the predicted results and the dynamic alarm thresholds, including: A multi-dimensional risk assessment is conducted based on the relationship between the prediction results and the dynamic alarm threshold to obtain the risk assessment results. Based on the risk assessment results, an alarm level is determined and generated, which includes one of the following: Attention, Warning, Alarm, and Emergency.

[0014] On the other hand, embodiments of this application provide a reactor initial fuel loading monitoring system, including: The data acquisition module is used to acquire the original count rate and environmental parameters of at least one detector, and to compensate the original count rate of at least one detector based on the environmental parameters to obtain the compensated count rate of at least one detector. The parameter data determination module is used to preprocess the compensation count rate of at least one detector to obtain at least one preprocessed detector data, and to perform data fusion processing on the at least one preprocessed detector data to obtain the overall core parameter data. The result prediction module is used to acquire historical core overall parameter data and, based on the core overall parameter data and historical core overall parameter data, obtain prediction results using a time series model. The prediction results include predicted neutron flux, doubling time, and time to reach the alarm threshold. The monitoring result determination module is used to obtain the dynamic alarm threshold and determine the final monitoring result based on the relationship between the prediction result and the dynamic alarm threshold.

[0015] In another aspect, embodiments of this application provide an electronic device, including a processor and a memory: The memory is configured to store machine-readable instructions that, when executed by a processor, cause the processor to perform any of the methods in the reactor initial fueling monitoring method provided in this application embodiment.

[0016] The beneficial effects of the technical solutions provided in this application include at least the following: This application allows for the acquisition of raw count rates and environmental parameters from at least one detector. The raw count rates from at least one detector are then compensated based on the environmental parameters, eliminating the influence of environmental factors on the data and further improving the accuracy of predictions in subsequent processes. Furthermore, the raw count rates from at least one preprocessed detector and environmental parameters can be fused to obtain core-level parameter data representing the overall state of the reactor. This achieves a multi-dimensional sensing system through physical measurements and environmental parameters. Further, trend prediction and probabilistic risk assessment can be performed based on time-series models using the core-level parameter data and historical core-level parameter data, leading to the final monitoring results. Therefore, the entire process, from raw signals to intelligent decision-making, is optimized through a complete data flow processing chain, providing safer, more reliable, and intelligent monitoring assurance for the initial fueling of nuclear reactors. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A schematic flowchart illustrating a reactor initial fuel loading monitoring method provided in this application embodiment; Figure 2 A schematic diagram of the amplifier circuit design provided in the embodiments of this application; Figure 3 A schematic diagram of a reactor initial fuel loading monitoring device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting the invention.

[0020] Those skilled in the art will understand that, unless explicitly stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application’s specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0022] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0023] Specifically, such as Figure 1 As shown, the method may include: Step S101: Obtain the original count rate and environmental parameters of at least one detector, and compensate the original count rate of at least one detector based on the environmental parameters to obtain the compensated count rate of at least one detector.

[0024] Optionally, the detector's initial count rate can be based on the initial loading monitoring system. 3 He proportional counter tube assembly monitoring obtained, where each 3 The He proportional counter tube assembly mainly consists of 3 The system consists of a proportional counter tube, a preamplifier, a highly shielded, interference-resistant measurement cable, cable connectors, cable hooks, wire rope, and a counterweight. Environmental parameters can be obtained from environmental sensors configured in the system, such as temperature and humidity sensors. Furthermore, the original count rate of each detector can be compensated based on the acquired environmental parameters to obtain the compensated count rate for each detector.

[0025] In an optional embodiment of this application, the raw count rate of each detector is obtained in the following manner: The neutron flux rate in the reactor core is obtained, and an electrical pulse signal is obtained based on the neutron flux rate in the reactor core. The electrical pulse signal is then amplified to obtain an amplified electrical pulse signal. The amplified electrical pulse signal is filtered to obtain a square wave pulse, and the original count rate of each detector is calculated based on the square wave pulse.

[0026] Optionally, the core neutron flux of the nuclear reactor can be obtained, and then the core neutron flux can be input. 3 In the He proportional counter tube assembly 3 In the He proportional counter tube assembly 3 He gas undergoes a nuclear reaction, which generates a weak electrical pulse signal. The amplitude of this electrical pulse signal is small, and its number is proportional to the neutron fluence rate.

[0027] Furthermore, a weak electrical pulse signal is input into the detector. 3 The preamplifier in the proportional counter assembly amplifies weak signals to obtain amplified electrical pulse signals, thereby increasing the signal amplitude for long-distance transmission. The design scheme of this amplifier circuit is as follows: Figure 2 As shown, it mainly consists of five parts: a high-voltage filter circuit, an integrating amplifier, a second-stage amplifier, a third-stage amplifier, and a signal conditioning circuit. The high-voltage filter circuit is primarily used to filter interference signals from the high-voltage power supply, providing the filtered signal to the detector. The integrating amplifier, second-stage amplifier, and third-stage amplifier form a three-stage amplifier used to amplify signals from the high-voltage source. 3 The signal conditioning circuit mainly filters, shapes, and drives the amplified signal to output voltage pulses of different frequencies.

[0028] Correspondingly, the amplified electrical pulse signal is input into a highly shielded, anti-interference measurement cable, which transmits the signal from the detector to the measurement channel chassis. The cable shields against external interference, and the amplified electrical pulse signal is further amplified to a suitable level by the amplification module in the measurement channel chassis. Noise and small-amplitude gamma pulses are filtered out by setting a discrimination threshold, thereby shaping the pulse into a regular square wave pulse. Finally, the pulse is counted by the signal processing module in the measurement channel chassis within a set time interval, and the original count rate of each detector is calculated.

[0029] In optional embodiments of this application, environmental parameters include temperature data and pressure data. Compensation is performed on the original count rate of at least one detector based on these environmental parameters to obtain a compensated count rate for at least one detector, including: Obtain the compensation model pre-established based on experimental data, input the temperature and pressure data into the compensation model, and obtain the compensation coefficients; The compensated count rate for each detector is obtained by multiplying the original count rate of each detector by the compensation coefficient.

[0030] Optionally, environmental parameters include temperature and pressure data. In this case, temperature and pressure sensors can be installed on each detector to read the temperature and pressure data in real time. Then, based on experimental data, a compensation coefficient is determined for the currently read temperature and pressure data. The original count rate of each detector is multiplied by the obtained compensation coefficient to obtain the compensated count rate of each detector.

[0031] The compensation coefficient can be calculated based on the following formula:

[0032] in, It is the apparent activation energy. k It is Boltzmann's constant. This is a reference temperature value. This is the real-time temperature data; the number 273.15 is the conversion constant between the Kelvin and Celsius scales; and P is the real-time pressure data. For reference pressure value, These are calibration parameters, which can be obtained through experimental calibration. The cross term coefficient, It is the aging rate coefficient, obtained through periodic calibration. It is the current time. It is the initial time when the detector is put into operation.

[0033] The compensation coefficients used in this application to compensate for the original count rate of each detector include nonlinear temperature compensation and pressure compensation, as well as the cross term of temperature and pressure, which can more accurately describe the complex physical process. At the same time, by introducing aging compensation, the influence of equipment performance drift is offset, thereby ensuring that the compensated count rate is more accurate.

[0034] Step S102: Perform data preprocessing on the compensation count rate of at least one detector to obtain at least one preprocessed detector data, and perform data fusion processing on the at least one preprocessed detector data to obtain the overall core parameter data.

[0035] Optionally, after compensating the original detector compensation count rate based on real-time temperature and pressure data, the obtained detector compensation count rate can be preprocessed.

[0036] In optional embodiments of this application, data preprocessing is performed on at least one detector compensation count rate to obtain at least one preprocessed detector data, including: Align at least one detector compensation count rate to a unified timestamp to obtain the aligned detector compensation count rates. The compensated count rates of each aligned detector are filtered to obtain the filtered compensated count rates of each detector. The data missing of each filtered detector is filled by interpolation algorithm to obtain at least one preprocessed detector data.

[0037] Optionally, since the time obtained by each detector compensation count rate is different, in order to ensure the uniformity of data time and improve the final prediction result, at least one detector compensation count rate is aligned to a unified timestamp. The unified timestamp can be set according to actual needs. For example, the timestamp in the middle of each detector compensation count rate can be set as the unified timestamp. At this time, the aligned detector compensation count rates can be obtained.

[0038] Furthermore, the compensated count rates of each aligned detector can be filtered to obtain filtered detector compensated count rates, thereby reducing the impact of statistical fluctuations. Simultaneously, it is determined whether there are missing data in each filtered detector compensated count rate. If missing data exists, interpolation algorithms are used to fill in the missing data to obtain the pre-processed detector data. Data fusion processing is then performed on at least one pre-processed detector data set to obtain the overall core parameter data.

[0039] In an optional embodiment of this application, at least one preprocessed detector data is subjected to data fusion processing to obtain overall core parameter data, including: The location information of the detector corresponding to each preprocessed detector data is obtained, and the three-dimensional neutron fluence distribution is obtained through a data fusion algorithm based on each preprocessed detector data and the location information of each detector. The overall core parameters characterizing the overall state of the reactor core are calculated based on the three-dimensional neutron flux distribution.

[0040] Optionally, the detector's position information refers to its precise three-dimensional position coordinates within the reactor core. A unified coordinate system for the core is then established, and the positions of each detector are mapped onto a standard grid. Simultaneously, an interpolation algorithm is used to unify the preprocessed detector data from different sampling frequencies to the same time grid. Further, based on the mapped standard grid, a data fusion algorithm is used to obtain the three-dimensional neutron fluence distribution of each preprocessed detector data. Finally, based on the three-dimensional neutron fluence distribution, overall core parameters characterizing the overall state of the reactor core are calculated.

[0041] Among them, the data fusion algorithm can refer to the physical model fusion algorithm based on Kalman filtering. In this case, the reactor core is discretized into thousands of grid points, the neutron flux value of each point constitutes the state vector, the count rate measurement value of each detector constitutes the observation vector, and a state transition matrix is ​​constructed based on the simplified neutron diffusion equation to describe the propagation law of neutron flux in the reactor core. Finally, based on the detector spatial response function, a mapping relationship from grid points to detector positions is established.

[0042] Correspondingly, when performing data fusion using the physical model fusion algorithm based on Kalman filtering, the state transition matrix is ​​used to predict the current state based on the state at the previous moment. Then, the actual measured value is compared with the predicted value to calculate the Kalman gain matrix. Based on the Kalman gain and the prediction error, the state estimate is corrected and the uncertainty covariance matrix of the state estimate is updated, thus obtaining the three-dimensional neutron fluence distribution.

[0043] Optionally, the data fusion algorithm can also refer to a data-driven fusion algorithm based on neural networks. In this case, the convolutional layer and fully connected layer extract features from each preprocessed detector data and the position information of each detector. Then, the extracted features are input into the fusion inference layer. The fusion inference layer learns the complex nonlinear relationship between detector readings and spatial flux distribution and generates a detailed three-dimensional flux distribution map of the entire core, i.e., the three-dimensional neutron flux rate distribution, which is then output through the output layer.

[0044] Optionally, the training data for the neural network is obtained by training samples generated using high-precision Monte Carlo simulation. During training, a physical constraint term is added to the loss function to ensure that the output conforms to the laws of neutron transport. A pre-trained model with a similar stack type is used to accelerate the training process, thereby improving efficiency.

[0045] In optional embodiments of this application, the overall core parameter data includes total core power, power peak factor, and flux tilt. The overall core parameter data characterizing the overall core state is calculated based on the three-dimensional neutron flux rate distribution, including: The total core power was obtained by integrating the three-dimensional neutron flux rate distribution. The local maximum fluence rate and the average fluence rate are determined based on the three-dimensional neutron fluence rate distribution, and the ratio of the local maximum fluence rate to the average fluence rate is used as the power peak factor. Obtain the core axial power and core radial power, and based on the core axial power and core radial power, obtain the flux tilt.

[0046] Optionally, after obtaining the three-dimensional neutron flux distribution, the total core power can be obtained by integrating the three-dimensional neutron flux distribution. Simultaneously, the average flux rate is calculated based on the three-dimensional neutron flux distribution, and the local maximum flux rate is determined from the three-dimensional neutron flux distribution. The ratio between the local maximum flux rate and the average flux rate is then used as the reactor's power peak factor. Further, the power imbalance between the upper and lower halves of the core can be calculated as the core axial power, and the difference in power distribution between the inner and outer rings of the core can be calculated as the core radial power. Correspondingly, the flux tilt can be obtained based on the obtained core axial and radial powers, such as by weighting the core axial and radial powers according to a preset weight and using the sum as the flux tilt.

[0047] In this application, advanced algorithms and rigorous quality control are used in the data fusion process to transform discrete detector measurement data into accurate core status information, providing a reliable foundation for subsequent trend prediction and safety decisions.

[0048] Step S103: Obtain historical core overall parameter data, and based on the core overall parameter data and historical core overall parameter data, obtain prediction results using a time series model. The prediction results include predicted neutron flux, doubling time, and time to reach the alarm threshold.

[0049] In optional embodiments of this application, prediction results are obtained based on a time series model using overall core parameter data and historical overall core parameter data, including: Input the overall core parameter data and historical overall core parameter data into the time series model to obtain the predicted neutron flux; The flux exponential growth rate is calculated based on the neutron flux distribution in the reactor core, and the doubling time is calculated based on the flux exponential growth rate. Obtain the preset alarm neutron flux threshold, and determine the alarm threshold time based on the relationship between the predicted neutron flux and the alarm neutron flux threshold.

[0050] Optionally, historical core parameters are obtained, including total power, power peak factor, flux tilt, etc., ensuring the time series of the data is continuous. Then, the core parameter data (total power, power peak factor, flux tilt, etc.) are arranged in chronological order to form continuous time series data, and a fixed... The time window of a certain length is used as the model input. The data points within the window are arranged at a fixed sampling interval, and parameters of different dimensions are normalized to ensure that each feature has the same importance, thereby achieving feature standardization.

[0051] Optionally, the time series models include LSTM (Long Short-Term Memory) models for high-precision short-term prediction and ARIMA (Autoregressive Integrated Moving Average) models for medium-term trend prediction. The LSTM model's input layer receives historical core parameters, its hidden layer captures the time dependencies of the input data, and its output layer generates future predictions. The ARIMA model includes three parameters: p, d, and q, representing the autoregressive order, differencing order, and moving average order, respectively. These parameters are determined using ACF (Autocorrelation Function) and PACF (Partial Autocorrelation Function) plots, or automatically selected using ARIMA. This time series model uses mean squared error as the loss function and employs the Adam (Adaptive Moment Estimation) optimizer with appropriate iteration counts and batch sizes.

[0052] Optionally, after the time series model is trained, we can directly call the prediction function of the ARIMA model to specify the prediction steps, and input the overall core parameter data and historical core parameter data into the LSTM model to obtain the prediction for the next time point. Then, we can perform rolling prediction (using the predicted value as part of the input) to obtain the neutron flux at multiple time points.

[0053] Optionally, an adaptive window size can be used, employing a longer window to improve accuracy during the stable phase and a shorter window to improve response speed during the rapidly changing phase. Correspondingly, a linear regression is performed on the logarithmic count rate within the window versus time, and the reciprocal of the slope is the doubling time. The logarithmic count rate within the window can be calculated based on the core neutron flux distribution to obtain the flux exponential growth rate, which is then used to calculate the doubling time. At this point, the statistical significance of the calculated doubling time is evaluated, excluding the influence of random fluctuations.

[0054] Furthermore, a preset alarm neutron flux threshold is obtained, the predicted neutron flux is compared with the alarm neutron flux threshold, and the first time point exceeding the threshold is found. If the alarm neutron flux threshold is exceeded, the alarm threshold time is calculated by linear interpolation.

[0055] In this application, the process of predicting future trends is carried out through multi-model fusion, uncertainty quantification, and strict quality control measures, which provides reliable forward-looking information for fuel loading safety decisions, enabling operators to identify potential risks in advance and take preventive measures.

[0056] Step S104: Obtain the dynamic alarm threshold and determine the final monitoring result based on the relationship between the prediction result and the dynamic alarm threshold.

[0057] In an optional embodiment of this application, obtaining the dynamic alarm threshold includes: Obtain the alarm threshold, current loading stage, and current operation step for each loading stage; The alarm threshold corresponding to the current loading stage is dynamically adjusted based on the current operation steps to obtain the dynamic alarm threshold.

[0058] Optionally, the fuel loading phase can be divided into an initial fuel loading phase, a mid-stage fuel loading phase, a late-stage fuel loading phase, and a near-critical phase, with corresponding alarm thresholds set for each phase. In the initial fuel loading phase, the core contains fewer fuel assemblies and the neutron flux level is low, so the alarm threshold can be set higher to avoid false alarms caused by background fluctuations and statistical fluctuations. In the mid-stage fuel loading phase, when the number of fuel assemblies in the core reaches a certain level and the neutron flux gradually increases, the alarm threshold should be appropriately lowered to more sensitively detect anomalies. In the late-stage fuel loading phase, approaching criticality, the neutron flux level is high, so the alarm threshold is set lower to allow for rapid response to any abnormal changes. In the near-critical phase, when fuel loading is almost complete and the core is in a critical state, the alarm threshold is set very low, and any minor abnormal change may trigger an alarm. The alarm thresholds can be determined based on safety analysis, historical data, and expert experience.

[0059] Furthermore, the current charging stage and current operating procedure can be obtained, and the alarm threshold corresponding to the current charging stage can be dynamically adjusted according to the current operating procedure to obtain a dynamic alarm threshold. This is because during the charging process, certain operating procedures can cause changes in neutron flux. For example, during fuel assembly movement, changes in assembly position can cause local flux changes. In this case, the alarm threshold can be temporarily relaxed (raised) to avoid triggering alarms due to normal changes caused by the operation. During charging intervals or while waiting for flux to stabilize, the alarm threshold should be restored or reduced to improve monitoring sensitivity. During other special operations, such as inserting or removing control rods or changing moderator conditions, the threshold should be adjusted according to the expected impact of the operation.

[0060] In an optional embodiment of this application, the final monitoring result includes a risk assessment result and an alarm level. The final monitoring result is determined based on the relationship between the prediction result and the dynamic alarm threshold, including: A multi-dimensional risk assessment is conducted based on the relationship between the prediction results and the dynamic alarm threshold to obtain the risk assessment results. Based on the risk assessment results, an alarm level is determined and generated, which includes one of the following: Attention, Warning, Alarm, and Emergency.

[0061] Optionally, the predicted results (such as total power, power peak factor, flux tilt, etc.) are compared with dynamic alarm thresholds to check for parameters that exceed dynamic alarm thresholds. If any parameters exceed these thresholds, the extent of the exceedance needs to be determined. This yields a risk assessment result characterizing the situation where multiple parameters are simultaneously abnormal. This risk assessment result can be used for risk quantification, such as designing a risk scoring model to convert the risk assessment result into a risk score. This risk score can be calculated based on a weighted average of multiple factors, such as: the greater the degree to which the current parameter exceeds the threshold, the higher the score; the steeper the parameter change trend, the higher the score; the shorter the doubling time, the more dangerous it is; the shorter the time to reach the alarm threshold, the higher the score, etc.

[0062] Furthermore, the risk score ranges corresponding to each alarm level (attention, warning, alarm, and emergency) can be obtained, and it can be determined which alarm level's risk score range the currently calculated risk score belongs to, thus obtaining the final monitoring result.

[0063] In this application, at least one detector's raw count rate and environmental parameters can be obtained. Then, the raw count rate of the at least one detector is compensated based on the environmental parameters, eliminating the influence of environmental factors on the data and further improving the accuracy of predictions in subsequent processes. Furthermore, the raw count rate of at least one preprocessed detector and environmental parameters can be fused to obtain the overall core parameter data of the reactor's overall state, i.e., a multi-dimensional sensing system is obtained through physical measurements and environmental parameters. Further, trend prediction and probabilistic risk assessment can be performed based on the overall core parameter data and historical overall core parameter data using a time series model, thereby obtaining the final monitoring results. It is evident that the entire process, from raw signals to intelligent decision-making, is optimized through a complete data flow processing chain, providing a safer, more reliable, and intelligent monitoring guarantee for the initial fueling of nuclear reactors.

[0064] This application provides a reactor initial fuel loading monitoring system, such as... Figure 3 As shown, the device may include: a data acquisition module 301, a parameter data determination module 302, a result prediction module 303, and a monitoring result determination module 304, wherein... The data acquisition module is used to acquire the original count rate and environmental parameters of at least one detector, and to compensate the original count rate of at least one detector based on the environmental parameters to obtain the compensated count rate of at least one detector. The parameter data determination module is used to preprocess the compensation count rate of at least one detector to obtain at least one preprocessed detector data, and to perform data fusion processing on the at least one preprocessed detector data to obtain the overall core parameter data. The result prediction module is used to acquire historical core overall parameter data and, based on the core overall parameter data and historical core overall parameter data, obtain prediction results using a time series model. The prediction results include predicted neutron flux, doubling time, and time to reach the alarm threshold. The monitoring result determination module is used to obtain the dynamic alarm threshold and determine the final monitoring result based on the relationship between the prediction result and the dynamic alarm threshold.

[0065] Optionally, the raw count rate for each detector is obtained in the following way: The neutron flux rate in the reactor core is obtained, and an electrical pulse signal is obtained based on the neutron flux rate in the reactor core. The electrical pulse signal is then amplified to obtain an amplified electrical pulse signal. The amplified electrical pulse signal is filtered to obtain a square wave pulse, and the original count rate of each detector is calculated based on the square wave pulse.

[0066] Optionally, the environmental parameters include temperature and pressure data. When the data acquisition module compensates for the original count rate of at least one detector based on these environmental parameters to obtain a compensated count rate for at least one detector, it is specifically used for: Obtain the compensation model pre-established based on experimental data, input the temperature and pressure data into the compensation model, and obtain the compensation coefficients; The compensated count rate for each detector is obtained by multiplying the original count rate of each detector by the compensation coefficient.

[0067] Optionally, when the parameter data determination module performs data preprocessing on the compensation count rate of at least one detector to obtain at least one preprocessed detector count, it is specifically used for: Align at least one detector compensation count rate to a unified timestamp to obtain the aligned detector compensation count rates. The compensated count rates of each aligned detector are filtered to obtain the filtered compensated count rates of each detector. The data missing of each filtered detector is filled by interpolation algorithm to obtain at least one preprocessed detector data.

[0068] Optionally, when the parameter data determination module performs data fusion processing on at least one preprocessed detector data to obtain overall core parameter data, it is specifically used for: The location information of the detector corresponding to each preprocessed detector data is obtained, and the three-dimensional neutron fluence distribution is obtained through a data fusion algorithm based on each preprocessed detector data and the location information of each detector. The overall core parameters characterizing the overall state of the reactor core are calculated based on the three-dimensional neutron flux distribution.

[0069] Optionally, the overall core parameter data includes total core power, power peak factor, and flux tilt. When calculating the overall core parameter data characterizing the overall core state based on the three-dimensional neutron flux rate distribution, the result prediction module is specifically used for: The total core power was obtained by integrating the three-dimensional neutron flux rate distribution. The local maximum fluence rate and the average fluence rate are determined based on the three-dimensional neutron fluence rate distribution, and the ratio of the local maximum fluence rate to the average fluence rate is used as the power peak factor. The core axial power and core radial power are obtained, and the tilt angle is obtained based on the core axial power and core radial power.

[0070] Optionally, when the result prediction module obtains prediction results based on the overall core parameter data and historical overall core parameter data using a time series model, it is specifically used for: Input the overall core parameter data and historical overall core parameter data into the time series model to obtain the predicted neutron flux; The flux exponential growth rate is calculated based on the neutron flux distribution in the reactor core, and the doubling time is calculated based on the flux exponential growth rate. Obtain the preset alarm neutron flux threshold, and determine the alarm threshold time based on the relationship between the predicted neutron flux and the alarm neutron flux threshold.

[0071] Optionally, the monitoring result determination module, when acquiring the dynamic alarm threshold, is specifically used for: Obtain the alarm threshold, current loading stage, and current operation step for each loading stage; The alarm threshold corresponding to the current loading stage is dynamically adjusted based on the current operation steps to obtain the dynamic alarm threshold.

[0072] Optionally, the final monitoring results include risk assessment results and alarm levels. When determining the final monitoring results based on the relationship between the prediction results and the dynamic alarm thresholds, the monitoring result determination module is specifically used for: A multi-dimensional risk assessment is conducted based on the relationship between the prediction results and the dynamic alarm threshold to obtain the risk assessment results. Based on the risk assessment results, an alarm level is determined and generated, which includes one of the following: Attention, Warning, Alarm, and Emergency.

[0073] The reactor initial loading monitoring system of this embodiment can execute the reactor initial loading monitoring method shown in the embodiment of this application. The implementation principle is similar and will not be described again here.

[0074] This application provides an electronic device, which includes a processor and a memory configured to store machine-readable instructions that, when executed by the processor, cause the processor to perform a reactor initial loading monitoring method.

[0075] This application provides an electronic device, such as... Figure 4 As shown, Figure 4 The illustrated electronic device includes a processor 2001 and a memory 2003. The processor 2001 and the memory 2003 are connected, for example, via a bus 2002. Optionally, the electronic device 2000 may further include a transceiver 2004. It should be noted that in practical applications, the transceiver 2004 is not limited to one type, and the structure of this electronic device 2000 does not constitute a limitation on the embodiments of this application.

[0076] Processor 2001 may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 2001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0077] Bus 2002 may include a pathway for transmitting information between the aforementioned components. Bus 2002 may be a PCI bus or an EISA bus, etc. Bus 2002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0078] The memory 2003 may be ROM or other type of static storage device capable of storing static information and instructions, RAM or other type of dynamic storage device capable of storing information and instructions, or EEPROM, CD-ROM or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0079] The memory 2003 stores the application code that executes the scheme of this application, and its execution is controlled by the processor 2001. The processor 2001 executes the application code stored in the memory 2003 to implement... Figure 3 The embodiment shown illustrates the operation of a reactor initial fuel loading monitoring system.

[0080] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0081] The above description is only a partial embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for monitoring the initial fuel loading of a reactor, characterized in that, include: Obtain the original count rate and environmental parameters of at least one detector, and compensate the original count rate of the at least one detector based on the environmental parameters to obtain the compensated count rate of at least one detector; The compensation count rate of the at least one detector is preprocessed to obtain at least one preprocessed detector data, and the at least one preprocessed detector data is fused to obtain the overall core parameter data. Historical core overall parameter data is obtained, and prediction results are obtained based on the core overall parameter data and the historical core overall parameter data using a time series model. The prediction results include predicted neutron flux, doubling time, and time to reach alarm threshold. Obtain the dynamic alarm threshold, and determine the final monitoring result based on the relationship between the prediction result and the dynamic alarm threshold.

2. The method according to claim 1, characterized in that, The raw count rate for each detector is obtained in the following manner: The neutron flux rate in the reactor core is obtained, and an electrical pulse signal is obtained based on the neutron flux rate in the reactor core. The electrical pulse signal is then amplified to obtain an amplified electrical pulse signal. The amplified electrical pulse signal is subjected to discrimination filtering to obtain a square wave pulse, and the original count rate of each detector is calculated based on the square wave pulse.

3. The method according to claim 1, characterized in that, The environmental parameters include temperature data and pressure data. The compensation of the original count rate of the at least one detector based on the environmental parameters to obtain a compensated count rate for the at least one detector includes: Obtain a compensation model pre-established based on experimental data, input the temperature data and pressure data into the compensation model, and obtain the compensation coefficient; The original count rate of each detector is multiplied by the compensation coefficient to obtain the compensated count rate of each detector.

4. The method according to claim 1, characterized in that, The step of preprocessing the at least one detector's compensated count rate to obtain at least one preprocessed detector data includes: Align the at least one detector compensation count rate to a unified timestamp to obtain the aligned detector compensation count rates; The aligned detector compensation count rates are filtered to obtain the filtered detector compensation count rates. The filtered detector compensation count rate is processed by interpolation algorithm to fill in missing data, resulting in at least one preprocessed detector data.

5. The method according to claim 1, characterized in that, The process of performing data fusion on the at least one preprocessed detector data to obtain overall core parameter data includes: The location information of the detector corresponding to each of the preprocessed detector data is obtained, and a three-dimensional neutron fluence distribution is obtained by a data fusion algorithm based on each of the preprocessed detector data and the location information of each detector. The overall core parameter data characterizing the overall state of the core are calculated based on the three-dimensional neutron flux distribution.

6. The method according to claim 5, characterized in that, The overall core parameter data includes total core power, power peak factor, and flux tilt. The overall core parameter data, calculated based on the three-dimensional neutron flux distribution to characterize the overall core state, includes: The total core power is obtained by integrating the three-dimensional neutron flux rate distribution. Based on the three-dimensional neutron fluence rate distribution, the local maximum fluence rate and the average fluence rate are determined, and the ratio of the local maximum fluence rate to the average fluence rate is used as the power peak factor. Obtain the core axial power and core radial power, and based on the core axial power and core radial power, obtain the tilt angle.

7. The method according to claim 1, characterized in that, Based on the overall core parameter data and the historical overall core parameter data, a time series model is used to obtain prediction results, including: The overall core parameter data and the historical overall core parameter data are input into a time series model to obtain the predicted neutron flux; The flux exponential growth rate is calculated based on the neutron flux distribution in the reactor core, and the doubling time is calculated based on the flux exponential growth rate. Obtain a preset alarm neutron flux threshold, and determine the alarm threshold time based on the relationship between the predicted neutron flux and the alarm neutron flux threshold.

8. The method according to claim 1, characterized in that, The acquisition of the dynamic alarm threshold includes: Obtain the alarm threshold, current loading stage, and current operation step for each loading stage; The alarm threshold corresponding to the current loading stage is dynamically adjusted according to the current operation steps to obtain the dynamic alarm threshold.

9. The method according to claim 1, characterized in that, The final monitoring result includes risk assessment results and alarm levels. Determining the final monitoring result based on the relationship between the prediction results and the dynamic alarm threshold includes: A multi-dimensional risk assessment is performed based on the relationship between the prediction results and the dynamic alarm threshold to obtain the risk assessment results; Based on the risk assessment results, the alarm level is determined and generated, which includes one of the following: Attention, Warning, Alarm, and Emergency.

10. A reactor initial fuel loading monitoring system, characterized in that, include: The data acquisition module is used to acquire the original count rate of at least one detector and environmental parameters, and to compensate the original count rate of the at least one detector based on the environmental parameters to obtain the compensated count rate of at least one detector. The parameter data determination module is used to preprocess the compensation count rate of the at least one detector to obtain at least one preprocessed detector data, and to perform data fusion processing on the at least one preprocessed detector data to obtain the overall core parameter data. The result prediction module is used to acquire historical core overall parameter data and obtain prediction results based on the core overall parameter data and the historical core overall parameter data using a time series model. The prediction results include predicted neutron flux, doubling time, and time to reach alarm threshold. The monitoring result determination module is used to obtain the dynamic alarm threshold and determine the final monitoring result based on the relationship between the prediction result and the dynamic alarm threshold.

Images