Pressurized water reactor primary loop main pump flow prediction and control method and system

Abstract

The invention discloses a pressurized water reactor primary loop main pump flow prediction and control method and system. The method comprises the steps that an original main pump flow signal of a pressurized water reactor primary loop is obtained; performing multi-scale decomposition on the main pump flow signal by using an HOFEM module of an NL-FCNN to obtain multi-size main pump flow; the multi-scale main pump flow component is input into an ANSA dynamic optimization network structure for feature extraction, and a multi-scale feature vector is obtained; on the basis of the extracted multi-scale feature vector, NL-FCNN is used for predicting a main pump flow signal, and an optimal main pump flow predicted value is obtained; based on a D-ADC algorithm, the optimal main pump flow predicted value is converted into an electric signal through a digital-to-analog conversion circuit, then the electric signal is input into a main pump frequency converter to drive a main pump to operate in a frequency conversion mode, the main pump flow of the pressurized water reactor primary loop is controlled, and the method and system can accurately control the main pump flow of the pressurized water reactor primary loop.

Description

Technical Field

[0001] The present invention belongs to the technical field of nuclear power engineering, and relates to a method and system for predicting and controlling the flow rate of the primary pump in a pressurized water reactor primary loop. Background Art

[0002] The primary loop system of a pressurized water reactor nuclear power plant mainly consists of equipment such as a reactor pressure vessel, a steam generator, a primary pump, and a pressurizer. The primary pump plays a crucial role in the primary loop system. Its main function is to transport the coolant from the reactor pressure vessel to the steam generator and then back to the reactor, forming a closed-loop cycle. The roles of the primary pump in a nuclear power plant include: 1) Heat transfer: The primary pump transfers the heat generated by the reactor to the secondary loop working medium through the steam generator, generating steam to drive the steam turbine generator to generate electricity. 2) Pressure control: The working state of the primary pump directly affects the pressure and flow rate of the primary loop system. By adjusting the flow rate of the primary pump, the pressure stability of the system can be maintained, preventing the leakage of radioactive substances.

[0003] The primary pump is one of the key equipment in the primary loop system of a nuclear power plant. Its reliability and stability are crucial for the safe operation of the nuclear power plant, and its flow rate control is of great importance. In terms of the future participation of pressurized water reactors in the deep peak shaving and frequency modulation operation of the power grid, the existing methods for predicting and controlling the flow rate of the primary pump in the primary loop of a pressurized water reactor are prone to problems such as large adjustment fluctuations and poor reliability, and it is necessary to improve the existing prevention methods. In terms of parameter prediction processing, the existing PSO (Particle Swarm Optimization) is prone to falling into local optima and having a fast convergence speed, resulting in low convergence accuracy; the RNN (Recurrent Neural Network) is prone to problems of gradient disappearance and gradient explosion, resulting in the model being difficult to learn the long-distance dependencies in the sequence; the traditional fully connected neural network (FCNN) often relies on simple activation functions (such as ReLU, Sigmoid, etc.) and a fixed network structure when dealing with complex nonlinear problems, resulting in limited performance of the model when dealing with high-dimensional and nonlinear data. In addition, the existing methods lack dynamic adaptability in parameter optimization and feature extraction, and it is difficult to effectively capture the high-order nonlinear relationships in the data. At the same time, in terms of actuator control, the traditional DAC (Digital-to-Analog Conversion) is difficult to eliminate the nonlinear errors caused by component mismatch and has problems such as low conversion accuracy. It is necessary to develop a more accurate method for predicting and controlling the flow rate of the primary pump in the primary loop, which is beneficial for the subsequent participation of pressurized water reactor nuclear power plants in the deep peak shaving and frequency modulation operation of the power grid. Summary of the Invention

[0004] The purpose of the present invention is to overcome the above-mentioned disadvantages of the prior art, and provide a method and system for predicting and controlling the flow rate of the primary pump in a pressurized water reactor primary loop, which can accurately control the flow rate of the primary pump in the pressurized water reactor primary loop.

[0005] To achieve the above object, the present invention discloses a method for predicting and controlling the flow rate of the primary pump in a pressurized water reactor primary loop, including:

[0006] Obtain the original main pump flow signal of the primary loop of a pressurized water reactor;

[0007] Use the HOFEM module of NL-FCNN to perform multi-scale decomposition on the main pump flow signal to obtain multi-size main pump flows;

[0008] Input the multi-scale main pump flow components into the ANSA dynamic optimization network structure for feature extraction to obtain multi-scale feature vectors;

[0009] Based on the extracted multi-scale feature vectors, use NL-FCNN to predict the main pump flow signal to obtain the optimized main pump flow prediction value;

[0010] Based on the D-ADC algorithm, convert the optimized main pump flow prediction value into an electrical signal through a digital-to-analog conversion circuit, and then input the electrical signal into the main pump frequency converter to drive the main pump to operate in variable frequency and control the main pump flow of the primary loop of the pressurized water reactor.

[0011] A further improvement of the method for predicting and controlling the main pump flow of the primary loop of a pressurized water reactor according to the present invention lies in:

[0012] Further, after obtaining the original main pump flow signal of the primary loop of the pressurized water reactor, it further includes:

[0013] Preprocess the original main pump flow signal to eliminate the dimensional and amplitude differences.

[0014] Further, in the process of using the HOFEM module of NL-FCNN to perform multi-scale decomposition on the main pump flow signal to obtain multi-size main pump flows, DNAF is used to enhance the feature extraction ability of each scale of main pump flow components.

[0015] Further, it further includes: optimizing the ANSA dynamic optimization network structure based on the HOA algorithm.

[0016] Further, it further includes: optimizing NL-FCNN by using RTLM and DSFA.

[0017] Further, the electrical signal is:

[0018]

[0019] where v out(n) is the analog voltage of the main pump flow output at the nth sampling moment, f i,n is the conversion coefficient, and N k，n is the digital signal value of the main pump flow input at the nth sampling moment.

[0020] The present invention discloses a system for predicting and controlling the main pump flow of the primary loop of a pressurized water reactor, including:

[0021] An acquisition module, configured to acquire the original main pump flow signal of the primary loop of a pressurized water reactor;

[0022] A decomposition module, configured to perform multi-scale decomposition on the main pump flow signal by using the HOFEM module of NL-FCNN to obtain multi-size main pump flows;

[0023] An extraction module, configured to input the multi-scale main pump flow components into an ANSA dynamic optimization network structure for feature extraction to obtain multi-scale feature vectors;

[0024] A prediction module, configured to predict the main pump flow signal by using NL-FCNN based on the extracted multi-scale feature vectors to obtain an optimized main pump flow prediction value;

[0025] A control module, configured to convert the optimized main pump flow prediction value into an electrical signal through a digital-to-analog conversion circuit based on the D-ADC algorithm, and then input the electrical signal into a main pump frequency converter to drive the main pump to operate in a variable frequency manner and control the main pump flow of the primary loop of the pressurized water reactor.

[0026] A further improvement of the main pump flow prediction and control system for the primary loop of the pressurized water reactor according to the present invention lies in:

[0027] Further, after acquiring the original main pump flow signal of the primary loop of the pressurized water reactor, it further includes:

[0028] Preprocessing the original main pump flow signal to eliminate the dimension and amplitude differences.

[0029] 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, the steps of the main pump flow prediction and control method for the primary loop of the pressurized water reactor are implemented.

[0030] The present invention discloses a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the main pump flow prediction and control method for the primary loop of the pressurized water reactor are implemented.

[0031] The present invention has the following beneficial effects:

[0032] When the method and system for predicting and controlling the primary pump flow rate in the primary loop of a pressurized water reactor of the present invention are specifically operated, a nonlinear fully connected neural network (NL-FCNN) is adopted, and a dynamic nonlinear activation function (DNAF) is utilized. The shape and parameters of the activation function can be adaptively adjusted according to the distribution characteristics of the input data. An adaptive network structure adjustment strategy (ANSA) based on gradient information feedback is designed to dynamically optimize the number of network layers and neurons. A high-order feature extraction module (HOFEM) is introduced to capture high-order nonlinear relationships in the data through multi-layer nonlinear transformation. A parameter optimization strategy based on a hybrid optimization algorithm (HOA) is proposed, and the gradient descent method and the global optimization algorithm are combined for parameter update. A real-time dynamic learning mechanism (RTLM) is developed, which can dynamically adjust the model parameters and structure according to the changes in the input data. By introducing the above dynamic nonlinear activation mechanism, adaptive network structure adjustment, and efficient parameter optimization strategy, the modeling ability of the primary pump flow rate model for complex nonlinear data is significantly improved, and the prediction accuracy of the primary pump flow rate in the primary loop of the pressurized water reactor is greatly enhanced. At the same time, aiming at the problems that the traditional DAC (digital-to-analog conversion) is difficult to eliminate the nonlinear error caused by component mismatch and has low conversion accuracy in the control of the actuator, the present invention utilizes the D-ADC (dynamic resolution adjustment - adaptive digital-to-analog conversion algorithm) digital-to-analog conversion technology, which can reduce the nonlinear error caused by component mismatch and effectively improve the control accuracy of the frequency converter of the primary pump in the primary loop of the pressurized water reactor. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings forming a part of this specification are used to provide a further understanding of the present invention. The schematic embodiments and descriptions thereof of the present invention are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0034] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] Hereinafter, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0036] In the description of the present invention, it should be understood that the terms "including" and "comprising" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0037] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the present 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.

[0038] It should be further understood that the term "and / or" as used in the present specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects are in an "or" relationship.

[0039] It should be understood that although the terms "first," "second," and "third" may be used to describe preset ranges in embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are merely used to distinguish one preset range from another. For example, without departing from the scope of 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.

[0040] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0042] Various structural schematic diagrams according to the disclosed embodiments of the present invention are shown in the accompanying drawings. These figures are not drawn to scale, where for the purpose of clear expression, some details are enlarged and some details may be omitted. The shapes of various regions and layers shown in the figures, as well as their relative sizes and positional relationships, are merely exemplary and may deviate in practice due to manufacturing tolerances or technical limitations. Those skilled in the art can additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0043] Embodiment 1

[0044] Reference Figure 1 , the primary pump flow prediction and control method for the primary loop of the pressurized water reactor according to the present invention includes the following steps:

[0045] 1) Obtain the original primary pump flow signal of the primary loop of the pressurized water reactor, and preprocess the original primary pump flow signal to eliminate the dimensional and amplitude differences;

[0046] 2) Use the HOFEM module of NL-FCNN to perform multi-scale decomposition on the primary pump flow signal processed in step 1); enhance the feature extraction ability of each scale primary pump flow component through DNAF to obtain multi-size primary pump flow;

[0047] 3) Input the multi-scale primary pump flow components into the ANSA dynamic optimization network structure for feature extraction, and optimize the parameters of the primary pump flow model based on the HOA algorithm to capture the non-linear features in the primary pump flow signal and obtain multi-scale feature vectors;

[0048] 4) Based on the extracted multi-scale feature vectors, use NL-FCNN to predict the primary pump flow signal to obtain the optimized primary pump flow prediction value. Among them, dynamically adjust the model parameters through RTLM to adapt to the changes in the primary pump flow signal, and perform error iterative correction based on DSFA to obtain the optimized primary pump flow prediction value;

[0049] 5) Based on the D-ADC algorithm, convert the optimized primary pump flow prediction value into an electrical signal through a digital-to-analog conversion circuit, and then input the electrical signal into the primary pump frequency converter to drive the primary pump to operate in a variable frequency manner, thereby controlling the primary pump flow of the primary loop of the pressurized water reactor.

[0050] In step 1), the process of using the HOFEM module of NL-FCNN to perform multi-scale decomposition on the primary pump flow signal processed in step 1) is as follows:

[0051] 11) Signal preprocessing;

[0052] 111) Standardization processing;

[0053] The original main pump flow signal x(t) is normalized to eliminate the differences in dimension and amplitude, enabling data modeling and analysis on the same scale. The original main pump flow signal is converted into a distribution with a mean of 0 and a standard deviation of 1, i.e.:

[0054]

[0055] where μ is the mean of the signal, σ is the standard deviation of the signal, and x std (t) is the normalized signal.

[0056] 112) Model training and validation;

[0057] Determine the proportion α of the main pump flow training set: Usually, α = 0.8 is taken.

[0058] Calculate the length of the main pump flow training set

[0059] The normalized main pump flow signal is divided into a training set and a test set for model training and validation.

[0060] Training set: x train (t) = x(t), t = 1, 2,..., T train

[0061] Test set: x test (t) = x(t), t = T train +1, T train +2,..., N

[0062] 12) Multi-scale signal decomposition;

[0063] Use the high-order feature extraction module (HOFEM) of NL-FCNN to perform multi-scale decomposition on the preprocessed main pump flow signal, i.e.:

[0064]

[0065] where c i (t) is the main pump flow signal component at the i-th scale, and r(t) is the residual component.

[0066] Enhance the feature extraction ability of each scale main pump flow signal component through the dynamic non-linear activation function (DNAF), i.e.:

[0067] f(x; α, β) = α · tanh(β · x) + (1 - α) · ReLU(x)

[0068] Where: X is the input data, α is the dynamic weight parameter, with a value range of [0, 1], used to control the ratio of the tanh function and the ReLU function, and β is the non-linear adjustment parameter, used to control the non-linearity of the tanh function.

[0069] Dynamic parameter adjustment, i.e.:

[0070]

[0071] Calculate the gradient:

[0072]

[0073] 13) Feature extraction and modeling;

[0074] 131) Feature extraction;

[0075] For each scale main pump flow signal component c i (t) after multi-scale decomposition, perform feature extraction:

[0076] Use the Adaptive Network Structure Adjustment Strategy (ANSA) of NL-FCNN to dynamically optimize the network structure:

[0077]

[0078] Where L old is the current network layer number, L new is the adjusted network layer number, η is the learning rate, controlling the step size of network structure adjustment, is the loss function Gradient of the network layer number L.

[0079] Optimize the model parameters through the Hybrid Optimization Algorithm (HOA) to capture the non-linear features in the main pump flow signal, specifically:

[0080] 1311) Initialize the parameters;

[0081] Initialize the model parameters, the main pump flow signal, and the genetic algorithm population.

[0082] 1312) Optimize by the gradient descent method;

[0083] Use the gradient descent method to update the main pump flow signal parameters as:

[0084]

[0085] 1313) Optimize by the genetic algorithm, specifically:

[0086] Selection: Select individuals with higher fitness from the population.

[0087] Crossover: Generate new individuals through crossover operations.

[0088] Mutation: Introduce new genes through mutation operations.

[0089]

[0090] Among them, GA(θ t ) is the optimization result of the genetic algorithm for the main pump flow signal parameter θ t ; λ is the mixing weight parameter used to control the proportion of the gradient descent method and the genetic algorithm.

[0091] 1314) Repeat the above steps until the parameters converge or the maximum number of iterations is reached.

[0092] 132) Modeling;

[0093] Construct a multi-scale main pump flow signal feature vector:

[0094] F = [f1, f2... f n

[0095] Among them, fi is the feature vector of the i-th scale component.

[0096] 133) Signal prediction;

[0097] 1331) Based on the extracted multi-scale main pump flow feature vector F, use NL-FCNN for signal prediction:

[0098]

[0099] Among them, is the predicted value of the signal.

[0100] 1332) Dynamic adjustment of model parameters;

[0101] Dynamically adjust the main pump flow model parameters through a real-time dynamic learning mechanism (RTLM) to adapt to signal changes.

[0102] In step 4), the process of dynamically adjusting the model parameters through RTLM to adapt to the changes in the main pump flow signal is as follows:

[0103] 21) Monitor signal changes in real time;

[0104] Monitor the change of the input main pump flow signal x t , and calculate the change amount ||Δx t ||.

[0105] 22) Calculate the dynamic learning rate;

[0106] RTLM uses the dynamic learning rate η t , and adaptively adjusts according to the change of the input main pump flow signal. Its mathematical expression is:​

[0107] η t = η0·exp(-γ·||Δx t ||)

[0108] where η0 is the initial learning rate, γ is the decay coefficient that controls the adjustment speed of the learning rate, and ||Δx t || is the change in the input signal, usually calculated as:

[0109] ||Δx t || = ||x t - x t-1 ||

[0110] 23) Update the model parameters;

[0111] RTLM dynamically updates the input main pump flow model parameter θ t , that is:

[0112]

[0113] where θ t is the main pump flow model parameter at the t-th iteration, and η t is the dynamic learning rate; is the gradient of the loss function L with respect to the parameter θ t , calculated based on the current input main pump flow signal x t .

[0114] The loss function L usually selects the mean squared error (MSE) or cross-entropy (Cross-Entropy), that is:

[0115]

[0116] where y i is the true value, and f(x i ; θ t ) is the predicted value of the main pump flow model.

[0117] 24) Repeat real-time learning;

[0118] Repeat steps 21) to 23) continuously to adapt to the change of the main pump flow signal.

[0119] 25) Result evaluation and optimization;

[0120] 251) Calculate the dynamic error e of the main pump flow i :

[0121]

[0122] 252) Error aggregation;

[0123] Average all the errors in the main pump flow rate:

[0124]

[0125] Aggregate in segments:

[0126]

[0127] 253) Output the predicted value;

[0128] Multiply the average value obtained by aggregating the errors by 100% to obtain the final SMAPE value, which represents the main pump flow rate error coefficients ΔY1, ΔY2,..., ΔY predicted by the model in percentage form n ; Optimize the main pump flow rate model parameters and structure according to the error results to obtain the optimized main pump flow rate predicted value with the minimum error

[0129] The process of converting the optimized main pump flow rate predicted value into an electrical signal through a digital-to-analog conversion circuit based on the D-ADC algorithm in step 5) is as follows:

[0130] 31) Dynamic resolution adjustment;

[0131] Detect the frequency f of the input main pump flow rate signal k ;

[0132] Dynamically adjust the main pump flow rate resolution N according to the frequency k :

[0133]

[0134] Re-quantize the main pump flow rate signal N using the adjusted resolution k .

[0135] 32) The output electrical signal is:

[0136]

[0137] where v out(n) is the main pump flow rate analog voltage output at the nth sampling moment, f i，n is the conversion coefficient, and N k，n is the main pump flow rate digital signal value input at the nth sampling moment.

[0138] Simulation experiment

[0139] To verify the reliability of the present invention, the experimental data obtained (i.e., the original main pump flow rate) comes from a pressurized water reactor with a load regulation range of 60%-100% and a test time of 45 days. The data of the first 30 days are selected, and a total of 8282 data samples at 15-minute intervals are provided to train the prediction model. After the self-learning function of the model is completed, the data of the last 15 days are selected to test the performance of the proposed model. At the same time, to compare the advancement of the present invention, the symmetric mean absolute percentage error algorithm (D-SMAPE) is used for evaluation, and the traditional PSO, RNN, FCNN are selected for comparison with the present invention.

[0140] Taking the error evaluation index D-SMAPE as the evaluation standard for each model, the experimental results are shown in Table 1.

[0141] Table 1

[0142] Evaluation Index PS0 RNN FCNN The model of the present application D-SMAPE(%) 67.11 52.10 38.09 16.01

[0143] As shown in Table 1, when compared with all other benchmark models, the present invention has the smallest error coefficient. Compared with the PSO model, the error coefficients of RNN, FCNN and the present invention have all decreased significantly, proving that the model proposed by the present invention can better improve the prediction accuracy compared with the PS0 model; at the same time, when the model of the present invention is compared with the RNN and FCNN models, its error coefficient is smaller than the other two models, proving that the algorithm model of the present invention based on the NL-FCNN non-linear fully connected neural network can improve the prediction accuracy of the primary loop main pump flow rate of the pressurized water reactor.

[0144] Embodiment 2

[0145] The primary loop main pump flow rate prediction and control system of the present invention includes:

[0146] An acquisition module for acquiring the original main pump flow rate signal of the primary loop of the pressurized water reactor;

[0147] A decomposition module for performing multi-scale decomposition on the main pump flow rate signal using the HOFEM module of NL-FCNN to obtain multi-size main pump flow rates;

[0148] An extraction module for inputting the multi-scale main pump flow rate components into the ANSA dynamic optimization network structure for feature extraction to obtain multi-scale feature vectors;

[0149] A prediction module for predicting the main pump flow rate signal using NL-FCNN based on the extracted multi-scale feature vectors to obtain the optimized main pump flow rate prediction value;

[0150] A control module, which is configured to convert the predicted value of the optimized main pump flow rate into an electrical signal through a digital-to-analog conversion circuit based on the D-ADC algorithm, and then input the electrical signal into the main pump frequency converter to drive the main pump to operate variably and control the main pump flow rate of the primary loop of the pressurized water reactor.

[0151] In this embodiment, after obtaining the original main pump flow signal of the primary loop of the pressurized water reactor, the following steps are further included:

[0152] Preprocess the original main pump flow signal to eliminate the dimensional and amplitude differences.

[0153] The division of modules in the embodiments of the present application is illustrative, merely a logical function division. In actual implementation, there may be other division methods. In addition, in each embodiment of the present application, each functional module may be integrated in a processor, may also exist physically alone, or two or more modules may be integrated in one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0154] Embodiment III

[0155] 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, the steps of the method for predicting and controlling the main pump flow rate of the primary loop of the pressurized water reactor are implemented. For example, it includes: obtaining the original main pump flow signal of the primary loop of the pressurized water reactor; using the HOFEM module of NL-FCNN to perform multi-scale decomposition on the main pump flow signal to obtain multi-size main pump flow rates; inputting the multi-scale main pump flow rate components into the ANSA dynamic optimization network structure for feature extraction to obtain multi-scale feature vectors; based on the extracted multi-scale feature vectors, using NL-FCNN to predict the main pump flow signal to obtain the predicted value of the optimized main pump flow rate; based on the D-ADC algorithm, converting the predicted value of the optimized main pump flow rate into an electrical signal through a digital-to-analog conversion circuit, and then inputting the electrical signal into the main pump frequency converter to drive the main pump to operate variably and control the main pump flow rate of the primary loop of the pressurized water reactor. Among them, the memory may include internal memory, such as high-speed random access memory, and may also include non-volatile memory, such as at least one disk memory, etc.; the processor, network interface, and memory are interconnected through an internal bus, and this internal bus may be an Industry Standard Architecture bus, a Peripheral Component Interconnect standard bus, an Extended Industry Standard Architecture bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include internal memory and non-volatile memory and provide instructions and data to the processor.

[0156] Embodiment IV

[0157] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the steps of the method for predicting and controlling the flow rate of the primary pump in the pressurized water reactor. For example, it includes: obtaining the original primary pump flow signal of the primary loop of the pressurized water reactor; using the HOFEM module of NL-FCNN to perform multi-scale decomposition on the primary pump flow signal to obtain multi-scale primary pump flow rates; inputting the multi-scale primary pump flow components into the ANSA dynamic optimization network structure for feature extraction to obtain multi-scale feature vectors; based on the extracted multi-scale feature vectors, using NL-FCNN to predict the primary pump flow signal to obtain the optimized primary pump flow prediction value; based on the D-ADC algorithm, converting the optimized primary pump flow prediction value into an electrical signal through a digital-to-analog conversion circuit, and then inputting the electrical signal into the primary pump frequency converter to drive the primary pump to operate in a variable frequency manner to control the flow rate of the primary pump in the primary loop of the pressurized water reactor. Specifically, the computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include read-only memory (ROM), hard disk, flash memory, optical disc, magnetic disk, etc.

[0158] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0159] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0160] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the function specified in one or more of the blocks and / or processes Figure 1 in one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0161] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the function specified in one or more of the processes and / or blocks Figure 1 in one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0162] Those skilled in the art will readily conceive of other embodiments of the present invention 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 known or customary techniques in the art that are not disclosed in the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are pointed out by the following claims.

[0163] It should be understood that the present invention is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is limited only by the appended claims.

[0164] The above are only the preferred embodiments of the present invention, and do not limit the present invention in any way. Any simple modifications, changes, and equivalent structural changes made to the above embodiments according to the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A method for predicting and controlling the flow rate of the primary pump in the primary loop of a pressurized water reactor, characterized in that, Including: Obtain the original main pump flow signal of the primary loop of a pressurized water reactor; Use the HOFEM module of NL-FCNN to perform multi-scale decomposition on the main pump flow signal to obtain multi-sized main pump flows; Input the multi-scale main pump flow components into the ANSA dynamic optimization network structure for feature extraction to obtain multi-scale feature vectors; Based on the extracted multi-scale feature vectors, use NL-FCNN to predict the main pump flow signal to obtain the optimized main pump flow prediction value; Based on the D-ADC algorithm, convert the optimized main pump flow prediction value into an electrical signal through a digital-to-analog conversion circuit, and then input the electrical signal into the main pump frequency converter to drive the main pump to operate variably and control the main pump flow of the primary loop of the pressurized water reactor.

2. The method for predicting and controlling the flow rate of the primary pump in the primary loop of a pressurized water reactor according to claim 1, characterized in that, After obtaining the original main pump flow signal of the primary loop of the pressurized water reactor, it further includes: Preprocess the original main pump flow signal to eliminate the dimensional and amplitude differences.

3. The method for predicting and controlling the flow rate of the primary pump in the primary circuit of a pressurized water reactor according to claim 1, characterized in that, During the process of using the HOFEM module of NL-FCNN to perform multi-scale decomposition on the main pump flow signal to obtain multi-sized main pump flows, enhance the feature extraction ability of each scale of main pump flow components through DNAF.

4. The method for predicting and controlling the flow rate of the primary pump in the primary loop of a pressurized water reactor according to claim 1, wherein It also includes: Optimize the ANSA dynamic optimization network structure based on the HOA algorithm.

5. The method for predicting and controlling the flow rate of the primary pump in the primary loop of a pressurized water reactor according to claim 1, wherein It also includes: Optimize NL-FCNN using RTLM and DSFA.

6. The method for predicting and controlling the flow rate of the primary pump in the primary loop of a pressurized water reactor according to claim 1, wherein The electrical signal is expressed as: where, v out(n) is the analog voltage of the main pump flow rate output at the nth sampling moment, f i,n is the conversion coefficient, N k,n is the digital signal value of the main pump flow rate input at the nth sampling moment.

7. A flow prediction and control system for the primary pump of a pressurized water reactor loop, characterized in that Including: An acquisition module for obtaining the original main pump flow signal of the primary loop of a pressurized water reactor; A decomposition module for using the HOFEM module of NL-FCNN to perform multi-scale decomposition on the main pump flow signal to obtain multi-sized main pump flows; An extraction module for inputting the multi-scale main pump flow components into the ANSA dynamic optimization network structure for feature extraction to obtain multi-scale feature vectors; A prediction module for predicting the main pump flow signal using NL-FCNN based on the extracted multi-scale feature vectors to obtain the optimized main pump flow prediction value; A control module for converting the optimized main pump flow prediction value into an electrical signal through a digital-to-analog conversion circuit based on the D-ADC algorithm, and then inputting the electrical signal into the main pump frequency converter to drive the main pump to operate variably and control the main pump flow of the primary loop of the pressurized water reactor.

8. The primary pump flow prediction and control system for the primary circuit of a pressurized water reactor according to claim 7, wherein After obtaining the original main pump flow signal of the primary loop of the pressurized water reactor, it further includes: Preprocess the original main pump flow signal to eliminate the dimensional and amplitude differences.

9. 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 method for predicting and controlling the main pump flow of the primary loop of a pressurized water reactor according to any one of claims 1-6.

10. 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 main pump flow of the primary loop of a pressurized water reactor according to any one of claims 1-6.

Images