Method and device for controlling once-through steam generator of nuclear reactor

Abstract

The invention discloses a nuclear reactor once-through steam generator control method and device, and the method comprises the steps: predicting output values of a once-through steam generator at a plurality of moments according to a first prediction model, and obtaining first output values at the plurality of moments, each training sample comprises the primary side inlet temperature of a primary side inlet of the once-through steam generator, the steam valve opening degree of the once-through steam generator and the relative water supply flow of a secondary side inlet of the once-through steam generator, and the first output value comprises the predicted primary side outlet temperature and the predicted secondary side outlet steam pressure; the control quantity of the once-through steam generator is obtained according to the first output values of the once-through steam generator at the multiple moments and the pre-configured target function, the once-through steam generator is controlled by adopting the control quantity of the once-through steam generator, and the once-through steam generator can be accurately controlled by adopting the internal information of the once-through steam generator.

Description

Technical Field

[0001] This application belongs to the field of control, and particularly relates to a control method and device for a once-through steam generator of a nuclear reactor. Background Art

[0002] A once-through steam generator (OTSG) is a key device of a small nuclear reactor, which transfers the heat generated in the primary loop to the secondary loop to generate saturated steam and drive a steam turbine to do work. The working medium flow in the secondary loop of the once-through steam generator is forced circulation, and the feed water reaches the steam quality required for unit operation through preheating, evaporation, and superheating. Since the capacity of the secondary loop of the once-through steam generator is small, if the feed water is interrupted, it will cause dry burning of the secondary loop and damage the equipment. Therefore, the control requirements for the once-through steam generator are relatively high.

[0003] In the prior art, a proportional-integral-derivative (PID) control method is used to control the once-through steam generator. However, this method only considers the external characteristics of the dynamic system input-output and lacks the use of the internal state information of the system, resulting in problems such as overshoot and poor anti-disturbance performance, and cannot accurately control the once-through steam generator. Summary of the Invention

[0004] Embodiments of this application provide a control method and device for a once-through steam generator of a nuclear reactor, which can accurately control the once-through steam generator and ensure the safe and stable operation of the nuclear reactor.

[0005] In a first aspect, embodiments of this application provide a control method for a once-through steam generator of a nuclear reactor, and the method includes:

[0006] Predicting the output values of the once-through steam generator at multiple moments according to a first prediction model to obtain first output values at multiple moments, where the first prediction model is obtained by training an initial prediction model of the once-through steam generator with multiple training samples as inputs and the reference temperature of the primary side outlet of the once-through steam generator and the reference steam pressure of the secondary side outlet of the once-through steam generator as outputs; each training sample includes the temperature of the primary side inlet of the once-through steam generator, the opening of the steam valve of the once-through steam generator, and the relative feed water flow of the secondary side inlet of the once-through steam generator; each moment corresponds to a first output value, and the first output value includes the predicted temperature of the primary side outlet of the once-through steam generator and the steam pressure of the secondary side outlet of the once-through steam generator.

[0007] Obtain the control quantity of the once-through steam generator according to the first output values at multiple moments of the once-through steam generator and a pre-configured objective function;

[0008] Control the once-through steam generator by using the control quantity of the once-through steam generator. In an embodiment of the present application, the obtaining the control quantity of the once-through steam generator according to the first output values at multiple moments of the once-through steam generator and a pre-configured objective function includes:

[0009] Construct the constraint conditions of the objective function;

[0010] Use the covariance matrix adaptation evolution strategy to solve the pre-configured objective function according to the constraint conditions and the first output values at multiple moments, so as to obtain the control quantity of the once-through steam generator.

[0011] In an embodiment of the present application, the objective function is constructed in the following manner:

[0012] Obtain the set values at multiple moments of the once-through steam generator;

[0013] Calculate the sum of squares of the errors between the set values at multiple moments and the first output values at multiple moments according to the set values at multiple moments of the once-through steam generator and the first output values at multiple moments;

[0014] Construct the objective function according to the sum of squares of the errors and the sum of squares of the deviations between the control quantities at two adjacent moments among the multiple moments.

[0015] In an embodiment of the present application, the constructing the constraint conditions of the objective function includes:

[0016] Obtain the maximum value and the minimum value of the output value of the pre-set once-through steam generator;

[0017] Obtain the maximum value and the minimum value of the control quantity of the pre-set once-through steam generator;

[0018] Determine the constraint conditions of the objective function according to the maximum value and the minimum value of the output value of the once-through steam generator and the maximum value and the minimum value of the control quantity of the once-through steam generator.

[0019] In an embodiment of the present application, the controlling the once-through steam generator by using the control quantity of the once-through steam generator includes:

[0020] Control the once-through steam generator by using the control quantity of the once-through steam generator to obtain the response value of the once-through steam generator;

[0021] Optimize the first prediction model according to the response value of the once-through steam generator to obtain an optimized first prediction model, and the optimized first prediction model is used to control the once-through steam generator.

[0022] In an embodiment of the present application, the step of optimizing the first prediction model according to the response value of the once-through steam generator to obtain an optimized first prediction model includes:

[0023] Obtain the expected value of the once-through steam generator;

[0024] Calculate the deviation between the response value and the expected value of the once-through steam generator;

[0025] Optimize the first prediction model by using the deviation to obtain an optimized first prediction model.

[0026] In an embodiment of the present application, before predicting the output values of the once-through steam generator at multiple moments according to the first prediction model to obtain the first output values at multiple moments, the method further includes:

[0027] Determine the initial prediction model of the once-through steam generator by using the subspace identification method;

[0028] During the process of training the initial prediction model by using multiple training samples, if the mean square error between the multiple primary side outlet temperatures and the multiple secondary side steam pressures predicted by the initial prediction model is a preset threshold, then use the initial prediction model as the first prediction model.

[0029] In an embodiment of the present application, the step of determining the initial prediction model of the once-through steam generator by using the subspace identification method includes:

[0030] Construct a state equation of the once-through steam generator with multiple inputs and multiple outputs;

[0031] Process the state equation of the once-through steam generator with multiple inputs and multiple outputs by using the subspace identification method to obtain the initial prediction model of the once-through steam generator.

[0032] In an embodiment of the present application, each training sample is processed as follows:

[0033] The primary side inlet temperature at the primary side inlet of the collected once-through steam generator, the steam valve opening of the collected once-through steam generator, and the relative feed water flow rate at the secondary side inlet of the collected once-through steam generator are successively subjected to filtering processing, noise removal processing, and normalization processing to obtain the primary side inlet temperature at the primary side inlet of the once-through steam generator, the steam valve opening of the once-through steam generator, and the relative feed water flow rate at the secondary side inlet of the once-through steam generator.

[0034] In a second aspect, an embodiment of the present application provides a control device for a once-through steam generator of a nuclear reactor. The device includes:

[0035] A prediction module, configured to predict the output values of the once-through steam generator at multiple moments according to a first prediction model to obtain first output values at multiple moments. The first prediction model is obtained by training an initial prediction model with multiple training samples as the input of the initial prediction model of the once-through steam generator, and the primary side outlet reference temperature at the primary side outlet of the once-through steam generator and the secondary side outlet steam reference pressure at the secondary side outlet of the once-through steam generator as the output of the initial prediction model. Each training sample includes the primary side inlet temperature at the primary side inlet of the once-through steam generator, the steam valve opening of the once-through steam generator, and the relative feed water flow rate at the secondary side inlet of the once-through steam generator. Each moment corresponds to one first output value, and the first output value includes the predicted primary side outlet temperature at the primary side outlet of the once-through steam generator and the secondary side outlet steam pressure at the secondary side outlet of the once-through steam generator.

[0036] A processing module, configured to obtain a control quantity of the once-through steam generator according to the first output values of the once-through steam generator at multiple moments and a pre-configured objective function.

[0037] A control module, configured to control the once-through steam generator by using the control quantity of the once-through steam generator.

[0038] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory storing computer program instructions;

[0039] When the processor executes the computer program instructions, the control method for the once-through steam generator of the nuclear reactor as described in the first aspect is implemented.

[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the control method for the once-through steam generator of the nuclear reactor as described in the first aspect is implemented.

[0041] In a fifth aspect, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device is caused to execute the method for controlling a direct current steam generator of a nuclear reactor as described in the first aspect.

[0042] For the method and device for controlling a direct current steam generator of a nuclear reactor according to an embodiment of the present application, first output values at multiple moments of the direct current steam generator are predicted according to a first preset model, a control quantity of the direct current steam generator is obtained according to the first output values at multiple moments of the direct current steam generator and a pre-configured objective function, and the direct current steam generator is controlled by using the control quantity of the direct current steam generator. By using the internal information of the direct current steam generator, the direct current steam generator can be accurately controlled to ensure the safe and stable operation of the nuclear reactor. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required to be used in the embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0044] Figure 1 FIG. is a flowchart of a method for controlling a direct current steam generator of a nuclear reactor provided by an embodiment of the present application;

[0045] Figure 2 FIG. is another flowchart of a method for controlling a direct current steam generator of a nuclear reactor provided by an embodiment of the present application;

[0046] Figure 3 FIG. is a structural diagram of a device for controlling a direct current steam generator of a nuclear reactor provided by an embodiment of the present application;

[0047] Figure 4 FIG. is a structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] The features and exemplary embodiments of each aspect of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without some of these specific details. The following description of the embodiments is only intended to provide a better understanding of the present application by showing examples of the present application.

[0049] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0050] To solve the problems of the prior art, an embodiment of the present application provides a method and device for controlling a direct current steam generator of a nuclear reactor. First, the method for controlling a direct current steam generator of a nuclear reactor provided by the embodiment of the present application will be introduced below.

[0051] Figure 1 It is a schematic flow chart of the method for controlling a direct current steam generator of a nuclear reactor provided by an embodiment of the present application. As Figure 1 shown, the method for controlling a direct current steam generator of a nuclear reactor provided by an embodiment of the present application is applied to an electronic device and includes the following steps 101 - step 103, where:

[0052] Step 101, predicting the output values of the direct current steam generator at multiple moments according to a first prediction model to obtain first output values at multiple moments, where the first prediction model is obtained by training an initial prediction model of the direct current steam generator with multiple training samples as the input of the initial prediction model, and the reference temperature of the primary side outlet of the direct current steam generator and the reference steam pressure of the secondary side outlet of the direct current steam generator as the output of the initial prediction model; each training sample includes the temperature of the primary side inlet of the direct current steam generator, the opening of the steam valve of the direct current steam generator, and the relative feed water flow of the secondary side inlet of the direct current steam generator; each moment corresponds to a first output value, and the first output value includes the predicted temperature of the primary side outlet of the direct current steam generator and the steam pressure of the secondary side outlet of the direct current steam generator.

[0053] The method of this embodiment is applied to controlling a once-through steam generator of a small modular reactor. The prediction model is trained in advance. Specifically, a plurality of training samples are used as the input of the initial prediction model of the once-through steam generator, and the primary side outlet reference temperature of the primary side outlet of the once-through steam generator and the secondary side outlet steam reference pressure of the secondary side outlet of the once-through steam generator are used as the output of the initial prediction model. The initial model is trained to obtain a first prediction model. Each training sample includes the primary side inlet temperature of the once-through steam generator, the steam valve opening of the once-through steam generator, and the relative feed water flow rate of the secondary side inlet of the once-through steam generator.

[0054] According to the first prediction model, the output values of the once-through steam generator at multiple moments are predicted to obtain the first output values at multiple moments. Each moment corresponds to a first output value. The first output value includes the predicted primary side outlet temperature of the once-through steam generator and the secondary side outlet steam pressure of the once-through steam generator.

[0055] From the perspective of the interface boundary conditions between the once-through steam generator and the primary coolant and the steam turbine, the once-through steam generator can be regarded as a four-input and three-output system. That is, the inputs are the primary side inlet temperature of the once-through steam generator, the feed water temperature of the secondary side inlet, the relative feed water flow rate of the secondary side inlet, and the secondary side outlet steam flow rate, and the outputs are the primary side outlet temperature of the once-through steam generator, the secondary side outlet steam temperature of the once-through steam generator, and the secondary side outlet steam pressure of the once-through steam generator. When studying the control system design of the nuclear steam supply system composed of the once-through steam generator and the reactor core, the main concerns are the steam pressure and the primary side outlet temperature of the once-through steam generator. In addition, since the feed water temperature is constant and does not change with power, the primary side inlet temperature, the steam valve opening, and the relative feed water flow rate of the secondary side inlet are selected as the inputs of the prediction model, and the primary side outlet temperature and the secondary side outlet steam pressure are used as the outputs of the prediction model.

[0056] Step 102: Obtain the control quantity of the once-through steam generator according to the first output values of the once-through steam generator at multiple moments and a pre-configured objective function.

[0057] In this embodiment, an objective function is pre-configured. The objective function is a function that needs to be maximized or minimized in an optimization problem, which maps the solution of the problem to a numerical value. By adjusting the decision variables, the optimal value of the objective function is found, so as to obtain the optimal solution of the problem. The control quantity of the once-through steam generator is obtained according to the first output values of the once-through steam generator at multiple moments and the pre-configured objective function.

[0058] Step 103: Control the once-through steam generator using the control quantity of the once-through steam generator.

[0059] In this embodiment, the once-through steam generator is controlled using the control quantity of the once-through steam generator to achieve precise control of the once-through steam generator.

[0060] In this embodiment, the output values of the once-through steam generator at multiple moments are predicted according to a first preset model to obtain first output values at multiple moments. According to the first output values of the once-through steam generator at multiple moments and a preconfigured objective function, the control quantity of the once-through steam generator is obtained. The once-through steam generator is controlled using the control quantity of the once-through steam generator. By using the internal information of the once-through steam generator, the once-through steam generator can be accurately controlled.

[0061] In an embodiment of the present application, in step 102, according to the first output values of the once-through steam generator at multiple moments and a preconfigured objective function, obtaining the control quantity of the once-through steam generator includes:

[0062] Construct the constraint conditions of the objective function;

[0063] Use the covariance matrix adaptation evolution strategy to solve the preconfigured objective function according to the constraint conditions and the first output values at multiple moments to obtain the control quantity of the once-through steam generator.

[0064] In this embodiment, the objective function can be defined according to specific performance indicators. Different performance indicators reflect different aspects of the model's performance. Therefore, when constructing the objective function, it is necessary to rely on the performance indicators of concern. Constraint conditions are constructed for the objective function, and the covariance matrix adaptation evolution strategy is used to solve the preconfigured objective function according to the constraint conditions and the first output values at multiple moments, gradually approaching the optimal control quantity increment, and finally obtaining the optimal control quantity under the condition of satisfying the constraints, that is, obtaining the control quantity of the once-through steam generator.

[0065] The optimization process of the objective function is essentially to adjust the model parameters to make the model output closer to the expectation. When the objective function reaches the optimal solution, the model performs best on the training data, and usually the corresponding performance indicators will also be improved. For example, when training a model, minimizing the mean square error objective function, the objective function is usually designed according to the performance indicators of concern, aiming to improve the performance indicators by optimizing the decision variables. For example, if the error between the predicted value and the true value is concerned, the mean square error (MSE) can be selected as the performance indicator, and the objective function is constructed based on the MSE, and the prediction error is reduced by minimizing the objective function.

[0066] In an embodiment of the present application, the objective function is constructed in the following manner:

[0067] Obtain the set values of the once-through steam generator at multiple moments;

[0068] According to the set values of the once-through steam generator at multiple moments and the first output values at multiple moments, calculate the sum of squares of the errors between the set values at multiple moments and the first output values at multiple moments;

[0069] Construct the objective function based on the sum of squares of the errors and the sum of squares of the deviations between the control quantities at two adjacent moments among the multiple moments.

[0070] In this embodiment, obtain the set values of the once-through steam generator at multiple moments, calculate the sum of squares of the errors between the set values of the once-through steam generator at multiple moments and the first output values at multiple moments according to the set values of the once-through steam generator at multiple moments and the first output values at multiple moments, and construct the objective function based on the sum of squares of the errors and the sum of squares of the deviations between the control quantities at two adjacent moments among the multiple moments. The objective function is specifically as follows:

[0071]

[0072] where Np is the number of output values, r (t+k) is the set value at the moment t + k, is the first output value at the moment t + k, P is the first coefficient, Q is the second coefficient, Nc is the input value data, and △u is the deviation between the control quantities at two adjacent moments among the multiple moments.

[0073] The objective function presents the optimization effect in numerical form, making the evaluation of different solutions intuitive and accurate, and enabling better control of the once-through steam generator.

[0074] In an embodiment of the present application, the constraint conditions for constructing the objective function include:

[0075] Obtain the maximum and minimum values of the output values of the once-through steam generator set in advance;

[0076] Obtain the maximum and minimum values of the control quantities of the once-through steam generator set in advance;

[0077] Determine the constraint conditions of the objective function according to the maximum and minimum values of the output values of the once-through steam generator and the maximum and minimum values of the control quantities of the once-through steam generator.

[0078] In this embodiment, the maximum and minimum values of the output value of the preset once-through steam generator, i.e., the upper and lower limits of the once-through steam generator, are obtained, and the maximum and minimum values of the control quantity of the preset once-through steam generator are obtained. Further, the constraint conditions of the objective function are determined according to the maximum and minimum values of the output value of the once-through steam generator and the maximum and minimum values of the control quantity of the once-through steam generator, as follows:

[0079]

[0080] Among them, is the first output value at time t + k, is the subspace matrix, w p(t+k) , u f(t+k) , w v(t+k) are data vectors, u min is the minimum value of the control quantity, u max is the maximum value of the control quantity, u (t+k-1) is the control quantity at time t + k - 1, Δu (t+k) is the control quantity deviation, y min is the minimum value of the output value, y max is the maximum value of the output value.

[0081] The covariance matrix adaptation evolutionary strategy (CMA-ES) is used to solve the control quantity, and the steps are as follows:

[0082] Step 1, initialize parameters:

[0083] First, it is expressed that the population of the once-through steam generator of the small modular reactor is generated by a multi-dimensional normal distribution N(m, σ 2 C), where m represents the population mean, C represents the covariance matrix of the algorithm, m ∈ R n , C = I ∈ R n×n , σ ∈ R + . In addition, initial parameters such as the population size, the number of truncated selected offspring, the control step learning rate, and the cumulative step learning rate need to be determined in advance.

[0084] Step 2, generate a population:

[0085] The algorithm generates a new generation of offspring individuals, i.e., control quantity increments, through mutation. The formula is as follows:

[0086]

[0087] Among them, is the kth individual of the (g + 1)th generation population, m gis the mean of the population distribution in the g-th generation, σ g is the distribution step size of the population in the g-th generation, C g is the covariance matrix of the population distribution in the g-th generation.

[0088] Step 3, evaluate fitness:

[0089] Evaluate the fitness of each offspring individual one by one and sort them. The smaller the fitness value, the closer the solution vector is to the optimal solution, the smaller the prediction error, and the higher the control accuracy. Perform (μ, λ) truncation selection to form the current optimal subgroup.

[0090] Step 4, update the mean vector, covariance matrix, and step size: The mean vector m of the next generation g+1 is selected from μ optimal subgroups in and perform a weighted average, specifically as follows:

[0091]

[0092] where, w1 ≥ w2 ≥... ≥ w μ ≥ 0, μ ≤ λ is the size of the new population, ω 1.....μ ∈ R>0 is the coefficient that determines the proportion of individuals after recombination; represents in the population, ranked i, and the fitness function

[0093] The update of the covariance adaptation matrix is as follows:

[0094]

[0095] where, c c is the update learning rate of p c h σ is the Heaviside function, used to control the excessive growth of ‖p c ‖, μ eff means the variance effective selection quality, and 1 ≤ μ eff ≤ μ,, c1 and cμ are the update learning rates of the "rank 1" and "rank μ" of C respectively, δ(h σ ) = (1 - h σ )c c (2 - c c ).

[0096] The step size is updated as follows:

[0097]

[0098] where, It can be regarded as the scaling factor of the step size change, c σ is pσ The updated learning rate, d σ is a damping coefficient close to 1, and E(||N(0, I)||) is the expected length of the normalized evolution path under random selection.

[0099] Update the covariance matrix according to the fitness values of each solution vector in the population. This step uses the strategy of covariance matrix adaptation, and by continuously adjusting the size and shape of the covariance matrix, it adapts to the characteristics of the performance index problem.

[0100] Step 5, termination condition judgment:

[0101] Judge whether the termination condition is satisfied. If the preset termination condition is set to reach the maximum number of iterations, and if the termination condition is not satisfied, then return to Step 2 and continue the iterative optimization. Each iteration will update the mean vector, covariance matrix, and step size, and gradually optimize the value of the objective function.

[0102] Take the sum of the squares of the errors between the set value and the predicted value (i.e., the first output value) of the steam generator of the small reactor, and the squares of the deviations between adjacent control quantities multiplied by their respective weighting coefficients (the first coefficient and the second coefficient) as the performance index of the predictive control problem of the steam generator system of the small reactor. The problem of minimizing the performance index is solved by the CMA-ES algorithm. First, determine the initialization parameters, then generate a population through a multi-dimensional normal distribution, use the performance index as the fitness and evaluate it, update the mean vector, covariance matrix, and step size, gradually approach the optimal control quantity increment, and finally obtain the optimal control quantity under the condition of satisfying the constraints of the objective function.

[0103] In an embodiment of the present application, in Step 103, controlling the once-through steam generator with the control quantity of the once-through steam generator includes:

[0104] Controlling the once-through steam generator with the control quantity of the once-through steam generator to obtain the response value of the once-through steam generator;

[0105] Optimizing the first prediction model according to the response value of the once-through steam generator to obtain an optimized first prediction model, and the optimized first prediction model is used to control the once-through steam generator.

[0106] In this embodiment, controlling the once-through steam generator with the control quantity of the once-through steam generator to obtain the response value of the once-through steam generator, optimizing the first prediction model according to the response value to obtain an optimized first prediction model, and using the optimized first prediction model to control the once-through steam generator.

[0107] Specifically, the output values of the once-through steam generator at multiple moments are predicted according to the optimized first prediction model, and second output values at multiple moments are obtained. Each moment corresponds to a second output value, and the second output value includes the predicted primary side outlet temperature at the primary side outlet of the once-through steam generator and the secondary side outlet steam pressure at the secondary side outlet of the once-through steam generator. Further, according to the second output values of the once-through steam generator at multiple moments and a preconfigured objective function, a control quantity of the once-through steam generator is obtained, and the once-through steam generator is controlled by using the control quantity of the once-through steam generator.

[0108] In an embodiment of the present application, the optimizing the first prediction model according to the response value of the once-through steam generator to obtain an optimized first prediction model includes:

[0109] Obtain the expected value of the once-through steam generator;

[0110] Calculate the deviation between the response value of the once-through steam generator and the expected value;

[0111] Optimize the first prediction model by using the deviation to obtain an optimized first prediction model.

[0112] In this embodiment, the expected value of the once-through steam generator is obtained, the deviation between the response value of the once-through steam generator and the expected value is calculated, the first prediction model is optimized according to the deviation between the response value of the once-through steam generator and the expected value to obtain an optimized first prediction model, and the once-through steam generator is controlled by using the optimized first prediction model.

[0113] In an embodiment of the present application, before predicting the output values of the once-through steam generator at multiple moments according to the first prediction model to obtain first output values at multiple moments, the method further includes:

[0114] Determine an initial prediction model of the once-through steam generator by using a subspace identification method;

[0115] During the process of training the initial prediction model by using multiple training samples, if the mean square error between the multiple predicted primary side outlet temperatures and the multiple predicted secondary side steam pressures obtained by the initial prediction model is a preset threshold, the initial prediction model is used as the first prediction model.

[0116] In this embodiment, the subspace identification method is used to determine the initial prediction model of the once-through steam generator. Further, a plurality of the training samples are used to train the initial prediction model. During the training process, the mean square error between the plurality of primary side outlet temperatures predicted by the calculated initial prediction model and the plurality of secondary side steam pressures is calculated. If the mean square error is a preset threshold, the training ends, and the initial prediction model is used as the first prediction model; if the mean square error is not the preset threshold, the training continues.

[0117] In an embodiment of the present application, the subspace identification method is used to determine the initial prediction model of the once-through steam generator, including:

[0118] Construct the state equation of the once-through steam generator with multiple inputs and multiple outputs;

[0119] Use the subspace identification method to process the state equation of the once-through steam generator with multiple inputs and multiple outputs to obtain the initial prediction model of the once-through steam generator.

[0120] In this embodiment, the subspace identification method is used to determine the initial prediction model of the once-through steam generator. First, construct the following state equation of the once-through steam generator of the small modular reactor:

[0121]

[0122] where u t ∈R m represents the control input of the once-through steam generator of the small modular reactor, y t ∈R l represents the output of the once-through steam generator of the small modular reactor, x t ∈R n represents the state vector of the once-through steam generator of the small modular reactor, K n×l is the Kalman filter gain, e t represents a zero-mean Gaussian white noise sequence independent of the control input, and its covariance matrix is The matrix N n×nm =[N1 N2 L N m characterizes the characteristics of the model, and the Kronecker product of the vectors a ∈ R p and b ∈ R q is defined as

[0123] The Kronecker product of the control input vector and the state vector is introduced into the above state equation, where the state output at time t is expressed as:

[0124]

[0125] where xt is the state vector, y t is the control output vector, C and D are system matrices, ut is the control input vector, and et is a Gaussian white noise sequence, where, + is the pseudo-inverse symbol.

[0126] Then the non-linear product term u t and x t The Kronecker product of is represented by f(ui, yi):

[0127]

[0128] Substituting Equation (10) into Equation (11), we get:

[0129]

[0130] where the diagonal matrices P and Q are respectively represented as:

[0131]

[0132] The state equation at time t+1 is represented as:

[0133]

[0134] Define the extended input vector:

[0135]

[0136] Define the extended system matrix:

[0137] Define the gain matrix:

[0138] Then the state equation of the small modular reactor once-through steam generator can be transformed into:

[0139]

[0140] y t = Cx t + Du t + e t (14)

[0141] Based on the input-output data measurement values of the steam generator system, the Hankel matrix is constructed in the following way for subspace identification:

[0142]

[0143]

[0144] The Hankel matrix is a special square matrix, characterized by the elements on the diagonals parallel to the main diagonal being equal. Let U represent the input matrix. The subscripts f and p in the above Hankel matrix represent the sampling times of "future" and "past", respectively.

[0145] Let the number of rows and columns of the Hankel matrix be represented by i and j, respectively. The future and past state sequences are defined as follows:

[0146] X f =[x i x i+1 L x i+j-1 (15)

[0147] X p =[x0x1L x j-1 (16)

[0148] The following input and output equations play a crucial role in subspace identification:

[0149]

[0150] Let be controllable and {A, C} be observable. Then the inverse extended controllability matrix Γ i and the extended observability matrix Δ i are defined as follows:

[0151]

[0152] Γ i =[C T (CA) T (CA 2 ) T … (CA i-1 ) T [[ID=5&6]]] T (21)

[0153] In addition, the low - dimensional block - triangular Toeplitz matrix H i and the diagonal - block matrix are defined as follows:

[0154]

[0155] Then:

[0156]

[0157] Y f =L p W p +L u W u +L ν Wν (25)

[0158] The optimal output prediction can be calculated by solving the following least - squares problem:

[0159]

[0160] It should be noted that the prediction model of the once - through steam generator of the small - scale reactor obtained by the least - squares algorithm cannot update the model parameters online with the latest data, so it cannot characterize the non - linear time - varying dynamics of complex industrial processes. For this reason, a recursive learning algorithm is used here to solve the above optimization problem, so that the subspace matrices Lp, Lu, and Lv can be updated online with the latest data. The recursive learning algorithm with a forgetting factor is as follows:

[0161]

[0162] where, is the parameter matrix at time k, is the data vector at time k, I is the identity matrix, P k is the covariance matrix, g k is the gain vector, and λ is the forgetting factor, which is used to adjust the sensitivity of the algorithm to parameter changes. Generally, 0.95 ≤ λ ≤ 1.

[0163] Finally, using the least - squares algorithm based on recursive learning, the initial prediction model established for the once - through steam generator of the small - scale reactor is:

[0164]

[0165] where, is the first output value, is the parameter matrix, φ is the data vector, represents the subspace matrix, w p 、u f 、w v are data vectors.

[0166] In the process of training the initial prediction model with multiple training samples, if the mean square error between the multiple primary - side outlet temperatures and the multiple secondary - side steam pressures predicted by the initial prediction model is the preset threshold, then the initial prediction model is used as the first prediction model; if the mean square error between the multiple primary - side outlet temperatures and the multiple secondary - side steam pressures predicted by the initial prediction model is not the preset threshold, then retraining is carried out.

[0167] In this embodiment, the internal information of the once - through steam generator is used to achieve high - performance and precise control of the once - through steam generator, ensuring the safe and stable operation of the nuclear reactor.

[0168] In an embodiment of the present application, each of the training samples is processed as follows:

[0169] The primary inlet temperature at the primary side inlet of the collected once-through steam generator, the steam valve opening degree of the collected once-through steam generator, and the relative feed water flow rate at the secondary side inlet of the collected once-through steam generator are sequentially subjected to filtering processing, noise elimination processing, and normalization processing to obtain the primary inlet temperature at the primary side inlet of the once-through steam generator, the steam valve opening degree of the once-through steam generator, and the relative feed water flow rate at the secondary side inlet of the once-through steam generator.

[0170] In this embodiment, data of the once-through steam generator is collected in advance, such as the primary inlet temperature at the primary side inlet of the once-through steam generator of a small nuclear reactor, the steam valve opening degree of the once-through steam generator, the relative feed water flow rate at the secondary side inlet of the once-through steam generator, the primary outlet temperature at the primary side outlet of the once-through steam generator, and the secondary side outlet steam pressure at the secondary side outlet of the once-through steam generator.

[0171] For each training sample: the primary inlet temperature at the primary side inlet of the collected once-through steam generator is sequentially subjected to filtering processing, noise elimination processing, and normalization processing to obtain the primary inlet temperature at the primary side inlet of the once-through steam generator; the steam valve opening degree of the collected once-through steam generator is sequentially subjected to filtering processing, noise elimination processing, and normalization processing to obtain the steam valve opening degree of the once-through steam generator; the relative feed water flow rate at the secondary side inlet of the collected once-through steam generator is sequentially subjected to filtering processing, noise elimination processing, and normalization processing to obtain the relative feed water flow rate at the secondary side inlet of the once-through steam generator.

[0172] The primary outlet temperature at the primary side outlet of the collected once-through steam generator is sequentially subjected to filtering processing, noise elimination processing, and normalization processing to obtain the primary outlet reference temperature at the primary side outlet of the once-through steam generator; the secondary side outlet steam pressure at the secondary side outlet of the collected once-through steam generator is subjected to filtering processing, noise elimination processing, and normalization processing to obtain the secondary side outlet steam reference pressure at the secondary side outlet of the once-through steam generator. Among them, the above filtering processing is interpolation filtering processing, and the noise elimination processing is noise spike filtering processing.

[0173] Through the above processing method, the filtering processing can improve the data quality, the noise elimination processing can remove the noise, retain the useful data, simplify the calculation, reduce the magnitude, and make the data comparable.

[0174] The following is an example of the control method for the once-through steam generator of a nuclear reactor provided by the embodiment of the present application.

[0175] Step 1: Select indicators.

[0176] From the interface boundary conditions of the steam generator with the primary coolant and the steam turbine, the steam generator can be regarded as a four-input and three-output system. That is, the inputs are the primary side inlet temperature, the secondary side inlet feed water temperature, the secondary side inlet feed water flow rate, and the secondary side outlet steam flow rate, and the outputs are the primary side outlet temperature, the secondary side outlet steam temperature, and the secondary side steam pressure of the system. When studying the control system design of the nuclear steam supply system composed of the steam generator and the reactor core, the main concerns are the steam pressure of the steam generator and the primary side outlet temperature. In addition, since the feed water temperature is constant and does not change with power, the primary side inlet temperature, the steam valve opening, and the relative feed water flow rate at the secondary side inlet are used as input variables, and the primary side outlet temperature and the secondary side steam pressure are used as output variables.

[0177] Step 2: Collect data.

[0178] Obtain the historical data of the steam generator system of the small nuclear reactor, including process parameters, controlled variables, control variables, etc. See Figure 2 , and collect the input and output data of the once-through steam generator. For example, collect the primary side inlet temperature at the primary side inlet of the once-through steam generator of the small nuclear reactor, the steam valve opening of the once-through steam generator, the relative feed water flow rate at the secondary side inlet of the once-through steam generator, the primary side outlet temperature at the primary side outlet of the once-through steam generator, and the secondary side outlet steam pressure at the secondary side outlet of the once-through steam generator.

[0179] Step 3: Data preprocessing.

[0180] Perform preprocessing on the obtained data. See Figure 2 , and after filtering, noise elimination, and normalization processing of the above-mentioned collected data, divide the processed data into a test set and a validation set.

[0181] Step 4: Model training.

[0182] Adopt the subspace identification method to establish a prediction model for the steam generator system of the small reactor, update the parameters based on the recursive least squares algorithm with a forgetting factor, use the mean square error MSE as the evaluation index to judge whether the prediction model of the steam generator system of the small reactor meets the requirements. If it meets the requirements, obtain the prediction model of the once-through steam generator (i.e., the first prediction model in the above text), then go to Step 5. If it does not meet the requirements, retrain and execute the step of updating the parameters based on the recursive least squares algorithm with a forgetting factor.

[0183] Step 5: Iterative optimization.

[0184] Obtain the set values at multiple moments of the once-through steam generator; calculate the sum of squares of the errors between the set values at multiple moments and the first output values at multiple moments according to the set values at multiple moments of the once-through steam generator and the first output values at multiple moments; construct the objective function, that is, the performance index, according to the sum of squares of the errors and the sum of squares of the deviations between the control quantities at two adjacent moments among the multiple moments; obtain the maximum and minimum values of the output value of the once-through steam generator set in advance; obtain the maximum and minimum values of the control quantity of the once-through steam generator set in advance; determine the constraint conditions of the objective function according to the maximum and minimum values of the output value of the once-through steam generator and the maximum and minimum values of the control quantity of the once-through steam generator.

[0185] The problem of minimizing the performance index is solved by the CMA-ES algorithm. See Figure 2 , first initialize the parameters, then generate a population through a multi-dimensional normal distribution, use the performance index as the fitness and evaluate it, update the mean vector, covariance matrix and step size, and determine whether the requirements are met, that is, whether it gradually approaches the optimal control quantity increment. If so, finally obtain the optimal control quantity under the condition of meeting the constraints.

[0186] Step 6: Feedback correction.

[0187] Apply the calculated control input to the system and observe the response of the system. If there is a deviation between the system output and the desired trajectory, use the feedback information to adjust the model prediction (that is, in the above text, control the once-through steam generator by using the control quantity of the once-through steam generator to obtain the response value of the once-through steam generator; optimize the first prediction model according to the deviation between the response value of the once-through steam generator and the expected value to obtain the optimized first prediction model, and the optimized first prediction model is used to control the once-through steam generator).

[0188] Aiming at the characteristics of small water capacity and small heat storage capacity of the once-through steam generator, with uncertainty, nonlinearity, dynamic time-variation, etc., considering the utilization of the internal state information of the once-through steam generator, a subspace modeling method based on the recursive least square technique is adopted to accurately describe the nonlinear dynamic time-varying characteristics of the once-through steam generator of the small reactor. A model predictive control method based on the covariance matrix adaptation evolution strategy is adopted to realize the high-performance precise control of the once-through steam generator and ensure the safe and stable operation of the small nuclear reactor. While the established nonlinear dynamic model meets the control design requirements, it can improve the calculation efficiency and reduce the calculation cost. The above predictive control algorithm improves the control performance. It provides an important technical support for the design of the control system of relevant small nuclear reactors and has important engineering application value.

[0189] Figure 3 The structure diagram of the nuclear reactor once-through steam generator control device provided by the embodiment of the present application is shown. As Figure 3 shown, the nuclear reactor once-through steam generator control device 300 includes:

[0190] A prediction module 301, configured to predict the output values of the once-through steam generator at multiple moments according to a first prediction model, and obtain first output values at multiple moments. The first prediction model is obtained by training an initial prediction model with multiple training samples as the input of the initial prediction model of the once-through steam generator, and using the primary side outlet reference temperature of the primary side of the once-through steam generator and the secondary side outlet steam reference pressure of the secondary side of the once-through steam generator as the output of the initial prediction model. Each training sample includes the primary side inlet temperature of the primary side of the once-through steam generator, the steam valve opening of the once-through steam generator, and the relative feed water flow of the secondary side inlet of the once-through steam generator. Each moment corresponds to one first output value, and the first output value includes the predicted primary side outlet temperature of the primary side of the once-through steam generator and the secondary side outlet steam pressure of the secondary side of the once-through steam generator;

[0191] A processing module 302, configured to obtain a control quantity of the once-through steam generator according to the first output values at multiple moments of the once-through steam generator and a pre-configured objective function;

[0192] A control module 303, configured to control the once-through steam generator by using the control quantity of the once-through steam generator.

[0193] In an embodiment of the present application, the processing module 302 includes a first construction sub-module and a processing sub-module;

[0194] The first construction sub-module is configured to construct the constraint conditions of the objective function;

[0195] The processing sub-module is configured to solve the pre-configured objective function according to the constraint conditions and the first output values at multiple moments by using the covariance matrix adaptation evolution strategy, and obtain the control quantity of the once-through steam generator.

[0196] In an embodiment of the present application, the processing module 302 further includes a second construction sub-module;

[0197] A second construction sub-module, configured to obtain set values of the once-through steam generator at multiple moments; calculate the sum of squares of errors between the set values at multiple moments and the first output values at multiple moments according to the set values at multiple moments of the once-through steam generator and the first output values at multiple moments; construct the objective function according to the sum of squares of errors and the sum of squares of deviations between control quantities at two adjacent moments among the multiple moments.

[0198] In an embodiment of the present application, the first construction sub-module is specifically configured to obtain the maximum value and the minimum value of the output value of the once-through steam generator set in advance; obtain the maximum value and the minimum value of the control quantity of the once-through steam generator set in advance; determine the constraint conditions of the objective function according to the maximum value and the minimum value of the output value of the once-through steam generator and the maximum value and the minimum value of the control quantity of the once-through steam generator.

[0199] In an embodiment of the present application, the once-through steam generator control device of the nuclear reactor further includes an optimization module;

[0200] The control module is specifically configured to control the once-through steam generator by using the control quantity of the once-through steam generator to obtain a response value of the once-through steam generator;

[0201] The optimization module is configured to optimize the first prediction model according to the response value of the once-through steam generator to obtain an optimized first prediction model, and the optimized first prediction model is used to control the once-through steam generator.

[0202] In an embodiment of the present application, the optimization module is specifically configured to obtain an expected value of the once-through steam generator; calculate a deviation between the response value of the once-through steam generator and the expected value; optimize the first prediction model by using the deviation to obtain an optimized first prediction model.

[0203] In an embodiment of the present application, the once-through steam generator control device of the nuclear reactor further includes a training module;

[0204] The training module is configured to determine an initial prediction model of the once-through steam generator by using a subspace identification method; during the process of training the initial prediction model by using a plurality of the training samples, if the mean square error between a plurality of primary side outlet temperatures and a plurality of secondary side steam pressures predicted by the initial prediction model is a preset threshold, then use the initial prediction model as the first prediction model.

[0205] In one embodiment of the present application, the training module is specifically configured to construct a state equation of a multi-input multi-output once-through steam generator; and process the state equation of the multi-input multi-output once-through steam generator by using a subspace identification method to obtain an initial prediction model of the once-through steam generator.

[0206] In one embodiment of the present application, the once-through steam generator control device of a nuclear reactor further includes a data processing module;

[0207] The data processing module is configured to perform filtering processing, noise rejection processing, and normalization processing on the primary side inlet temperature of the once-through steam generator collected, the steam valve opening degree of the once-through steam generator collected, and the relative feed water flow rate of the secondary side inlet of the once-through steam generator collected in sequence, to obtain the primary side inlet temperature of the once-through steam generator, the steam valve opening degree of the once-through steam generator, and the relative feed water flow rate of the secondary side inlet of the once-through steam generator.

[0208] The once-through steam generator control device provided by the embodiments of the present application can implement each process implemented by the foregoing embodiments of the once-through steam generator control method and achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0209] Figure 4 The hardware structure diagram of the electronic device provided by the embodiments of the present application is shown.

[0210] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0211] Specifically, the foregoing processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0212] The memory 402 may include a mass memory for data or instructions. By way of example and not limitation, the memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disc, a magneto-optical disc, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In a suitable case, the memory 402 may include a removable or non-removable (or fixed) medium. In a suitable case, the memory 402 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 402 is a non-volatile solid state memory.

[0213] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect or the second aspect of the present disclosure.

[0214] The processor 401 realizes any one of the information auditing methods in the above embodiments by reading and executing the computer program instructions stored in the memory 402.

[0215] In one example, the electronic device may further include a communication interface 403 and a bus 410. Among them, as Figure 4 shown, the processor 401, the memory 402, and the communication interface 403 are connected through the bus 410 to complete communication with each other.

[0216] The communication interface 403 is mainly used to implement communication between various modules, devices, units, and / or devices in the embodiments of the present application.

[0217] The bus 410 includes hardware, software, or both, and couples the components of the information auditing method or the verification device to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses or a combination of two or more of these. In a suitable case, the bus 410 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0218] In addition, in combination with the nuclear reactor once-through steam generator control method in the above embodiments, the embodiments of the present application can provide a computer storage medium to implement. Computer program instructions are stored on the computer storage medium; when the computer program instructions are executed by a processor, any one of the nuclear reactor once-through steam generator control methods in the above embodiments is realized.

[0219] In addition, embodiments of the present application may be implemented by providing a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device implements any one of the nuclear reactor DC steam generator control methods in the above embodiments.

[0220] It should be clear that the present application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described as examples. However, the method process of the present application is not limited to the specific steps described. Those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present application.

[0221] The functional blocks shown in the above structural block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments for performing the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via a data signal carried in a carrier wave. A "machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical discs, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0222] It should also be noted that the exemplary embodiments mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps. That is, the steps can be executed in the order mentioned in the embodiments, can be different from the order in the embodiments, or several steps can be executed simultaneously.

[0223] As described above with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block in the flowchart and / or block diagram, and the combination of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / actions specified in one or more blocks of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It should also be understood that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can also be implemented by dedicated hardware that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0224] As described above, the above is only the specific implementation manner of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. It should be understood that the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered by the protection scope of the present application.

Claims

1. A control method for a direct current steam generator of a nuclear reactor, characterized in that, The method includes: Predicting the output values of the once-through steam generator at multiple moments according to a first prediction model to obtain first output values at multiple moments, where the first prediction model is obtained by training an initial prediction model of the once-through steam generator with multiple training samples as inputs and the reference temperature of the primary side outlet and the reference steam pressure of the secondary side outlet of the once-through steam generator as outputs; each training sample includes the temperature of the primary side inlet of the once-through steam generator, the opening of the steam valve of the once-through steam generator, and the relative feed water flow of the secondary side inlet of the once-through steam generator; each moment corresponds to one first output value, and the first output value includes the predicted temperature of the primary side outlet and the steam pressure of the secondary side outlet of the once-through steam generator. Obtaining a control quantity of the once-through steam generator according to the first output values at multiple moments of the once-through steam generator and a preconfigured objective function. Controlling the once-through steam generator by using the control quantity of the once-through steam generator.

2. The control method of the direct current steam generator of the nuclear reactor according to claim 1, characterized in that The obtaining a control quantity of the once-through steam generator according to the first output values at multiple moments of the once-through steam generator and a preconfigured objective function includes: Constructing constraint conditions of the objective function. Using a covariance matrix adaptation evolution strategy to solve the preconfigured objective function according to the constraint conditions and the first output values at multiple moments to obtain the control quantity of the once-through steam generator.

3. The control method of the direct current steam generator of the nuclear reactor according to claim 2, wherein The objective function is constructed in the following manner: Obtaining set values of the once-through steam generator at multiple moments. Calculating the sum of squares of errors between the set values at multiple moments and the first output values at multiple moments according to the set values at multiple moments of the once-through steam generator and the first output values at multiple moments. Constructing the objective function according to the sum of squares of errors and the sum of squares of deviations between the control quantities at two adjacent moments among the multiple moments.

4. The control method of the direct current steam generator of the nuclear reactor according to claim 2, characterized in that, The constructing constraint conditions of the objective function includes: Obtaining the maximum and minimum values of the output values of the pre-set once-through steam generator. Obtaining the maximum and minimum values of the control quantity of the pre-set once-through steam generator. Determining the constraint conditions of the objective function according to the maximum and minimum values of the output values of the once-through steam generator and the maximum and minimum values of the control quantity of the once-through steam generator.

5. The control method of the direct current steam generator of a nuclear reactor according to claim 1, characterized in that, The controlling the once-through steam generator by using the control quantity of the once-through steam generator includes: Controlling the once-through steam generator by using the control quantity of the once-through steam generator to obtain a response value of the once-through steam generator. Optimizing the first prediction model according to the response value of the once-through steam generator to obtain an optimized first prediction model, and the optimized first prediction model is used to control the once-through steam generator.

6. The control method of the nuclear reactor once-through steam generator according to claim 5, characterized in that Optimizing the first prediction model according to the response value of the once-through steam generator to obtain an optimized first prediction model includes: Obtaining the expected value of the once-through steam generator; Calculating the deviation between the response value of the once-through steam generator and the expected value; Optimizing the first prediction model by using the deviation to obtain an optimized first prediction model.

7. The control method of the direct current steam generator of a nuclear reactor according to claim 1, wherein Before predicting the output values of the once-through steam generator at multiple moments according to the first prediction model to obtain the first output values at multiple moments, the method further includes: Determining the initial prediction model of the once-through steam generator by using the subspace identification method; During the process of training the initial prediction model by using multiple training samples, if the mean square error between the multiple primary side outlet temperatures and the multiple secondary side steam pressures predicted by the initial prediction model is a preset threshold, then taking the initial prediction model as the first prediction model.

8. The control method of the direct current steam generator of a nuclear reactor according to claim 7, wherein Determining the initial prediction model of the once-through steam generator by using the subspace identification method includes: Constructing the state equation of the once-through steam generator with multiple inputs and multiple outputs; Processing the state equation of the once-through steam generator with multiple inputs and multiple outputs by using the subspace identification method to obtain the initial prediction model of the once-through steam generator.

9. The control method of the direct current steam generator of the nuclear reactor according to claim 1, characterized in that, Performing the following processing on each training sample: Successively performing filtering processing, noise rejection processing, and normalization processing on the primary side inlet temperature of the once-through steam generator collected, the steam valve opening of the once-through steam generator collected, and the relative feed water flow rate of the secondary side inlet of the once-through steam generator collected to obtain the primary side inlet temperature of the once-through steam generator at the primary side inlet, the steam valve opening of the once-through steam generator, and the relative feed water flow rate of the secondary side inlet of the once-through steam generator.

10. A control device for a direct current steam generator of a nuclear reactor, characterized in that, The device includes: A prediction module, configured to predict the output values of the once-through steam generator at multiple moments according to the first prediction model to obtain the first output values at multiple moments, where the first prediction model is obtained by training the initial prediction model by using multiple training samples as the input of the initial prediction model of the once-through steam generator and using the primary side outlet reference temperature of the once-through steam generator at the primary side outlet and the secondary side outlet steam reference pressure of the once-through steam generator at the secondary side outlet as the output of the initial prediction model; each training sample includes the primary side inlet temperature of the once-through steam generator at the primary side inlet, the steam valve opening of the once-through steam generator, and the relative feed water flow rate of the secondary side inlet of the once-through steam generator; each moment corresponds to one first output value, and the first output value includes the predicted primary side outlet temperature of the once-through steam generator at the primary side outlet and the secondary side outlet steam pressure of the once-through steam generator at the secondary side outlet; A processing module, configured to obtain the control quantity of the once-through steam generator according to the first output values at multiple moments of the once-through steam generator and a pre-configured objective function; A control module, configured to control the once-through steam generator by using the control quantity of the once-through steam generator.

Images