Nuclear reactor core control method, apparatus, and electronic device

Abstract

The application provides a nuclear reactor control method and device and electronic equipment, and relates to the field of nuclear control. The method comprises the following steps: in the case that a plurality of first predicted working condition parameter groups corresponding to a plurality of first control parameter groups are predicted based on a reactor core working condition prediction model, the plurality of first predicted working condition parameter groups are taken as an initialization population; based on a deviation value of each individual in the initialization population, iterative processing of adaptive evaluation and dominant population generation is performed to obtain an optimal individual; and the first control parameter corresponding to the optimal individual is used for reactor core control. Through the above method, it is not necessary to continuously adjust the control strategy and calculate the control result, so that the staff can quickly and efficiently obtain an ideal reactor core control strategy, and the first control parameter in the first control parameter group corresponding to the optimal individual representing the reactor core control strategy is used for reactor core control.

Description

Technical Field

[0001] This invention relates to the field of nuclear control, and more specifically to a method, apparatus, and electronic equipment for controlling the core of a nuclear reactor. Background Technology

[0002] Currently, in the operation of nuclear power plants, core control requires specific strategies to ensure the stable operation of the reactor core. Common control methods include, but are not limited to, adjusting boron concentration and inserting control rods. However, core control is still largely performed by staff based on their experience and the current core condition. Sometimes, staff will perform theoretical calculations based on the core's operating history to obtain a reference control strategy, but this process requires staff to continuously adjust the control strategy and perform calculations to meet operational requirements, making the search process cumbersome. Summary of the Invention

[0003] The purpose of this application is to provide a nuclear reactor core control method, apparatus, and electronic equipment, enabling personnel to quickly and efficiently obtain the ideal core control strategy.

[0004] In a first aspect, embodiments of this application provide a method for controlling a nuclear reactor core, the method comprising:

[0005] When multiple first predicted operating condition parameter groups corresponding to multiple first control parameter groups are predicted based on the core operating condition prediction model, the multiple first predicted operating condition parameter groups are used as an initial population. Each first control parameter group includes at least one first control parameter corresponding to at least one time step, each first predicted operating condition parameter group includes at least one first predicted operating condition parameter corresponding to at least one time step, each first predicted operating condition parameter group corresponds to an individual in the initial population, and the factor in the individual is the first control parameter corresponding to each time step in the first control parameter group.

[0006] Based on the deviation value of each individual in the initial population, an iterative process of adaptive evaluation and dominant population generation is performed to obtain the optimal individual. The deviation value is associated with the difference between each of the first predicted working condition parameters and the preset initial working condition parameters in the first predicted working condition parameter group corresponding to the individual. The dominant population generation is used to generate a dominant population based on the results of the adaptive evaluation, and the optimal individual is an individual in the dominant population generated when the iterative process meets the iteration termination condition.

[0007] Core control is performed using the first control parameters corresponding to the optimal individual.

[0008] In some implementations, the adaptability assessment includes:

[0009] Determine the difference between each of the first predicted operating condition parameters and the initial operating condition parameters in the first predicted operating condition parameter group corresponding to each individual;

[0010] The deviation value of each individual is determined based on all the differences of each individual.

[0011] In some embodiments, before determining the deviation value of each of the individuals based on all the differences of each of the individuals, the method further includes:

[0012] Determine whether each of the aforementioned differences meets the error requirements;

[0013] If the difference does not meet the error requirement, the difference will be processed to differentiate it.

[0014] The differential processing is used to prevent individuals with a given difference from participating in the generation of the dominant population.

[0015] In some implementations, the generation of the dominant population includes:

[0016] Based on the deviation value of each individual, determine the probability of exclusion for each individual;

[0017] Based on the exclusion probability of each individual, individual exclusion is performed among all individuals to obtain multiple elite individuals;

[0018] The dominant population is obtained by performing individual factor mutations and factor crossovers between the multiple elite individuals.

[0019] In some embodiments, before using the plurality of first predicted operating condition parameter sets corresponding to the plurality of first control parameter sets as the initial population, when multiple sets of first predicted operating condition parameter sets are predicted based on the core operating condition prediction model, the method further includes:

[0020] Using a second set of control parameters for multiple operating conditions to be simulated, xenon oscillation simulation processing is performed to obtain simulation data for each operating condition to be simulated. The multiple operating conditions to be simulated are generated based on a random strategy. Each set of simulation data includes a second set of control parameters and a second set of predicted operating condition parameters. Each second set of control parameters includes at least one second control parameter corresponding to at least one time step, and each second set of predicted operating condition parameters includes at least one second predicted operating condition parameter corresponding to at least one time step.

[0021] Using the second predicted operating condition parameter group in each of the simulation data, the second control parameter group in the simulation data is labeled to generate training samples corresponding to the simulation data.

[0022] Based on the training samples corresponding to the simulation data of the multiple operating conditions to be simulated, the model to be trained is iteratively trained to obtain the core operating condition prediction model.

[0023] In some embodiments, the model to be trained is a long short-term memory network model. Before iteratively training the model to be trained based on training samples corresponding to the simulation data of the plurality of simulated operating conditions to obtain the core operating condition prediction model, the method further includes:

[0024] The parameters to be added are added to the training samples, and together with the second control parameter group in the training samples, they serve as the annotation objects for the second predicted working condition parameter group in the training samples. The parameters to be added include...

[0025] The preset initial operating parameters.

[0026] In some implementations, each set of simulated data includes parameters relating to a first number of time steps, and each training sample includes parameters relating to a second number of time steps, wherein the first number is greater than the second number.

[0027] The step of using the second predicted operating condition parameter group in each of the simulated data to annotate the second control parameter group in the simulated data and generate training samples corresponding to the simulated data includes:

[0028] Among the time steps involved in the parameters included in the simulation data, multiple sets of the second number of time steps are selected, starting from any time step.

[0029] Based on the second control parameters corresponding to the second number of time steps in each group, generate samples to be labeled;

[0030] Based on the second predicted operating condition parameters corresponding to the second number of time steps in each group, labeled samples are generated.

[0031] The corresponding unlabeled samples are labeled using the labeled samples to generate training samples corresponding to the simulated data.

[0032] In some implementations, the parameter type of the first control parameter includes:

[0033] Core control power type parameters, core control rod position type parameters, and time step size.

[0034] Secondly, embodiments of this application provide a nuclear reactor core control device, the device comprising:

[0035] The initial population determination module is used to use the multiple first predicted operating condition parameter groups as the initial population when multiple first predicted operating condition parameter groups corresponding to multiple first control parameter groups are predicted based on the core operating condition prediction model. Each first control parameter group includes at least one first control parameter corresponding to at least one time step, each first predicted operating condition parameter group includes at least one first predicted operating condition parameter corresponding to at least one time step, each first predicted operating condition parameter group corresponds to an individual in the initial population, and the factor in the individual is the first control parameter corresponding to each time step in the first control parameter group.

[0036] The optimal individual acquisition module is used to perform adaptive evaluation and iterative processing of dominant population generation based on the deviation value of each individual in the initial population to obtain the optimal individual. The deviation value is associated with the difference between each of the first predicted working condition parameters and the preset initial working condition parameters in the first predicted working condition parameter group corresponding to the individual. The dominant population generation is used to generate a dominant population based on the result of the adaptive evaluation, and the optimal individual is an individual in the dominant population generated when the iterative processing meets the iteration termination condition.

[0037] The core control module is used to perform core control using the first control parameters corresponding to the optimal individual.

[0038] A third aspect of this application provides an electronic device, comprising:

[0039] The memory is configured to store instructions; and

[0040] The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the nuclear reactor core control method provided in the first aspect of this application.

[0041] In this embodiment, multiple sets of first control parameters, representing various core control strategies, are used as the initial population in a genetic algorithm. A core condition prediction model predicts multiple first predicted operating parameters corresponding to these sets. The first predicted operating parameters from these sets are then used to iteratively evaluate the adaptability of corresponding individuals in the initial population and generate a dominant population, resulting in an optimal individual. This optimal individual represents the ideal core control strategy obtained through the genetic algorithm's iteration. Thus, there is no need to continuously adjust the control strategy and calculate the control results, allowing staff to quickly and efficiently obtain the ideal core control strategy and utilize the first control parameters from the first set of first control parameters corresponding to the optimal individual representing that strategy for core control. Attached Figure Description

[0042] Figure 1This is a schematic flowchart of the nuclear reactor core control method provided in the embodiments of this application;

[0043] Figure 2 This is a schematic diagram of the structure of the nuclear reactor core control device provided in the embodiments of this application;

[0044] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0046] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0047] The nuclear reactor core control method and apparatus, as well as electronic equipment provided in this application, will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.

[0048] Please see Figure 1 This is a flowchart illustrating a nuclear reactor core control method provided in an embodiment of this application, which is applied to electronic equipment. For example... Figure 1 As shown, the nuclear reactor core control method includes the following steps S100 to S300:

[0049] Step S100: When multiple first predicted operating condition parameter groups corresponding to multiple first control parameter groups are predicted based on the core operating condition prediction model, the multiple first predicted operating condition parameter groups are used as an initialization population. Each first control parameter group includes at least one first control parameter corresponding to at least one time step, each first predicted operating condition parameter group includes at least one first predicted operating condition parameter corresponding to at least one time step, and each first predicted operating condition parameter group corresponds to an individual in the initialization population. The factor in the individual is the first control parameter corresponding to each time step in the first control parameter group.

[0050] The core condition prediction model in this embodiment can predict the core's operating state by receiving a first set of control parameters that characterizes the core control strategy. The core's operating state is characterized by the first set of predicted operating parameters. In other words, the core condition prediction model is used to predict the operating state of the core after it has been controlled according to the core control strategy.

[0051] In the embodiments of this application, the first control parameter group characterizing the core control strategy includes at least one first control parameter corresponding to at least one time step; that is, in the first control parameter group, each time step corresponds to one first control parameter. Those skilled in the art will understand that a time step characterizes a time interval in the core control strategy, and two adjacent time steps are the adjacent time intervals at both ends of the core control strategy. Therefore, each first control parameter in the first control parameter group characterizes the core control strategy within each time step.

[0052] The first predicted operating condition parameter set, which characterizes the operating condition of the reactor core, includes at least one first predicted parameter corresponding to at least one time step. That is, in the first predicted operating condition parameter set, each time step corresponds to one first predicted operating condition parameter. Each first predicted operating condition parameter in the first predicted operating condition parameter set characterizes the operating condition of the reactor core at the end of each time step.

[0053] Electronic devices can generate multiple different sets of first control parameters based on a random strategy, thus generating multiple core control strategies. After predicting multiple sets of first predicted operating parameters corresponding to these sets based on the core operating condition prediction model, each set of first control parameters is treated as an individual. Each first control parameter in the set is a factor that can be crossovered or mutated, and all individuals form an initial population for subsequent iterative processing based on a genetic algorithm and for generating a dominant population.

[0054] For example, the parameter types of the first predicted operating condition parameter may include the core axial power offset (AO) and the core enthalpy rise factor (FDH), and the parameter types of the first control parameter may include the core relative power (P), time step size (T), and the position of the temperature control rod (S). The core control strategy includes three time steps. A first predicted operating condition parameter group can be written as [(AO1, FDH1), (AO2, FDH2), (AO3, FDH3)], and a first control parameter group can be written as [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)]. The electronic device generates multiple [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] with different specific parameter values ​​according to a random strategy. Each [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] is considered an individual, and (P1, T1, S1), (P2, T2, S2), and (P3, T3, S3) are factors within that individual. All [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] constitute an initial population, which is used for subsequent iterative processing based on genetic algorithms and for the generation of dominant populations.

[0055] Step S200: Based on the deviation value of each individual in the initial population, perform adaptive evaluation and iterative processing for dominant population generation to obtain the optimal individual. The deviation value is associated with the difference between each first predicted working condition parameter and the preset initial working condition parameter in the first predicted working condition parameter group corresponding to the individual. Dominant population generation is used to generate a dominant population based on the results of adaptive evaluation, and the optimal individual is the individual in the dominant population generated when the iterative processing meets the iteration termination condition.

[0056] The electronic device uses multiple sets of first predicted operating condition parameters to adaptively evaluate the corresponding multiple sets of first control parameters, and performs iterative processing to generate a dominant population based on the adaptive evaluation results, until the iteration termination condition is met, so as to obtain the optimal individual in the dominant population at the time of iteration termination.

[0057] In this embodiment of the application, when performing adaptive evaluation using multiple sets of first predicted operating condition parameters, the electronic device needs to determine the deviation value of each individual. The determination of the deviation value involves the difference between each first predicted operating condition parameter and the preset initial operating condition parameter in the individual.

[0058] For example, during the execution of the genetic algorithm, the electronic device first needs to perform an fitness assessment on each individual in the initial population, that is, [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] with different specific parameter values.

[0059] For a single [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)], the adaptability assessment, i.e., the determination of the deviation value, requires the use of [(AO1, FDH1), (AO2, FDH2), (AO3, FDH3)] corresponding to the [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] predicted by the core operating condition prediction model. The adaptability assessment also utilizes the preset initial operating condition parameters of the core already existing in the database. The adaptability assessment is correlated with the difference between [(AO1, FDH1), (AO2, FDH2), (AO3, FDH3)] and the preset initial operating condition parameters. Those skilled in the art will understand that the parameter types of the preset initial operating condition parameters are the same as those of the first preset operating condition parameters, including the initial axial power offset (AO0) of the core and the initial enthalpy rise factor (FDH0) of the core. The adaptive assessment involves the difference between the axial power offset and enthalpy rise factor at each time step in an individual and the initial axial power offset and initial enthalpy rise factor. All the differences of an individual can be expressed as: [(AO1-AO0, FDH1-FDH0), (AO2-AO0, FDH2-FDH0), (AO3-AO0, FDH3-FDH0)].

[0060] After the fitness assessment of each [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] is completed, a dominant population is generated based on the fitness assessment results, i.e., an iterative update of all individuals is performed. The dominant population obtained after the iteration is then subjected to fitness assessment and dominant population generation again, i.e., iteration continues until the iteration termination condition is met, obtaining the optimal individual corresponding to [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)]. Those skilled in the art will understand that in each iteration, the first predicted operating condition parameters corresponding to each individual need to be predicted using the core operating condition prediction model as the basis for fitness assessment.

[0061] Step S300: Perform core control using the first control parameters corresponding to the optimal individual.

[0062] The first set of control parameters corresponding to the optimal individual represents the ideal core control strategy obtained by the genetic algorithm iteration. The electronic equipment can then use the first control parameters in the first set of control parameters corresponding to the optimal individual to perform core control.

[0063] For example, the first control parameters corresponding to the optimal individual are [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)]. The staff can use these first control parameters as control strategies to control the relative power of the reactor core, the time step size, and the position of the temperature control rods.

[0064] Through steps S100-S300, multiple sets of first control parameters, representing various core control strategies, are used as the initial population in the genetic algorithm. Multiple first predicted operating parameters, corresponding to these sets of first control parameters, are predicted using the core operating condition prediction model. The first predicted operating parameters from these sets are then used to iteratively evaluate the fitness of the corresponding individuals in the initial population and generate a dominant population, ultimately obtaining the optimal individual. This optimal individual represents the ideal core control strategy obtained through the genetic algorithm's iteration. In this way, there is no need to constantly adjust the control strategy and calculate the control results, allowing staff to quickly and efficiently obtain the ideal core control strategy and use the first control parameters from the first control parameter set corresponding to the optimal individual representing that strategy for core control.

[0065] In some implementations, the parameter type of the first control parameter may include at least one of the following:

[0066] Core control power type parameters, core control rod position type parameters, and time step size.

[0067] The first control parameter can include at least one of the following: core control power type parameters, core control rod position type parameters, and time step size. Core control power type parameters include the relative power of the core and the burnup of the core, while core control rod position type parameters include the position of the temperature control rod and the total position of the power control rods. Operators can adaptively select parameters during the training phase of the core operating condition prediction model, based on the implementation scenario or control requirements of the control strategy and the network structure type of the core operating condition prediction model.

[0068] In some implementations, the parameter type of the first predicted operating condition parameter may include at least one of the following:

[0069] The axial power offset of the core, the enthalpy rise factor of the core, the hot spot factor of the core, and the boron concentration of the core.

[0070] The parameter types for the first predicted operating condition can include at least one of the following: core enthalpy rise factor, core hotspot factor, and core boron concentration. During the training phase of the core operating condition prediction model, personnel can select adaptive parameters based on the implementation scenario or control requirements of the control strategy and the network structure type of the core operating condition prediction model.

[0071] In some implementations, the iteration termination condition can be that the number of iterations reaches a preset threshold, or that the deviation value of a certain individual in the generated dominant population reaches a preset threshold.

[0072] In some implementations, the adaptation assessment may include:

[0073] Determine the difference between each first predicted working condition parameter and the initial working condition parameter in the first predicted working condition parameter group corresponding to each individual;

[0074] The deviation value of each individual is determined based on all the differences among the individuals.

[0075] When conducting an adaptability assessment, the electronic device first determines the difference between each first predicted operating condition parameter in the first predicted operating condition parameter group corresponding to each individual and the initial operating condition parameter. Then, it determines the deviation value of each individual based on all the differences of each individual. The deviation value can be determined by selecting the absolute value of the largest difference among all the differences of an individual as the deviation value of that individual, or by the sum of the absolute values ​​of all the differences of an individual.

[0076] The goal of selecting, iterating, and optimizing the core control strategy in this application embodiment is to maintain the first predicted operating condition parameter at a relatively stable level at each time step, that is, to minimize the difference between the first predicted operating condition parameter and the initial operating condition parameter. Therefore, if the deviation value is defined as the absolute value of the largest absolute value among the differences corresponding to each time step of an individual, then this absolute value represents the maximum difference between the first predicted operating condition parameter and the initial operating condition parameter in the first predicted operating condition parameter group corresponding to that individual. If the deviation value is defined as the sum of the absolute values ​​of all differences for an individual, then this sum of the absolute values ​​of all differences represents the overall difference between the first predicted operating condition parameter and the initial operating condition parameter in the first predicted operating condition parameter group corresponding to that individual. It can be seen that, under the adaptive evaluation method provided in this application embodiment, the smaller the deviation value, the better the control strategy corresponding to that individual. The optimal individual is the one with the best fitness evaluation performance in the dominant population at the end of the iteration, that is, the individual with the smallest deviation value.

[0077] For example, the differences between each first predicted operating condition parameter in the first predicted operating condition parameter group corresponding to an individual and the initial operating condition parameter are represented as [(AO1-AO0, FDH1-FDH0), (AO2-AO0, FDH2-FDH0), (AO3-AO0, FDH3-FDH0)]. The electronic device first takes the absolute value of all the differences in the individual. For ease of description, the [(AO1-AO0, FDH1-FDH0), (AO2-AO0, FDH2-FDH0), (AO3-AO0, FDH3-FDH0)] after taking the absolute value is simplified to [(d1, e1), (d2, e2), (d3, e3)], and set as: k1 = d1 + e1, k2 = d2 + e2, k3 = d3 + e3. If the deviation value is determined as the sum of the absolute values ​​of all the differences in the individual, then the deviation value K of the individual is: K = k1 + k2 + k3.

[0078] In some implementations, before determining the deviation value of each individual based on all the differences among the individuals, the method may further include:

[0079] Determine whether each difference meets the error requirements;

[0080] If the difference does not meet the error requirements, the difference will be processed to differentiate it.

[0081] The differential treatment is used to prevent individuals with a given difference from participating in the generation of a dominant population.

[0082] Sometimes, the difference between an individual's first predicted operating condition parameter and its initial operating condition parameter is significant. In such cases, the control strategy for that individual cannot be selected, and the individual, as a weaker one, cannot participate in the generation of a dominant population. Therefore, before determining the deviation value of each individual, it is possible to first determine whether each difference meets the error requirement. This determination can be based on the relationship between the absolute value of each difference and a preset error threshold. If the absolute value of a difference is greater than the preset error threshold, then that difference does not meet the error requirement and needs to be differentiated. Differentiation processing can be achieved by adding a very large number to the absolute value of the difference, so that the deviation value of the individual corresponding to that difference reaches a level that prevents it from participating in the generation of a dominant population.

[0083] For example, the absolute value of the difference between each first predicted operating condition parameter in the first predicted operating condition parameter group corresponding to an individual and the initial operating condition parameter is represented as [(d1, e1), (d2, e2), (d3, e3)]. If e1 is greater than a preset error threshold, i.e., e1 is added with a very large value, the specific size of which can be adaptively determined according to the parameter type of the first predicted operating condition parameters and the optimization requirements of the genetic algorithm. In this way, the deviation value of the individual is added with a very large value. Since the generation of the dominant population needs to be based on the results of the fitness assessment, the inferior individual cannot participate in the generation of the dominant population, and its factors will not be passed on to the next generation of the dominant population.

[0084] In some implementations, dominant population generation may include:

[0085] Based on the deviation value of each individual, determine the probability of each individual being excluded;

[0086] Based on the probability of each individual being excluded, individual exclusion is performed among all individuals to obtain multiple elite individuals;

[0087] By utilizing multiple elite individuals to undergo individual mutations and crossovers, a dominant population can be obtained.

[0088] The generation of a dominant population requires first identifying elite individuals that perform well in the fitness assessment. The electronic device determines the probability of exclusion for each individual based on its deviation value; the smaller the deviation value, the better the individual's performance in the fitness assessment, and the lower the probability of exclusion should be. For example, the probability of exclusion can be set as K / K. s K is the individual's deviation value, K s The sum of the deviation values ​​of all individuals at present.

[0089] The electronic device then uses a roulette wheel method to exclude individuals from all individuals based on their exclusion probability, resulting in multiple elite individuals. These elite individuals undergo individual factor mutation and factor crossover to obtain new individuals, forming a dominant population. The number of individuals in the dominant population is the same as the number of individuals before the exclusion process.

[0090] It is worth noting that when performing individual factor variation, that is, when changing the first control parameter corresponding to an individual, the range of variation of the first control parameter can be set according to the parameter type of the first control parameter.

[0091] In some implementations, when multiple sets of first predicted operating condition parameter sets corresponding to multiple sets of first control parameter sets are predicted based on the core operating condition prediction model, before using the multiple sets of first predicted operating condition parameter sets as the initial population, the method may further include:

[0092] Using a set of second control parameters for multiple operating conditions to be simulated, xenon oscillation simulation is performed to obtain simulation data for each operating condition to be simulated. The multiple operating conditions to be simulated are generated based on a random strategy. Each simulation data includes a set of second control parameters and a set of second predicted operating condition parameters. Each set of second control parameters includes at least one second control parameter corresponding to at least one time step, and each set of second predicted operating condition parameters includes at least one second predicted operating condition parameter corresponding to at least one time step.

[0093] Using the second predicted working condition parameter group in each simulation data, the second control parameter group in the simulation data is labeled to generate training samples corresponding to the simulation data;

[0094] Based on training samples corresponding to simulation data of multiple operating conditions to be simulated, the model to be trained is iteratively trained to obtain a core operating condition prediction model.

[0095] For training the core operating condition prediction model, operators can use a computer to calculate and determine the training samples for the model through xenon oscillation simulation. First, the electronic equipment can generate multiple different sets of second control parameters according to a random strategy, thus generating multiple core control strategies. Those skilled in the art will understand that each set of second control parameters also includes at least one second control parameter corresponding to at least one time step, and the parameter types included in the second control parameters are the same as those included in the first control parameters.

[0096] The electronic device uses multiple sets of second control parameters to perform xenon oscillation simulation processing to obtain simulation data for each set of second control parameters. The simulation data includes a set of second predicted operating condition parameters corresponding to the second control parameter set. Those skilled in the art will understand that each set of second predicted operating condition parameters also includes at least one second predicted operating condition parameter corresponding to at least one time step, and the parameter types included in the second control parameters are the same as those included in the first predicted operating condition parameters.

[0097] The simulation data also includes a second set of control parameters used for xenon oscillation simulation processing.

[0098] For example, similar to the first control parameter and the first predicted operating condition parameter, the parameter type of the second predicted operating condition parameter is axial power offset. The parameter type of the second control parameter, in addition to the relative power of the core, may also include the time step size and the position of the temperature control rod. The core control strategy includes three time steps. A second predicted operating condition parameter set can be written as [(AO1, FDH1), (AO2, FDH2), (AO3, FDH3)], and a second control parameter set can be written as [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)]. The electronic equipment generates multiple [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] with different specific parameter values ​​according to a random strategy, for xenon oscillation simulation processing, to obtain simulation data for each [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)]. The simulation data includes [(AO1,FDH1), (AO2,FDH2), (AO3,FDH3)] corresponding to [(P1,T1,S1), (P2,T2,S2), (P3,T3,S3)], and also includes [(P1,T1,S1), (P2,T2,S2), (P3,T3,S3)] itself.

[0099] Using the second predicted operating condition parameter group in the obtained simulation data, the second control parameter group in the simulation data is labeled to generate training samples for model training. The training samples corresponding to the simulation data of multiple operating conditions to be simulated are used to iteratively train the model to be trained in order to obtain the core operating condition prediction model.

[0100] In some implementations, the model to be trained is a long short-term memory network model. Before iteratively training the model to be trained based on training samples corresponding to multiple simulated operating conditions to obtain a core operating condition prediction model, the method may further include:

[0101] The parameters to be added are added to the training samples, and together with the second control parameter group in the training samples, they serve as the annotation objects for the second predicted working condition parameter group in the training samples. The parameters to be added may include preset initial working condition parameters.

[0102] The network structure of the model to be trained, i.e., the core operating condition prediction model, can be a Long Short-Term Memory (LSTM) network. Because LSTM networks are sensitive to time-related data and excel at capturing long-term dependencies between features, the labeled parts of the training samples are suitable for adding initial features during training to enhance model accuracy. Therefore, data related to the core control strategy can be added to the training samples; this data serves as the parameters to be added. The parameters to be added are selected from the database as preset initial operating condition parameters for the core.

[0103] For example, the preset initial operating condition parameters may include at least one of the following parameter types: temperature control rod position, reactor effective multiplication factor, axial power offset, core enthalpy rise factor, core hot spot factor, core boron concentration, and core burnup.

[0104] Those skilled in the art will understand that when the network structure of the core condition prediction model is a network structure other than the long short-term memory network, the types of parameters to be added can be adaptively adjusted according to the network structure type of the core condition prediction model.

[0105] In some implementations, each simulated data set includes parameters involving a first number of time steps, and each training sample includes parameters involving a second number of time steps, where the first number is greater than the second number.

[0106] Using the second predicted operating condition parameter set from each simulation data set, the second control parameter set in the simulation data is labeled to generate training samples corresponding to the simulation data, which may include:

[0107] In the time steps involved in the parameters included in the simulation data, multiple sets of a second number of time steps are selected, starting from any time step.

[0108] The set of second control parameters corresponding to the second number of time steps in each group is used as a sample to be labeled.

[0109] The set of second predicted working condition parameters corresponding to each second number of time steps is compiled into a labeled sample;

[0110] The corresponding unlabeled samples are labeled using each labeled sample to generate training samples that correspond to the simulated data.

[0111] To expand the number of training samples, during xenon oscillation simulation, the number of time steps involved in the parameters of the simulation data can be set to be greater than the number of time steps required for the control strategy, i.e., greater than the number of time steps involved in the parameters of the training samples. In this embodiment, the parameters included in the simulation data involve a first number of time steps, and the parameters included in the training samples involve a second number of time steps.

[0112] In this way, starting from any time step in the simulation data, multiple sets of a second number of time steps can be selected. The second control parameters corresponding to each set of a second number of time steps can be grouped into a sample to be labeled, and the second predicted operating condition parameters corresponding to each set of a second number of time steps can be grouped into a labeled sample. Finally, the labeled samples are used to label the corresponding samples to be labeled, generating training samples corresponding to the simulation data. This allows the number of training samples to be greater than the number of simulation data points, thus expanding the number of training samples and giving the trained core operating condition prediction model stronger generalization ability.

[0113] For example, the first quantity is 4, the second quantity is 3, and the second control parameter group included in the simulation data can be represented as [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3), (P4, T4, S4)]. In [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3), (P4, T4, S4)], starting from any time step, multiple groups of second control parameters involving 3 time steps are selected. The selected groups of second control parameters involving 3 time steps are: [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] and [(P2, T2, S2), (P3, T3, S3), (P4, T4, S4)].

[0114] Correspondingly, the second predicted operating condition parameters selected from the simulation data, which involve three time steps, are: [(AO1, FDH1), (AO2, FDH2), (AO3, FDH3)] and [(AO2, FDH2), (AO3, FDH3), (AO4, FDH4)].

[0115] The first training sample of the simulated data is formed by labeling [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] with [(AO1, FDH1), (AO2, FDH2), (AO3, FDH3)]. The second training sample of the simulated data is formed by labeling [(P2, T2, S2), (P3, T3, S3), (P4, T4, S4)] with [(AO2, FDH2), (AO3, FDH3), (AO4, FDH4)]. In other words, two different training samples are obtained using one simulated data, thus expanding the number of training samples.

[0116] Please see Figure 2 This is a schematic diagram of the structure of a nuclear reactor core control device provided in an embodiment of this application. A second aspect of this application provides a nuclear reactor core control device 10, which includes:

[0117] The initial population determination module is used to use multiple first predicted operating condition parameter groups as an initial population when multiple first predicted operating condition parameter groups corresponding to multiple first control parameter groups are predicted based on the core operating condition prediction model. Each first control parameter group includes at least one first control parameter corresponding to at least one time step, each first predicted operating condition parameter group includes at least one first predicted operating condition parameter corresponding to at least one time step, and each first predicted operating condition parameter group corresponds to an individual in the initial population. The factor in the individual is the first control parameter corresponding to each time step in the first control parameter group.

[0118] The optimal individual acquisition module is used to perform adaptive evaluation and iterative processing of dominant population generation based on the deviation value of each individual in the initial population to obtain the optimal individual. The deviation value is associated with the difference between each first predicted working condition parameter and the preset initial working condition parameter in the first predicted working condition parameter group corresponding to the individual. The dominant population generation is used to generate a dominant population based on the results of the adaptive evaluation, and the optimal individual is the individual in the dominant population generated when the iterative processing meets the iteration termination condition.

[0119] The core control module is used to control the core using the first control parameters corresponding to the optimal individual.

[0120] The nuclear reactor core control device 10 provided in the second aspect of the embodiments of this application can realize the various processes implemented in the above method embodiments and achieve the same beneficial effects. To avoid repetition, it will not be described again here.

[0121] Please see Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. A third aspect of this application provides an electronic device 1000, including a processor 1100 and a memory 1200. The memory 1200 stores machine-executable instructions that can be executed by the processor 1100. The processor 1100 can execute the machine-executable instructions to implement the above-mentioned nuclear reactor core control method.

[0122] A fourth aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, cause the processor to implement the aforementioned nuclear reactor core control method.

[0123] In some embodiments, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the nuclear reactor core control method according to the above embodiments.

[0124] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0126] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0127] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0128] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0129] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0130] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

[0131] Furthermore, various different embodiments of the present invention can be combined in any way, as long as they do not violate the spirit of the present invention, they should also be regarded as the content disclosed by the present invention.

Claims

1. A method for controlling the core of a nuclear reactor, characterized in that, The method includes: When multiple first predicted operating condition parameter groups corresponding to multiple first control parameter groups are predicted based on the core operating condition prediction model, the multiple first predicted operating condition parameter groups are used as an initial population. Each first control parameter group includes at least one first control parameter corresponding to at least one time step, each first predicted operating condition parameter group includes at least one first predicted operating condition parameter corresponding to at least one time step, each first predicted operating condition parameter group corresponds to an individual in the initial population, and the factor in the individual is the first control parameter corresponding to each time step in the first control parameter group. Based on the deviation value of each individual in the initial population, an iterative process of adaptive evaluation and dominant population generation is performed to obtain the optimal individual. The deviation value is associated with the difference between each of the first predicted working condition parameters and the preset initial working condition parameters in the first predicted working condition parameter group corresponding to the individual. The dominant population generation is used to generate a dominant population based on the results of the adaptive evaluation, and the optimal individual is an individual in the dominant population generated when the iterative process meets the iteration termination condition. Core control is performed using the first control parameters corresponding to the optimal individual.

2. The method according to claim 1, characterized in that, The adaptation assessment includes: Determine the difference between each of the first predicted operating condition parameters and the initial operating condition parameters in the first predicted operating condition parameter group corresponding to each individual; The deviation value of each individual is determined based on all the differences of each individual.

3. The method according to claim 2, characterized in that, Before determining the deviation value of each of the individuals based on all the differences of each of the individuals, the method further includes: Determine whether each of the aforementioned differences meets the error requirements; If the difference does not meet the error requirement, the difference will be processed to differentiate it. The differential processing is used to prevent individuals with a given difference from participating in the generation of the dominant population.

4. The method according to claim 1, characterized in that, The generation of the dominant population includes: Based on the deviation value of each individual, determine the probability of exclusion for each individual; Based on the exclusion probability of each individual, individual exclusion is performed among all individuals to obtain multiple elite individuals; The dominant population is obtained by performing individual factor mutations and factor crossovers between the multiple elite individuals.

5. The method according to claim 1, characterized in that, Before using the multiple sets of first predicted operating condition parameter sets corresponding to multiple sets of first control parameter sets as the initial population, the method further includes: Using a second set of control parameters for multiple operating conditions to be simulated, xenon oscillation simulation processing is performed to obtain simulation data for each operating condition to be simulated. The multiple operating conditions to be simulated are generated based on a random strategy. Each set of simulation data includes a second set of control parameters and a second set of predicted operating condition parameters. Each second set of control parameters includes at least one second control parameter corresponding to at least one time step, and each second set of predicted operating condition parameters includes at least one second predicted operating condition parameter corresponding to at least one time step. Using the second predicted operating condition parameter group in each of the simulation data, the second control parameter group in the simulation data is labeled to generate training samples corresponding to the simulation data. Based on the training samples corresponding to the simulation data of the multiple operating conditions to be simulated, the model to be trained is iteratively trained to obtain the core operating condition prediction model.

6. The method according to claim 5, characterized in that, The model to be trained is a Long Short-Term Memory (LSTM) network model. Before iteratively training the model to be trained based on training samples corresponding to the simulation data of the multiple simulated operating conditions to obtain the core operating condition prediction model, the method further includes: The parameter to be added is added to the training sample, and together with the second control parameter group in the training sample, they serve as the annotation objects of the second predicted working condition parameter group in the training sample. The parameter to be added includes the preset initial working condition parameter.

7. The method according to claim 5, characterized in that, Each of the simulated data sets includes parameters involving a first number of time steps, and each of the training samples includes parameters involving a second number of time steps, wherein the first number is greater than the second number. The step of using the second predicted operating condition parameter group in each of the simulated data to annotate the second control parameter group in the simulated data and generate training samples corresponding to the simulated data includes: Among the time steps involved in the parameters included in the simulation data, multiple sets of the second number of time steps are selected, starting from any time step. Based on the second control parameters corresponding to the second number of time steps in each group, generate samples to be labeled; Based on the second predicted operating condition parameters corresponding to the second number of time steps in each group, labeled samples are generated. The corresponding unlabeled samples are labeled using the labeled samples to generate training samples corresponding to the simulated data.

8. The method according to claim 1, characterized in that, The parameter types of the first control parameter include: Core control power type parameters, core control rod position type parameters, and time step size.

9. A nuclear reactor core control device, characterized in that, The device includes: The initial population determination module is used to use the multiple first predicted operating condition parameter groups as the initial population when multiple first predicted operating condition parameter groups corresponding to multiple first control parameter groups are predicted based on the core operating condition prediction model. Each first control parameter group includes at least one first control parameter corresponding to at least one time step, each first predicted operating condition parameter group includes at least one first predicted operating condition parameter corresponding to at least one time step, each first predicted operating condition parameter group corresponds to an individual in the initial population, and the factor in the individual is the first control parameter corresponding to each time step in the first control parameter group. The optimal individual acquisition module is used to perform adaptive evaluation and iterative processing of dominant population generation based on the deviation value of each individual in the initial population to obtain the optimal individual. The deviation value is associated with the difference between each of the first predicted working condition parameters and the preset initial working condition parameters in the first predicted working condition parameter group corresponding to the individual. The dominant population generation is used to generate a dominant population based on the result of the adaptive evaluation, and the optimal individual is an individual in the dominant population generated when the iterative processing meets the iteration termination condition. The core control module is used to perform core control using the first control parameters corresponding to the optimal individual.

10. An electronic device, characterized in that, include: The memory is configured to store instructions; as well as The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the nuclear reactor core control method according to any one of claims 1 to 8.

Images