Preheating System and Preheating Method for Nuclear Fuel Assembly

Abstract

The present invention provides a preheating system and a preheating method for a nuclear fuel assembly, including: inputting preheating data sets of the nuclear fuel assembly under various historical working conditions into a preset preheating model for training to obtain predicted temperature values of a target temperature measurement point on the nuclear fuel assembly within a preset thermal uniformity threshold range; training the predicted temperature values according to a preset loss function to determine loss values of the preheating model under different historical working conditions; updating the preheating model through the loss values to obtain a trained preheating model; inputting the preheating data set of the nuclear fuel assembly under the current working condition into the trained preheating model to generate a preheating strategy, and controlling the preheating system to heat argon in response to the preheating strategy. By combining the preheating data of the nuclear fuel assembly under different historical working conditions for training and controlling the preheating system to execute the preheating strategy, the target temperature measurement point reaches the actually required temperature, thereby ensuring uniform heating of each part of the nuclear fuel assembly.

Description

Technical Field

[0001] The present invention relates to the field of nuclear reactors, and in particular, to a preheating system and a preheating method for a nuclear fuel assembly. Background Art

[0002] Before a new sodium-cooled fast reactor assembly is loaded into the reactor core, the nuclear fuel assembly needs to be heated to a certain temperature. When a large number of nuclear fuel assemblies are continuously loaded into the reactor, the new sodium-cooled fast reactor assembly is preheated by a temporary heating container and then loaded into the new assembly conversion barrel. The new assembly conversion barrel can be loaded with the assembly without cooling, which can effectively save the time for reheating the new assembly conversion barrel after repeated cooling.

[0003] The related technology preheats the nuclear fuel assembly by heating argon gas, and then accelerates the flow of argon gas by a fan to rapidly circulate and exchange heat the argon gas heated to the target temperature in the container to achieve the function of temperature rise. Although heating by argon gas circulation and heat exchange can ensure relatively uniform heating, it is not easy to ensure that each assembly can be uniformly heated to the target temperature in the case of continuous loading of a large number of nuclear fuel assemblies. Due to the possible differences in the flow rate and heat exchange efficiency of argon gas at different positions in the container, some assemblies may be underheated and some may be overheated, affecting the performance and safety of the assemblies. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a preheating system and a preheating method for a nuclear fuel assembly, which solve the problem of uneven heating of the nuclear fuel assembly in the prior art during the preheating process.

[0005] In a first aspect, the present application provides a preheating method for a nuclear fuel assembly, the method comprising:

[0006] Inputting the preheating data sets of the nuclear fuel assembly under various historical conditions into a preset preheating model for training to obtain the predicted temperature values of the target temperature measurement points on the nuclear fuel assembly within a preset thermal uniformity threshold range;

[0007] Training the predicted temperature values according to a preset loss function to determine the loss values of the preheating model under different historical conditions; and based on a preset update rule, updating the preheating model through the loss values to obtain a trained preheating model;

[0008] Inputting the preheating data set of the nuclear fuel assembly under the current condition into the trained preheating model to generate a preheating strategy, and controlling the preheating system to heat the argon gas in response to the preheating strategy.

[0009] In one embodiment, the preset data set at least includes the surface temperature data of multiple target temperature measurement points under various historical operating conditions, the Biot number of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotation speed of the fan; the process of inputting the preheating data set of the nuclear fuel assembly under multiple historical operating conditions into a preset preheating model for training to obtain the predicted temperature value of the target temperature measurement point on the nuclear fuel assembly that meets the preset thermal uniformity threshold range specifically includes:

[0010] Construct a Markov joint probability distribution based on the interaction relationship among the surface temperature data of the target temperature measurement points, the Biot number of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotation speed of the fan;

[0011] Determine the predicted temperature value of each target temperature measurement point that meets the thermal uniformity threshold range based on the Markov joint probability distribution.

[0012] In one embodiment, the process of constructing a Markov joint probability distribution based on the interaction relationship among the surface temperature data of the target temperature measurement points, the Biot number of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotation speed of the fan specifically includes:

[0013] Construct energy clusters respectively according to the surface temperature data and Biot number of adjacent two target temperature measurement points, and construct energy clusters according to the surface temperature data of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotation speed of the fan, and establish an energy function based on the energy clusters;

[0014] Generate a corresponding Boltzmann potential function according to the energy function, and determine the change parameter of the Boltzmann potential function based on maximum likelihood estimation;

[0015] Generate the Markov joint probability distribution based on the change parameter and the Boltzmann potential function.

[0016] In one embodiment, the expression of the Boltzmann function is:

[0017]

[0018] Wherein, The energy function of the energy cluster constructed from the surface temperature data of adjacent two target temperature measurement points, The energy function of the energy cluster constructed from the Biot number of adjacent two target temperature measurement points, The energy function of the energy cluster constructed for the surface temperature data of the target temperature measurement point, the opening degree of the argon regulating valve, the pressure of the argon near the target temperature measurement point, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan;

[0019]

[0020]

[0021]

[0022] Among them, and are respectively the surface temperature data of two adjacent target temperature measurement points, and are respectively the Biot numbers of two adjacent target temperature measurement points, T is the surface temperature data, V is the opening degree, P is the pressure, W is the power, R is the rotational speed, N is the number of nuclear fuel assemblies, is the target surface temperature data, the target opening degree, is the target pressure, is the target power, is the target rotational speed, N t is the target number of nuclear fuel assemblies, is the average surface temperature, , , , , , and are all weight parameters.

[0023] In one embodiment, determining the change parameters of the Boltzmann potential function based on the maximum likelihood estimation specifically includes:

[0024] Construct the conditional probabilities of the surface temperature data of the target temperature measurement point, the Biot number of the target temperature measurement point, the opening degree of the argon regulating valve, the pressure of the argon near the target temperature measurement point, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan respectively under the condition that other variables are fixed through pseudo-likelihood estimation, and determine the pseudo-approximate likelihood function according to the conditional probabilities;

[0025] Calculate the gradients of the pseudo-approximate likelihood function with respect to the corresponding variables respectively, and update the parameter values of the corresponding variables through the gradient ascent method until the parameter values of the corresponding variables when the pseudo-approximate likelihood function satisfies the preset iteration conditions are used as the change parameters of the Boltzmann potential function.

[0026] In one embodiment, the loss value includes the mean square error loss value and the mean absolute error loss value, and the expression of the loss function is:

[0027]

[0028]

[0029] Among them, is the mean square error loss value, is the mean absolute error loss value, and n is the number of target temperature measurement points. is the surface temperature data of the target temperature measurement points in the preheating dataset; is the predicted temperature value.

[0030] In one embodiment, after inputting the preheating dataset of the nuclear fuel assembly under the current working condition into the trained preheating model to generate a preheating strategy, it further includes:

[0031] Matching the reference thermal uniformity data corresponding to the current working condition for each target temperature measurement point based on historical working conditions;

[0032] Comparing the uncertainty value between the thermal uniformity data of the preheating strategy of the target temperature measurement point and the reference thermal uniformity data;

[0033] Marking the target temperature measurement points whose uncertainty value exceeds the preset uncertainty threshold as abnormal target temperature measurement points;

[0034] Extracting the preheating parameters of the abnormal target temperature measurement points in the preset dataset corresponding to the historical working condition of the reference thermal uniformity data, updating the preheating dataset according to the preheating parameters, and regenerating a new preheating strategy.

[0035] In one embodiment, the updating the preheating dataset according to the preheating parameters specifically includes:

[0036] Randomly deleting the data in the preheating dataset under the current working condition through a random forest algorithm, and establishing multiple groups of deleted datasets to be restored for the same data;

[0037] Based on the pre-established recovery model, performing data recovery on the deleted dataset to obtain a recovered data set;

[0038] Calculating the similarity between the deleted dataset and the recovered dataset, and updating the preheating dataset with the preheating parameters corresponding to the abnormal target temperature measurement points in the recovered dataset whose similarity meets the similarity threshold.

[0039] Second aspect, the present application provides a preheating system for a nuclear fuel assembly, including an argon regulating valve for controlling the argon flow rate, a heater for heating the argon, a blower for conducting the argon flow, a first temperature sensor for monitoring the surface temperature data of a target temperature measurement point, a second temperature sensor for monitoring the ambient temperature of the nuclear fuel assembly, a camera for identifying the number of nuclear fuel assemblies, and a control center for controlling the argon regulating valve, the heater, the blower, the camera, the first temperature sensor and the second temperature sensor to execute a preheating strategy. The control center is configured to execute the preheating method for the nuclear fuel assembly according to any one of the first aspects.

[0040] Third aspect, the present application provides a computer-readable storage medium storing instructions for being loaded and executed by a processor to perform the preheating method for the nuclear fuel assembly according to any one of the first aspects.

[0041] In the preheating system and preheating method of the nuclear fuel assembly in this embodiment, by combining the preheating data of the nuclear fuel assembly under different historical working conditions for training, under the guidance of the thermal uniformity data, the preheating model is prompted to predict the actual required temperature of each target temperature measurement point under the actual working conditions, and the argon regulating valve, the heater and the blower of the preheating system are controlled to execute the preheating strategy, so that the target temperature measurement point reaches the actual required temperature, thereby ensuring uniform heating of each part of the nuclear fuel assembly. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0043] Figure 1 It is a schematic flow chart of the preheating method for the nuclear fuel assembly in the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] The following will describe in detail specific embodiments of the present invention in conjunction with the drawings. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all of the embodiments. Based on the description of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0045] In the description of the present invention, unless otherwise clearly specified and defined, terms such as "arranged", "installed", "connected", etc. shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances.

[0046] The orientation or positional relationship indicated by terms such as "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the inventive product is usually placed during use. It is only for the convenience of description and simplification of the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0047] Terms such as "first", "second", "third", etc. are only used to distinguish elements with similar attributes, rather than indicating or implying relative importance or a specific order.

[0048] The term "comprises", "comprising", or any other variation thereof, is intended to cover a non-exclusive inclusion. In addition to the listed elements, it may also include other elements not specifically listed.

[0049] The preheating of the nuclear fuel assembly is an important operation link in the operation of a high-temperature nuclear reactor or related tests. When the nuclear fuel assembly enters the reactor, if it is not preheated, uneven thermal expansion may occur in various parts of the assembly due to thermal shock, resulting in stress concentration and even damage. Preheating can make the temperatures of various parts of the assembly rise slowly and more evenly, allowing the material to have enough time for thermal expansion, enabling the internal stress to be released and distributed evenly in advance, and avoiding damage to the assembly due to excessive stress during subsequent operation, which affects the normal operation of the nuclear reactor.

[0050] When preheating the nuclear fuel assembly, the nuclear fuel assembly is vertically placed in the basket and arranged in a hexagonal pattern. Its overall structure is honeycomb-shaped. The innermost hexagon is the connection mechanism of the basket gripper, without placing the nuclear fuel assembly. Then, six nuclear fuel assemblies are evenly arranged in the first circle close to the center; twelve nuclear fuel assemblies are evenly arranged in the second circle and are arranged with a half-body offset from the nuclear fuel assemblies in the first circle; eighteen nuclear fuel assemblies are evenly arranged in the third circle and are arranged with a half-body offset from the nuclear fuel assemblies in the second circle. It can be understood that the quantity and arrangement of the above nuclear fuel assemblies can be set according to actual requirements.

[0051] This embodiment provides a preheating system for a nuclear fuel assembly, including an argon regulating valve for controlling the argon flow rate, a heater for heating argon, a blower for conducting the argon flow, a first temperature sensor for monitoring the surface temperature data of a target temperature measurement point, a second temperature sensor for monitoring the ambient temperature of the nuclear fuel assembly, a camera for identifying the number of nuclear fuel assemblies, a pressure sensor for monitoring the argon pressure, and a control center for controlling the argon regulating valve, heater, blower, camera, first temperature sensor, and second temperature sensor to execute the preheating strategy.

[0052] The gas is heated by the heater, and then the blower accelerates the gas flow to rapidly circulate and exchange heat the heated gas in the container to achieve the function of temperature rise. When cooling down, the heater is turned off, and normal-temperature air is introduced. The blower continuously blows air into the container to discharge the hot air to achieve the function of cooling down. In addition, the argon regulating valve includes a pressure relief valve, an intake valve, and an exhaust valve. During the heating process, when the internal pressure of the heating container for loading the nuclear fuel assembly rises above the required value, the pressure relief valve automatically opens for pressure relief; when the pressure is lower than the required value, the intake valve opens to continuously charge argon for pressure boost. The preheating system of this embodiment can maintain the temperature in the heating container within the range of 200°C to 250°C and the pressure within the range of 5 kPa to 6 kPa.

[0053] As Figure 1 shown, based on the above preheating system for nuclear fuel assemblies, this embodiment further provides a preheating method for nuclear fuel assemblies, and the method includes:

[0054] Step S10: Input the preheating data set of the nuclear fuel assembly under multiple historical working conditions into a pre-set preheating model for training to obtain the predicted temperature value of the target temperature measurement point on the nuclear fuel assembly that meets the pre-set thermal uniformity threshold range;

[0055] Step S20: Train the predicted temperature value according to a pre-set loss function to determine the loss value of the preheating model under different historical working conditions; and based on a pre-set update rule, update the preheating model through the loss value to obtain a trained preheating model;

[0056] Step S30: Input the preheating data set of the nuclear fuel assembly under the current working condition into the trained preheating model to generate a preheating strategy, and control the preheating system to heat the argon in response to the preheating strategy.

[0057] In the preheating method of the nuclear fuel assembly of this embodiment, by combining the preheating data of the nuclear fuel assembly under different historical working conditions for training, under the guidance of the thermal uniformity data, the preheating model is prompted to predict the actual required temperatures of each target temperature measurement point under the actual working conditions, and the argon regulating valve, heater, and fan of the preheating system are controlled to execute the preheating strategy, so that the target temperature measurement points reach the actual required temperatures, thereby ensuring uniform heating of each part of the nuclear fuel assembly.

[0058] Step S10: Input the preheating data sets of the nuclear fuel assembly under multiple historical working conditions into a pre-set preheating model for training to obtain the predicted temperature values of the target temperature measurement points on the nuclear fuel assembly that meet the pre-set thermal uniformity threshold range.

[0059] In step S10, the new components of the sodium-cooled fast reactor usually include a nuclear fuel assembly, a control assembly, a conversion zone assembly, a reflector assembly, and a shielding layer assembly, etc. The nuclear fuel assembly includes fuel rods filled with nuclear fuel inside, positioning grids for fixing the fuel rods, and upper and lower nozzle assemblies for supporting the fuel assembly; the control assembly includes control rods and a transmission mechanism for driving the control rods to move, and the control rods are used to control the number of neutrons and adjust the rate of nuclear reaction by inserting or withdrawing from the core; the conversion zone assembly includes depleted uranium rods for realizing the breeding of the nuclear fuel assembly and sleeves for accommodating the depleted uranium rods; the reflector assembly includes a reflecting material for maintaining the chain reaction in the reactor and a structural frame for fixing the reflecting material; the shielding layer assembly includes a neutron absorption material for absorbing leaked neutrons and a protective shell for wrapping the neutron absorption material.

[0060] When the preheating system preheats the nuclear fuel assembly, the temperature in the heating container is usually maintained within the range of 200°C to 250°C and the pressure is within the range of 5 kPa to 6 kPa. However, due to changes in the structure, size, and composition of the nuclear fuel assembly, it is easy to cause uneven heat transfer on the surface and deep layer of the nuclear fuel assembly corresponding to the target temperature measurement points. And due to the argon flow, there are large pressure deviations near multiple target temperature measurement points, which also easily affects the heat transfer efficiency of argon to the nuclear fuel assembly near the target temperature measurement points, resulting in uneven heating of the nuclear fuel assembly.

[0061] The thermal uniformity data is used to measure the temperature distribution uniformity of the entire nuclear fuel assembly during the heat transfer of argon to the nuclear fuel assembly and the heat conduction from the surface layer to the deep layer of the nuclear fuel assembly. Usually, the closer the value of the thermal uniformity data is to 1, the more uniform each part of the nuclear fuel assembly is. In this embodiment, the value of the thermal uniformity threshold range is 0.95 - 1. It can be understood that the thermal uniformity threshold range can be set according to the actual reaction results of the nuclear fuel assembly under various historical working conditions.

[0062] The preset data set at least includes the surface temperature data of multiple target temperature measurement points under various historical working conditions, the Biot number of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotation speed of the fan.

[0063] The surface temperature data of the target temperature measurement points usually refers to the surface temperature of the fuel rods, and the detection of the surface temperature data can be realized by an infrared temperature sensor. According to theories such as Planck's law, the infrared radiation intensity of an object is related to the temperature, and the infrared temperature sensor can measure the surface temperature data of the target temperature measurement points according to the infrared radiation energy emitted by the surface of the nuclear fuel assembly.

[0064] When manufacturing nuclear fuel assemblies, the nuclear fuel assemblies entering the same nuclear reactor have the same specifications and composition. The Biot number is a ratio representing the conduction thermal resistance per unit conduction area inside the nuclear fuel assembly to the heat transfer thermal resistance per unit area (i.e., the external thermal resistance) on the unit area, and its expression is , where B is the Biot number, is the surface heat transfer coefficient, h is the characteristic length, is the solid thermal conductivity. The solid thermal conductivity of each component can be determined by determining the outer surface composition and the internal composition of the nuclear fuel assembly and the surface heat transfer coefficient , and then the characteristic length h of the nuclear fuel assembly can be determined by combining the specifications of the nuclear fuel assembly, so that the Biot number of the target temperature measurement points can be determined.

[0065] The argon regulating valve includes a pressure relief valve, an intake valve, an exhaust valve, etc. A flowmeter can be set at the valve port of the argon regulating valve to determine the flow rate of argon through the flowmeter, and the opening degree of the argon regulating valve can be determined according to the flow rate formula. It can be understood that the opening degree of the valve body can be controlled by a PID controller.

[0066] A pressure sensor is also provided near the target temperature measurement points, and the pressure of argon near the target temperature measurement points can be detected by the pressure sensor.

[0067] Inputting the preheating data set of the nuclear fuel assembly under various historical working conditions into a preset preheating model for training to obtain the predicted temperature value of the target temperature measurement points on the nuclear fuel assembly that meets the preset thermal uniformity threshold range specifically includes:

[0068] Step S11: Construct a Markov joint probability distribution based on the interaction relationship among the surface temperature data of the target temperature measurement points, the Biot number of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotation speed of the fan;

[0069] Step S12: Determine the predicted temperature values of each of the target temperature measurement points that satisfy the thermal uniformity threshold range based on the Markov joint probability distribution.

[0070] In this embodiment, by establishing the joint probability distribution among variables with poor correlation, such as the surface temperature data of the target temperature measurement points, the Biot number of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan, whether these variables are in a discrete state or a continuous state, they can be correlated by a simplified Markov chain, and the predicted temperature values of the target temperature measurement points within the corresponding thermal uniformity threshold range can be predicted.

[0071] In step S11, constructing the Markov joint probability distribution based on the interaction relationships among the surface temperature data of the target temperature measurement points, the Biot number of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan specifically includes:

[0072] Step S111: Construct energy clusters respectively according to the surface temperature data and Biot number of two adjacent target temperature measurement points, and construct energy clusters according to the surface temperature data of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan, and establish an energy function based on the energy clusters;

[0073] Step S112: Generate a corresponding Boltzmann potential function according to the energy function, and determine the change parameter of the Boltzmann potential function based on maximum likelihood estimation;

[0074] Step S113: Generate the Markov joint probability distribution based on the change parameter and the Boltzmann potential function.

[0075] In step S111, in the Markov random field, each variable among variables such as the surface temperature data, Biot number, opening degree of the argon regulating valve, pressure of argon near the target temperature measurement points, power of the heater, number of nuclear fuel assemblies, and rotational speed of the fan is regarded as a node. If there are n target temperature measurement points, there are n temperature nodes; assuming there are n argon regulating valves, there are n opening degree nodes; plus the Biot number node, heater power node, and fan rotational speed node, they altogether constitute the node set of the graph structure of the Markov random field.

[0076] The joint probability distribution among multiple variables can be decomposed into the product of multiple factors based on cliques, and each factor is only related to one energy clique. There are strong interdependencies among the variables within an energy clique, and the relationships among these variables are characterized by an energy function defined on the energy clique. The value of the energy function reflects a certain "preference" or "energy" state of the variables within the energy clique. A high value means that a certain combination of variables within the energy clique is more likely to occur, and a low value means the opposite.

[0077] The energy clique established through the surface temperature data of two adjacent target temperature measurement points can characterize the heat transfer relationship caused by thermal radiation from one target temperature measurement point to another; the energy clique established through the Biot numbers of two adjacent target temperature measurement points can characterize the heat conduction relationship of the heat from one target temperature measurement point to another within the nuclear fuel assembly; the energy clique constructed according to the surface temperature data of the target temperature measurement point, the opening of the argon regulating valve, the argon pressure near the target temperature measurement point, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan can characterize the relationship of heat radiation of the target temperature measurement point affected by the argon flow rate and argon pressure.

[0078] In step S112, the expression of the Boltzmann function is:

[0079]

[0080] where is the energy function of the energy clique constructed from the surface temperature data of two adjacent target temperature measurement points, is the energy function of the energy clique constructed from the Biot numbers of two adjacent target temperature measurement points, is the energy function of the energy clique constructed from the surface temperature data of the target temperature measurement point, the opening of the argon regulating valve, the argon pressure near the target temperature measurement point, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan;

[0081]

[0082]

[0083]

[0084] where and are respectively the surface temperature data of two adjacent target temperature measurement points, and are respectively the Biot numbers of two adjacent target temperature measurement points, T is the surface temperature data, V is the opening, P is the pressure, W is the power, R is the rotational speed, N is the number of nuclear fuel assemblies, is the target surface temperature data, the target opening, is the target pressure, is the target power, is the target rotational speed, N t is the target number of nuclear fuel assemblies, is the average surface temperature, 、 、 、 、 、 and are all weight parameters used to measure the influence degree of each variable on the temperature difference between two adjacent target temperature measurement points.

[0085] Determine the change parameters of the Boltzmann potential function based on maximum likelihood estimation, specifically including:

[0086] Step S1121: Construct the conditional probabilities of the surface temperature data of the target temperature measurement points, the Biot numbers of the target temperature measurement points, the opening degrees of the argon regulating valves, the pressures of the argon near the target temperature measurement points, the powers of the heaters, the numbers of nuclear fuel assemblies, and the rotational speeds of the fans respectively under the condition that other variables are fixed through pseudo-likelihood estimation, and determine the pseudo-approximate likelihood function according to the conditional probabilities;

[0087] Step S1122: Calculate the gradients of the pseudo-approximate likelihood function with respect to the corresponding variables respectively, and update the parameter values of the corresponding variables through the gradient ascent method until the parameter values of the corresponding variables when the pseudo-approximate likelihood function meets the preset iteration conditions are used as the change parameters of the Boltzmann potential function.

[0088] In this embodiment, by using the pseudo-likelihood estimation method, a pseudo-likelihood function is constructed and maximized to estimate the parameters of the Markov random field model, thereby completing the modeling of the relationship between relevant variables during the argon preheating process.

[0089] In step S1121, first set the variable set X = {T n , B n , V n , P n , W n , R n} for the target temperature measurement points, where T n is the set containing the surface temperature data of all target temperature measurement points, B n is the set containing the Biot numbers of all target temperature measurement points, V n is the set containing the opening degrees of the argon regulating valves, P n is the set containing the pressures of the argon near all target temperature measurement points, W n is the set containing the powers of all heaters, and R n is the set containing the rotational speeds of all fans.

[0090] Taking the surface temperature data variable X T as an example, under the condition that other variables X \T ={ B n , V n , P n , W n , R n} are fixed, construct its conditional probability P(X T |X \T ;θ T ) that follows a Gaussian distribution N(u(X \T ;θ T ), σ 2 (X \T ;θ T ))), where u(X \T ;θ T ) and σ 2 (X \T ;θ T ) are non-linear functions of other variables X \T and parameter θ T , and θ T is a set of parameter values to be estimated.

[0091] Then, the pseudo-likelihood function of the surface temperature data variable X T

[0092] In step S1122, first take the logarithm of the pseudo-likelihood function to obtain the log pseudo-likelihood function , then the gradient can be calculated according to the gradient ascent method:

[0093]

[0094] where, is the parameter value of the surface temperature data to be updated.

[0095] As the gradient is updated, until the log pseudo-likelihood function converges, or all the data in the warm-up dataset are iterated, the gradient update can be ended.

[0096] For the Biot number variable X B , the opening variable X V , the pressure variable X P , the power variable X W and the rotational speed variable X R , they can be obtained similarly to the surface temperature data variable X T , and the corresponding parameter values B , V , P ​ W and R 。

[0097] After all iterations are completed, with all updated parameter values 、 B 、 V 、 P 、 W 、 R Calculate the thermal uniformity of the surface temperature data of all target temperature measurement points, and select the parameter values that meet the thermal uniformity threshold to calculate the temperature of the target temperature measurement point as the predicted temperature value.

[0098] Step S20: Train the predicted temperature value according to a pre-set loss function to determine the loss values of the preheating model under different historical working conditions; and based on a pre-set update rule, update the preheating model through the loss values to obtain a trained preheating model.

[0099] Among them, the loss values include the mean square error loss value and the mean absolute error loss value, and the expression of the loss function is:

[0100]

[0101]

[0102] Where is the mean square error loss value, is the mean absolute error loss value, n is the number of target temperature measurement points, is the surface temperature data of the target temperature measurement point in the preheating dataset; is the predicted temperature value.

[0103] The mean square error loss value with a smaller value indicates that the overall deviation between the predicted value and the true value of the preheating model is smaller, the accuracy of the model is higher, and it can more accurately predict the surface temperature of the target temperature measurement point. The mean absolute error loss value directly measures the average absolute deviation between the predicted value and the true value, with a smaller value indicating that the prediction deviation of the model in the average sense is smaller, and it can more intuitively reflect the average prediction error of the model.

[0104] By calculating the mean square error loss value and the mean absolute error loss value under different training rounds, and at the mean square error loss value And the average absolute error loss value When both meet the preset threshold, stop the polling and obtain the trained preheating model.

[0105] Step S30: Input the preheating dataset of the nuclear fuel assembly under the current working condition into the trained preheating model to generate a preheating strategy, and control the preheating system to heat argon in response to the preheating strategy.

[0106] In the preheating strategy, the opening degree of the appropriate argon regulating valve, the pressure of argon near the target temperature measurement point, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan can be output to maintain the surface temperature data of the target temperature measurement point at a relatively high thermal uniformity.

[0107] In addition, due to production or assembly errors, the nuclear fuel assemblies themselves, or the differences in the installation of the containers for accommodating the nuclear fuel assemblies when installing the nuclear fuel assemblies, there are certain differences in the working conditions every time the nuclear fuel assemblies are preheated, which may easily lead to the problem of abnormal heating in some areas of the nuclear fuel assemblies.

[0108] After inputting the preheating dataset of the nuclear fuel assembly under the current working condition into the trained preheating model to generate a preheating strategy, it further includes:

[0109] Step S40: Match the reference thermal uniformity data corresponding to the current working condition for each target temperature measurement point based on historical working conditions;

[0110] Step S50: Compare the uncertainty value between the thermal uniformity data of the preheating strategy of the target temperature measurement point and the reference thermal uniformity data;

[0111] Step S60: Mark the target temperature measurement points whose uncertainty value exceeds the preset uncertainty threshold as abnormal target temperature measurement points;

[0112] Step S70: Extract the preheating parameters in the preset dataset corresponding to the historical working conditions of the abnormal target temperature measurement points, update the preheating dataset according to the preheating parameters, and regenerate a new preheating strategy.

[0113] In steps S40 - S70, select the temperature of similar historical working conditions as the reference thermal uniformity data. Through uncertainty analysis, the target temperature measurement points with abnormal heating in some areas of the nuclear fuel assembly can be compared as abnormal target temperature measurement points, and corrected with the preheating parameters of the historical working conditions at these abnormal target temperature measurement points. On the premise of ensuring a relatively high thermal uniformity, prevent the abnormal target temperature measurement points from overheating.

[0114] In step S50, the loss function can be used Determine the uncertainty value between the thermal uniformity data of the preheating strategy and the reference thermal uniformity data, where L is the uncertainty value; X is the thermal uniformity data of the preheating strategy; and Y is the reference thermal uniformity data.

[0115] In step S70, the updating of the preheating data set according to the preheating parameters specifically includes:

[0116] Step S701: Randomly delete the data in the preheating data set under the current working condition through the random forest algorithm, and establish multiple groups of deleted data sets to be restored for the same data;

[0117] Step S702: Based on the pre-established recovery model, perform data recovery on the deleted data set to obtain a recovery data set;

[0118] Step S703: Calculate the similarity between the deleted data set and the recovered data set, and update the preheating data set with the preheating parameters corresponding to the abnormal target temperature measurement points in the recovered data set that meet the similarity threshold.

[0119] In steps S701 - S703, randomly delete the data in the preheating data set under the current working condition through the random forest algorithm, and establish multiple groups of deleted data sets to be restored for the same data; then perform data recovery on the deleted data set through the pre-established recovery model diagnosed by the damage degree type to obtain a recovery data set; compare the recovery data set with the deleted data set.

[0120] When calculating the similarity between the deleted data set and the recovered data set, combine the thermal uniformity data with the cosine similarity to construct the abnormal feature difference between the deleted data set and the recovered data set. The value range of the cosine similarity is between [-1, 1]. Calculate the similarity between the deleted data set and the recovered data set. When the cosine similarity between the deleted data set and the recovered data set is closer to 1, they are more similar, indicating a higher thermal uniformity. However, if the cosine similarity between the deleted data set and the recovered data set is approximately -1, it means that the deleted data set and the recovered data set are extremely dissimilar, and the preheating parameters of the abnormal target temperature measurement points provided by the recovered data set are inaccurate. It is necessary to reconstruct the deleted data set according to the preheating parameters of the historical working condition until the cosine similarity between the deleted data set and the recovered data set is closer to 1.

[0121] Due to the influence of heat transfer, the temperature deviation between two adjacent target temperature measurement points will not be particularly large. When correcting with the preheating parameters of the historical working condition, it is not a direct replacement, but a way of deleting and restoring, which can avoid misjudgment of the model and thus improve the accuracy of model recognition.

[0122] In addition, when the nuclear fuel assembly is heated, the temperature of the outer layer is usually higher than that of the inner layer. Since the nuclear fuel assembly has multiple layers from the inside to the outside, the nuclear fuel assembly in the outer layer is usually heated to the target temperature, while the temperature of the nuclear fuel assembly in the inner layer remains relatively low. Therefore, when generating the preheating strategy, by means of segmented heating, after each heating to the target temperature of a stage, heat preservation treatment is carried out on the nuclear fuel assembly. On the premise of maintaining the temperature of the outer layer of the nuclear fuel assembly, the inner layer of the nuclear fuel assembly is also fully heated.

[0123] In this embodiment, a heat preservation model is also established based on the Bayesian network, enabling the nuclear fuel assembly to achieve a high degree of thermal uniformity during the heat preservation process.

[0124] The specific method for establishing the heat preservation model is as follows:

[0125] Based on the multi-dimensional transient heat conduction equation, an objective function regarding the heat preservation temperature and the heater power is established, and the surface temperature data actually measured by the first temperature sensor is input into the objective function; then, a prior probability density function of the surface temperature data and the internal temperature data of the nuclear fuel assembly is established, and all parameters in the prior probability density function satisfy the normal distribution; the objective function is combined into the likelihood function of Bayesian inference to obtain the posterior distribution probability density function; then, the posterior probability density function is trained according to the preheating data set under historical working conditions, and the heat preservation model can be obtained.

[0126] The multi-dimensional transient heat conduction equation is:

[0127] where T is the heat preservation temperature, t is the heat preservation time, is the heat diffusion efficiency, , k is the thermal conductivity of the nuclear fuel assembly, is the density of the nuclear fuel assembly, is the specific heat capacity, (x, y, z) are the coordinates of the nuclear fuel assembly at different positions, and Q is the heating intensity of the heating component.

[0128] By setting the target heat preservation temperature as , and the power of the heating component as P, the objective function J can be obtained. The objective function J can be defined as: , where t1 and t2 are the start heat preservation time node and the end heat preservation time node within the preset time period respectively, and is the heating power coefficient, and its value range is usually 0 - 1.

[0129] Assume that the internal temperature data of the nuclear fuel is T i , and the surface temperature data is T s . Then the prior probability density function in the form of a normal distribution of p(T i |T s ) is:

[0130]

[0131] Among them, n is the dimension of the surface temperature data, which is determined according to the number and arrangement of nuclear fuel assemblies. is the mean vector. is the covariance vector. and are determined according to the preheating data set under historical operating conditions.

[0132] Therefore, the posterior probability density function is: .

[0133] Based on the same inventive concept as the above embodiments, this embodiment also provides a computer-readable storage medium, which stores instructions for being loaded and executed by a processor to perform the preheating method of the nuclear fuel assembly as described above.

[0134] In the embodiments of the mobile terminal and the computer-readable storage medium provided in this application, all the technical features of each embodiment of the above control method are included. The expansion and explanation content of the specification is basically the same as that of each embodiment of the above method, and will not be repeated here.

[0135] This application embodiment also provides a computer program product, which includes computer program code. When the computer program code runs on a computer, it causes the computer to execute the methods in various possible implementation manners as above.

[0136] This application embodiment also provides a chip, including a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the device equipped with the chip executes the methods in various possible implementation manners as above.

[0137] The serial numbers of the above embodiments of this application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0138] In this application, for the description of the same or similar term concepts, technical solutions, and / or application scenarios, generally only the first occurrence is described in detail. When it appears repeatedly later, for the sake of brevity, it is generally not repeated. When understanding the technical solutions and other contents of this application, for the same or similar term concepts, technical solutions, and / or application scenarios that are not described in detail later, reference can be made to the relevant detailed descriptions before.

[0139] In this application, the descriptions of each embodiment have their own emphases. For the parts not described or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0140] The technical features of the technical solution of the present application can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present application.

[0141] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium as described above and includes several instructions for causing a terminal device to execute the methods of each embodiment of the present application. The above is only the preferred embodiment of the present application and does not limit the patent scope of the present application. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

[0142] It should be noted that the various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0143] As mentioned above, the above are only the specific implementation manners of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the appended claims.

Claims

1. A preheating method for a nuclear fuel assembly, characterized in that, The method includes: Inputting the preheating data sets of the nuclear fuel assembly under various historical conditions into a preset preheating model for training to obtain the predicted temperature values of the target temperature measurement points on the nuclear fuel assembly that meet the preset thermal uniformity threshold range; Training the predicted temperature values according to a preset loss function to determine the loss values of the preheating model under different historical conditions; and updating the preheating model based on a preset update rule through the loss values to obtain a trained preheating model; Inputting the preheating data set of the nuclear fuel assembly under the current condition into the trained preheating model to generate a preheating strategy, and controlling the preheating system to heat argon in response to the preheating strategy; The preheating data set at least includes the surface temperature data of multiple target temperature measurement points under each historical condition, the Biot number of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of the argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan; the step of inputting the preheating data sets of the nuclear fuel assembly under various historical conditions into a preset preheating model for training to obtain the predicted temperature values of the target temperature measurement points on the nuclear fuel assembly that meet the preset thermal uniformity threshold range specifically includes: Constructing a Markov joint probability distribution based on the interaction relationships among the surface temperature data of the target temperature measurement points, the Biot number of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of the argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan; Determining the predicted temperature values of each target temperature measurement point that meet the thermal uniformity threshold range based on the Markov joint probability distribution.

2. The preheating method of the nuclear fuel assembly according to claim 1, characterized in that The step of constructing a Markov joint probability distribution based on the interaction relationships among the surface temperature data of the target temperature measurement points, the Biot number of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of the argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan specifically includes: Constructing energy clusters respectively according to the surface temperature data and Biot number of adjacent two target temperature measurement points, and constructing energy clusters according to the surface temperature data of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of the argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan, and establishing an energy function based on the energy clusters; Generating a corresponding Boltzmann potential function according to the energy function, and determining the change parameters of the Boltzmann potential function based on maximum likelihood estimation; Generating the Markov joint probability distribution based on the change parameters and the Boltzmann potential function.

3. The preheating method of the nuclear fuel assembly according to claim 2, characterized in that, The expression of the Boltzmann potential function is: Among them, E(T i , T j ) is the energy function of the energy cluster constructed from the surface temperature data of two adjacent target temperature measurement points, E(B i , B j ) is the energy function of the energy cluster constructed from the Biot numbers of two adjacent target temperature measurement points, and E(T, V, P, W, R, N) is the energy function of the energy cluster constructed from the surface temperature data of the target temperature measurement point, the opening degree of the argon regulating valve, the pressure of argon near the target temperature measurement point, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan; E(T i ,T j ) = α1·(T i -T j ) 2 E(B i ,B j ) = α2·(B i -B j ) 2 E(T, V, P, W, R, N) = α3·(T - T t ) 2 + α4·(V - V t ) 2 + α5·(P - P t ) 2 + α6·(W - W t ) 2 + α7·(R - R t ) 2 + α8·(N - N t ) 2 Among them, T i and T j are the surface temperature data of two adjacent target temperature measurement points respectively, B i and B j are the Biot numbers of two adjacent target temperature measurement points respectively, T is the surface temperature data, V is the opening degree, P is the pressure, W is the power, R is the rotational speed, N is the number of nuclear fuel assemblies, T t is the target surface temperature data, V t is the target opening degree, P t is the target pressure, W t is the target power, R t is the target rotational speed, N t is the target number of nuclear fuel assemblies, is the average surface temperature, and α1, α2, α3, α4, α5, α6, α7 and α8 are all weight parameters.

4. The preheating method of the nuclear fuel assembly according to claim 2, characterized in that, The step of determining the change parameters of the Boltzmann potential function based on maximum likelihood estimation specifically includes: Constructing the conditional probabilities of the surface temperature data of the target temperature measurement points, the Biot number of the target temperature measurement points, the opening degree of the argon regulating valve, the pressure of the argon near the target temperature measurement points, the power of the heater, the number of nuclear fuel assemblies, and the rotational speed of the fan respectively under the condition that other variables are fixed through pseudo-likelihood estimation, and determining a pseudo-approximate likelihood function according to the conditional probabilities; Calculate the gradients of the pseudo - approximate likelihood function with respect to the corresponding variables, and update the parameter values of the corresponding variables by the gradient ascent method until the parameter values of the corresponding variables are used as the change parameters of the Boltzmann potential function when the pseudo - approximate likelihood function satisfies the preset iteration conditions.

5. The preheating method of the nuclear fuel assembly according to claim 1, characterized in that, The loss value includes the mean square error loss value and the mean absolute error loss value, and the expression of the loss function is: Among them, M1 is the mean square error loss value, M2 is the mean absolute error loss value, n is the number of target temperature measurement points, and y i is the surface temperature data of the target temperature measurement points in the preheating dataset; is the predicted temperature value.

6. The preheating method of the nuclear fuel assembly according to claim 1, characterized in that After inputting the pre - heating data set of the nuclear fuel assembly under the current working condition into the trained pre - heating model to generate a pre - heating strategy, it further includes: Match the reference thermal uniformity data corresponding to the current working condition for each target temperature measurement point based on historical working conditions; Compare the uncertainty value between the thermal uniformity data of the pre - heating strategy of the target temperature measurement point and the reference thermal uniformity data; Mark the target temperature measurement points whose uncertainty values exceed the preset uncertainty threshold as abnormal target temperature measurement points; Extract the pre - heating parameters in the pre - heating data set corresponding to the historical working conditions of the abnormal target temperature measurement points in the reference thermal uniformity data, update the pre - heating data set according to the pre - heating parameters, and regenerate a new pre - heating strategy.

7. The preheating method of the nuclear fuel assembly according to claim 6, wherein The updating of the pre - heating data set according to the pre - heating parameters specifically includes: Randomly delete the data in the pre - heating data set under the current working condition through the random forest algorithm, and establish multiple sets of deleted data sets to be restored for the same data; Based on the pre - established recovery model, perform data recovery on the deleted data sets to obtain a recovery data set; Calculate the similarity between the deleted data sets and the recovery data sets, and update the pre - heating data set with the pre - heating parameters corresponding to the abnormal target temperature measurement points in the recovery data sets whose similarity meets the similarity threshold.

8. A preheating system for a nuclear fuel assembly, characterized in that, It includes an argon regulating valve for controlling the argon flow rate, a heater for heating argon, a blower for conducting the argon flow, a first temperature sensor for monitoring the surface temperature data of the target temperature measurement point, a second temperature sensor for monitoring the ambient temperature of the nuclear fuel assembly, a camera for identifying the number of nuclear fuel assemblies, and a control center for controlling the argon regulating valve, heater, blower, camera, first temperature sensor and second temperature sensor to execute the pre - heating strategy. The control center is used to execute the pre - heating method of the nuclear fuel assembly according to any one of claims 1 - 7.

9. A computer-readable storage medium, characterized in that, The computer - readable storage medium stores instructions, and the instructions are used to be loaded and executed by a processor to execute the pre - heating method of the nuclear fuel assembly according to any one of claims 1 - 7.

Images