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 the fitness 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] The present application relates to the field of nuclear control, in particular to a nuclear reactor core control method, device and electronic equipment. BACKGROUND

[0002] At present, in order to ensure the stable operation of the nuclear reactor core, the nuclear power plant needs to control the core according to a specific strategy during operation. The commonly used control methods include but are not limited to adjusting the boron concentration and inserting the control rod. However, the core control is still completed by the staff relying on their own experience according to the current core state. Sometimes, the staff will obtain a reference core control strategy by theoretical calculation according to the core operating history, but this process requires the staff to continuously adjust the core control strategy and calculate the control results to meet the operation requirements, resulting in a tedious search process. SUMMARY

[0003] The purpose of the embodiments of the present application is to provide a nuclear reactor core control method, device and electronic equipment, so that the staff can quickly and efficiently obtain an ideal core control strategy.

[0004] In a first aspect, the embodiments of the present application provide a nuclear reactor core control method, which comprises:

[0005] In the case of predicting a plurality of first predicted operating condition parameter groups corresponding to a plurality of first control parameter groups based on a core operating condition prediction model, taking the plurality of first predicted operating condition parameter groups as an initialization population, wherein each of the first control parameter groups comprises at least one first control parameter corresponding to at least one time step, each of the first predicted operating condition parameter groups comprises at least one first predicted operating condition parameter corresponding to at least one time step, each of the first control parameter groups 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, the parameter type of the first predicted operating condition parameter includes the axial power deviation of the core, and the parameter type of the first control parameter includes the relative power of the core;

[0006] performing an iterative process of fitness evaluation and dominant population generation based on a fitness value of each individual in the initialized population, wherein the fitness value of each individual is determined by a fitness evaluation function involving a difference between an axial power offset corresponding to each time step in the first predicted operating condition parameter set and a reference axial power offset corresponding to each time step, the reference axial power offset being determined according to a corresponding relative power and an axial power offset at full power of the core, the dominant population generation is used to generate a dominant population according to a result of the fitness evaluation, and the optimal individual is an individual in the dominant population generated in a case where the iterative process satisfies an iteration termination condition;

[0007] performing core control by using the first control parameter corresponding to the optimal individual.

[0008] In some embodiments, the fitness value is determined by the following steps:

[0009] determining a reference axial power offset corresponding to each time step;

[0010] determining a difference between an axial power offset corresponding to each time step in the first predicted operating condition parameter set and a reference axial power offset corresponding to each time step, to obtain at least one difference value, different difference values corresponding to different time steps;

[0011] determining the fitness value based on the at least one difference value.

[0012] In some embodiments, the determining the fitness value based on the at least one difference value comprises:

[0013] determining a ratio between an absolute value of each difference value and a corresponding reference axial power offset;

[0014] transforming the difference value based on the ratio corresponding to each difference value, to obtain a transformed value of the at least one difference value;

[0015] determining the fitness value based on the transformed value of the at least one difference value.

[0016] In some embodiments, the transforming the difference value based on the ratio corresponding to each difference value, to obtain a transformed value of the at least one difference value, comprises any one of the following:

[0017] in a case where the ratio corresponding to the difference value is less than a first threshold value, transforming the difference value into a first transformed value;

[0018] in a case where the ratio corresponding to the difference value is less than or equal to a second threshold value and greater than or equal to the first threshold value, transforming the difference value into a second transformed value.

[0019] In a case where the ratio corresponding to the difference value is greater than the second threshold value, the difference value is converted into a third conversion value.

[0020] In some embodiments, the determining the fitness value based on the conversion value of the at least one difference value comprises:

[0021] determining a maximum absolute value in the absolute values of the at least one difference value as a correction amount;

[0022] summing the conversion values of the at least one difference value, and determining the fitness value according to a result of the summation and the correction amount.

[0023] In some embodiments, the generating the dominant population comprises:

[0024] dividing all the individuals into a first population and a plurality of second populations according to the ranking results of all the individuals, wherein the ranking results are obtained based on the fitness values of the individuals, the individuals in the first population are used for performing factor reservation, factor mutation and factor crossover, and the individuals in each of the second populations are used for performing factor mutation and factor crossover;

[0025] performing factor crossover and factor mutation by using the individuals in the first population and the plurality of second populations;

[0026] obtaining the dominant population by combining the individuals obtained by performing factor crossover and factor mutation by using the individuals in the first population and the plurality of second populations, and the individuals in the first population that have performed factor reservation.

[0027] In some embodiments, the plurality of second populations comprises a first sub-population, a second sub-population and a third sub-population, the first sub-population, the second sub-population and the third sub-population are divided according to the ranking results of the individuals in the initialization population, the individuals used for performing factor crossover in the first population, the first sub-population and the second sub-population comprise elite individuals, when the elite individuals perform factor crossover with other individuals to obtain new individuals, a probability that factors of the elite individuals are reserved in the new individuals is a first preset probability, the first preset probability is greater than 0.5,

[0028] the performing factor crossover by using the individuals in the first population and the plurality of second populations comprises:

[0029] Factor crossover is performed on individuals of the first population, the first subpopulation and the second subpopulation, a probability of individuals of the first population being determined as the elite individual is a second preset probability, a probability of individuals of the first subpopulation being determined as the elite individual is a third preset probability, and the third preset probability is less than the second preset probability;

[0030] Factor crossover is performed on individuals of the first subpopulation, the second subpopulation and the third subpopulation, a probability of individuals of the second subpopulation being determined as the elite individual is a fourth preset probability, a probability of individuals of the third subpopulation being determined as the elite individual is 0, and the fourth preset probability is less than the third preset probability.

[0031] In some embodiments, in a case where a plurality of first predicted core condition parameter groups corresponding to a plurality of first control parameter groups are predicted based on the core condition prediction model, before the plurality of first predicted core condition parameter groups are used as an initialization population, the method further comprises:

[0032] Second control parameter groups of a plurality of to-be-simulated core conditions are used to perform xenon oscillation simulation processing to obtain simulation data of each of the to-be-simulated core conditions, wherein the plurality of to-be-simulated core conditions are generated based on a random strategy, each of the simulation data includes a second control parameter group and a second predicted core condition parameter group, each of the second control parameter groups includes at least one second control parameter corresponding to at least one time step, and each of the second predicted core condition parameter groups includes at least one second predicted core condition parameter corresponding to at least one time step.

[0033] The second control parameter groups in the simulation data are labeled based on the second predicted core condition parameter groups in each of the simulation data to generate training samples corresponding to the simulation data.

[0034] The to-be-trained model is iteratively trained based on the training samples corresponding to the simulation data of the plurality of to-be-simulated core conditions to obtain the core condition prediction model.

[0035] In some embodiments, the to-be-trained model is a convolutional neural network model, and before the to-be-trained model is iteratively trained based on the training samples corresponding to the simulation data of the plurality of to-be-simulated core conditions to obtain the core condition prediction model, the method further comprises:

[0036] A to-be-added parameter is added to the training samples, and the to-be-added parameter and the second control parameter groups in the training samples are used as labeling objects of the second predicted core condition parameter groups in the training samples.

[0037] at least one target control parameter group associated with a second control parameter group in the training sample, part of parameters in the target control parameter group correspond to time steps before time steps corresponding to each parameter in the second control parameter group.

[0038] In some embodiments, each of the simulation data includes parameters related to a first number of time steps, each of the training samples includes parameters related to a second number of time steps, the first number is greater than the second number,

[0039] The training sample corresponding to the simulation data is generated by using a second predicted working condition parameter group in each of the simulation data to label a second control parameter group in the simulation data, including:

[0040] In the time steps related to the parameters included in the simulation data, a plurality of groups of the second number of time steps are selected from any time step as a starting point;

[0041] A second control parameter set corresponding to each of the groups of the second number of time steps is set as a to-be-labeled sample;

[0042] A second predicted working condition parameter set corresponding to each of the groups of the second number of time steps is set as a labeled sample;

[0043] Each of the labeled samples is used to label a corresponding to-be-labeled sample to generate a training sample corresponding to the simulation data.

[0044] In a second aspect, the embodiments of the present application provide a nuclear reactor core control device, the device comprising:

[0045] An initialization population determination module is configured to, in a case where a plurality of first predicted working condition parameter groups corresponding to a plurality of first control parameter groups are predicted based on a core working condition prediction model, take the plurality of first predicted working condition parameter groups as an initialization population, wherein each of the first control parameter groups includes at least one first control parameter corresponding to at least one time step, each of the first predicted working condition parameter groups includes at least one first predicted working condition parameter corresponding to at least one time step, each of the first control parameter groups corresponds to an individual in the initialization population, a factor in the individual is a first control parameter corresponding to each time step in the first control parameter group, a parameter type of the first predicted working condition parameter includes an axial power shift of the core, and a parameter type of the first control parameter includes a relative power of the core.

[0046] an optimal individual obtaining module configured to obtain an optimal individual based on fitness values of each individual in the initial population, adaptive evaluation, and iteration of dominant population generation, wherein the fitness value of each individual is determined by using an adaptive evaluation function, the adaptive evaluation function involves a difference between an axial power offset corresponding to each time step in the first predicted core condition parameter group and a reference axial power offset corresponding to each time step, the reference axial power offset is determined according to a corresponding relative power and an axial power offset at full power of the core, the dominant population generation is used to generate a dominant population according to a result of the adaptive evaluation, and the optimal individual is an individual in the dominant population generated in a case where the iteration meets an iteration termination condition;

[0047] a core control module configured to perform core control by using the first control parameter corresponding to the optimal individual.

[0048] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0049] a memory configured to store instructions; and

[0050] a processor configured to call the instructions from the memory and implement the nuclear reactor core control method provided in the first aspect of the present application when the instructions are executed.

[0051] In the embodiment of the present application, a plurality of first control parameter groups representing a plurality of core control strategies are taken as an initial population in a genetic algorithm, a plurality of first predicted core condition parameters corresponding to the plurality of first control parameter groups are predicted by using a core condition prediction model, and iteration of adaptive evaluation and dominant population generation of corresponding individuals in the initial population is performed by using the first predicted core condition parameters in the first predicted core condition parameter group, so as to obtain an optimal individual representing an ideal core control strategy obtained by iteration of the genetic algorithm. In this way, the control strategy does not need to be continuously adjusted and the control result does not need to be continuously calculated, so that a worker can quickly and efficiently obtain the ideal core control strategy, and the first control parameters in the first control parameter group corresponding to the optimal individual representing the core control strategy are used to perform core control. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 is a flowchart of the nuclear reactor core control method provided in the embodiment of the present application;

[0053] Figure 2 is a structural schematic diagram of the nuclear reactor core control device provided in the embodiment of the present application;

[0054] Figure 3 is a structural schematic diagram of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art belong to the scope of protection of the present application.

[0056] The terms "first", "second", and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than that illustrated or described herein, and the objects distinguished by "first", "second", and the like are generally of a kind and are not limited in number, for example, the first object can be one or more. In addition, "and / or" in the specification and claims indicates at least one of the connected objects, and the character " / ", generally indicates that the objects before and after are in an "or" relationship.

[0057] The nuclear reactor core control method and device provided by the embodiments of the present application, and the electronic device will be described in detail below with reference to the drawings, through specific embodiments and application scenarios.

[0058] Please refer to Figure 1 , which is a flowchart of the nuclear reactor core control method provided by the embodiments of the present application, and the method is applied to an electronic device. As Figure 1 shown, the nuclear reactor core control method includes the following steps S100 to S300.

[0059] Step S100: In the case that a plurality of first predicted operating condition parameter groups corresponding to a plurality of first control parameter groups are predicted based on a core operating condition prediction model, the plurality of first predicted operating condition parameter groups are taken as an initialization population, wherein 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 control 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, and the parameter type of the first predicted operating condition parameter includes an axial power shift of the core, and the parameter type of the first control parameter includes a relative power of the core.

[0060] The core condition prediction model in the embodiments of the present application can predict the condition state of the core by the received first control parameter group representing the core control strategy. The condition state of the core is represented by the first predicted condition parameter group. That is, the core condition prediction model is used to predict the condition state of the core controlled according to the core control strategy.

[0061] In the embodiments of the present application, the first control parameter group representing 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 a first control parameter. Those skilled in the art can understand that the time step represents a time interval in the core control strategy, and the adjacent two time steps represent the adjacent two end time intervals in the core control strategy. It can be seen that each first control parameter in the first control parameter group represents the core control strategy in each time step.

[0062] The first predicted condition parameter group representing the condition state of the core includes at least one first predicted parameter corresponding to at least one time step, that is, in the first predicted condition parameter group, each time step corresponds to a first predicted condition parameter. Each first predicted condition parameter in the first predicted condition parameter group represents the condition state of the core at the end of each time step.

[0063] In the embodiments of the present application, the parameter type of the first predicted condition parameter includes the axial power offset of the core, and the parameter type of the first control parameter includes the relative power of the core.

[0064] The electronic device can generate a plurality of different first control parameter groups according to a random strategy, that is, a plurality of core control strategies are generated. After predicting a plurality of first predicted condition parameter groups corresponding to the plurality of first control parameter groups based on the core condition prediction model, each first control parameter group is regarded as an individual, and each first control parameter in the first control parameter group is a factor that can be crossed or mutated to form the individual. All individuals form an initialization population for subsequent iterative processing based on the genetic algorithm and advantage population generation.

[0065] Exemplarily, the parameter type of the first predicted operating condition parameter is axial offset (AO), and the parameter type of the first control parameter can include time step length (T) and rod position (S) of the temperature control rod in addition to the relative power (P) of the core. The core control strategy includes 3 time steps, and a first predicted operating condition parameter group can be written as [AO1, AO2, AO3], and a first control parameter group can be written as [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)]. The electronic device generates a plurality of [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] with different specific parameter values according to the random strategy, each [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] is an individual, (P1, T1, S1), (P2, T2, S2) and (P3, T3, S3) are factors in the individual, all [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] form an initial population, which is used for subsequent iterative processing based on the genetic algorithm and generation of a dominant population.

[0066] Step S200: based on the fitness value of each individual in the initial population, perform adaptive evaluation and iterative processing of dominant population generation to obtain an optimal individual, wherein the fitness value of each individual is determined by using an adaptive evaluation function, the adaptive evaluation function involves the difference between the axial power offset corresponding to each time step in the first predicted operating condition parameter group and the reference axial power offset corresponding to each time step, the reference axial power offset is determined according to the corresponding relative power and the axial power offset when the core is at full power, the dominant population generation is used to generate a dominant population according to the result of adaptive evaluation, and the optimal individual is the individual in the dominant population generated under the condition that the iterative processing meets the iteration termination condition.

[0067] The electronic device performs adaptive evaluation on the corresponding plurality of first control parameter groups by using the plurality of first predicted operating condition parameter groups, and performs iterative processing of dominant population generation according to the adaptive evaluation result until the iteration termination condition is met, so as to obtain the optimal individual in the dominant population at the iteration termination.

[0068] In the embodiments of the present application, the parameter type of the first predicted operating condition parameter includes an axial power shift of the core, and the parameter type of the first control parameter includes a relative power of the core. When adaptive evaluation is performed by using the plurality of first predicted operating condition parameter groups, the electronic device needs to determine the fitness value of each individual, and the fitness value is calculated and determined according to an adaptive evaluation function. The adaptive evaluation function involves the difference between the axial power shift corresponding to each time step in the first predicted operating condition parameter group and the reference axial power shift corresponding to each time step, and the reference axial power shift of each time step is determined according to the axial power shift when the core is at full power and the corresponding relative power.

[0069] For example, in the process of the genetic algorithm, the electronic device first performs adaptive evaluation on each individual in the initial population, i.e., each specific parameter value different [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] based on the adaptive evaluation function.

[0070] For a single [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)], the adaptive evaluation needs to use [AO1, AO2, AO3] corresponding to the [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] predicted by the core operating condition prediction model, and the adaptive evaluation also uses the reference axial power shift corresponding to each time step. The reference axial power shift corresponding to each time step is determined according to the axial power shift when the core is at full power and the corresponding relative power. The reference axial power shift of each time step is the product of the axial power shift when the core is at full power and the corresponding relative power. If the axial power shift when the core is at full power is represented as AO0, the reference axial power shift corresponding to the [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] can be represented as [(P1×AO0, P2×AO0, P3×AO0]. The adaptive evaluation function involves the difference between the axial power shift corresponding to each time step and the reference axial power shift corresponding to each time step. All the differences of an individual can be represented as [AO1-P1×AO0, AO2-P2×AO0, AO3-P3×AO0].

[0071] After the fitness evaluation of each [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] is completed, the generation of the dominant population is performed according to the fitness evaluation results, that is, the iterative update of all individuals is performed. The fitness evaluation and the generation of the dominant population are performed on the dominant population obtained after the iteration, that is, iteration is performed again until the iteration termination condition is met, and the [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] corresponding to the optimal individual is obtained. Those skilled in the art can understand that in each iteration process, the first predicted operating condition parameter corresponding to each individual needs to be predicted by using the core operating condition prediction model as the basis for fitness evaluation.

[0072] Step S300: performing core control by using the first control parameter corresponding to the optimal individual.

[0073] The first control parameter group corresponding to the optimal individual represents an ideal core control strategy obtained by iteration of the genetic algorithm, and the electronic device can perform core control by using the first control parameter in the first control parameter group corresponding to the optimal individual.

[0074] Exemplarily, the first control parameter corresponding to the optimal individual is [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)], and the worker can use these first control parameters as a control strategy to control the relative power of the core, the time step length, and the rod position of the temperature control rod.

[0075] Through the above steps S100-S300, the plurality of first control parameter groups representing a plurality of core control strategies are used as initial populations in the genetic algorithm, a plurality of first predicted operating condition parameters corresponding to the plurality of first control parameter groups are predicted by using the core operating condition prediction model, the corresponding individuals in the initial population are evaluated for fitness and iteratively processed for generation of the dominant population by using the first predicted operating condition parameters in the first predicted operating condition parameter group, so as to obtain an optimal individual. The optimal individual represents an ideal core control strategy obtained by iteration of the genetic algorithm. In this way, it is not necessary to continuously adjust the control strategy and calculate the control result, so that the worker can quickly and efficiently obtain an ideal core control strategy, and perform core control by using the first control parameter in the first control parameter group corresponding to the optimal individual representing the core control strategy.

[0076] In some embodiments, in addition to the relative power of the core, the parameter type of the first control parameter can also include at least one of the following:

[0077] The core control power type parameter, the core control rod position type parameter, and the time step length.

[0078] In addition to the relative power of the core, the parameter type of the first control parameter can include at least one of a core control power type parameter, a core control rod rod position type parameter, and a time step length. The core control power type parameter includes relative power of the core, burnup of the core, etc., and the core control rod rod position type parameter includes temperature control rod rod position, total rod position of power control rod, etc. The worker can adaptively select the parameters during the training of the core working condition prediction model according to the implementation scene or control demand of the control strategy and the network structure type of the core working condition prediction model.

[0079] In some embodiments, in addition to the axial power offset of the core, the parameter type of the first predicted working condition parameter can further include at least one of:

[0080] The enthalpy rise factor of the core, the hot spot factor of the core, and the boron concentration of the core.

[0081] In addition to the axial power offset of the core, the parameter type of the first predicted working condition parameter can further include at least one of the enthalpy rise factor of the core, the hot spot factor of the core, and the boron concentration of the core. The worker can adaptively select the parameters during the training of the core working condition prediction model according to the implementation scene or control demand of the control strategy and the network structure type of the core working condition prediction model.

[0082] In some embodiments, the iteration termination condition can be that the number of iterations reaches a preset threshold, or that the fitness value of a certain individual in the generated dominant population reaches a preset threshold.

[0083] In some embodiments, the fitness value can be determined by the following steps:

[0084] Determine the reference axial power offset corresponding to each time step;

[0085] Determine the difference between the axial power offset corresponding to each time step in the first predicted working condition parameter group and the reference axial power offset corresponding to each time step, to obtain at least one difference value, different difference values corresponding to different time steps;

[0086] Based on the at least one difference value, determine the fitness value.

[0087] Adaptive evaluation needs to determine the fitness value of each individual. For the determination of the fitness value of a certain individual, first, the reference axial power offset corresponding to each time step of the individual is determined by using the first predicted working condition parameter group of the individual, and then the difference between the axial power offset corresponding to each time step in the first predicted working condition parameter group and the reference axial power offset corresponding to each time step is determined. The number of difference values is equal to the number of time steps of the first predicted working condition parameter group, and each difference value corresponds to a different time step. Finally, based on all the obtained difference values, the fitness value of the individual is determined.

[0088] For example, all the differences of one individual can be expressed as [AO1-P1×AO0, AO2-P2×AO0, AO3-P3×AO0], and based on all the obtained differences, the fitness value of the individual is determined.

[0089] In some embodiments, determining the fitness value based on the at least one difference can include:

[0090] Determining the absolute value of the difference with the largest absolute value in the at least one difference as the fitness value.

[0091] The embodiments of the present application aim to maintain the first predicted working condition parameters at a relatively stable level at each time step, i.e., to minimize the difference between the first predicted working condition parameters and the reference quantity, during the selection, iteration and optimization of the control strategy of the core. Therefore, the fitness value can be determined as the absolute value of the difference with the largest absolute value in all the differences of the individual, which represents the maximum difference between the first predicted working condition parameters in the first predicted working condition parameter group corresponding to the individual and the reference quantity. It can be seen that, in the case of determining the fitness value by using this determination method, the smaller the fitness value, the better the control strategy corresponding to the individual, and the optimal individual is the individual with the smallest fitness value in the dominant population at the end of iteration.

[0092] For example, first, the absolute values of all the differences of the individual are removed, and all the obtained absolute values can be expressed as: [|AO1-P1×AO0|, |AO2-P2×AO0|, |AO3-P3×AO0|]. If the largest value in all the absolute values is |AO2-P2×AO0|, then the fitness value of the individual is |AO2-P2×AO0|.

[0093] In some embodiments, determining the fitness value based on the at least one difference can include:

[0094] Determining the ratio between the absolute value of each difference and the corresponding reference axial power offset;

[0095] Converting the differences based on the ratio corresponding to each difference to obtain the conversion value of the at least one difference;

[0096] Determining the fitness value based on the conversion value of the at least one difference.

[0097] The fitness value of an individual can also be determined by numerical conversion. First, the ratio between the absolute value of each difference and the corresponding reference axial power offset, i.e., the reference axial power offset at the same time step, is determined, and each difference is numerically converted based on the ratio of each difference to obtain a conversion value, and then the fitness value of the individual is determined based on all the conversion values.

[0098] Exemplarily, the ratio between the absolute value of each difference value and the corresponding reference axial power offset can be expressed as:

[0099]

[0100] wherein x is the ratio, i is the number of time step, AO i is the axial power offset, P i x AO0is the reference axial power offset, P i is the relative power, AO0is the axial power offset at full power of the core.

[0101] In some embodiments, the converting the difference values based on the corresponding ratio of each difference value to obtain a converted value of at least one difference value can include any one of the following:

[0102] converting the difference value to a first converted value when the ratio corresponding to the difference value is less than a first threshold value;

[0103] converting the difference value to a second converted value when the ratio corresponding to the difference value is less than or equal to a second threshold value and greater than or equal to the first threshold value;

[0104] converting the difference value to a third converted value when the ratio corresponding to the difference value is greater than the second threshold value.

[0105] The converting the difference values based on the size relationship between the ratio corresponding to each difference value and the first threshold value and the second threshold value to obtain a converted value of each difference value, the converted value being one of the first converted value, the second converted value and the third converted value. Converting the difference value to a first converted value when the ratio corresponding to the difference value is less than a first threshold value; converting the difference value to a second converted value when the ratio corresponding to the difference value is less than or equal to a second threshold value and greater than or equal to the first threshold value; converting the difference value to a third converted value when the ratio corresponding to the difference value is greater than the second threshold value.

[0106] Exemplarily, the specific manner of determining the converted value can be expressed by the following formula:

[0107]

[0108] wherein x is the ratio, f(x) is the converted value, 1 is the first converted value, 0 is the second converted value, -1.5 is the third converted value, 0.5% is the first threshold value, and 1% is the second threshold value.

[0109] It can be seen that, in the conversion value determination mode of formula (2), if the difference between the axial power offset of a time step and the reference axial power offset is small (x < 0.5%), the conversion value of the time step is large (1); if the difference between the axial power offset of a time step and the reference axial power offset is large (0.5% ≤ x ≤ 1% or x > 1%), the conversion value of the time step is small (0 or -1.5).

[0110] In some embodiments, determining the fitness value based on the conversion values of the at least one difference value can include:

[0111] determining the maximum absolute value in the absolute values of the at least one difference value as the correction amount;

[0112] summing the conversion values of the at least one difference value, and determining the fitness value based on the sum and the correction amount.

[0113] The determination of the fitness value of each individual is based on the sum of the conversion values of all time steps of each individual, but if the sum of all conversion values of each individual is simply taken as the fitness value of each individual, the fitness values of some individuals will be the same, and accurate fitness evaluation cannot be performed. Therefore, the sum of the conversion values of each individual needs to be corrected to increase the difference between the fitness values of individuals.

[0114] The maximum absolute value in the absolute values of all the difference values in the individual is taken as the correction amount, and the sum of all the conversion values of the individual is corrected using the correction amount to obtain the corrected fitness value of the individual.

[0115] For example, the specific way of correcting the sum of all conversion values of the individual using the correction amount can be expressed as the following formula:

[0116]

[0117] where f(x i ) is the conversion value determined according to the above formula (2), x i is the above ratio, i is the number of time steps, n is the number of time steps included in the individual, AO i is the axial power offset, P i × AO0 is the reference axial power offset, P i is the relative power, AO0 is the axial power offset at full power of the core, AO i -P i × AO0 is the above difference value, |AO i -P i × AO0| is the above absolute value, and k is a preset correction coefficient.

[0118] It can be seen that, in the case that the conversion value is determined by formula (2), and the sum of all conversion values of the individual is corrected by formula (3) to obtain the fitness value of the individual, the smaller the gap between all axial power offset values corresponding to the individual and the reference axial power offset value as a whole, the greater the fitness value, the better the control strategy corresponding to the individual, and the optimal individual is the individual with the optimal fitness value, i.e., the individual with the maximum fitness value in the dominant population at the end of iteration.

[0119] In some embodiments, the dominant population generation can include:

[0120] According to the ranking results of all individuals, all individuals are divided into a first population and a plurality of second populations, wherein the ranking results are obtained based on the fitness values of the individuals, the individuals in the first population are used for factor reservation, factor mutation and factor crossover, and the individuals in each second population are used for factor mutation and factor crossover;

[0121] Factor crossover and factor mutation are performed using the individuals in the first population and the plurality of second populations;

[0122] The individuals obtained by performing factor crossover and factor mutation using the individuals in the first population and the plurality of second populations are combined with the individuals in the first population that have undergone factor reservation to obtain a dominant population.

[0123] In the iteration process, the generation of the dominant population is performed according to the ranking results of the fitness values of all individuals. The ranking results of the fitness values represent the advantages and disadvantages of the control strategies corresponding to each individual. According to the ranking results, all individuals are first divided into a first population and a plurality of second populations. The individuals in the first population correspond to better control strategies and can be used for factor reservation, factor mutation and factor crossover. The control strategies corresponding to the plurality of second populations are relatively worse than the control strategies corresponding to the first population and can be used for factor mutation and factor crossover.

[0124] In the generation process of the dominant population, factor crossover and factor mutation are performed using the first population and the plurality of second populations to generate new individuals. The new individuals are combined with the individuals in the first population that have undergone factor reservation (i.e., the individuals that are completely passed to the next generation of dominant population) to form the dominant population.

[0125] Exemplarily, the fitness values of all individuals are sorted from large to small in the case that the higher the fitness value of an individual is, the better the control strategy represented by the individual is, and according to the sorting result, individuals located in the top 5% of the sorting result are taken as the first population, and the remaining individuals are further divided into a plurality of second individuals according to the sorting result. The total number of individuals in the generated dominant population is consistent with the total number of all individuals for which the dominant population is generated, and the proportion of individuals reserved by factors, the proportion of new individuals obtained by factor mutation, and the proportion of new individuals obtained by factor crossover in the generated dominant population can be adaptively adjusted and determined according to optimization needs.

[0126] In some embodiments, the plurality of second populations can include a first sub-population, a second sub-population, and a third sub-population, the first sub-population, the second sub-population, and the third sub-population are divided according to the sorting result of the individuals in the initialization population, and in the first population, the first sub-population, and the second sub-population, the individuals for performing factor crossover include elite individuals, when the elite individuals perform factor crossover with other individuals to obtain new individuals, the probability that the factors of the elite individuals are reserved in the new individuals is a first preset probability, the first preset probability is greater than 0.5,

[0127] The factor crossover using the individuals in the first population and the plurality of second populations can include:

[0128] The factor crossover using the individuals in the first population, the first sub-population, and the second sub-population, the probability that the individuals in the first population are determined as elite individuals is a second preset probability, the probability that the individuals in the first sub-population are determined as elite individuals is a third preset probability, and the third preset probability is less than the second preset probability;

[0129] The factor crossover using the individuals in the first sub-population, the second sub-population, and the third sub-population, the probability that the individuals in the second sub-population are determined as elite individuals is a fourth preset probability, the probability that the third sub-population is determined as elite individuals is 0, and the fourth preset probability is less than the third preset probability.

[0130] According to the plurality of second populations divided according to the fitness value sorting result, the first sub-population, the second sub-population, and the third sub-population, the excellent degree of the control strategy represented by the individuals contained in the first sub-population, the second sub-population, and the third sub-population decreases in turn, and it can be seen that the excellent degree of the control strategy represented by the individuals in the third sub-population is the lowest. Therefore, among all the individuals included in the first population, the first sub-population, and the second sub-population, the individuals for performing factor crossover include elite individuals, while the individuals in the third sub-population for performing factor crossover do not include elite individuals.

[0131] The elite individual refers to an individual whose probability of retaining its own factors in the process of generating a new individual through factor crossover between two individuals is greater than a first preset probability. According to the definition of the elite individual, the first preset probability is greater than 50%.

[0132] For example, the factors of individual A are (a1, a2, a3, a4, a5), the factors of individual B are (b1, b2, b3, b4, b5), individual A is an elite individual, and the first preset probability is 80%. That is, when individual A and individual B are crossed to obtain individual C, the factors of individual A have a probability of 0.8 of being retained in individual C, i.e., the possible form of the factors of individual C is (a1, a2, a3, a4, b5).

[0133] In the factor crossover using the individuals of the first population, the first subpopulation, and the second subpopulation, the probability that the individual of the first population with the best fitness performance is determined as an elite individual is a second preset probability, and the probability that the individual of the first subpopulation with a fitness performance worse than that of the first population is determined as an elite individual is a third preset probability, which is less than the first preset probability.

[0134] In the factor crossover using the individuals of the first subpopulation, the second subpopulation, and the third subpopulation, the probability that the individual of the second subpopulation with a fitness performance worse than that of the first subpopulation is determined as an elite individual is a fourth preset probability, which is less than the third preset probability. The individual of the third subpopulation for factor crossover does not include an elite individual, and thus the probability that the third subpopulation is determined as an elite individual is 0.

[0135] The individual in the first population and the individual in the third subpopulation will not be subjected to factor crossover.

[0136] Exemplarily, in the factor crossover using the individuals of the first population, the first subpopulation, the second subpopulation, and the third subpopulation, the probability that the individual in each population is determined as an elite individual, and the probability that the individual in each population is determined as an individual for factor crossover with an elite individual can be expressed by the following matrix C:

[0137]

[0138] The matrix C includes 4 columns, diagonal elements from the 1st column to the 4th column are 0.5, 0.3, 0.2, 0, which respectively represent the probability that the individual in the first population, the individual in the first sub-population, the individual in the second sub-population and the individual in the third sub-population are determined as the elite individual, i.e., the second preset probability is 0.5, the third preset probability is 0.3, and the fourth preset probability is 0.2, and the individual in the third sub-population will not be determined as the elite individual; non-diagonal elements from the 1st column to the 4th column respectively represent the probability that the individual in the first population, the individual in the first sub-population, the individual in the second sub-population and the individual in the third sub-population are determined as the individual performing factor crossover with the elite individual.

[0139] Taking the first row of the matrix C as an example, the probability that the individual in the first population is determined as the elite individual is 0.5, and in the case that the individual in the first population is selected as the elite individual, the probability that the individual in the first sub-population and the individual in the second sub-population are determined as the individual performing factor crossover with the elite individual is 0.5; taking the second row of the matrix C as an example, the probability that the individual in the first sub-population is determined as the elite individual is 0.3, and in the case that the individual in the first sub-population is selected as the elite individual, the probability that the individual in the first population and the individual in the second sub-population are determined as the individual performing factor crossover with the elite individual is 0.6 and 0.4 respectively.

[0140] In some embodiments, in the case that a plurality of groups of first predicted operating condition parameters corresponding to a plurality of groups of first control parameters are predicted based on the core operating condition prediction model, before the plurality of groups of first predicted operating condition parameters are used as the initialization population, the method can further include:

[0141] Simulate the xenon oscillation by using a plurality of second control parameter groups of a plurality of to-be-simulated operating conditions, to obtain simulation data of each to-be-simulated operating condition, wherein the plurality of to-be-simulated operating conditions are generated based on a random strategy, each simulation data includes a second control parameter group and a second predicted operating condition parameter group, each second control parameter group includes at least one second control parameter corresponding to at least one time step, and each second predicted operating condition parameter group includes at least one second predicted operating condition parameter corresponding to at least one time step;

[0142] Label the second control parameter group in the simulation data by using the second predicted operating condition parameter group in each simulation data, to generate a training sample corresponding to the simulation data;

[0143] Iteratively train the to-be-trained model based on the training samples corresponding to the simulation data of the plurality of to-be-simulated operating conditions, to obtain the core operating condition prediction model.

[0144] For training of the core condition prediction model, the staff can use a computer to determine the training samples of the core condition prediction model through xenon oscillation simulation processing. First, the electronic device can generate a plurality of different second control parameter groups according to a random strategy, that is, a plurality of core control strategies are generated. Those skilled in the art can understand that each second control parameter group also includes at least one second control parameter corresponding to at least one time step, and the parameter types included in the second control parameter are the same as the parameter types included in the first control parameter.

[0145] The electronic device performs xenon oscillation simulation processing on the plurality of second control parameter groups to obtain simulation data of each second control parameter group, and the simulation data includes a second predicted condition parameter group corresponding to the second control parameter group. Those skilled in the art can understand that each second predicted condition parameter group also includes at least one second predicted condition parameter corresponding to at least one time step, and the parameter types included in the second control parameter are the same as the parameter types included in the first predicted condition parameter.

[0146] The simulation data also includes the second control parameter group used for xenon oscillation simulation processing.

[0147] Exemplarily, the parameter types of the second predicted condition parameters are the same as those of the first control parameters and the first predicted condition parameters, and the parameter types of the second control parameters can include the time step and the rod position of the temperature control rod in addition to the relative power of the core. The core control strategy includes 3 time steps, and a second predicted condition parameter group can be written as [AO1, AO2, AO3], and a second control parameter group can be written as [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)]. The electronic device generates a plurality of [(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 of each [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)]. In the simulation data, there are [AO1, AO2, AO3] corresponding to [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)], and there are [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] themselves.

[0148] Using the second predicted condition parameter groups in the obtained simulation data, the second control parameter groups in the simulation data are labeled to generate training samples for model training, and the training samples corresponding to the simulation data of the plurality of to-be-simulated conditions are used to iteratively train the to-be-trained model to obtain the core condition prediction model.

[0149] In some embodiments, the model to be trained is a convolutional neural network model, and before the model to be trained is iteratively trained based on the training samples corresponding to the simulation data of the plurality of simulated working conditions to obtain the core working condition prediction model, the method can further include:

[0150] The to-be-added parameters are added to the training samples and used as the labeled objects of the second predicted working condition parameter group in the training samples together with the second control parameter group in the training samples. The to-be-added parameters can include:

[0151] The at least one target control parameter group associated with the second control parameter group in the training samples, and the time steps of some parameters in the target control parameter group are located before the time steps of each parameter in the second control parameter group.

[0152] The network structure of the model to be trained, i.e., the core working condition prediction model, can be a convolutional neural network (CNN). Because the convolutional neural network has strong feature extraction capability, in order to enhance the accuracy of the model during training, the labeled part in the training samples is suitable for adding adjacent or previous related features. Therefore, data related to the core control strategy can be added to the training samples, and the data is the to-be-added parameters. The to-be-added parameters are selected as the at least one target control parameter group associated with the second control parameter group in the training samples, and the time steps of some parameters in the target control parameter group are located before the time steps of each parameter in the second control parameter group.

[0153] For example, the time steps of some parameters in the target control parameter group are the previous or second previous time steps of the time steps of each parameter in the second control parameter group. For example, the second control parameter group is represented as [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)], and the target control parameter group of the second control parameter group can be determined as: [(P1, T1, S1), (P1, T1, S1), (P2, T2, S2)], i.e., the target control parameter group includes the parameter (P2, T2, S2) of the previous time step of (P3, T3, S3), the parameter (P1, T1, S1) of the previous time step of (P2, T2, S2), and (P1, T1, S1) itself (because there is no parameter of the previous time step of (P1, T1, S1), (P1, T1, S1) itself is added to the target control parameter group).

[0154] The target control parameter group corresponding to each second control parameter group can be multiple, so the target parameter group in the to-be-added parameter can also be determined as: [(P1, T1, S1), (P2, T2, S2), (P1, T1, S1)], that is, the target control parameter group includes the parameters of the previous two time steps of (P3, T3, S3) - (P1, T1, S1), and (P1, T1, S1) and (P2, T2, S2) themselves (because there is no parameter of (P1, T1, S1) and (P2, T2, S2) in the previous two time steps, (P1, T1, S1) and (P2, T2, S2) are added to the target control parameter group).

[0155] Those skilled in the art can understand that when the network structure of the core operating condition prediction model is other network structures except for the convolutional neural network, the types of the to-be-added parameters can also be adaptively adjusted according to the types of the network structures of the core operating condition prediction model.

[0156] In some embodiments, each simulation data includes parameters related to a first number of time steps, each training sample includes parameters related to a second number of time steps, the first number is greater than the second number,

[0157] The second control parameter group in the simulation data is labeled using the second predicted operating condition parameter group in each simulation data, to generate a training sample corresponding to the simulation data, which can include:

[0158] In the time steps related to the parameters included in the simulation data, a plurality of groups of the second number of time steps are selected from any time step as a starting point;

[0159] The second control parameters corresponding to each group of the second number of time steps are collected as a to-be-labeled sample;

[0160] The second predicted operating condition parameters corresponding to each group of the second number of time steps are collected as a labeled sample;

[0161] Each labeled sample is used to label the corresponding to-be-labeled sample to generate a training sample corresponding to the simulation data.

[0162] In order to expand the number of training samples, when performing xenon oscillation simulation processing, the number of time steps related to the parameters in the simulation data can be set to be greater than the number of time steps of the required control strategy, that is, greater than the number of time steps related to the parameters in the training sample. In the embodiments of the present application, the simulation data includes parameters related to a first number of time steps, and the training sample includes parameters related to a second number of time steps.

[0163] In this way, the training sample quantity can be greater than the simulation data quantity, and the training sample quantity is expanded, so that the core condition prediction model has stronger generalization ability.

[0164] For example, the first quantity is 4, the second quantity is 3, and the simulation data includes the second control parameter group [(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, and 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)].

[0165] Correspondingly, the selected groups of second prediction condition parameters involving 3 time steps in the simulation data are [AO1, AO2, AO3] and [AO2, AO3, AO4].

[0166] The first training sample of the simulation data is obtained by labeling [(P1, T1, S1), (P2, T2, S2), (P3, T3, S3)] with [AO1, AO2, AO3], and the second training sample of the simulation data is obtained by labeling [(P2, T2, S2), (P3, T3, S3), (P4, T4, S4)] with [AO2, AO3, AO4], that is, two different training samples are obtained by using one simulation data, and the training sample quantity is expanded.

[0167] Please refer to Figure 2 The second aspect of the present application provides a nuclear reactor core control device 10, the device 10 comprises:

[0168] The initialization population determining module 11 is configured to, in a case where the plurality of first predicted core state parameter sets corresponding to the plurality of first control parameter sets are predicted based on the core state prediction model, take the plurality of first predicted core state parameter sets as an initialization population, wherein each first control parameter set comprises at least one first control parameter corresponding to at least one time step, each first predicted core state parameter set comprises at least one first predicted core state parameter corresponding to at least one time step, each first control parameter set corresponds to an individual in the initialization population, the factors in the individual are the first control parameters corresponding to each time step in the first control parameter set, and the parameter type of the first predicted core state parameter comprises an axial power offset of the core, and the parameter type of the first control parameter comprises a relative power of the core.

[0169] The optimal individual obtaining module 12 is configured to perform iterative processing of adaptive evaluation and dominant population generation based on the fitness value of each individual in the initialization population to obtain an optimal individual, wherein the fitness value of each individual is determined by using an adaptive evaluation function, the adaptive evaluation function involves the difference between the axial power offset corresponding to each time step in the first predicted core state parameter set and the reference axial power offset corresponding to each time step, the reference axial power offset is determined according to the corresponding relative power and the axial power offset when the core is at full power, the dominant population generation is used to generate a dominant population according to the result of adaptive evaluation, and the optimal individual is an individual in the dominant population generated in a case where the iterative processing satisfies an iteration termination condition.

[0170] The core control module 13 is configured to perform core control by using the first control parameter corresponding to the optimal individual.

[0171] The nuclear reactor core control device 10 provided in the second aspect of the embodiments of the present application can implement each process implemented by the method embodiments described above and achieve the same beneficial effects. To avoid repetition, details are not described herein.

[0172] Please refer to Figure 3 The third aspect of the embodiments of the present application provides an electronic device 1000, which comprises a processor 1100 and a memory 1200. The memory 1200 stores machine executable instructions capable of being executed by the processor 1100. The processor 1100 can execute the machine executable instructions to implement the nuclear reactor core control method described above.

[0173] The fourth aspect of the embodiments of the present application provides a machine readable storage medium, which stores instructions. When the instructions are executed by a processor, the processor implements the nuclear reactor core control method described above.

[0174] In some embodiments, the present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the nuclear reactor core control method according to the above-mentioned embodiments.

[0175] Those skilled in the art understand that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0176] The present application is described with reference to the flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts 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, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams. These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams. These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams. These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams.

[0177] In a typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0178] The memory can include non-persistent memory in the computer readable medium, random access memory (RAM), and / or non-volatile memory such as read only memory (ROM) or flash memory. The memory is an example of computer readable media.

[0179] Computer readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology for storing information. Information can be computer readable instructions, data structures, program modules 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 technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. According to the definition herein, computer readable media does not include transitory computer readable media, such as modulated data signals and carrier waves.

[0180] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or device that includes the element.

[0181] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

[0182] In addition, any combination of various embodiments of the present application can also be made, as long as it does not deviate from the idea of the present application, it should also be considered as disclosed by the present application.

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 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, each first control parameter group corresponds to an individual in the initialization population, and the factor in the individual is the first control parameter corresponding to each time step in the first control parameter group. The parameter type of the first predicted operating condition parameter includes the axial power offset of the core, and the parameter type of the first control parameter includes the relative power of the core. Based on the fitness value of each individual in the initial population, an iterative process of fitness evaluation and dominant population generation is performed to obtain the optimal individual. The fitness value of each individual is determined using a fitness evaluation function, which involves the difference between the axial power offset corresponding to each time step in the first predicted operating condition parameter group and the reference axial power offset corresponding to each time step. The reference axial power offset is determined based on the axial power offset when the corresponding relative power is equal to the core full power. The dominant population generation is used to generate a dominant population based on the results of the fitness 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. The fitness value is determined through the following steps: Determine the reference axial power offset for each time step; Determine the difference between the axial power offset corresponding to each time step in the first predicted operating condition parameter group and the reference axial power offset corresponding to each time step, and obtain at least one difference value, with different differences corresponding to different time steps; Determine the ratio between the absolute value of each difference and the corresponding reference axial power offset; Based on the ratio corresponding to each difference, the differences are transformed to obtain the transformed value of the at least one difference; The fitness value is determined based on the transformation value of the at least one difference.

2. The method according to claim 1, characterized in that, The step of transforming the differences based on the ratio corresponding to each difference to obtain a transformed value for at least one difference includes any one of the following: If the ratio corresponding to the difference is less than a first threshold, the difference is converted into a first conversion value; If the ratio corresponding to the difference is less than or equal to the second threshold and greater than or equal to the first threshold, the difference is converted into a second conversion value; If the ratio corresponding to the difference is greater than the second threshold, the difference is converted into a third conversion value.

3. The method according to claim 1, characterized in that, Determining the fitness value based on the transformation value of the at least one difference includes: The largest absolute value among the absolute values ​​of the at least one difference is determined as the correction amount; The transformed values ​​of the at least one difference are summed, and the fitness value is determined based on the summation result and the correction amount.

4. The method according to claim 1, characterized in that, The generation of the dominant population includes: Based on the ranking results of all individuals, all individuals are divided into a first group and multiple second groups, wherein the ranking results are obtained based on the fitness values ​​of the individuals. Individuals in the first group are used for factor retention, factor mutation, and factor crossover, and individuals in each of the second groups are used for factor mutation and factor crossover. Factor crossover and factor mutation are performed using individuals from the first population and the plurality of second populations; The dominant population is obtained by combining individuals obtained through factor crossover and factor mutation from individuals in the first population and the plurality of second populations with individuals in the first population whose factors have been preserved.

5. The method according to claim 4, characterized in that, Multiple second populations include a first subpopulation, a second subpopulation, and a third subpopulation. These three subpopulations are divided based on the ranking of individuals in the initial population. Within the first population, the first subpopulation, and the second subpopulation, individuals used for factor crossover include elite individuals. When an elite individual undergoes factor crossover with other individuals to obtain a new individual, the probability that the elite individual's factors are retained in the new individual is a first preset probability, which is greater than 0.

5. The step of performing factor crossover using individuals from the first population and the plurality of second populations includes: Factor crossover is performed using individuals from the first population, the first subpopulation, and the second subpopulation. The probability that an individual from the first population is identified as an elite individual is a second preset probability, and the probability that an individual from the first subpopulation is identified as an elite individual is a third preset probability. The third preset probability is less than the second preset probability. Factor crossover is performed using individuals from the first subpopulation, the second subpopulation, and the third subpopulation. The probability that an individual from the second subpopulation is identified as an elite individual is a fourth preset probability, and the probability that an individual from the third subpopulation is identified as an elite individual is 0. The fourth preset probability is less than the third preset probability.

6. 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.

7. The method according to claim 6, characterized in that, The model to be trained is a convolutional neural 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 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: At least one target control parameter group associated with the second control parameter group in the training sample, wherein the time steps corresponding to some parameters in the target control parameter group are located before the time steps corresponding to each parameter in the second control parameter group.

8. The method according to claim 6, 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. 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. The set of second predicted working condition parameters corresponding to the second number of time steps in each group is a labeled sample; The corresponding unlabeled samples are labeled using the labeled samples to generate training samples corresponding to the simulated data.

9. A nuclear reactor core control device, characterized in that, The device includes: An initialization population determination module is used to use multiple first predicted operating condition parameter groups as an initialization 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 control parameter group corresponds to an individual in the initialization population, and the factor in the individual is the first control parameter corresponding to each time step in the first control parameter group. The parameter type of the first predicted operating condition parameter includes the axial power offset of the core, and the parameter type of the first control parameter includes the relative power of the core. The optimal individual acquisition module is used to perform adaptive evaluation and iterative processing of dominant population generation based on the fitness value of each individual in the initial population to obtain the optimal individual. The fitness value of each individual is determined using an adaptive evaluation function, which involves the difference between the axial power offset corresponding to each time step in the first predicted operating condition parameter group and the reference axial power offset corresponding to each time step. The reference axial power offset is determined based on the axial power offset when the corresponding relative power is equal to the core full power. 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 processing meets the iteration termination condition. Core control module, used to perform core control using the first control parameters corresponding to the optimal individual; The optimal individual acquisition module is also used for: Determine the reference axial power offset for each time step; Determine the difference between the axial power offset corresponding to each time step in the first predicted operating condition parameter group and the reference axial power offset corresponding to each time step, and obtain at least one difference value, with different differences corresponding to different time steps; Determine the ratio between the absolute value of each difference and the corresponding reference axial power offset; Based on the ratio corresponding to each difference, the differences are transformed to obtain the transformed value of the at least one difference; The fitness value is determined based on the transformation value of the at least one difference.

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