Critical heat flux determination method, device, equipment, storage medium and product

Abstract

The present application provides a critical heat flux determination method, device, equipment, storage medium and product. The method includes: obtaining multiple fluid characteristic data and multiple temperature field data of the fluid in the rectangular channel of the nuclear power system; inputting the multiple fluid characteristic data into the preset critical heat flux empirical correlation formula respectively, and calculating the multiple first critical heat flux values ​​corresponding to the fluid; inputting the multiple temperature field data into the preset critical heat flux determination model for processing respectively, and obtaining the multiple second critical heat flux values ​​corresponding to the fluid; respectively calculating the residual between each of the first critical heat flux values ​​and the corresponding second critical heat flux values; determining the target first critical heat flux value and the target second critical heat flux value with the minimum residual; according to the target first critical heat flux value and the target second critical heat flux value, obtaining the critical heat flux prediction value of the fluid.

Description

Technical Field

[0001] The present application relates to the technical field of nuclear power systems, and in particular to a critical heat flux determination method, device, equipment, storage medium and product. Background Art

[0002] As an emerging energy technology, nuclear energy and nuclear power systems are becoming increasingly important with the development of technology. Critical heat flux (CHF) is a very important parameter in the operation of nuclear power systems. When the coolant in a nuclear power system reaches CHF, the heat transfer coefficient in the channel will drop rapidly and the wall superheat will rise sharply, which may seriously endanger the safety of the heat exchange equipment and affect the stable operation of the system.

[0003] Accurate prediction of critical heat flux (CHF) is crucial for the optimal design and safety assessment of nuclear and thermal energy systems. Traditional CHF prediction methods mainly rely on empirical relationships based on a large amount of experimental data. These methods are limited in scope and accuracy. Summary of the invention

[0004] The embodiments of the present application provide a critical heat flux determination method, device, equipment, storage medium and product, which can improve the application scope and accuracy of critical heat flux prediction.

[0005] In a first aspect, the present application provides a method for determining a critical heat flux density, comprising:

[0006] Acquire multiple fluid characteristic data and multiple temperature field data of the fluid in the rectangular channel of the nuclear power system;

[0007] Inputting the plurality of fluid characteristic data into a preset critical heat flux density empirical correlation formula respectively, and calculating and obtaining a plurality of first critical heat flux density values ​​corresponding to the fluid;

[0008] Inputting the plurality of temperature field data into a preset critical heat flux determination model for processing, respectively, to obtain a plurality of second critical heat flux values ​​corresponding to the fluid;

[0009] respectively calculating the residual between each of the first critical heat flux values ​​and the corresponding second critical heat flux value;

[0010] Determine a target first critical heat flux value and a target second critical heat flux value with the minimum residual;

[0011] A predicted critical heat flux value of the fluid is obtained according to the target first critical heat flux value and the target second critical heat flux value.

[0012] In some possible implementations, the fluid characteristic data includes mass flow rate, wall superheat corresponding to the rectangular channel, and surface roughness corresponding to the rectangular channel.

[0013] In some possible implementations, the inputting of the plurality of fluid characteristic data into a preset critical heat flux density empirical correlation formula to calculate a plurality of first critical heat flux density values ​​corresponding to the fluid includes:

[0014] Normalizing the mass flow rate, the wall superheat and the surface roughness in each of the fluid characteristic data to obtain normalized mass flow rate, wall superheat and surface roughness;

[0015] Each normalized mass flow rate, normalized wall superheat and normalized surface roughness is input into a preset critical heat flux empirical correlation formula to calculate and obtain a plurality of first critical heat flux values ​​corresponding to the fluid.

[0016] In some possible implementations, the preset critical heat flux density empirical correlation includes:

[0017]

[0018] in, represents the first critical heat flux value, represents the normalized mass flow rate of the fluid, represents the normalized wall superheat corresponding to the rectangular channel, Represents the normalized surface roughness of the rectangular channel.

[0019] In some possible implementations, normalizing the mass flow rate, the wall superheat, and the surface roughness in each of the fluid characteristic data to obtain the normalized mass flow rate, the wall superheat, and the surface roughness includes:

[0020]

[0021]

[0022]

[0023]

[0024] in, represents the initial mass flow rate, represents the acceleration due to gravity, represents the vapor density of the fluid, represents the liquid density corresponding to the fluid, represents the specific heat capacity of the fluid, represents the initial wall superheat, represents the latent heat of vaporization of the fluid, represents the initial surface roughness, represents the Laplace length corresponding to the fluid, represents the surface tension of the fluid, represents the normalized mass flow rate of the fluid, represents the normalized wall superheat corresponding to the rectangular channel, Represents the normalized surface roughness of the rectangular channel.

[0025] In some possible implementations, before respectively inputting the plurality of temperature field data into a preset critical heat flux determination model for processing to obtain a plurality of second critical heat flux values ​​corresponding to the fluid, the method further includes:

[0026] Acquire a training sample set; the training sample set includes a plurality of training samples; each of the training samples includes a temperature field data sample of a fluid in a rectangular channel, a fluid characteristic data sample and a corresponding critical heat flux density value label;

[0027] For each training sample, perform the following steps:

[0028] Inputting the fluid characteristic data sample into a preset critical heat flux density empirical correlation formula to calculate a first critical heat flux density value;

[0029] Obtaining a first residual according to a difference between the first critical heat flux value and the critical heat flux value label;

[0030] Inputting the temperature field data sample into a preset model for processing to obtain a second critical heat flux value;

[0031] Obtaining a second residual according to a difference between the second critical heat flux value and the critical heat flux value label;

[0032] Determine a loss function value of the preset model based on the first residual and the second residual and the loss function;

[0033] When the loss function value of the preset model does not satisfy the preset training stop condition, the model parameters of the preset model are adjusted, and the step of returning to inputting the fluid characteristic data sample into a preset critical heat flux density empirical correlation formula and calculating a first residual between the empirical correlation formula result and the critical heat flux density value label is performed;

[0034] When the loss function value of the preset model meets the preset training stop condition, the training is stopped to obtain the trained critical heat flux density determination model.

[0035] In some possible implementations, obtaining a training sample set includes:

[0036] Create a geometric model of a rectangular channel;

[0037] Based on the geometric model of the rectangular channel, simulating the rectangular channel fluid;

[0038] Determining simulated temperature field data and simulated fluid characteristic data of the fluid according to the simulation results of the simulation;

[0039] A training sample set is obtained based on the simulated temperature field data and the simulated fluid characteristic data.

[0040] In a second aspect, the present application provides a critical heat flux determination device, the device comprising:

[0041] Acquire multiple fluid characteristic data and multiple temperature field data of the fluid in the rectangular channel of the nuclear power system;

[0042] Inputting the plurality of fluid characteristic data into a preset critical heat flux density empirical correlation formula respectively, and calculating and obtaining a plurality of first critical heat flux density values ​​corresponding to the fluid;

[0043] Inputting the plurality of temperature field data into a preset critical heat flux determination model for processing, respectively, to obtain a plurality of second critical heat flux values ​​corresponding to the fluid;

[0044] respectively calculating the residual between each of the first critical heat flux values ​​and the corresponding second critical heat flux value;

[0045] Determine a target first critical heat flux value and a target second critical heat flux value with the minimum residual;

[0046] A predicted critical heat flux value of the fluid is obtained according to the target first critical heat flux value and the target second critical heat flux value.

[0047] In a third aspect, the present application provides a critical heat flux density determination device, the device comprising: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the critical heat flux density determination method as described above.

[0048] In a fourth aspect, the present application provides a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the critical heat flux density determination method as described above is implemented.

[0049] In a fifth aspect, the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the critical heat flux density determination method as described above.

[0050] The critical heat flux determination method, device, equipment, storage medium and product provided in the embodiments of the present application, after obtaining multiple fluid characteristic data and multiple temperature field data of the fluid in the rectangular channel of the nuclear power system, calculate the first critical heat flux value corresponding to the fluid characteristic data through a preset critical heat flux empirical correlation formula, determine the second critical heat flux value corresponding to the temperature field data through a preset critical heat flux determination model, and then calculate the residuals between each of the first critical heat flux values ​​and each of the second critical heat flux values ​​respectively, so as to obtain the critical heat flux prediction value of the fluid according to the first critical heat flux value and the second critical heat flux value corresponding to the case where the residual is minimized, and use the machine learning model to make predictions through the acquired fluid characteristic data and temperature field data, and combine the empirical correlation formula to optimize the prediction results, thereby combining physical information and machine learning algorithms to improve the accuracy and scope of CHF value prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The present application can be better understood from the following description of the specific embodiments of the present application in conjunction with the accompanying drawings, in which:

[0052] Other features, objects and advantages of the present application will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings, in which the same or similar reference numerals represent the same or similar features.

[0053] Figure 1 is a flow chart of a method for determining critical heat flux density provided by an embodiment of the present application;

[0054] Figure 2 is a flow chart of a critical heat flux determination model training process provided by an embodiment of the present application;

[0055] Figure 3 is a schematic flow chart of a method for determining critical heat flux density provided by another embodiment of the present application;

[0056] Figure 4 is a schematic structural diagram of a critical heat flux determination device provided by an embodiment of the present application;

[0057] Figure 5 It is a schematic diagram of the hardware structure of the critical heat flux density determination device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0059] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0060] In order to solve the problems of the prior art, the embodiments of the present application provide a critical heat flux determination method, device, equipment, storage medium and product. The critical heat flux determination method provided in the embodiments of the present application is first introduced below.

[0061] Figure 1 FIG. 1 is a flow chart of a method for determining critical heat flux density provided by an embodiment of the present application. Figure 1 As shown, the method includes the following steps: S101 to S106.

[0062] S101: Acquire multiple fluid characteristic data and multiple temperature field data of the fluid in the rectangular channel of the nuclear power system.

[0063] In a specific implementation, multiple characteristic data of the fluid can be obtained through sensors or model simulation, such as flow rate, density, viscosity, etc. At the same time, temperature field data can be obtained based on temperature readings at multiple measurement points.

[0064] As another example, the collected fluid characteristics and temperature field data may be stored in an appropriate data structure (such as an array, a list, or a database) for subsequent processing.

[0065] S102: Inputting the plurality of fluid characteristic data into a preset critical heat flux density empirical correlation formula respectively, and calculating and obtaining a plurality of first critical heat flux density values ​​corresponding to the plurality of fluids.

[0066] In a specific implementation, a preset critical heat flux density empirical correlation formula suitable for the nuclear power system is selected. For each fluid characteristic data, it is input into the empirical correlation formula, and a loop structure can be used to traverse all fluid characteristic data, store the calculation results in a new array, and record multiple calculated first critical heat flux density values.

[0067] S103: Inputting the plurality of temperature field data into a preset critical heat flux determination model for processing, respectively, to obtain a plurality of second critical heat flux values ​​corresponding to the fluid.

[0068] In a specific implementation, a preset critical heat flux determination model is determined, and each temperature field data is input into the selected model for processing. Similar to step S102, a loop structure can be used to traverse all temperature field data and perform calculations to obtain multiple second critical heat flux values ​​corresponding to the above fluid. The obtained multiple second critical heat flux values ​​are stored in a corresponding data structure, ready for residual analysis.

[0069] S104: Calculate the residual between each of the first critical heat flux values ​​and the corresponding second critical heat flux value.

[0070] In a specific implementation, the array of the first and second critical heat flux values ​​is traversed, the difference between the first critical heat flux value and the corresponding second critical heat flux value is calculated, and the residual between each pair of values ​​is obtained.

[0071] S105: Determine the target first critical heat flux value and the target second critical heat flux value with the minimum residual.

[0072] In a specific implementation, all residuals are traversed to determine the value of the minimum residual, and the corresponding target first and target second critical heat flux density values ​​are extracted according to the minimum residual.

[0073] S106: Obtaining a predicted critical heat flux value of the fluid according to the target first critical heat flux value and the target second critical heat flux value.

[0074] In a specific implementation, within the range corresponding to the above-mentioned target first critical heat flux density value and the target second critical heat flux density value, the predicted critical heat flux density value of the fluid is selected. For example, the target first critical heat flux density value and the target second critical heat flux density value are weighted averaged to obtain the predicted critical heat flux density value of the above-mentioned fluid, or the predicted critical heat flux density value of the above-mentioned fluid is selected from the target first critical heat flux density value and the target second critical heat flux density value.

[0075] The critical heat flux determination method provided in the embodiment of the present application, after obtaining multiple fluid characteristic data and multiple temperature field data of the fluid in the rectangular channel of the nuclear power system, calculates the first critical heat flux value corresponding to the fluid characteristic data through a preset critical heat flux empirical correlation formula, determines the second critical heat flux value corresponding to the temperature field data through a preset critical heat flux determination model, and then calculates the residuals between each of the above-mentioned first critical heat flux values ​​and each of the above-mentioned second critical heat flux values, thereby obtaining the critical heat flux prediction value of the above-mentioned fluid based on the first critical heat flux value and the second critical heat flux value corresponding to the case where the above-mentioned residual is minimum, and predicts by using the machine learning model through the acquired fluid characteristic data and temperature field data, and optimizes the prediction result by combining the empirical correlation formula, combining physical information and machine learning algorithms, and improving the accuracy and scope of application of CHF value prediction.

[0076] In some embodiments, the fluid characteristic data may include mass flow rate, wall superheat corresponding to the rectangular channel, and surface roughness corresponding to the rectangular channel.

[0077] In order to obtain a more accurate first critical heat flux value, in some embodiments, the above S102 may include the following steps: S1021 to S1022.

[0078] S1021: respectively normalizing the mass flow rate, the wall superheat and the surface roughness in each of the above fluid characteristic data to obtain normalized mass flow rate, wall superheat and surface roughness.

[0079] In the specific implementation, a normalization function is created in advance, which accepts the original data and returns the normalized value after calculation. The mass flow rate, wall superheat and surface roughness are traversed respectively. For each characteristic data, the normalization function is called to convert the original value into a normalized value to obtain the normalized mass flow rate, wall superheat and surface roughness.

[0080] S1022: Input each normalized mass flow rate, normalized wall superheat and normalized surface roughness into a preset critical heat flux empirical correlation formula, and calculate a plurality of first critical heat flux values ​​corresponding to the above fluid.

[0081] In the specific implementation, after defining the preset empirical correlation, a calculation function is created, which accepts the normalized mass flow rate, wall superheat and surface roughness as input and returns the first critical heat flux value based on the empirical correlation. A loop structure is used to traverse the normalized mass flow rate, wall superheat and surface roughness arrays. For each set of data, the calculation function is called to calculate multiple first critical heat flux values ​​corresponding to the above fluid.

[0082] The above-mentioned implementation method of the embodiment of the present application normalizes the mass flow rate, the wall superheat and the surface roughness in each of the above-mentioned fluid characteristic data respectively, and uses the normalized data to calculate multiple first critical heat flux density values ​​corresponding to the above-mentioned fluid, so that different parameters are in the same quantitative range, and a more accurate first critical heat flux density value can be obtained.

[0083] In order to obtain a first critical heat flux value that is more in line with the actual situation, in some embodiments, the above-mentioned preset critical heat flux empirical correlation formula may include:

[0084]

[0085] in, represents the first critical heat flux value, represents the normalized mass flow rate of the fluid, represents the normalized wall superheat corresponding to the rectangular channel, Represents the normalized surface roughness of the rectangular channel.

[0086] The above implementation of the embodiment of the present application defines a specific preset critical heat flux density empirical correlation formula, so that a first critical heat flux density value that is more in line with actual conditions can be obtained.

[0087] In order to obtain more accurate normalized mass flow rate, wall superheat and surface roughness, in some embodiments, the above S1021 may include:

[0088]

[0089]

[0090]

[0091]

[0092] in, represents the initial mass flow rate, represents the acceleration due to gravity, represents the vapor density of the fluid, represents the liquid density corresponding to the fluid, represents the specific heat capacity of the fluid, represents the initial wall superheat, represents the latent heat of vaporization of the fluid, represents the initial surface roughness, represents the Laplace length corresponding to the fluid, represents the surface tension of the fluid, represents the normalized mass flow rate of the fluid, represents the normalized wall superheat corresponding to the rectangular channel, Represents the normalized surface roughness of the rectangular channel.

[0093] The above implementation of the embodiment of the present application defines a specific normalization processing formula, so that more accurate normalized mass flow rate, wall superheat and surface roughness can be obtained.

[0094] In order to train a suitable critical heat flux determination model, in some embodiments, reference may be made to Figure 2 Before the above S103, the above method may further include the following steps: S201 to S209.

[0095] S201: Acquire a training sample set; the training sample set includes a plurality of training samples; each of the training samples includes a temperature field data sample of a fluid in a rectangular channel, a fluid characteristic data sample and a corresponding critical heat flux density value label.

[0096] In the specific implementation, first, a training sample set containing multiple training samples needs to be collected. Each training sample should contain the following three parts of data: temperature field data samples, which represent the temperature distribution of the fluid in the rectangular channel; fluid characteristic data samples, including mass flow rate, wall superheat, surface roughness and other characteristics; critical heat flux value label, corresponding to the real critical heat flux value, as the target of supervised learning.

[0097] As another example, temperature field data and fluid characteristic data can be generated through experiments or simulations, and then these data are integrated with corresponding critical heat flux density value labels to form a training sample set. The data can be stored in a structured format.

[0098] For each training sample, perform the following steps:

[0099] S202: Input the fluid characteristic data sample into a preset critical heat flux density empirical correlation formula to calculate a first critical heat flux density value.

[0100] In a specific implementation, for each training sample, the fluid characteristic data is input into a preset critical heat flux density empirical correlation formula, and calculation is performed based on the empirical correlation formula. The calculation results of all training samples are stored in an array or a list.

[0101] S203: Obtain a first residual according to a difference between the first critical heat flux value and the critical heat flux value label.

[0102] In a specific implementation, each training sample is traversed, and a first residual is calculated according to a difference between the first critical heat flux value and a true critical heat flux value label.

[0103] S204: Input the temperature field data sample into a preset model for processing to obtain a second critical heat flux value.

[0104] S205: Obtain a second residual according to a difference between the second critical heat flux value and the critical heat flux value label.

[0105] In a specific implementation, each training sample is traversed, and the second residual is calculated according to the difference between the second critical heat flux value and the true critical heat flux value label.

[0106] S206: Determine the loss function value of the preset model based on the loss function according to the first residual and the second residual.

[0107] In a specific implementation, a loss function is defined, and a loss value of the model is calculated using a preset loss function according to the first residual and the second residual.

[0108] S207: Determine whether the loss function value of the preset model meets the preset training stop condition.

[0109] In the specific implementation, a threshold is set. If the current loss value is lower than the threshold, the training is stopped; otherwise, the model parameters are adjusted. This judgment can be implemented through conditional statements.

[0110] S208: When the loss function value of the above-mentioned preset model does not meet the preset training stop condition, adjust the model parameters of the above-mentioned preset model, return to the step of inputting the above-mentioned fluid characteristic data sample into the preset critical heat flux density empirical correlation formula, and calculate the first residual between the empirical correlation formula result and the above-mentioned critical heat flux density value label.

[0111] In a specific implementation, when the loss function value of the above-mentioned preset model does not meet the preset training stop condition, an optimization algorithm such as gradient descent is used to update the model parameters. Specifically, the gradient of the loss function is calculated, and the model parameters are adjusted by the learning rate. After completion, return to S202 to continue calculating the first critical heat flux value.

[0112] S209: When the loss function value of the above preset model meets the preset training stop condition, stop the training to obtain the trained critical heat flux density determination model.

[0113] In a specific implementation, when the loss function value of the above-mentioned preset model meets the preset training stop condition, the training is stopped and the trained model parameters are saved.

[0114] The above implementation method of the embodiment of the present application trains the critical heat flux determination model by using a training sample set. During the training process, a first residual is obtained according to the difference between the above first critical heat flux value and the above critical heat flux value label; the above temperature field data sample is input into the preset model for processing to obtain a second critical heat flux value; a second residual is obtained according to the difference between the above second critical heat flux value and the above critical heat flux value label; and a loss function value of the above preset model is determined based on the loss function according to the above first residual and the above second residual, so that a suitable critical heat flux determination model can be trained.

[0115] In order to quickly obtain a suitable training sample set, in some implementations, the above S201 may include the following steps: S2011 to S2014.

[0116] S2011: Create a geometric model of a rectangular channel.

[0117] In a specific implementation, computational fluid dynamics (CFD) software is used to create a geometric model. The dimensions of the rectangular channel, such as width, height, and length, are determined. The outline of the rectangular channel is drawn in the selected software, and the boundary conditions of the channel are ensured to be correctly set to obtain a geometric model of the rectangular channel.

[0118] S2012: Based on the geometric model of the rectangular channel, simulate the rectangular channel fluid.

[0119] In the specific implementation, the rectangular channel geometry model is imported into the fluid simulation software, and the physical properties of the fluid (such as density, viscosity, specific heat, etc.) are defined, and the inlet flow rate, outlet pressure, and boundary conditions are set. The geometry model is meshed to divide the channel into multiple small units for numerical calculations. Ensure that the mesh is fine enough to improve the simulation accuracy. Start the simulation program and perform a time step simulation of the fluid flow. Monitor the convergence and stability of the simulation process. After the simulation is completed, extract the data of the fluid flow, such as the velocity field, pressure field, etc.

[0120] S2013: Determine the simulated temperature field data and simulated fluid characteristic data of the fluid according to the simulation results of the above simulation.

[0121] In the specific implementation, fluid characteristic data such as mass flow rate, wall superheat and surface roughness are obtained according to the simulation results. If the simulation software supports heat conduction or fluid thermodynamics modules, the temperature field data can be directly extracted from the results. If not, the temperature distribution can be calculated by the heat balance equation.

[0122] S2014: Based on the simulated temperature field data and the simulated fluid characteristic data, a training sample set is obtained.

[0123] In the specific implementation, each fluid characteristic data is matched with the corresponding temperature field data to form a one-to-one relationship. A label is added to each sample, and the data is converted into a format suitable for processing by the machine learning algorithm to obtain a training sample set.

[0124] The above implementation of the embodiment of the present application creates a geometric model of a rectangular channel to simulate the fluid in the rectangular channel. According to the simulation results of the above simulation, the simulated temperature field data and simulated fluid characteristic data of the fluid are determined to construct a training sample set, so as to quickly obtain a suitable training sample set.

[0125] In one embodiment of the present application, based on the numerical simulation results of rectangular channel flow boiling, the rectangular channel inlet temperature, inlet flow rate and wall heat flux density can be extracted to form a feature data set, and the temperature field cloud map can be extracted as an image data set. Using a method combining a large amount of physical information based on numerical simulation results with a convolutional neural network algorithm (CNN), a hybrid prediction model is constructed based on the critical heat flux density empirical relationship to achieve the prediction of the critical heat flux density CHF of rectangular channel vapor-liquid two-phase flow boiling.

[0126] Specifically, the fluid mechanics software simulates the CHF of a rectangular narrow slit channel and obtains the data set of the model consisting of the inlet temperature, inlet flow rate and wall heat flux density under the corresponding working conditions. The location of the CHF is determined based on the sudden rise in wall temperature along the vertical heating length. Based on the data set of the numerical simulation image, the boiling critical value (CHF) prediction result is obtained using the convolutional neural network algorithm (CNN).

[0127] Directly input the processed image into the convolutional neural network CNN, train the convolutional neural network, use the trained model to predict, and finally output CHF. Construct the convolutional neural network CNN, set 3 convolutional layers, the size of the convolution kernel is 3×3, 2 pooling layers, the first one is set to maximum pooling, the pooling kernel size is 2×2, the second one is set to average pooling, the pooling kernel size is 2×2, a drop layer, the drop layer parameter is 0.1, followed by 2 fully connected layers and an output layer, output a neuron, that is, the critical heat flux density CHF value.

[0128] The convolutional neural network parameter settings are shown in Table 1, where CH is the height of the convolution kernel, CW is the width of the convolution kernel, CD is the depth of the convolution kernel, Strides is the step size of the convolution kernel, and S is the pooling width of the pooling layer. The optimizer is set to adaptive momentum optimization (ADAM), the learning rate is set to 0.001, the batch size is set to 64, the number of iterations is 100, and the loss function is set to mean squared error.

[0129] Table 1

[0130]

[0131] In order to make the model prediction more accurate and more explainable, the traditional empirical correlation is first used as the prior model. The inlet temperature, flow rate and heat flux density are substituted into it to obtain a prior CHF. The CNN prediction target is the residual between the prior CHF and the intermediate CHF. When the residual approaches the minimum, the current CHF value is output. The traditional empirical correlation is calculated as follows:

[0132]

[0133] in, represents the first critical heat flux value, represents the normalized mass flow rate of the fluid, represents the normalized wall superheat corresponding to the rectangular channel, Represents the normalized surface roughness of the rectangular channel.

[0134]

[0135]

[0136]

[0137]

[0138] in, represents the initial mass flow rate, represents the acceleration due to gravity, represents the vapor density of the fluid, represents the liquid density corresponding to the fluid, represents the specific heat capacity of the fluid, represents the initial wall superheat, represents the latent heat of vaporization of the fluid, represents the initial surface roughness, represents the Laplace length corresponding to the fluid, represents the surface tension of the fluid, represents the normalized mass flow rate of the fluid, represents the normalized wall superheat corresponding to the rectangular channel, Represents the normalized surface roughness of the rectangular channel.

[0139] In summary, you can refer to Figure 3 ,Firstly, the numerical simulation of the critical process of flow boiling in a rectangular channel is started by using ,software, the inlet temperature, inlet flow rate and wall heat flux density of the rectangular ,channel are extracted to form the characteristic data set, and the temperature field ,cloud image is extracted as the image data set.

[0140] S301: Input the processed rectangular channel temperature field cloud image into the convolutional neural network (CNN), train the convolutional neural network, use the trained model to predict the CHF value, and finally output the critical heat flux density (CHF) value of the rectangular channel.

[0141] S302: Calculate the rectangular channel CHF value based on the traditional empirical correlation formula using parameters such as the rectangular channel inlet temperature, flow rate, and pressure, which is the prior model CHF value.

[0142] S303: According to the CNN algorithm logic, the basic training parameter set of the image is analyzed and calculated to calculate the intermediate CHF value, and the residual between the CHF value of the prior model and the intermediate CHF value is calculated. When the residual approaches the minimum, the current CHF value is output, which is the predicted value of the critical heat flux density CHF of the rectangular channel under this working condition.

[0143] Based on the critical heat flux determination method provided in the above embodiment, the present application also provides a specific implementation of a critical heat flux determination device. Please refer to the following embodiment.

[0144] See first Figure 4 The critical heat flux determination device 400 provided in the embodiment of the present application includes the following modules:

[0145] The acquisition module 401 is used to acquire a plurality of fluid characteristic data and a plurality of temperature field data of the fluid in the rectangular channel of the nuclear power system.

[0146] The calculation module 402 is used to input the plurality of the above-mentioned fluid characteristic data into a preset critical heat flux density empirical correlation formula respectively, and calculate a plurality of first critical heat flux density values ​​corresponding to the above-mentioned fluid.

[0147] The processing module 403 is used to input the plurality of temperature field data into a preset critical heat flux determination model for processing, so as to obtain a plurality of second critical heat flux values ​​corresponding to the fluid.

[0148] The calculation module 402 is further used to respectively calculate the residual between each of the above-mentioned first critical heat flux density values ​​and the corresponding above-mentioned second critical heat flux density value.

[0149] The determination module 404 is used to determine the target first critical heat flux value and the target second critical heat flux value with the minimum residual.

[0150] The determination module 404 is further configured to obtain a predicted critical heat flux value of the fluid according to the target first critical heat flux value and the target second critical heat flux value.

[0151] The critical heat flux determination device provided in the embodiment of the present application, after obtaining multiple fluid characteristic data and multiple temperature field data of the fluid in the rectangular channel of the nuclear power system, calculates the first critical heat flux value corresponding to the fluid characteristic data through a preset critical heat flux empirical correlation formula, determines the second critical heat flux value corresponding to the temperature field data through a preset critical heat flux determination model, and then calculates the residuals between each of the above-mentioned first critical heat flux values ​​and each of the above-mentioned second critical heat flux values, thereby obtaining the critical heat flux prediction value of the above-mentioned fluid based on the first critical heat flux value and the second critical heat flux value corresponding to the case where the above-mentioned residual is minimum, and predicts by using the machine learning model through the acquired fluid characteristic data and temperature field data, and optimizes the prediction result by combining the empirical correlation formula, thereby combining physical information and machine learning algorithms, and improving the accuracy and scope of application of CHF value prediction.

[0152] As an implementation of the present application, the calculation module 402 includes:

[0153] The processing unit is used to normalize the mass flow rate, the wall superheat and the surface roughness in each of the above fluid characteristic data to obtain the normalized mass flow rate, wall superheat and surface roughness.

[0154] The calculation unit is used to input each normalized mass flow rate, normalized wall superheat and normalized surface roughness into a preset critical heat flux density empirical correlation formula, and calculate multiple first critical heat flux density values ​​corresponding to the above fluid.

[0155] The above-mentioned implementation method of the embodiment of the present application normalizes the mass flow rate, the wall superheat and the surface roughness in each of the above-mentioned fluid characteristic data respectively, and uses the normalized data to calculate multiple first critical heat flux density values ​​corresponding to the above-mentioned fluid, so that different parameters are in the same quantitative range, and a more accurate first critical heat flux density value can be obtained.

[0156] As an implementation of the present application, the critical heat flux determination device 400 further includes:

[0157] The acquisition module is used to obtain the training sample set.

[0158] The calculation module is used to input the above fluid characteristic data samples into a preset critical heat flux density empirical correlation formula to calculate and obtain a first critical heat flux density value.

[0159] The determination module is used to obtain a first residual according to a difference between the first critical heat flux value and the critical heat flux value label.

[0160] The processing module is used to input the temperature field data sample into a preset model for processing to obtain a second critical heat flux density value.

[0161] The calculation module is further used to obtain a second residual according to a difference between the second critical heat flux value and the critical heat flux value label.

[0162] The determination module is also used to determine the loss function value of the above-mentioned preset model based on the above-mentioned first residual and the above-mentioned second residual and based on the loss function.

[0163] The adjustment module is used to adjust the model parameters of the above-mentioned preset model when the loss function value of the above-mentioned preset model does not meet the preset training stop condition, return to the step of inputting the above-mentioned fluid characteristic data sample into the preset critical heat flux density empirical correlation formula, and calculate the first residual between the empirical correlation formula result and the above-mentioned critical heat flux density value label.

[0164] The stopping module is used to stop the training when the loss function value of the above-mentioned preset model meets the preset training stopping condition, so as to obtain the critical heat flux density determination model after training.

[0165] The above implementation method of the embodiment of the present application trains the critical heat flux determination model by using a training sample set. During the training process, a first residual is obtained according to the difference between the above first critical heat flux value and the above critical heat flux value label; the above temperature field data sample is input into the preset model for processing to obtain a second critical heat flux value; a second residual is obtained according to the difference between the above second critical heat flux value and the above critical heat flux value label; and a loss function value of the above preset model is determined based on the loss function according to the above first residual and the above second residual, so that a suitable critical heat flux determination model can be trained.

[0166] As an implementation of the present application, the acquisition module includes:

[0167] Create a unit to create a geometric model of a rectangular channel.

[0168] The simulation unit is used to simulate the rectangular channel fluid based on the geometric model of the rectangular channel.

[0169] The determination unit is used to determine the simulated temperature field data and the simulated fluid characteristic data of the fluid according to the simulation results of the above simulation.

[0170] The determination unit is further used to obtain a training sample set based on the simulated temperature field data and the simulated fluid characteristic data.

[0171] The above implementation of the embodiment of the present application creates a geometric model of a rectangular channel to simulate the fluid in the rectangular channel. According to the simulation results of the above simulation, the simulated temperature field data and simulated fluid characteristic data of the fluid are determined to construct a training sample set.

[0172] Each module in the critical heat flux determination device provided in the embodiment of the present application can implement each step in the above-mentioned critical heat flux determination method and achieve corresponding effects, which will not be repeated here for the sake of brevity.

[0173] Figure 5 A schematic diagram of the structure of critical heat flux determination hardware provided in an embodiment of the present application is shown.

[0174] The critical heat flux determination device may include a processor 501 and a memory 502 storing computer program instructions.

[0175] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0176] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 502 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.

[0177] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the critical heat flux determination method according to any one of the embodiments of the present disclosure.

[0178] The processor 501 reads and executes computer program instructions stored in the memory 502 to implement any one of the critical heat flux determination methods in the above embodiments.

[0179] In one example, the critical heat flux determination device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.

[0180] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0181] Bus 510 includes hardware, software or both, and couples the components of online data traffic billing equipment to each other. For example, but not limitation, the bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnect (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or a combination of two or more of these. Where appropriate, bus 510 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0182] In addition, in combination with the method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any method for determining critical heat flux density in the above embodiment is implemented.

[0183] An embodiment of the present application also provides a computer program product, including a computer program, which, when processed and executed, implements any one of the methods for determining critical heat flux density in the above embodiments.

[0184] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0185] The functional blocks shown in the structural block diagram described above can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier. "Machine-readable medium" may include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0186] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0187] Aspects of the present disclosure are described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / actions specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0188] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for determining critical heat flux density, characterized in that: The method comprises: Acquire multiple fluid characteristic data and multiple temperature field data of the fluid in the rectangular channel of the nuclear power system; Inputting the plurality of fluid characteristic data into a preset critical heat flux density empirical correlation formula respectively, and calculating and obtaining a plurality of first critical heat flux density values ​​corresponding to the fluid; Acquire a training sample set; the training sample set includes a plurality of training samples; each of the training samples includes a temperature field data sample of a fluid in a rectangular channel, a fluid characteristic data sample and a corresponding critical heat flux density value label; For each training sample, perform the following steps: Inputting the fluid characteristic data sample into a preset critical heat flux density empirical correlation formula to calculate a first critical heat flux density value; Obtaining a first residual according to a difference between the first critical heat flux value and the critical heat flux value label; Inputting the temperature field data sample into a preset model for processing to obtain a second critical heat flux density value; Obtaining a second residual according to a difference between the second critical heat flux value and the critical heat flux value label; Determine a loss function value of the preset model based on the first residual and the second residual and the loss function; When the loss function value of the preset model does not satisfy the preset training stop condition, the model parameters of the preset model are adjusted, and the step of returning to inputting the fluid characteristic data sample into a preset critical heat flux density empirical correlation formula and calculating a first residual between the empirical correlation formula result and the critical heat flux density value label is performed; When the loss function value of the preset model satisfies the preset training stop condition, the training is stopped to obtain the trained critical heat flux density determination model; Inputting the plurality of temperature field data into a preset critical heat flux determination model for processing, respectively, to obtain a plurality of second critical heat flux values ​​corresponding to the fluid; respectively calculating the residual between each of the first critical heat flux values ​​and the corresponding second critical heat flux value; Determine a target first critical heat flux value and a target second critical heat flux value with the minimum residual; A predicted critical heat flux value of the fluid is obtained according to the target first critical heat flux value and the target second critical heat flux value.

2. The critical heat flux determination method according to claim 1, characterized in that: The fluid characteristic data include mass flow rate, wall superheat corresponding to the rectangular channel, and surface roughness corresponding to the rectangular channel.

3. The critical heat flux determination method according to claim 2, characterized in that: The step of inputting the plurality of fluid characteristic data into a preset critical heat flux density empirical correlation formula to calculate a plurality of first critical heat flux density values ​​corresponding to the fluid comprises: Normalizing the mass flow rate, the wall superheat and the surface roughness in each of the fluid characteristic data to obtain normalized mass flow rate, wall superheat and surface roughness; Each normalized mass flow rate, normalized wall superheat and normalized surface roughness is input into a preset critical heat flux empirical correlation formula to calculate and obtain a plurality of first critical heat flux values ​​corresponding to the fluid.

4. The critical heat flux determination method according to claim 3, characterized in that: The preset critical heat flux empirical correlation formula includes: in, represents the first critical heat flux value, represents the normalized mass flow rate of the fluid, represents the normalized wall superheat corresponding to the rectangular channel, Represents the normalized surface roughness of the rectangular channel.

5. The critical heat flux determination method according to claim 3, characterized in that: The mass flow rate, the wall superheat and the surface roughness in each of the fluid characteristic data are normalized to obtain the normalized mass flow rate, the wall superheat and the surface roughness, including: in, represents the initial mass flow rate, represents the acceleration due to gravity, represents the vapor density of the fluid, represents the liquid density corresponding to the fluid, represents the specific heat capacity of the fluid, represents the initial wall superheat, represents the latent heat of vaporization of the fluid, represents the initial surface roughness, represents the Laplace length corresponding to the fluid, represents the surface tension of the fluid, represents the normalized mass flow rate of the fluid, represents the normalized wall superheat corresponding to the rectangular channel, Represents the normalized surface roughness of the rectangular channel.

6. The critical heat flux determination method according to claim 1, characterized in that: The step of obtaining a training sample set includes: Create a geometric model of a rectangular channel; Based on the geometric model of the rectangular channel, simulating the rectangular channel fluid; Determining simulated temperature field data and simulated fluid characteristic data of the fluid according to the simulation results of the simulation; A training sample set is obtained based on the simulated temperature field data and the simulated fluid characteristic data.

7. A critical heat flux determination device, characterized in that: The device comprises: An acquisition module, used for acquiring a plurality of fluid characteristic data and a plurality of temperature field data of the fluid in the rectangular channel of the nuclear power system; A calculation module, used for inputting the plurality of fluid characteristic data into a preset critical heat flux density empirical correlation formula respectively, and calculating a plurality of first critical heat flux density values ​​corresponding to the fluid; A processing module, used for inputting the plurality of temperature field data into a preset critical heat flux density determination model for processing, to obtain a plurality of second critical heat flux density values ​​corresponding to the fluid; The calculation module is further used to respectively calculate the residual between each of the first critical heat flux values ​​and the corresponding second critical heat flux value; A determination module, used to determine a target first critical heat flux value and a target second critical heat flux value with the minimum residual; The determination module is further used to obtain a predicted critical heat flux value of the fluid according to the target first critical heat flux value and the target second critical heat flux value; The processing module is also used to obtain a training sample set; the training sample set includes multiple training samples; each of the training samples includes a temperature field data sample of the fluid in the rectangular channel, a fluid characteristic data sample and a corresponding critical heat flux value label; for each training sample, the following steps are performed respectively: the fluid characteristic data sample is input into a preset critical heat flux empirical correlation formula to calculate a first critical heat flux value; a first residual is obtained according to the difference between the first critical heat flux value and the critical heat flux value label; the temperature field data sample is input into a preset model for processing to obtain a second critical heat flux value; and a second critical heat flux value is obtained according to the second critical heat flux value label. The difference between the flow density value and the critical heat flux density value label is obtained to obtain a second residual; according to the first residual and the second residual, based on the loss function, the loss function value of the preset model is determined; when the loss function value of the preset model does not meet the preset training stop condition, the model parameters of the preset model are adjusted, and the step of inputting the fluid characteristic data sample into the preset critical heat flux density empirical correlation formula to calculate the first residual between the empirical correlation formula result and the critical heat flux density value label is returned; when the loss function value of the preset model meets the preset training stop condition, the training is stopped to obtain the trained critical heat flux density determination model.

8. A critical heat flux determination device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the critical heat flux determination method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the critical heat flux determination method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the critical heat flux determination method as described in any one of claims 1 to 6.

Images