Method for controlling sodium flow of primary loop of sodium-cooled fast reactor and related device

Abstract

The invention discloses a sodium flow control method for a primary loop of a sodium-cooled fast reactor and a related device, and the method comprises the steps: obtaining an original sodium flow signal sequence of the primary loop of the sodium-cooled fast reactor, and obtaining M sodium flow IMF components IMF1,..., IMFM according to the original sodium flow signal sequence of the primary loop of the sodium-cooled fast reactor; the M sodium flow IMF components IMF1,..., IMFM are input into the trained AG-LSTM network, and predicted values Y1, Y2,..., YM of the IMF components are obtained; on the basis of the predicted value of the IMF component and the actual value of the IMF component, error coefficients delta Y1, delta Y2,..., delta YM corresponding to the IMF component of each sodium flow are obtained through calculation; the error coefficients delta Y1, delta Y2,..., delta YM corresponding to the sodium flow IMF components are input into the trained DenseNet prediction model, the optimal IMF component prediction value # imgabs0 # of the sodium flow sequence is obtained, and the sodium flow of the sodium-cooled fast reactor primary loop is controlled according to the optimal IMF component prediction value # imgabs1 # of the sodium flow sequence, and the method and the related device can accurately control the sodium flow of the sodium-cooled fast reactor primary loop.

Description

Technical Field

[0001] The present invention belongs to the technical field of nuclear power engineering, and relates to a method for controlling the sodium flow rate in the primary loop of a sodium-cooled fast reactor and related devices. Background Art

[0002] A sodium-cooled fast neutron breeder reactor (hereinafter referred to as a sodium-cooled fast reactor) is a reactor that uses liquid sodium as a coolant and maintains a chain reaction caused by fast neutrons. Its advantages include: 1) High fuel utilization rate. The sodium-cooled fast reactor is currently the only reactor type that can relatively easily achieve fuel breeding. It can convert uranium-238 into plutonium-239, achieving a higher production of fissile nuclides than a thermal neutron reactor, thereby significantly improving the utilization rate of nuclear fuel resources, reaching 60% - 70%; 2) High power density and safety: The sodium-cooled fast reactor has a large power density and high safety. Its volume can be reduced to a micro level, without frequent refueling, and has a long life cycle; 3) Good cooling performance: The sodium-cooled fast reactor uses liquid sodium as a coolant, with advantages such as a small neutron absorption cross-section, good thermal conductivity, large specific heat capacity, and high boiling point. 4) Wide application range. The sodium-cooled fast reactor has broad application prospects in nuclear energy utilization. It can not only be used for power generation, but also play an important role in fields such as clean heating, industrial heating, and seawater desalination.

[0003] The primary loop of a sodium-cooled fast reactor mainly includes a reactor core, a primary loop sodium circulation pump, and an intermediate heat exchanger. A circulation system is formed through pipelines, and heat transfer by the sodium coolant is used to transfer the heat of the reactor core to the primary loop. The main goal of controlling the sodium flow rate in the primary loop is to ensure the stable flow of the coolant to maintain the normal operating temperature and pressure of the reactor core. Control strategies usually include adjusting the rotation speed and flow rate of the primary loop sodium circulation pump, and adjusting the flow rate and temperature of the coolant through the intermediate heat exchanger. Existing sodium-cooled fast reactors have problems of poor prediction accuracy and unstable control in predicting and controlling the sodium flow rate in the primary loop, which easily cause technical problems such as poor operational flexibility of the reactor and poor transient response ability when the load changes rapidly and significantly.

[0004] The main reason is that in the prediction and processing of sodium flow parameters, the existing NLM (Non-Local Means Filtering) and EMD (Empirical Mode Decomposition) still have certain limitations when dealing with complex coupled flow signals. For example, NLM is sensitive to noise, and when EMD processes some extremely complex or severely noise-interfered signals, the decomposition results may be unstable. The existing deep learning methods, such as LSTM, perform well in processing time series data, but their performance is limited when dealing with data with complex spatial dependencies. Traditional fully connected neural network algorithms often rely on simple activation functions (such as ReLU, Sigmoid, etc.) and fixed network structures when dealing with complex non-linear problems, resulting in limited performance of the model when dealing with high-dimensional and non-linear data. The existing ResNet model usually adopts static parameters during the prediction stage and cannot dynamically adjust the model parameters according to real-time prediction errors. At the same time, in the control of the actuator, traditional DAC (Digital-to-Analog Conversion) is difficult to eliminate non-linear errors caused by component mismatch and has problems such as low conversion accuracy. It is necessary to develop a more accurate control method for the primary loop sodium flow of sodium-cooled fast reactors, which is crucial for the safe and stable operation of sodium-cooled fast reactor nuclear power plants. Summary of the Invention

[0005] The object of the present invention is to overcome the above-mentioned disadvantages of the prior art and provide a control method and related device for the primary loop sodium flow of a sodium-cooled fast reactor, which can accurately control the sodium flow in the primary loop of the sodium-cooled fast reactor.

[0006] To achieve the above object, the present invention discloses a control method for the primary loop sodium flow of a sodium-cooled fast reactor, including:

[0007] Obtain the original sodium flow signal sequence of the primary loop of the sodium-cooled fast reactor, and obtain M sodium flow IMF components IMF1,..., IMF according to the original sodium flow signal sequence of the primary loop of the sodium-cooled fast reactor M ;

[0008] Input the M sodium flow IMF components IMF1,..., IMFM into the trained AG-LSTM network to obtain the predicted values Y1, Y2,..., Y of the IMF components M ;

[0009] Calculate the error coefficients ΔY1, ΔY2,..., ΔY corresponding to each sodium flow IMF component based on the predicted values and actual values of the IMF components M ;

[0010] Input the error coefficients ΔY1, ΔY2,..., ΔY corresponding to each sodium flow IMF component M into the trained DenseNet prediction model to obtain the optimal predicted value of the IMF component of the sodium flow sequence Optimal IMF component prediction value according to sodium flow rate sequence Control the sodium flow rate in the primary circuit of a sodium-cooled fast reactor.

[0011] A further improvement of the method for controlling the sodium flow rate in the primary circuit of the sodium-cooled fast reactor according to the present invention lies in:[[]]

[0012] Furthermore, the process of obtaining the original sodium flow rate signal sequence of the primary circuit of the sodium-cooled fast reactor and obtaining M sodium flow rate IMF components IMF1,..., IMF M is as follows:[[]]

[0013] Perform NLM-EMD decomposition on the original sodium flow rate signal sequence, and then reconstruct the result of the NLM-EMD decomposition to obtain M sodium flow rate IMF components IMF1,..., IMF M .

[0014] Furthermore, the process of controlling the sodium flow rate in the primary circuit of the sodium-cooled fast reactor according to the optimal IMF component prediction value of the sodium flow rate sequence is as follows:[[]]

[0015] Based on the D-ADC algorithm, convert the optimal IMF component prediction value of the sodium flow rate sequence into an electrical signal, and control the frequency converter of the sodium circulation pump according to the electrical signal to drive the sodium circulation pump to operate at variable frequency and control the sodium flow rate in the primary circuit of the sodium-cooled fast reactor.

[0016] Furthermore, the electrical signal v out(n) is:[[]]

[0017]

[0018] where f i，n is the conversion coefficient, and N k，n is the sodium flow rate digital signal value input at n sampling moments.

[0019] The present invention discloses a control system for the sodium flow rate in the primary circuit of a sodium-cooled fast reactor, including:[[]]

[0020] An acquisition module for acquiring the original sodium flow rate signal sequence of the primary circuit of the sodium-cooled fast reactor, and obtaining M sodium flow rate IMF components IMF1,..., IMF according to the original sodium flow rate signal sequence of the primary circuit of the sodium-cooled fast reactor M ;

[0021] A prediction module for inputting the M sodium flow rate IMF components IMF1,..., IMF M into the trained AG-LSTM network to obtain the predicted values Y1, Y2,..., Y of the IMF components M ;

[0022] A calculation module, configured to calculate error coefficients ΔY1, ΔY2, ..., ΔY corresponding to each sodium flow IMF component based on the predicted value and the actual value of the IMF component M ;

[0023] A control module, configured to input the error coefficients ΔY1, ΔY2, ..., ΔY corresponding to each sodium flow IMF component M into the trained DenseNet prediction model to obtain the optimal IMF component prediction value of the sodium flow sequence Based on the optimal IMF component prediction value of the sodium flow sequence control the sodium flow of the primary loop of the sodium-cooled fast reactor.

[0024] A further improvement of the control system for the sodium flow of the primary loop of the sodium-cooled fast reactor according to the present invention lies in:

[0025] Further, the process of obtaining M sodium flow IMF components IMF1, ..., IMF according to the acquired original sodium flow signal sequence of the primary loop of the sodium-cooled fast reactor M is as follows:

[0026] Perform NLM-EMD decomposition on the original sodium flow signal sequence, and then reconstruct the result of the NLM-EMD decomposition to obtain M sodium flow IMF components IMF1, ..., IMF M .

[0027] Further, the process of controlling the sodium flow of the primary loop of the sodium-cooled fast reactor according to the optimal IMF component prediction value of the sodium flow sequence is as follows:

[0028] Based on the D-ADC algorithm, convert the optimal IMF component prediction value of the sodium flow sequence into an electrical signal, and control the frequency converter of the sodium circulation pump according to the electrical signal to drive the sodium circulation pump to operate with frequency conversion, so as to control the sodium flow of the primary loop of the sodium-cooled fast reactor.

[0029] Further, the electrical signal v out(n) is:

[0030]

[0031] where f i,n is the conversion coefficient, and N k，n is the sodium flow digital signal value input at n sampling moments.

[0032] 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 control method for the sodium flow of the primary loop of the sodium-cooled fast reactor are implemented.

[0033] 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 control method for the primary circuit sodium flow rate of the sodium-cooled fast reactor are implemented.

[0034] The present invention has the following beneficial effects:

[0035] When the control method for the primary circuit sodium flow rate of the sodium-cooled fast reactor and related devices of the present invention are specifically operated, the non-local mean empirical mode decomposition method (NLM-EMD) is used to decompose the original sodium flow rate sequence. During the signal decomposition process, the non-local mean denoising technology is introduced to suppress the influence of noise on the decomposition result. A hierarchical progressive decomposition method is used to couple the NLM and EMD technologies, overcoming the respective disadvantages of the two decomposition methods and improving the decomposition accuracy and stability. By combining the graph attention mechanism and the LSTM network, the modeling ability for complex spatio-temporal dependence data is significantly improved. Based on the multi-dimensional error fusion algorithm (MDF), the sodium flow rate error coefficient is obtained and introduced into DenseNet to obtain the optimized predicted value of the sodium flow rate, solving the problem that the traditional fully connected neural network algorithm cannot dynamically adjust the model parameters according to the real-time prediction error, and effectively improving the control accuracy of the primary circuit sodium circulation pump frequency converter.

[0036] Furthermore, for the problems that traditional digital-to-analog conversion (DAC) is difficult to eliminate the non-linear error caused by component mismatch and has low conversion accuracy in actuator control. The present invention proposes a D-DAC digital-to-analog improvement algorithm, which introduces a dynamic resolution adjustment mechanism and can reduce the non-linear error caused by component mismatch. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] 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:

[0038] Figure 1 is the flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to 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.

[0040] In the description of the present invention, it should be understood that the terms "comprising" and "including" 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.

[0041] It should also be understood that the terms used in the specification of the present invention are merely for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly dictates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0042] It should be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present invention generally represents an "or" relationship between the preceding and following related objects.

[0043] It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present invention to describe preset ranges, etc., these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from each other. 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.

[0044] Depending on the context, the word "if" as used herein can be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detected (stated condition or event)" can be interpreted as "when determined" or "in response to determining" or "when detected (stated condition or event)" or "in response to detecting (stated condition or event)".

[0045] To make the objectives, 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 with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components described and shown in the accompanying drawings here can 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 represents selected 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 fall within the scope of protection of the present invention.

[0046] Various schematic structural 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 and their relative sizes and positional relationships are merely exemplary. In practice, there may be deviations due to manufacturing tolerances or technical limitations, and those skilled in the art can design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0047] Embodiment 1

[0048] Reference Figure 1 , the control method for the primary sodium flow rate of the sodium-cooled fast reactor described in the present invention includes the following steps:

[0049] 1) Obtain the original sodium flow rate signal sequence of the primary loop of the sodium-cooled fast reactor, perform NLM-EMD decomposition on the original sodium flow rate signal sequence, and then reconstruct the result of the NLM-EMD decomposition to obtain M sodium flow IMF components IMF1,..., IMF M ;

[0050] 2) Input the M sodium flow IMF components IMF1,..., IMF M into the trained AG-LSTM network to obtain the predicted values Y1, Y2,..., Y M of the IMF components, where the actual values of the IMF components corresponding to the predicted values Y1, Y2,..., Y M [[ID=2K]] are M1, M2,..., M M , and calculate the error coefficients ΔY1, ΔY2,..., ΔY corresponding to each sodium flow IMF component based on the predicted values of the IMF components and the actual values of the IMF components M ;

[0051] 3) Input the error coefficient corresponding to the sodium flow IMF component into the trained DenseNet prediction model to obtain the optimal IMF component prediction value of the sodium flow sequence.

[0052] 4) Based on the D-ADC algorithm, the optimal IMF component prediction value of the sodium flow sequence is converted into an electrical signal, and the frequency converter of the sodium circulation pump is controlled according to the electrical signal to drive the sodium circulation pump to operate with frequency conversion.

[0053] It should be noted that the specific process of the NLM-EMD decomposition is as follows:

[0054] 1) Non-local means denoising (NLM)

[0055] 11) Calculate the similarity weight:

[0056] For each point x(i) in the sodium flow signal, calculate its similarity weight Z(i, j) with other points x(j) in the neighborhood as:

[0057]

[0058] where N i and N j represent the neighborhoods centered at points i and j respectively, H is a parameter controlling the attenuation rate, and || ||2 represents the Euclidean distance.

[0059] 12) Calculate the similarity weight:

[0060] Calculate the denoised sodium flow signal through weighted average as:

[0061]

[0062] where Ω i is the search window centered at point i.

[0063] Perform non-local means denoising on the sodium flow signal x(i) to obtain the denoised signal The core idea of non-local means denoising is to utilize the self-similarity of the signal and remove noise by weighted averaging of similar regions.

[0064] The process of empirical mode decomposition (EMD) is as follows:

[0065] 21) Initialize;

[0066] Let the sodium flow residual signal and the IMF component set be empty.

[0067] 22) Extract IMF components;

[0068] For the nth IMF component, the following iterative process is performed:

[0069] 221) Extract the local extreme points of the signal m n-1 (t).

[0070] 222) Fit the upper envelope e max (t) and the lower envelope e min (t) by interpolation.

[0071] 223) Calculate the mean envelope m n (t):

[0072]

[0073] 224) Update the candidate IMF component h n (t):

[0074] h n (t) = r n-1 (t) - m n (t)

[0075] 225) Check whether h n (t) satisfies the IMF conditions (the difference between the number of extreme points and the number of zero-crossing points does not exceed 1, and the mean envelope is close to zero). If it satisfies, then take h n (t) as the nth IMF component; otherwise, continue the iteration.

[0076] 226) Update the residual signal r n (t):

[0077] r n (t) = r n-1 (t) - h n (t)

[0078] 227) When the residual signal r n (t) is a monotonic function or the number of extreme points is less than 2, stop the decomposition.

[0079] The process of outputting the IMF components is as follows:

[0080] Output the IMF components of the sodium flow rate obtained by decomposition and the final residual signal:

[0081]

[0082] Among them, h n (t) is the nth IMF component, r n (t) is the final residual signal, and n is the total number of IMF components.

[0083] The specific operation of the AG-LSTM algorithm is as follows:

[0084] 31) Adaptive graph attention mechanism;

[0085] An adaptive graph attention mechanism is introduced, and the relationship weights between nodes are dynamically learned as:

[0086] e ij = LeakyReLU(α T [Wh i ||Wh j )

[0087] where e ij is the attention score between sodium flow node i and node j; α is the learnable attention vector; W is the learnable weight matrix; h i and h j are the feature representations of sodium flow node i and node j; α ij is the normalized attention weight.

[0088] 32) Spatiotemporal fusion module;

[0089] 321) Construct an LSTM network adaptive gating mechanism network, including:

[0090] Forget Gate:

[0091]

[0092] where f t is the output of the forget gate at time t, σ is the Sigmoid function, and its output value is between 0 and 1; W f is the weight matrix of the forget gate; represents concatenating the hidden state h t-1 at the previous time step and the input X t at the current time step together; b f is the bias term of the forget gate; g(t) is a time-related adaptive function used to dynamically adjust the weight of the forget gate; α f is the adaptive coefficient.

[0093] Input Gate:

[0094] The activation value of the input gate is:

[0095]

[0096] where i t is the output of the input gate at time t, W i is the weight matrix of the input gate, b i is the corresponding bias term, and α i is the adaptive coefficient.

[0097] Memory cell state:

[0098] Calculate the candidate memory cell state value is:

[0099]

[0100] Calculate the candidate memory cell state Ct as:

[0101]

[0102] where the tanh function maps the output value to between -1 and 1, and W c is the weight matrix of the candidate memory cell state, and b c is the corresponding bias term.

[0103] Output Gate:

[0104] Calculate the activation value of the output gate as:

[0105]

[0106] where o t is the output of the output gate at time step t, W o is the weight matrix of the output gate, b o is the bias term, and a o is the adaptive coefficient.

[0107] Update the hidden state:

[0108] h t = o t ·tanh(C t )

[0109] where the tanh function maps the output value to between -1 and 1.

[0110] 322) Design a spatio-temporal fusion module to combine the graph attention mechanism with the LSTM network:

[0111]

[0112] where, is the hidden state of the sodium flow node i at time step t; N(i) is the set of neighbor nodes of the sodium flow node i.

[0113] 33) Multi-scale feature extraction;

[0114] Capture spatio-temporal features at different time scales through a multi-scale feature extraction module:

[0115] H multi-scale=Concat(AvgPool(H,k1),AvgPool(H,k2),…)

[0116] Among them, H is the sodium flow rate feature matrix output by the spatio-temporal fusion module; k1, k2, … are different time scales.

[0117] 34) Adaptive learning rate adjustment;

[0118] Introduce an adaptive learning rate adjustment strategy, and optimize the model training process as:

[0119]

[0120] Among them, η t is the learning rate of the t-th iteration; η0 is the initial learning rate.

[0121] 35) Real-time prediction and update;

[0122] Support real-time data input and model update, suitable for dynamically changing scenarios:

[0123] y = Linear(H multi-scale )

[0124] Among them, y is the predicted value of sodium flow rate; Linear is the linear transformation layer.

[0125] The process of the MDF algorithm is:

[0126] 41) Single-dimensional error calculation;

[0127] Calculate the single-dimensional error e of each sodium flow rate i，j as:

[0128]

[0129] Among them, gj(·) is the calculation function of the j-th error dimension;

[0130] 42) Multi-dimensional error fusion

[0131] Perform weighted fusion on the errors of each dimension to obtain the multi-dimensional error E i as:

[0132]

[0133] Among them, β j is the weight coefficient of the j-th sodium flow rate error dimension.

[0134] The process of the DenseNet algorithm is:

[0135] 51) Network construction;

[0136] 511) Initialize the dynamic dense block;

[0137] Set the sliding window size D; Define the weight matrix of the gating function

[0138] 512) Configure the feature compensation path;

[0139] Add a 1×1 convolution compensator after each DenseBlock; Initialize the attenuation factor γ = 0.2.

[0140] 52) Training process;

[0141] 521) Warm-up stage (0 - 10 epochs);

[0142] Fix

[0143] Only train the convolution weights in H1(·);

[0144] 522) Dynamic training stage (11 - 50 epochs);

[0145] Activate the gating function learning; Decrease the temperature coefficient τ according to a linear schedule:

[0146] τ = 1.0 - 0.02 × epoch

[0147] Update rule:

[0148]

[0149] 523) Fine-tuning stage (51 - 100 epochs):

[0150] Freeze the gating coefficient α K,1 ; Remove the sparse regularization term (λ = 0); Fine-tune the convolution parameters.

[0151] 53) Inference deployment;

[0152] Gating pruning:

[0153] Delete the connection paths where α K,1 <0.1;

[0154] Quantization compression:

[0155] For the remaining α K，1 perform 8-bit fixed-point quantization as:

[0156] α K，1 = round(127·α) / 127.

[0157] The process of the D-ADC algorithm is as follows:

[0158] 61) Dynamic resolution adjustment;

[0159] Detect the frequency f of the primary sodium flow signal of the sodium-cooled fast reactor k ;

[0160] According to the frequency f k Dynamically adjust the sodium flow resolution N k ) is:

[0161]

[0162] Re-quantize the sodium flow signal N using the adjusted resolution k .

[0163] 62) Output the electrical signal

[0164]

[0165] where v out(n) is the analog voltage of the sodium 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 sodium flow input at the nth sampling moment.

[0166] Example 2

[0167] The control system for the primary sodium flow of the sodium-cooled fast reactor described in the present invention includes:

[0168] An acquisition module, configured to acquire the original sodium flow signal sequence of the primary loop of the sodium-cooled fast reactor, and obtain M sodium flow IMF components IMF1,..., IMF according to the original sodium flow signal sequence of the primary loop of the sodium-cooled fast reactor M ;

[0169] A prediction module, configured to input the M sodium flow IMF components IMF1,..., IMF M into the trained AG-LSTM network to obtain the predicted values Y1, Y2,..., Y of the IMF components M ;

[0170] A calculation module, configured to calculate the error coefficients ΔY1, ΔY2,..., ΔY corresponding to each sodium flow IMF component based on the predicted values of the IMF components and the actual values of the IMF components M ;

[0171] A control module, configured to input the error coefficients ΔY1, ΔY2,..., ΔY corresponding to each sodium flow IMF component M into the trained DenseNet prediction model to obtain the optimal predicted value of the IMF component of the sodium flow sequence According to the optimal predicted value of the IMF component of the sodium flow sequence Control the sodium flow of the primary loop of the sodium-cooled fast reactor.

[0172] In this embodiment, the process of obtaining M sodium flow IMF components IMF1, ..., IMF according to the original sodium flow signal sequence of the primary circuit of the sodium-cooled fast reactor is as follows: M :

[0173] Perform NLM-EMD decomposition on the original sodium flow signal sequence, and then reconstruct the result of the NLM-EMD decomposition to obtain M sodium flow IMF components IMF1, ..., IMF M .

[0174] In this embodiment, the process of controlling the sodium flow of the primary circuit of the sodium-cooled fast reactor according to the optimal IMF component prediction value of the sodium flow sequence is as follows: :

[0175] Based on the D-ADC algorithm, convert the optimal IMF component prediction value of the sodium flow sequence into an electrical signal, and control the frequency converter of the sodium circulation pump according to the electrical signal to drive the sodium circulation pump to operate with frequency conversion, so as to control the sodium flow of the primary circuit of the sodium-cooled fast reactor.

[0176] In this embodiment, the electrical signal v out(n) is:

[0177]

[0178] where f i,n is the conversion coefficient, and N k，n is the sodium flow digital signal value input at n sampling moments.

[0179] The division of modules in the embodiments of the present application is illustrative. It is only 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 can be integrated in a processor, or can exist separately physically, or two or more modules can be integrated in one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0180] Embodiment III

[0181] 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 the control method for the sodium flow of the primary circuit of the sodium-cooled fast reactor. For example, it includes: obtaining the original sodium flow signal sequence of the primary circuit of the sodium-cooled fast reactor, and obtaining M sodium flow IMF components IMF1, ..., IMF according to the original sodium flow signal sequence of the primary circuit of the sodium-cooled fast reactor M ; and the M sodium flow IMF components IMF1, ..., IMFM Input into the trained AG-LSTM network to obtain the predicted values Y1, Y2, ..., Y of the IMF components M ; Calculate the error coefficients ΔY1, ΔY2, ..., ΔY corresponding to each sodium flow IMF component based on the predicted values of the IMF components and the actual values of the IMF components M ; Input the error coefficients ΔY1, ΔY2, ..., ΔY corresponding to each sodium flow IMF component M Into the trained DenseNet prediction model to obtain the optimal predicted values of the IMF components of the sodium flow sequence According to the optimal predicted values of the IMF components of the sodium flow sequence Control the sodium flow of the primary circuit of the sodium-cooled fast 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 can be an Industry Standard Architecture bus, a Peripheral Component Interconnect standard bus, an Extended Industry Standard Architecture bus, etc., and 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.

[0182] Embodiment 4

[0183] 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 control method for the sodium flow of the primary circuit of the sodium-cooled fast reactor. For example, it includes: obtaining the original sodium flow signal sequence of the primary circuit of the sodium-cooled fast reactor, and based on the original sodium flow signal sequence of the primary circuit of the sodium-cooled fast reactor, obtaining M sodium flow IMF components IMF1, ..., IMF M ; Input the M sodium flow IMF components IMF1, ..., IMF M Into the trained AG-LSTM network to obtain the predicted values Y1, Y2, ..., Y of the IMF components M ; Calculate the error coefficients ΔY1, ΔY2, ..., ΔY corresponding to each sodium flow IMF component based on the predicted values of the IMF components and the actual values of the IMF components M ; Input the error coefficients ΔY1, ΔY2, ..., ΔY corresponding to each sodium flow IMF component M Into the trained DenseNet prediction model to obtain the optimal predicted values of the IMF components of the sodium flow sequence According to the optimal predicted values of the IMF components of the sodium flow sequence Control the sodium flow rate in the primary circuit of a sodium-cooled fast 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 and / or cache memory, etc. The non-volatile memory may include read-only memory, hard disk, flash memory, optical disc, magnetic disk, etc.

[0184] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a completely hardware embodiment, a completely 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 containing computer-usable program code.

[0185] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (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 can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also 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 functions specified in Figure 1 one or more flows Figure 1 or multiple flows and / or blocks

[0186] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one or more flows Figure 1 or multiple flows and / or blocks

[0187] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more flows Figure 1 or multiple flows and / or blocks

[0188] Other embodiments of the present invention will be readily apparent to those skilled in the art upon consideration of the specification and the disclosure of the invention. This application is intended to cover any variations, uses, or adaptations of the present invention, which follow the general principles of the present invention and include known common knowledge or conventional technical means in the technical field not disclosed in the present invention. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of the present invention are pointed out by the following claims.

[0189] 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 only limited by the appended claims.

[0190] The above are only the preferred embodiments of the present invention, and do not impose any limitations on the present invention. 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 protection scope of the technical solution of the present invention.

Claims

1. A control method for the primary circuit sodium flow rate of a sodium-cooled fast reactor, characterized in that, including: Obtain the original sodium flow signal sequence of the primary loop of the sodium-cooled fast reactor, and based on the original sodium flow signal sequence of the primary loop of the sodium-cooled fast reactor, obtain M sodium flow IMF components IMF1,..., IMF M ; Input the M sodium flow IMF components IMF1, ..., IMF M into the trained AG-LSTM network to obtain the predicted values Y1, Y2, ..., Y of the IMF components M ; The error coefficients ΔY1, ΔY2, ..., ΔY corresponding to each sodium flow IMF component are calculated based on the predicted values and actual values of the IMF components M ; Input the error coefficients ΔY1, ΔY2,..., ΔY corresponding to the respective sodium flow IMF components M into the trained DenseNet prediction model to obtain the predicted values of the optimal IMF components of the sodium flow sequence According to the predicted values of the optimal IMF components of the sodium flow sequence control the sodium flow in the primary circuit of the sodium-cooled fast reactor.

2. The control method for the primary circuit sodium flow rate of the sodium-cooled fast reactor according to claim 1, characterized in that, The process of obtaining M sodium flow IMF components IMF1,... IMF from the original sodium flow signal sequence of the primary loop of a sodium-cooled fast reactor is as follows: M The process is as follows: Perform NLM-EMD decomposition on the original sodium flow signal sequence, and then reconstruct the result of the NLM-EMD decomposition to obtain M sodium flow IMF components IMF1, ..., IMF M .

3. The control method for the primary circuit sodium flow rate of the sodium-cooled fast reactor according to claim 1, characterized in that The predicted value of the optimal IMF component according to the sodium flow rate sequence The process of controlling the sodium flow rate in the primary loop of a sodium-cooled fast reactor is as follows: Based on the D-ADC algorithm, the predicted value of the optimal IMF component of the sodium flow rate sequence is converted into an electrical signal, and the frequency converter of the sodium circulation pump is controlled according to the electrical signal to drive the sodium circulation pump to operate with variable frequency, so as to control the sodium flow rate of the primary loop of the sodium-cooled fast reactor.

4. The control method for the primary circuit sodium flow rate of the sodium-cooled fast reactor according to claim 1, wherein The electrical signal v out(n) is as follows: Among them, f i,n is the conversion coefficient, and N k,n is the digital signal value of the sodium flow rate input at n sampling moments.

5. A control system for the primary sodium flow rate of a sodium-cooled fast reactor, characterized in that, including: An acquisition module is used to acquire the original sodium flow signal sequence of the primary loop of a sodium-cooled fast reactor, and M sodium flow IMF components IMF1,... IMF are obtained according to the original sodium flow signal sequence of the primary loop of the sodium-cooled fast reactor M ; A prediction module, which is used to input the M sodium flow IMF components IMF1, ..., IMF M into the trained AG-LSTM network to obtain the predicted values Y1, Y2, ..., Y of the IMF components M ; A calculation module, configured to calculate error coefficients ΔY1, ΔY2, ..., ΔY corresponding to each sodium flow IMF component based on the predicted values and actual values of the IMF components M ; A control module for inputting error coefficients ΔY1, ΔY2, ..., ΔY corresponding to the respective sodium flow IMF components M into the trained DenseNet prediction model to obtain the optimal IMF component prediction value of the sodium flow sequence Based on the optimal IMF component prediction value of the sodium flow sequence control the sodium flow of the primary circuit of the sodium-cooled fast reactor.

6. The control system for the primary circuit sodium flow rate of the sodium-cooled fast reactor according to claim 5, characterized in that, The process of obtaining M sodium flow IMF components IMF1,..., IMF from the original sodium flow signal sequence of the primary circuit of a sodium-cooled fast reactor is as follows: M : Perform NLM-EMD decomposition on the original sodium flow signal sequence, and then reconstruct the result of the NLM-EMD decomposition to obtain M sodium flow IMF components IMF1, ..., IMF M .

7. The control system for the primary circuit sodium flow rate of the sodium-cooled fast reactor according to claim 5, characterized in that, The predicted value of the optimal IMF component according to the sodium flow rate sequence The process of controlling the sodium flow rate in the primary loop of a sodium-cooled fast reactor is as follows: Convert the predicted value of the optimal IMF component of the sodium flow rate sequence based on the D-ADC algorithm into an electrical signal, and control the frequency converter of the sodium circulation pump according to the electrical signal to drive the sodium circulation pump to operate with variable frequency, so as to control the sodium flow rate of the primary loop of the sodium-cooled fast reactor.

8. The control system for the primary circuit sodium flow rate of the sodium-cooled fast reactor according to claim 5, characterized in that, The electrical signal v out(n) is as follows: where, f i,n is the conversion coefficient, N k,n is the digital signal value of the sodium flow rate input at n sampling moments.

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, the steps of the control method for the primary circuit sodium flow rate of the sodium-cooled fast reactor according to any one of claims 1-4 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the control method for the primary circuit sodium flow rate of the sodium-cooled fast reactor according to any one of claims 1-4 are implemented.

Images