Methods and systems for predicting and controlling helium flow rate in the primary loop of a gas-cooled reactor

Abstract

This invention discloses a method and system for predicting and controlling helium flow rate in the primary loop of a gas-cooled reactor, comprising: acquiring the original helium flow rate sequence of the primary loop of the gas-cooled reactor; performing NLM-EMD decomposition on the original helium flow rate sequence; reconstructing the decomposition results to obtain M helium flow rate IMF components; and inputting the M helium flow rate IMF components into a trained STM model to obtain predicted values ​​Y1, Y2, ..., Y... for each helium flow rate IMF component. M Based on the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component M Calculate the error coefficients ΔY1, ΔY2, ..., ΔY for each helium flow rate IMF component. M The error coefficients corresponding to each helium flow rate IMF component are input into the trained ResNet prediction model to obtain the optimal IMF component prediction value of the helium flow rate sequence. The helium flow rate of the primary loop of the gas-cooled reactor is controlled based on the optimal IMF component prediction value of the helium flow rate sequence. This method and system can solve the problems of large fluctuations in the primary loop helium flow rate and poor unit load regulation performance during reactor variable load operation.

Description

Technical Field

[0001] This invention belongs to the field of nuclear power engineering technology and relates to a method and system for predicting and controlling the helium flow rate in the primary loop of a gas-cooled reactor. Background Technology

[0002] Gas-cooled reactors use helium as the coolant and graphite as the moderator in the primary loop. They offer advantages such as high thermal efficiency, high burnup, and high conversion ratio, making them one of the most promising advanced reactors. In gas-cooled reactors, helium circulates in the primary loop as the coolant, and its flow control is crucial for the safe and stable operation of the reactor. Specifically, the functions of helium flow control include: 1) Maintaining stable reactor power: By adjusting the helium flow rate, the reactor's power output can be controlled. When increased power is needed, the helium flow rate is increased; conversely, the flow rate is decreased to reduce power. This ensures stable operation of the reactor under various operating conditions; 2) Ensuring safety: Helium flow control helps prevent overheating or overcooling of the reactor. Appropriate flow rate ensures that the core temperature remains within a safe range, avoiding safety accidents caused by excessively high or low temperatures; 3) Optimizing performance: Precise control of the helium flow rate can improve the reactor's thermal efficiency and economic efficiency. Reasonable flow regulation can reduce energy loss and improve the overall system efficiency; 4) Equipment protection: In high-temperature gas-cooled reactors, helium not only serves as a coolant but also protects the core material. Appropriate flow control can extend the service life of equipment and reduce the frequency of maintenance and replacement.

[0003] Existing helium flow prediction and control technologies for gas-cooled reactors suffer from poor prediction accuracy, failing to meet the future requirements for gas-cooled reactors to participate in power grid peak shaving and frequency regulation. Firstly, in signal processing, existing NLM (Non-Local Mean Filtering) and EMD (Empirical Mode Decomposition) methods still have limitations when processing complex coupled flow signals. For example, NLM is sensitive to noise, and EMD may exhibit unstable decomposition results when processing extremely complex or noisy signals. Secondly, in parameter prediction processing, existing PSO (Particle Swarm Optimization) methods are prone to getting trapped in local optima and have fast convergence speeds leading to low convergence accuracy; WEM (Wavelet Energy Method) lacks adaptability, and wavelet transform is sensitive to noise, especially when processing complex signals, potentially resulting in edge blurring or loss; RNN (Recurrent Neural Network) is prone to gradient vanishing and gradient exploding problems, making it difficult for the model to learn long-range dependencies in the sequence. Finally, in actuator control, traditional DAC (Digital-to-Analog Converter) methods struggle to eliminate nonlinear errors caused by component mismatch, resulting in low conversion accuracy.

[0004] As the total installed capacity of gas-cooled reactor nuclear power units continues to increase, the demand for gas-cooled reactors to participate in peak shaving and frequency regulation in line with grid load will increase. During the operation of gas-cooled reactors, as the unit load is constantly adjusted, the primary loop helium flow needs to achieve dynamic and rapid response, which puts forward higher requirements for helium flow control. It is necessary to develop more accurate methods for predicting and controlling the primary loop helium flow, which is crucial for the safe and stable operation of gas-cooled reactor nuclear power plants. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method and system for predicting and controlling the helium flow rate in the primary loop of a gas-cooled reactor. This method and system can solve the problems of large fluctuations in the helium flow rate in the primary loop and poor unit load regulation performance during reactor variable load operation.

[0006] To achieve the above objectives, this invention discloses a method for predicting and controlling the helium flow rate in the primary loop of a gas-cooled reactor, comprising:

[0007] The original helium flow rate sequence of the gas-cooled reactor primary loop is obtained, the original helium flow rate sequence is decomposed by NLM-EMD, and the decomposition result is reconstructed to obtain M helium flow rate IMF components.

[0008] The M helium flow rate IMF components are input into the trained STM model to obtain the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component. M ;

[0009] Based on the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component M Calculate the error coefficients ΔY1, ΔY2, ..., ΔY for each helium flow rate IMF component. M ;

[0010] The error coefficients corresponding to each helium flow rate IMF component are input into the trained ResNet prediction model to obtain the optimized IMF component prediction values ​​of the helium flow rate sequence.

[0011] Based on the optimized IMF component prediction value of the helium flow sequence Control the helium flow rate in the primary loop of the gas-cooled reactor.

[0012] The further improvement of the helium flow prediction and control method for the primary loop of the gas-cooled reactor described in this invention lies in:

[0013] Furthermore, the predicted values ​​Y1, Y2, ..., Y based on each helium flow rate IMF component are... M Calculate the error coefficients ΔY1, ΔY2, ..., ΔY for each helium flow rate IMF component. M The process is as follows:

[0014] Let the predicted values ​​be Y1, Y2, ..., Y... M The actual values ​​of the corresponding IMF components are M1, M2, ..., M M Based on the predicted and actual values ​​of the IMF components, an error evaluation index MDF is established to obtain the error coefficients ΔY1, ΔY2, ..., ΔY corresponding to each helium flow rate IMF component. M .

[0015] Furthermore, the optimized IMF component prediction value based on the helium flow rate sequence The process of controlling the helium flow rate in the primary loop of a gas-cooled reactor is as follows:

[0016] The optimal IMF component prediction values ​​of the helium flow rate sequence were obtained using the DEM algorithm. The signal is converted into an electrical signal, which is used to control the drive mechanism of the main helium blower, and in turn, to control the helium flow rate in the primary loop of the gas-cooled reactor.

[0017] Furthermore, the optimized IMF component prediction values ​​of the helium flow sequence for:

[0018]

[0019] Among them, w y and b y These are the weight matrix and bias term of the fully connected layer, respectively.

[0020] Furthermore, the loss function of the ResNet prediction model during training is:

[0021]

[0022] Where N is the number of samples.

[0023] Furthermore, the electrical signal is:

[0024]

[0025] Among them, v out(n) f is the simulated voltage of helium flow rate output at the nth sampling time. i，n z is the conversion factor. l，n This represents the digital signal value of the helium flow rate input at the nth sampling time.

[0026] This invention discloses a helium flow prediction and control system for the primary loop of a gas-cooled reactor, comprising:

[0027] The acquisition module is used to acquire the original helium flow sequence of the gas-cooled reactor primary loop, perform NLM-EMD decomposition on the original helium flow sequence, and then reconstruct the decomposition results to obtain M helium flow IMF components.

[0028] The first prediction module is used to input the M helium flow rate IMF components into the trained STM model to obtain the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component. M ;

[0029] The calculation module is used to calculate the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component. M Calculate the error coefficients ΔY1, ΔY2, ..., ΔY for each helium flow rate IMF component. M ;

[0030] The second prediction module is used to input the error coefficients corresponding to each helium flow rate IMF component into the trained ResNet prediction model, thereby obtaining the optimal IMF component prediction values ​​for the helium flow rate sequence.

[0031] The control module is used to predict the optimal IMF component values ​​based on the helium flow rate sequence. Control the helium flow rate in the primary loop of the gas-cooled reactor.

[0032] The further improvement of the gas-cooled reactor primary loop helium flow prediction and control system described in this invention lies in:

[0033] Furthermore, the optimized IMF component prediction value based on the helium flow rate sequence The process of controlling the helium flow rate in the primary loop of a gas-cooled reactor is as follows:

[0034] The optimal IMF component prediction values ​​of the helium flow rate sequence were obtained using the DEM algorithm. The signal is converted into an electrical signal, which is used to control the drive mechanism of the main helium blower, and in turn, to control the helium flow rate in the primary loop of the gas-cooled reactor.

[0035] The present invention discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method for predicting and controlling the helium flow rate in the primary loop of the gas-cooled reactor.

[0036] The present invention discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for predicting and controlling the helium flow rate in the primary loop of a gas-cooled reactor.

[0037] The present invention has the following beneficial effects:

[0038] The gas-cooled reactor primary loop helium flow prediction and control method and system described in this invention introduces nonlocal mean denoising technology during signal decomposition to suppress the influence of noise on the decomposition results. A hierarchical decomposition method coupled with NLM and EMD techniques is employed to overcome the shortcomings of each method and improve the accuracy and stability of the decomposition. Based on LSTM (Long Short-Term Memory) network, component IMF prediction values ​​are obtained. MDF (Multi-Dimensional Error Fusion) algorithm is used to obtain the helium flow error coefficients, and ReSNet (Residual Network of Deep Learning) is introduced to obtain the optimal helium flow prediction value. This solves the gradient vanishing and gradient exploding problems that easily occur during the training process of traditional RNNs, effectively improving robustness. Attached Figure Description

[0039] The accompanying drawings, which form part of this specification, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0040] Figure 1 This is a flowchart of the method of the present invention;

[0041] Figure 2 This is a schematic diagram of the model of the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] In the description of this invention, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0044] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0045] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Additionally, the character " / " in this invention generally indicates that the preceding and following objects have an "or" relationship.

[0046] It should be understood that although terms such as first, second, third, etc., may be used in the embodiments of the present invention to describe the preset range, these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from one another. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0047] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0049] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0050] Example 1

[0051] The method for predicting and controlling the helium flow rate in the primary loop of a gas-cooled reactor according to the present invention includes the following steps:

[0052] 1) Obtain the original helium flow rate sequence of the gas-cooled reactor primary loop, perform NLM-EMD decomposition on the original helium flow rate sequence, and then reconstruct the decomposition results to obtain M helium flow rate IMF components.

[0053] 2) The M helium flow rate IMF components (MF1, ..., IMF) M The values ​​are input into the trained STM model to obtain the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component. M Let the predicted values ​​be Y1, Y2, ..., Y... M The actual values ​​of the corresponding IMF components are M1, M2, ..., M M Based on the predicted and actual values ​​of the IMF components, an error evaluation index MDF is established to obtain the error coefficients ΔY1, ΔY2, ..., ΔY corresponding to each helium flow rate IMF component. M ;

[0054] 3) The error coefficients corresponding to each helium flow rate IMF component are input into the trained ResNet prediction model to obtain the optimal IMF component prediction values ​​of the helium flow rate sequence.

[0055] 4) Optimize the IMF component prediction values ​​of the helium flow rate sequence using the DEM algorithm.

[0056] The signal is converted into an electrical signal, which is used to control the drive mechanism of the main helium blower, and in turn, to control the helium flow rate in the primary loop of the gas-cooled reactor.

[0057] The process of performing NLM-EMD decomposition on the original helium flow sequence is as follows:

[0058] 11) Nonlocal means denoising (NLM);

[0059] 111) Calculate similarity weights:

[0060] For each point x(i) in the helium flow signal, the similarity weight Z(i,j) between it and other points x(j) in its neighborhood is calculated as follows:

[0061]

[0062] Where, N i and N j Let i and j represent the neighborhoods centered at points i and j, respectively, h be a parameter controlling the decay rate, and ||||2 represent the Euclidean distance.

[0063] 112) Calculate similarity weights:

[0064] The denoised helium flow signal was calculated using a weighted average. for:

[0065]

[0066] Among them, Ω i This is the search window centered on point i.

[0067] Nonlocal mean denoising is performed on the helium flow rate signal x(i) to obtain the denoised signal. The core idea of ​​nonlocal mean denoising is to utilize the self-similarity of signals and remove noise by weighted averaging of similar regions.

[0068] 12) Empirical Mode Decomposition (EMD);

[0069] 121) Initialization;

[0070] Assume helium flow residual signal The IMF component set is empty.

[0071] 122) Extract IMF components;

[0072] For the nth IMF component, perform the following iterative process:

[0073] Extract signal m n-1 The local extreme points of (t).

[0074] The upper envelope e is fitted by interpolation. max (t) and lower envelope e min (t).

[0075] Calculate the mean envelope m n (t) is:

[0076]

[0077] Update candidate IMF components h n (t) is:

[0078] h n (t)=r n-1 (t)-m n (t)

[0079] Check h n (t) Does it satisfy the IMF condition (the difference between the number of extreme points and the number of zero crossings does not exceed 1, and the mean envelope is close to zero)? If it does, then h n (t) is the nth IMF component; otherwise, continue iterating.

[0080] Update residual signal r n (t) is:

[0081] r n (t)=r n-1 (t)-h n (t)

[0082] When the residual signal r n When (t) is a monotonic function or the number of extreme points is less than 2, the decomposition stops.

[0083] 13) Output IMF components;

[0084] The helium flow rate IMF component and the final residual signal obtained from the decomposition are output as follows:

[0085]

[0086] Among them, h n (t) represents the nth IMF component, rn ( t) is the final residual signal, and n is the total number of IMF components.

[0087] The M helium flow rate IMF components MF1, ..., IMF are then used to... M The values ​​are input into the trained STM model to obtain the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component. M The process is as follows:

[0088] 21) Initialize the network helium flow rate IMF parameters;

[0089] 211) Initialize the helium flow rate IMF parameters of the LSTM network, including the weight matrix W. f W i W o and W c and bias term b f b i b0, b c .

[0090] 212) Initialize the hidden state h0 and the memory cell state C0.

[0091] 22) Adaptive gating mechanism;

[0092] 221) The Forget Gate is:

[0093]

[0094] Among them, f t Let W be the output of the forget gate at time t, σ be the sigmoid function whose output value is between 0 and 1.f Here is the weight matrix for the forget gate. This indicates that the hidden state h from the previous time step is... t-1 and the input x at the current time t spliced ​​together, b f α is the bias term of the forget gate, g(t) is a time-dependent adaptive function used to dynamically adjust the weights of the forget gate, and α is the bias term of the forget gate. f These are adaptive coefficients.

[0095] 222) Input Gate;

[0096] The activation value of the input gate is:

[0097]

[0098] Where it is the output of the input gate at time t, and W i Let b be the weight matrix of the input gate. i For the corresponding bias term, α i These are adaptive coefficients.

[0099] 223) Memory unit state;

[0100] Calculate the state values ​​of candidate memory cells for:

[0101]

[0102] Calculate the state value C of the candidate memory cell t for:

[0103]

[0104] The tanh function maps the output value to the range of -1 to 1. c is the weight matrix for the candidate memory cell states, and bc is the corresponding bias term.

[0105] 224) The output gate is:

[0106] Calculate the activation value of the output gate:

[0107]

[0108] Among them, o t W is the output of the output gate at time t. o Let b be the weight matrix of the output gate. o For the bias term, α o These are adaptive coefficients.

[0109] 225) Update hidden status:

[0110] h t =o t ·tanh(C t )

[0111] The tanh function maps the output value to the range of -1 to 1.

[0112] 23) Multi-level memory units;

[0113] For each level l, update the memory cell state. for:

[0114]

[0115] in, and These are the forget gate and input gate outputs of the l-th layer, respectively. This represents the candidate memory cell state of the l-th layer.

[0116] Calculate multi-level hidden states for:

[0117]

[0118] in, This is the output gate of the l-th layer.

[0119] Determine the final concealment state h t for:

[0120]

[0121] Where, β l represents the weight coefficient of the l-th layer.

[0122] 24) Output the predicted helium flow rate;

[0123] The final hidden state h is hidden through a fully connected layer. t Mapping to the helium flow output space yields the helium flow prediction result. for:

[0124]

[0125] Among them, w y and b y These are the weight matrix and bias term of the fully connected layer, respectively.

[0126] The error coefficients corresponding to each helium flow rate IMF component are input into the trained ResNet prediction model to obtain the optimized IMF component prediction values ​​of the helium flow rate sequence. The process is as follows:

[0127] 31) Dynamic residual connection:

[0128] Introducing dynamic residual connection, based on the input helium flow rate error coefficient Δy i The dynamic characteristics adjust the weighting coefficient α(Δy) of the residual connection. i )for:

[0129] y i =F(Δy) i , {w i})+α(Δy i )·Δy i

[0130] Among them, y i Here is the predicted helium flow rate, Δy i For input features, F(Δy) represents the error coefficient of helium flow rate. i , {w i}) is the residual function, σ is the Sigmoid activation function, and α(Δy) is the residual function. i The range is limited to [0, 1].

[0131] α(Δyi) is calculated using a small neural network:

[0132] α(Δy i )=σ(W α ·Δy i +b α )

[0133] 32) Multi-scale feature fusion;

[0134] Multi-scale convolutional layers are introduced into the residual blocks to extract features at different scales:

[0135]

[0136] Among them, F s (Δy i , {W s，i}) represents the convolution operation at the s-th scale, where s is the total number of scales.

[0137] By weighted fusion of multi-scale features, a new generation of helium flow rate prediction value y is obtained. i for:

[0138] y i =F multi (Δy i )+α(Δy i )·Δy i

[0139] 33) Model training;

[0140] 331) Define the loss function;

[0141] The loss function is calculated as follows:

[0142]

[0143] Where N is the sample size. This is a corrected prediction of the coolant flow rate.

[0144] 332) Select the optimizer;

[0145] Calculate the gradient: Let the parameter be θ. The gradient of the loss function with respect to the parameter is:

[0146]

[0147] The first-order moment estimate and the second-order moment estimate are calculated as follows:

[0148]

[0149]

[0150] Wherein, β1 and β2 are the attenuation rates, which are usually set to 0.9 and 0.999, respectively.

[0151] Update parameters:

[0152]

[0153] Where α is the learning rate and ∈ is the factor constant.

[0154] 333) Cyclic training;

[0155] Forward propagation: Input xi is fed into the model, and the predicted helium flow rate is obtained through calculations at each layer.

[0156] Calculate the loss: Calculate the loss L for the current batch based on the loss function.

[0157] Backpropagation: Calculate the gradient of the loss with respect to the model parameters.

[0158] Parameter update: Update the model parameters θ using the optimizer.

[0159] 334) Output the prediction results;

[0160] The final features are mapped to the output space through a fully connected layer to obtain the final predicted value of helium flow rate. for:

[0161]

[0162] in, and These are the weight matrix and bias term of the fully connected layer, respectively.

[0163] The optimal IMF component prediction value of the helium flow sequence is obtained using the DEM algorithm. The process of converting to an electrical signal is as follows:

[0164] 41) Adaptive weight allocation

[0165]

[0166] in, Let be the dynamic characteristic function of the i-th input helium flow rate digital signal, used to measure the adaptability of the helium flow rate to the input signal, and α be the adaptive coefficient, which controls the sensitivity of the weight allocation.

[0167] 42) Multi-level mismatch compensation;

[0168] A multi-level mismatch compensation mechanism is introduced, dividing mismatch compensation into multiple levels {z1, z2, ..., z...}. L Each level corresponds to a different mismatch compensation strategy, which is then weighted and fused together:

[0169]

[0170] Among them, z i For the i-th helium flow rate digital signal output, ω l，i Let be the weight of the i-th element in the l-th level.

[0171]

[0172] 43) The output electrical signal is:

[0173]

[0174] Among them, v out(n) f is the simulated voltage of helium flow rate output at the nth sampling time. i，n z is the conversion factor. l，n This represents the digital signal value of the helium flow rate input at the nth sampling time.

[0175] Confirmatory test

[0176] To verify the reliability of the prediction method proposed in this application, the experimental data (i.e., the original rod control sequence) were obtained from a foreign nuclear power plant participating in peak shaving. The load regulation range of this nuclear power plant was 60%–100%, and the test period was one month. Data from the first 15 days were selected, and a total of 1252 data samples at 15-minute intervals were provided to train the prediction model. After the model's self-learning function was completed, data from the following 15 days were selected to test the performance of the proposed model. Furthermore, to compare the advancement of this prediction method, traditional PSO, WEM, and LMD methods were selected for comparison with this application.

[0177] Using the error evaluation index SMAPE as the evaluation standard for each model, the experimental results are shown in Table 1.

[0178] Table 1

[0179] Evaluation metrics PSO WEM RNN The model of this application MDF (%) 27.11 22.10 18.09 10.01

[0180] As shown in Table 1, this application has the smallest error coefficient when compared with all other benchmark models. Compared with the PSO model, the error coefficients of WEM, LMD and this application are all significantly reduced, proving that this application can improve the prediction accuracy better than the PSO model; at the same time, compared with the WEM and LMD models, the error coefficients of this application are smaller than the other two models, proving that the deep learning model based on the SWT-LMD mode decomposition method in this application can improve the prediction accuracy.

[0181] It should be noted that this application addresses the technical challenge of unstable and highly volatile control rod positions during peak and frequency regulation periods in nuclear power plants. This volatility often leads to irregular changes in control rod position prediction, severely impacting the safe and stable operation of the nuclear power plant. A prediction model based on the SWT-LMD modal decomposition method is established using a deep learning-based adaptive training method, effectively handling nonlinear time-series reactor rod position signals and improving the accuracy of rod position prediction.

[0182] Example 2

[0183] The gas-cooled reactor primary loop helium flow prediction and control system of the present invention includes:

[0184] The acquisition module is used to acquire the original helium flow sequence of the gas-cooled reactor primary loop, perform NLM-EMD decomposition on the original helium flow sequence, and then reconstruct the decomposition results to obtain M helium flow IMF components.

[0185] The first prediction module is used to input the M helium flow rate IMF components into the trained STM model to obtain the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component. M ;

[0186] The calculation module is used to calculate the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component. M Calculate the error coefficients ΔY1, ΔY2, ..., ΔY for each helium flow rate IMF component. M ;

[0187] The second prediction module is used to input the error coefficients corresponding to each helium flow rate IMF component into the trained ResNet prediction model, thereby obtaining the optimal IMF component prediction values ​​for the helium flow rate sequence.

[0188] The control module is used to predict the optimal IMF component values ​​based on the helium flow rate sequence. Control the helium flow rate in the primary loop of the gas-cooled reactor.

[0189] In this embodiment, the optimized IMF component prediction value based on the helium flow rate sequence The process of controlling the helium flow rate in the primary loop of a gas-cooled reactor is as follows:

[0190] The optimal IMF component prediction values ​​of the helium flow rate sequence were obtained using the DEM algorithm. The signal is converted into an electrical signal, which is used to control the drive mechanism of the main helium blower, and in turn, to control the helium flow rate in the primary loop of the gas-cooled reactor.

[0191] The module division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in each embodiment of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0192] Example 3

[0193] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a method for predicting and controlling the helium flow rate in the primary loop of a gas-cooled reactor. For example, the method includes: acquiring the original helium flow rate sequence of the primary loop of the gas-cooled reactor; performing NLM-EMD decomposition on the original helium flow rate sequence; reconstructing the decomposition results to obtain M helium flow rate IMF components; inputting the M helium flow rate IMF components into a trained STM model to obtain predicted values ​​Y1, Y2, ..., YM for each helium flow rate IMF component; and calculating the predicted values ​​Y1, Y2, ..., YM based on the predicted values ​​Y1, Y2, ..., YM for each helium flow rate IMF component. M Calculate the error coefficients ΔY1, ΔY2, ..., ΔY for each helium flow rate IMF component. MThe error coefficients corresponding to each helium flow rate IMF component are input into the trained ResNet prediction model to obtain the optimized IMF component prediction values ​​of the helium flow rate sequence. Based on the optimized IMF component prediction value of the helium flow sequence The helium flow rate in the primary loop of the gas-cooled reactor is controlled. The memory may include main memory, such as high-speed random access memory (RAM), or non-volatile memory, such as at least one disk storage device. The processor, network interface, and memory are interconnected via an internal bus, which can be an industry-standard architecture bus, a peripheral component interconnection standard bus, or an extended industry-standard architecture bus. The bus can be categorized as an address bus, data bus, and control bus. The memory stores programs; specifically, the program may include program code, which includes computer operation instructions. The memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0194] Example 4

[0195] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the helium flow prediction and control method for the primary loop of a gas-cooled reactor. For example, the method includes: acquiring the original helium flow sequence of the primary loop of the gas-cooled reactor; performing NLM-EMD decomposition on the original helium flow sequence; reconstructing the decomposition results to obtain M helium flow IMF components; and inputting the M helium flow IMF components into a trained STM model to obtain predicted values ​​Y1, Y2, ..., Y... for each helium flow IMF component. M Based on the predicted values ​​Y1, Y2, ..., YM of each helium flow rate IMF component, calculate the error coefficients ΔY1, ΔY2, ..., ΔYM of each helium flow rate IMF component. M The error coefficients corresponding to each helium flow rate IMF component are input into the trained ResNet prediction model to obtain the optimized IMF component prediction values ​​of the helium flow rate sequence. Based on the optimized IMF component prediction value of the helium flow sequence The flow rate of helium in the primary loop of the gas-cooled reactor is controlled. Specifically, the computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. The volatile memory may include random access memory and / or cache memory, etc. The non-volatile memory may include read-only memory, hard disk, flash memory, optical disk, magnetic disk, etc.

[0196] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0197] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0198] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0199] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0200] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and disclosure of the invention. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0201] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

[0202] The above description is merely a preferred embodiment of the present invention and does not constitute any limitation on the present invention. Any simple modifications, alterations, or equivalent structural changes made to the above embodiments based on the technical essence of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for predicting and controlling the helium flow rate in the primary loop of a gas-cooled reactor, characterized in that, include: The original helium flow rate sequence of the gas-cooled reactor primary loop is obtained, the original helium flow rate sequence is decomposed by NLM-EMD, and the decomposition result is reconstructed to obtain M helium flow rate IMF components. The M helium flow rate IMF components are input into the trained STM model to obtain the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component. M ; Based on the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component M Calculate the error coefficients ΔY1, ΔY2, ..., ΔY for each helium flow rate IMF component. M ; The error coefficients corresponding to each helium flow rate IMF component are input into the trained ResNet prediction model to obtain the optimized IMF component prediction values ​​for the helium flow rate sequence. ; Based on the optimized IMF component prediction value of the helium flow sequence Control the helium flow rate in the primary loop of the gas-cooled reactor; The optimized IMF component prediction value based on the helium flow sequence The process of controlling the helium flow rate in the primary loop of a gas-cooled reactor is as follows: The optimal IMF component prediction values ​​of the helium flow rate sequence were obtained using the DEM algorithm. The signal is converted into an electrical signal, which is used to control the drive mechanism of the main helium blower, and in turn, to control the helium flow rate in the primary loop of the gas-cooled reactor.

2. The method for predicting and controlling the helium flow rate in the primary loop of a gas-cooled reactor according to claim 1, characterized in that, The predicted values ​​Y1, Y2, ..., Y based on the IMF components of each helium flow rate M Calculate the error coefficients ΔY1, ΔY2, ..., ΔY for each helium flow rate IMF component. M The process is as follows: Let the predicted values ​​be Y1, Y2, ..., Y... M The actual values ​​of the corresponding IMF components are M1, M2, ..., M M Based on the predicted and actual values ​​of the IMF components, an error evaluation index MDF is established to obtain the error coefficients ΔY1, ΔY2, ..., ΔY corresponding to each helium flow rate IMF component. M .

3. The method for predicting and controlling the helium flow rate in the primary loop of a gas-cooled reactor according to claim 1, characterized in that, The optimized IMF component prediction value of the helium flow sequence for: in, and These are the weight matrix and bias term of the fully connected layer, respectively.

4. The method for predicting and controlling the helium flow rate in the primary loop of a gas-cooled reactor according to claim 1, characterized in that, The loss function for the ResNet prediction model during training is: in, N This represents the number of samples.

5. The method for predicting and controlling the helium flow rate in the primary loop of a gas-cooled reactor according to claim 1, characterized in that, The electrical signal is: in, The simulated voltage represents the helium flow rate output at the nth sampling time. For conversion factors, This represents the digital signal value of the helium flow rate input at the nth sampling time.

6. A helium flow prediction and control system for a gas-cooled reactor primary loop, characterized in that, include: The acquisition module is used to acquire the original helium flow sequence of the gas-cooled reactor primary loop, perform NLM-EMD decomposition on the original helium flow sequence, and then reconstruct the decomposition results to obtain M helium flow IMF components. The first prediction module is used to input the M helium flow rate IMF components into the trained STM model to obtain the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component. M ; The calculation module is used to calculate the predicted values ​​Y1, Y2, ..., Y of each helium flow rate IMF component. M Calculate the error coefficients ΔY1, ΔY2, ..., ΔY for each helium flow rate IMF component. M ; The second prediction module is used to input the error coefficients corresponding to each helium flow rate IMF component into the trained ResNet prediction model, thereby obtaining the optimal IMF component prediction values ​​for the helium flow rate sequence. ; The control module is used to predict the optimal IMF component values ​​based on the helium flow rate sequence. Control the helium flow rate in the primary loop of the gas-cooled reactor; The optimized IMF component prediction value based on the helium flow sequence The process of controlling the helium flow rate in the primary loop of a gas-cooled reactor is as follows: The optimal IMF component prediction values ​​of the helium flow rate sequence were obtained using the DEM algorithm. The signal is converted into an electrical signal, which is used to control the drive mechanism of the main helium blower, and in turn, to control the helium flow rate in the primary loop of the gas-cooled reactor.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the helium flow prediction and control method for the primary loop of a gas-cooled reactor as described in any one of claims 1-5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for predicting and controlling the helium flow rate in the primary loop of a gas-cooled reactor as described in any one of claims 1-5.

Images