Method, device, equipment, storage medium and product for determining fluid thermal property parameters

Abstract

The present application provides a method, device, equipment, storage medium and product for determining the thermal physical property parameters of a fluid. The method includes: obtaining the flow field data and temperature field data of the fluid in the rod bundle channel of the nuclear power system; inputting the flow field data and the temperature field data into a preset fluid thermal physical property parameter determination model for processing to obtain the thermal physical property parameters of the fluid, and the loss function used in the training process of the fluid thermal physical property parameter determination model is determined according to the flow heat transfer control equation. The flow heat transfer control equation is introduced into the loss function to ensure that the output of the trained model conforms to the known physical laws, so that the physical parameters of the fluid under actual operating conditions can be accurately obtained during use.

Description

Technical Field

[0001] The present application relates to the technical field of nuclear power systems, and in particular to a method, device, equipment, storage medium and product for determining thermal physical property parameters of a fluid. Background Art

[0002] Nuclear energy and nuclear power systems are currently critical energy technologies. Nuclear power systems generate heat energy through nuclear reactions in nuclear reactors. The heat generated by nuclear reactions is used to heat coolants, such as water. The heated coolant produces high-temperature steam, which drives the turbine, which in turn drives the generator to generate electricity. Since the use of nuclear energy has hidden dangers such as radioactive material leakage and runaway nuclear reactions, the safety and efficiency of nuclear power systems are crucial to energy supply and environmental impact.

[0003] In the prior art, the viscosity and thermal conductivity of the fluid in the rod bundle channel are usually obtained through experimental measurements, and these measurement results are generally used as input parameters. However, the viscosity and thermal conductivity of the fluid will change with the actual operating conditions such as temperature and gas content. The viscosity and thermal conductivity of the fluid obtained in this way cannot reflect these dynamic changes, and it is difficult to accurately reflect the physical parameters such as viscosity and thermal conductivity of the fluid under actual operating conditions. Summary of the invention

[0004] The embodiments of the present application provide a method, device, equipment, storage medium and product for determining the thermal physical property parameters of a fluid, which can accurately obtain the physical parameters of the fluid under actual operating conditions during use.

[0005] In a first aspect, the present application provides a method for determining fluid thermal property parameters, comprising:

[0006] Obtain the flow field data and temperature field data of the fluid in the rod bundle channel of the nuclear power system;

[0007] The flow field data and the temperature field data are input into a preset fluid thermal property parameter determination model for processing to obtain the thermal property parameters of the fluid. The loss function used in the fluid thermal property parameter determination model during training is determined according to the flow heat transfer control equation.

[0008] In some possible implementations, before acquiring the flow field data and temperature field data of the fluid in the rod bundle channel of the nuclear power system, the method further includes:

[0009] Obtain flow field data samples and temperature field data samples of the fluid in the rod bundle channel of the nuclear power system and corresponding thermophysical property parameter labels;

[0010] constructing a flow heat transfer control equation based on the flow field data samples and the temperature field data samples;

[0011] Determining a target loss function based on the flow heat transfer control equation and a preset loss function;

[0012] The flow field data samples and the temperature field data samples are used as the input of the model, the thermophysical property parameter labels are used as the output of the model, and the target loss function is used as the loss function of the model to train the preset model and obtain the fluid thermophysical property parameter determination model.

[0013] In some possible implementations, the governing equations for flow heat transfer include:

[0014]

[0015]

[0016] in, represents the rate of change of the velocity component of the fluid in the x-axis direction with time t, represents the rate of change of the velocity component of the fluid in the y-axis direction with time t, represents the gradient of fluid pressure in the x-axis direction, represents the gradient of fluid pressure in the y-axis direction, and represents the thermophysical parameters of the fluid, It represents the first derivative of the velocity component of the fluid in the x-axis direction. It represents the first derivative of the velocity component of the fluid in the x-axis direction in the y-axis direction. It represents the first derivative of the velocity component of the fluid in the y-axis direction in the x-axis direction. It represents the first derivative of the velocity component of the fluid in the y-axis direction. It represents the second derivative of the velocity component of the fluid in the x-axis direction. It represents the second derivative of the velocity component of the fluid in the x-axis direction in the y-axis direction. It represents the second derivative of the velocity component of the fluid in the y-axis direction in the x-axis direction, It represents the second derivative of the velocity component of the fluid in the y-axis direction. represents the velocity component of the fluid in the x-axis direction, Represents the velocity of the fluid in the y-axis direction.

[0017] In some possible implementations, determining a target loss function based on the flow heat transfer control equation and a preset loss function includes:

[0018] Obtaining a first weight factor corresponding to the flow heat transfer control equation and a second weight factor corresponding to the preset loss function;

[0019] The product of the flow heat transfer control equation and the first weight factor is combined with the product of the preset loss function and the second weight factor to obtain a target loss function.

[0020] In some possible implementations, the flow field data samples and the temperature field data samples are used as the input of the model, the thermophysical property parameter labels are used as the output of the model, and the target loss function is used as the loss function of the model to train a preset model to obtain a fluid thermophysical property parameter determination model, including:

[0021] Acquire a training sample set; the training sample set includes a plurality of training samples; each of the training samples includes the flow field data sample and the temperature field data sample, and a corresponding thermophysical property parameter label;

[0022] For each training sample, perform the following steps:

[0023] Inputting the flow field data and temperature field data of the fluid into a preset model to determine the corresponding thermophysical property parameter prediction results;

[0024] According to the prediction results of the thermophysical property parameters corresponding to each of the training samples, based on the loss function of the preset model, determining the loss function value of the preset model;

[0025] When the loss function value of the preset model does not satisfy the preset training stop condition, the model parameters of the target fluid thermophysical property parameter determination model are adjusted, and the flow field data and temperature field data of the fluid are input into the preset model to determine the prediction results of the corresponding thermophysical property parameters;

[0026] When the loss function value of the preset model meets the preset training stop condition, the training is stopped to obtain the trained fluid thermal property parameter determination model.

[0027] In some possible implementations, determining the loss function value of the preset model based on the loss function of the preset model according to the prediction results of the thermophysical property parameters corresponding to each of the training samples includes:

[0028] Calculating a first loss value according to the flow heat transfer control equation and the prediction result of the thermophysical property parameters;

[0029] Obtaining a second loss value according to a difference between the thermophysical property parameter prediction result and the corresponding thermophysical property parameter label;

[0030] The first loss value and the second loss value are weightedly summed to obtain the loss function value of the preset model.

[0031] In some possible implementations, when the loss function value of the target fluid thermophysical property parameter determination model does not satisfy a preset training stop condition, adjusting the model parameters of the target fluid thermophysical property parameter determination model includes:

[0032] When the loss function value of the preset model does not satisfy the preset training stop condition, calculating the gradient relative to each parameter in the preset model based on the back propagation algorithm;

[0033] According to each of the gradients, the corresponding parameters in the preset model are adjusted.

[0034] In some possible implementations, the thermophysical property parameter includes at least one of fluid viscosity and fluid thermal conductivity.

[0035] In a second aspect, the present application provides a device for determining fluid thermal physical property parameters, the device comprising:

[0036] An acquisition module, used to acquire flow field data and temperature field data of the fluid in the rod bundle channel of the nuclear power system;

[0037] A determination module is used to input the flow field data and the temperature field data into a preset fluid thermal property parameter determination model for processing to obtain the thermal property parameters of the fluid. The loss function used in the fluid thermal property parameter determination model during training is determined according to the flow heat transfer control equation.

[0038] In a third aspect, the present application provides a device for determining thermal properties parameters of a fluid, the device comprising: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the method for determining thermal properties parameters of a fluid as described above.

[0039] 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 method for determining the thermal physical property parameters of a fluid as described above is implemented.

[0040] 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 method for determining the thermal physical property parameters of the fluid as described above.

[0041] The method, device, equipment, storage medium and product for determining the thermal physical property parameters of a fluid provided in the embodiments of the present application obtain the flow field data and temperature field data of the fluid in the rod bundle channel of the nuclear power system, and then use the fluid thermal physical property parameter determination model obtained by training using a loss function containing a flow heat transfer control equation. The flow field data and the temperature field data are input into a preset fluid thermal physical property parameter determination model for processing, and the physical parameters of the fluid in the coolant pipeline are determined. The flow heat transfer control equation is introduced into the loss function to ensure that the output of the trained model conforms to the known physical laws, so that the physical parameters of the fluid under actual operating conditions can be accurately obtained during use. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] 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:

[0043] 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.

[0044] Figure 1 is a flow chart of a method for determining fluid thermal property parameters provided by an embodiment of the present application;

[0045] Figure 2 is a flow chart of a fluid thermal property parameter determination model training process provided by an embodiment of the present application;

[0046] Figure 3 is a flow chart of a method for determining fluid thermal physical property parameters provided by another embodiment of the present application;

[0047] Figure 4 It is a structural schematic diagram of a device for determining fluid thermal physical property parameters provided by an embodiment of the present application;

[0048] Figure 5 It is a schematic diagram of the hardware structure of the fluid thermal physical property parameter determination device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] 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.

[0050] 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.

[0051] Physics-Informed Neural Networks (PINN): A machine learning model that combines deep learning and physics knowledge. PINN uses physical laws to guide the model during training, thereby improving the generalization ability of the model, especially when there is less data or more noise. The main feature of PINN is that it incorporates physical laws into the loss function to ensure that the model's prediction results comply with physical laws, thereby improving the accuracy and reliability of the model.

[0052] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device, equipment, storage medium and product for determining the thermal physical property parameters of a fluid. The method for determining the thermal physical property parameters of a fluid provided in the embodiments of the present application is first introduced below.

[0053] Figure 1 FIG. 1 is a flow chart of a method for determining fluid thermal property parameters provided by an embodiment of the present application. Figure 1 As shown, the method includes the following steps S101 to S102.

[0054] Step S101: acquiring flow field data and temperature field data of the fluid in the rod bundle channel of the nuclear power system.

[0055] In a specific implementation, flow meters and temperature sensors can be used in the coolant pipeline of the nuclear power system to collect the flow field data and temperature field data of the fluid in real time. These sensors can be distributed in different positions of the pipeline to ensure the comprehensiveness and accuracy of the data. The collected data is recorded to form an original data set. The data record can include information such as time, flow rate, temperature, pressure, etc., so as to obtain the flow field data and temperature field data of the fluid in the rod bundle channel of the nuclear power system.

[0056] Step S102: Input the above flow field data and the above temperature field data into a preset fluid thermal property parameter determination model for processing to obtain the thermal property parameters of the above fluid. The loss function used in the above fluid thermal property parameter determination model during the training process is determined according to the flow heat transfer control equation.

[0057] In the specific implementation, the preprocessed flow field data and temperature field data are input into the preset fluid thermophysical property parameter determination model. This model is usually a machine learning model or a computational model, which can handle complex fluid thermophysical property problems after training. During the model training process, the loss function is used to measure the gap between the model prediction value and the actual value. In this model, the loss function is usually designed based on the flow heat transfer control equation to ensure that the model can accurately predict the thermophysical property parameters. The flow heat transfer control equation includes the heat conduction equation, the convection equation, etc., which describe the heat transfer mechanism of the fluid in the pipeline.

[0058] The model uses the input data to obtain the thermophysical parameters of the fluid, such as thermal conductivity, specific heat capacity, etc. through internal calculations and reasoning, and obtains the thermophysical parameters of the above-mentioned fluid.

[0059] As another example, before inputting the data into the model, the flow field data and the temperature field data may be preprocessed, which may include data cleaning, normalization, feature extraction, etc., to ensure that the data is suitable for the input requirements of the model.

[0060] The method for determining the thermal physical property parameters of a fluid provided in an embodiment of the present application obtains the flow field data and temperature field data of the fluid in the rod bundle channel of the nuclear power system, and then uses a fluid thermal physical property parameter determination model obtained by training using a loss function containing a flow heat transfer control equation. The above flow field data and the above temperature field data are input into a preset fluid thermal physical property parameter determination model for processing, and the physical parameters of the fluid in the above coolant pipeline are determined. The flow heat transfer control equation is introduced into the loss function to ensure that the output of the trained model conforms to the known physical laws, so that the physical parameters of the fluid under actual operating conditions can be accurately obtained during use.

[0061] In order to obtain an accurate fluid thermal property parameter determination model, in some embodiments, before the above step S101, the above method further includes steps A1 to D1:

[0062] Step A1: Obtain flow field data samples and temperature field data samples of the fluid in the rod bundle channel of the nuclear power system and corresponding thermophysical property parameter labels.

[0063] In the specific implementation, flow meters are installed in the coolant pipes in the nuclear power system to collect the velocity field data of the fluid in real time. These data usually include the flow rate, flow direction and vortex of the fluid. Temperature data of the fluid is collected at different positions in the pipeline using temperature sensors. These temperature sensors should have sufficient accuracy and resolution to capture the details of temperature changes in the pipeline. Thermophysical parameter labels can be obtained through experiments or high-precision calculations, and record the thermophysical parameters related to the corresponding flow field and temperature field data samples, such as thermal conductivity, specific heat capacity, etc. These parameters are used to supervise model training.

[0064] Step B1: constructing a flow heat transfer control equation based on the flow field data samples and the temperature field data samples.

[0065] In a specific implementation, according to fluid mechanics and heat transfer theory, based on the flow field data samples and the temperature field data samples, flow heat transfer control equations are established. These equations may include momentum equations and energy equations of the fluid, etc., to describe the flow and heat transfer behavior of the fluid in the pipeline. The momentum equation describes the flow of the fluid, and the energy equation describes the transfer of heat.

[0066] Step C1: Based on the above flow heat transfer control equation and the preset loss function, determine the target loss function.

[0067] In the specific implementation, for the problem of determining the fluid thermal property parameters, the loss function is usually based on the residual of the flow heat transfer control equation, that is, the difference between the actual data and the model prediction data. The loss function is integrated with the flow heat transfer control equation, and these equations are used to calculate the value of the loss function during the model training process. The error between the model prediction result and the actual data is calculated and fed back to the model for optimization.

[0068] Step D1: Using the flow field data samples and the temperature field data samples as the input of the model, using the thermophysical property parameter labels as the output of the model, using the target loss function as the loss function of the model, training the preset model, and obtaining the fluid thermophysical property parameter determination model.

[0069] In the specific implementation, flow field data samples and temperature field data samples are used as the input of the model. These data are used as the characteristic data for model training. The thermophysical parameter labels are used as the output of the model. These labels are the target values ​​that the model needs to predict during the training process. The model is trained using these data to obtain the fluid thermophysical parameter determination model.

[0070] After acquiring the flow field data samples and temperature field data samples of the fluid in the rod bundle channel of the nuclear power system and the corresponding thermophysical property parameter labels, the above-mentioned implementation method of the embodiment of the present application constructs the flow heat transfer control equation based on the above-mentioned flow field data samples and the above-mentioned temperature field data samples, and then determines the target loss function. Thereafter, this loss function is used to train the preset model to obtain the fluid thermophysical property parameter determination model, thereby obtaining an accurate fluid thermophysical property parameter determination model.

[0071] In order to obtain a loss function that is more in line with the actual situation, in some embodiments, the above flow heat transfer control equation includes:

[0072]

[0073]

[0074] in, represents the rate of change of the velocity component of the fluid in the x-axis direction with time t, represents the rate of change of the velocity component of the fluid in the y-axis direction with time t, represents the gradient of fluid pressure in the x-axis direction, represents the gradient of fluid pressure in the y-axis direction, and represents the thermophysical parameters of the fluid, It represents the first derivative of the velocity component of the fluid in the x-axis direction. It represents the first derivative of the velocity component of the fluid in the x-axis direction in the y-axis direction. It represents the first derivative of the velocity component of the fluid in the y-axis direction in the x-axis direction. It represents the first derivative of the velocity component of the fluid in the y-axis direction. It represents the second derivative of the velocity component of the fluid in the x-axis direction. It represents the second derivative of the velocity component of the fluid in the x-axis direction in the y-axis direction. It represents the second derivative of the velocity component of the fluid in the y-axis direction in the x-axis direction, It represents the second derivative of the velocity component of the fluid in the y-axis direction. represents the velocity component of the fluid in the x-axis direction, Represents the velocity of the fluid in the y-axis direction.

[0075] In the above implementation of the embodiment of the present application, a specific flow heat transfer control equation is defined, so that a loss function that is more in line with the actual situation can be obtained.

[0076] In order to obtain a loss function that meets actual needs, in some embodiments, the above step C1 includes steps C11 to C12:

[0077] Step C11: Obtain a first weight factor corresponding to the flow heat transfer control equation and a second weight factor corresponding to the preset loss function.

[0078] The first weight factor is the weight factor associated with the flow heat transfer control equation. It is used to adjust the importance of the control equation in the objective loss function. For example, if the control equation has a greater impact on the model performance, the first weight factor should be set higher. It can be a fixed constant or optimized during the model training process.

[0079] The second weight factor is a weight factor related to the preset loss function. It is used to adjust the importance of the preset loss function in the target loss function. The weight factor of the preset loss function determines the contribution of the error between the predicted value and the actual value to the overall loss. The second weight factor can also be a fixed constant or adjusted by the optimization algorithm during the training process.

[0080] In a specific implementation, the first weighting factor and the second weighting factor are predetermined, and the first weighting factor and the second weighting factor are obtained when they are needed.

[0081] Step C12: Combine the product of the flow heat transfer control equation and the first weight factor with the product of the preset loss function and the second weight factor to obtain a target loss function.

[0082] In the specific implementation, the output of the flow heat transfer control equation is multiplied by the first weight factor, the error between the predicted value and the actual value is calculated and multiplied by the second weight factor, and the contribution of the control equation loss and the preset loss function are added together to obtain the final target loss function.

[0083] The above-mentioned implementation method of the embodiment of the present application obtains the first weight factor corresponding to the above-mentioned flow heat transfer control equation and the second weight factor corresponding to the above-mentioned preset loss function, and then obtains the target loss function according to the weight factors. It can adjust the influence of different parts in the loss function to obtain a loss function that meets actual needs.

[0084] In order to obtain a fluid thermal property parameter determination model that meets the requirements, in some embodiments, the above step D1 can refer to Figure 2 , including steps S201 to S206:

[0085] Step S201: obtaining a training sample set; the training sample set includes a plurality of training samples; each of the training samples includes the flow field data sample and the temperature field data sample, as well as corresponding thermophysical property parameter labels.

[0086] The flow field data samples include information such as the velocity and pressure of the fluid under different conditions. The temperature field data samples include the temperature distribution of the fluid under different conditions. The thermal physical property parameter labels are the specific physical properties of the fluid, such as thermal conductivity, specific heat capacity, etc. These parameters are used as training targets.

[0087] In the specific implementation, the data is sorted by samples, each sample contains flow field data, temperature field data and thermophysical property parameter labels, and training samples are obtained. Multiple training samples form a training sample set, and the training sample set is obtained when needed.

[0088] For each training sample, the following steps S202 to S206 are performed respectively:

[0089] Step S202: inputting the flow field data and temperature field data of the above fluid into a preset model to determine the corresponding thermophysical property parameter prediction results.

[0090] In a specific implementation, the processed flow field data and temperature field data are input into a preset prediction model, and the model calculates the prediction results of the thermophysical property parameters.

[0091] As another implementation method, the flow field data and the temperature field data may be standardized or normalized to meet the input requirements of the model and ensure that the data format is consistent with the model input.

[0092] Step S203: determining the loss function value of the preset model according to the thermophysical property parameter prediction results corresponding to each of the training samples and based on the loss function.

[0093] In the specific implementation, the prediction results of the model are compared with the actual thermophysical parameter labels, the error of each sample is calculated, and the loss function value of the above preset model is determined.

[0094] Step S204: Determine whether the loss function value of the preset model meets the preset training stop condition.

[0095] In a specific implementation, a preset training stop condition is determined, such as a threshold of the loss function value, an upper limit of the training round, etc. The loss function value of the current model is compared with the preset stop condition. If the loss function value is less than or equal to the threshold, or reaches the upper limit of the training round, the stop condition is met.

[0096] Step S205: 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 target fluid thermal physical property parameter determination model, return to input the flow field data and temperature field data of the above-mentioned fluid into the preset model, and determine the corresponding prediction results of the thermal physical property parameters.

[0097] In the specific implementation, when the training stop condition is not met, the model parameters are adjusted according to the loss function value. The adjustment method may include gradient descent, Adam optimization algorithm, etc., and the weights and biases of the model are updated through the optimization algorithm. The adjusted model is retrained. New flow field data and temperature field data are input, and prediction is performed and a new loss function value is calculated.

[0098] Step S206: When the loss function value of the above preset model meets the preset training stop condition, stop the training to obtain the trained fluid thermal property parameter determination model.

[0099] In a specific implementation, when the loss function value meets a preset stop condition, the training process is stopped to obtain a trained fluid thermal property parameter determination model.

[0100] The above-mentioned implementation method of the embodiment of the present application obtains a training sample set, and based on each training sample in the training sample set, trains the preset model to obtain a trained fluid thermal property parameter determination model, thereby obtaining a fluid thermal property parameter determination model that meets the requirements.

[0101] In order to accurately obtain the loss function value of the preset model, in some embodiments, the above step S203 includes steps A2 to C2:

[0102] Step A2: Calculate and obtain a first loss value based on the above-mentioned flow heat transfer control equation and the above-mentioned thermophysical property parameter prediction results.

[0103] In a specific implementation, the flow heat transfer control equation of the preset model includes equations for data such as fluid velocity and pressure. These equations describe the behavior of the fluid under different thermophysical property parameters. The predicted results of the thermophysical property parameters are input into the flow heat transfer control equation. The predicted results may include thermal conductivity, specific heat capacity, etc. of the fluid. The performance of the fluid in the flow heat transfer control equation is calculated using the input predicted results, and the equation calculation results are compared with the actual experimental data or preset data to calculate the first loss value.

[0104] Step B2: Obtain a second loss value based on the difference between the above-mentioned thermophysical property parameter prediction result and the corresponding thermophysical property parameter label.

[0105] In the specific implementation, read the real thermophysical parameter labels, which are the known real values ​​in the training data set. Compare the difference between the thermophysical parameter predicted by the model and the actual thermophysical parameter labels. Common difference calculation methods include mean square error (MSE) or absolute error (MAE). Calculate the difference between the predicted value and the label value to get the second loss value. This reflects the accuracy of the model in predicting the thermophysical parameter.

[0106] Step C2: Perform a weighted summation on the first loss value and the second loss value to obtain the loss function value of the preset model.

[0107] In a specific implementation, a weighting coefficient of the first loss value and the second loss value is determined. The first loss value and the second loss value are weighted and summed according to the set weighting coefficient. This step combines the two loss values ​​into a comprehensive loss value to obtain the loss function value of the above-mentioned preset model. The comprehensive loss function value is the value after weighted summation, which is used to evaluate the overall prediction performance of the model.

[0108] The above implementation method of the embodiment of the present application calculates a first loss value based on the flow heat transfer control equation and the above-mentioned thermophysical property parameter prediction results, obtains a second loss value based on the difference between the thermophysical property parameter prediction results and the corresponding thermophysical property parameter labels, and then obtains the loss function value of the preset model by weighted summation of the first loss value and the second loss value, which can accurately derive the loss function value of the preset model.

[0109] In order to speed up the training, in some implementations, the above step S205 includes steps A3 to B3:

[0110] Step A3: When the loss function value of the above-mentioned preset model does not meet the preset training stop condition, the gradient relative to each parameter in the above-mentioned preset model is calculated based on the back propagation algorithm.

[0111] In the specific implementation, before calculating the gradient, forward propagation is first performed. This step is to pass the input data through the model to get the model's predicted output. The loss function value of the model is calculated based on the difference between the predicted output and the actual label. Starting from the output layer, the gradient is calculated backward layer by layer. For each layer, the contribution of the layer output to the loss function is calculated to obtain the gradient of each parameter in the above preset model.

[0112] Step B3: According to each of the above gradients, adjust the corresponding parameters in the preset model.

[0113] In the specific implementation, according to the rules of the optimization algorithm, the update amount of each parameter is calculated, the calculated update amount is applied to the model parameters, the chain rule is used to propagate the gradient from the output layer to the input layer, the gradient of each parameter is updated, and the corresponding parameters in the preset model are adjusted.

[0114] The above implementation of the embodiment of the present application uses a back-propagation algorithm to calculate the gradient of each parameter in the above preset model, thereby adjusting the corresponding parameters in the preset model, which can accurately adjust the parameters in the preset model and speed up the training.

[0115] In some embodiments, the above-mentioned thermophysical property parameter includes at least one of fluid viscosity and fluid thermal conductivity.

[0116] In one embodiment of the present application, Figure 3 As shown in FIG. 1 , the temperature field and flow field cloud map of the object under test are obtained through an infrared camera, a particle image velocimetry (PIV) system, etc. Figure 3 In , t represents the time data of the input data; x represents the data of the input data in the x-axis direction; y represents the data of the input data in the y-axis direction; σ represents the parameters corresponding to each neuron in the neural network; U represents the velocity component of the fluid in the x-axis direction; V represents the velocity of the fluid in the y-axis direction; P represents the fluid pressure; T represents the fluid temperature. Taking the two-dimensional plane PIV measurement as an example, after obtaining a small amount of PIV measurement point data, the PINN model is constructed and solved as follows:

[0117]

[0118]

[0119] in, represents the rate of change of the velocity component of the fluid in the x-axis direction with time t, represents the rate of change of the velocity component of the fluid in the y-axis direction with time t, represents the gradient of fluid pressure in the x-axis direction, represents the gradient of fluid pressure in the y-axis direction, and represents the thermophysical parameters of the fluid, It represents the first derivative of the velocity component of the fluid in the x-axis direction. It represents the first derivative of the velocity component of the fluid in the x-axis direction in the y-axis direction. It represents the first derivative of the velocity component of the fluid in the y-axis direction in the x-axis direction. It represents the first derivative of the velocity component of the fluid in the y-axis direction. It represents the second derivative of the velocity component of the fluid in the x-axis direction. It represents the second derivative of the velocity component of the fluid in the x-axis direction in the y-axis direction. It represents the second derivative of the velocity component of the fluid in the y-axis direction in the x-axis direction, It represents the second derivative of the velocity component of the fluid in the y-axis direction. represents the velocity component of the fluid in the x-axis direction, Represents the velocity of the fluid in the y-axis direction.

[0120] In this way, the deviation term of the control equation can be defined as:

[0121]

[0122]

[0123] Therefore, the model is trained based on this control equation.

[0124] Based on the method for determining the thermal physical property parameters of a fluid provided in the above embodiment, the present application also provides a specific implementation of a device for determining the thermal physical property parameters of a fluid. Please refer to the following embodiment.

[0125] See first Figure 4 The fluid thermal property parameter determination device 400 provided in the embodiment of the present application includes the following modules:

[0126] The acquisition module 401 is used to acquire the flow field data and temperature field data of the fluid in the rod bundle channel of the nuclear power system.

[0127] The determination module 402 is used to input the above-mentioned flow field data and the above-mentioned temperature field data into a preset fluid thermal property parameter determination model for processing to obtain the thermal property parameters of the above-mentioned fluid. The loss function used in the above-mentioned fluid thermal property parameter determination model during the training process is determined according to the flow heat transfer control equation.

[0128] The fluid thermal property parameter determination device provided in the embodiment of the present application obtains the flow field data and temperature field data of the fluid in the rod bundle channel of the nuclear power system, and then uses the fluid thermal property parameter determination model obtained by training using a loss function containing a flow heat transfer control equation. The above flow field data and the above temperature field data are input into a preset fluid thermal property parameter determination model for processing, and the physical parameters of the fluid in the above coolant pipeline are determined. The flow heat transfer control equation is introduced into the loss function to ensure that the output of the trained model conforms to the known physical laws, so that the physical parameters of the fluid under actual operating conditions can be accurately obtained during use.

[0129] As an implementation of the present application, the fluid thermal property parameter determination device 400 further includes:

[0130] The acquisition module is used to acquire flow field data samples and temperature field data samples of the fluid in the rod bundle channel of the nuclear power system and corresponding thermal physical property parameter labels.

[0131] A construction module is used to construct a flow heat transfer control equation based on the flow field data sample and the temperature field data sample.

[0132] The determination module is used to determine the target loss function based on the above-mentioned flow heat transfer control equation and the preset loss function.

[0133] The determination module is also used to use the above-mentioned flow field data samples and the above-mentioned temperature field data samples as the input of the model, the above-mentioned thermophysical property parameter labels as the output of the model, and the target loss function as the loss function of the model to train the preset model and obtain the fluid thermophysical property parameter determination model.

[0134] After acquiring the flow field data samples and temperature field data samples of the fluid in the rod bundle channel of the nuclear power system and the corresponding thermophysical property parameter labels, the above-mentioned implementation method of the embodiment of the present application constructs the flow heat transfer control equation based on the above-mentioned flow field data samples and the above-mentioned temperature field data samples, and then determines the target loss function. Thereafter, this loss function is used to train the preset model to obtain the fluid thermophysical property parameter determination model, thereby obtaining an accurate fluid thermophysical property parameter determination model.

[0135] As an implementation of the present application, the above-mentioned determination module includes:

[0136] An acquisition unit is used to acquire a first weight factor corresponding to the above-mentioned flow heat transfer control equation and a second weight factor corresponding to the above-mentioned preset loss function.

[0137] A combining unit is used to combine the product of the flow heat transfer control equation and the first weight factor with the product of the preset loss function and the second weight factor to obtain a target loss function.

[0138] The above-mentioned implementation method of the embodiment of the present application obtains the first weight factor corresponding to the above-mentioned flow heat transfer control equation and the second weight factor corresponding to the above-mentioned preset loss function, and then obtains the target loss function according to the weight factors. It can adjust the influence of different parts in the loss function to obtain a loss function that meets actual needs.

[0139] As an implementation of the present application, the above-mentioned determination module includes:

[0140] The acquisition unit is used to acquire a training sample set; the training sample set includes a plurality of training samples; each of the training samples includes the flow field data sample and the temperature field data sample, as well as corresponding thermophysical property parameter labels.

[0141] The determination unit is used to input the flow field data and temperature field data of the above fluid into a preset model to determine the corresponding thermophysical property parameter prediction results.

[0142] The determination unit is further used to determine the loss function value of the preset model based on the loss function according to the prediction results of the thermophysical property parameters corresponding to each of the training samples.

[0143] The adjustment unit is used to adjust the model parameters of the target fluid thermophysical property parameter determination model when the loss function value of the preset model does not meet the preset training stop condition, return the flow field data and temperature field data of the fluid to the preset model, and determine the corresponding prediction results of the thermophysical property parameters.

[0144] The determination unit is also used to stop training when the loss function value of the above-mentioned preset model meets the preset training stop condition, so as to obtain the trained fluid thermal property parameter determination model.

[0145] The above-mentioned implementation method of the embodiment of the present application obtains a training sample set, and based on each training sample in the training sample set, trains the preset model to obtain a trained fluid thermal property parameter determination model, thereby obtaining a fluid thermal property parameter determination model that meets the requirements.

[0146] As an implementation of the present application, the above-mentioned determination unit includes:

[0147] The calculation subunit is used to calculate the first loss value according to the flow heat transfer control equation and the prediction result of the thermophysical property parameters.

[0148] The determination subunit is used to obtain a second loss value according to the difference between the above-mentioned thermophysical property parameter prediction result and the corresponding thermophysical property parameter label.

[0149] The summing subunit is used to perform weighted summation of the first loss value and the second loss value to obtain the loss function value of the preset model.

[0150] The above implementation method of the embodiment of the present application calculates a first loss value based on the flow heat transfer control equation and the above-mentioned thermophysical property parameter prediction results, obtains a second loss value based on the difference between the thermophysical property parameter prediction results and the corresponding thermophysical property parameter labels, and then obtains the loss function value of the preset model by weighted summation of the first loss value and the second loss value, which can accurately derive the loss function value of the preset model.

[0151] The various modules in the fluid thermal property parameter determination device provided in the embodiment of the present application can implement the various steps in the above-mentioned fluid thermal property parameter determination method and achieve corresponding effects. For the sake of concise description, they will not be repeated here.

[0152] Figure 5 A schematic diagram of the structure of the fluid thermal property parameter determination hardware provided in an embodiment of the present application is shown.

[0153] The fluid thermophysical property parameter determination device may include a processor 501 and a memory 502 storing computer program instructions.

[0154] 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.

[0155] 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. In appropriate cases, the memory 502 may include a removable or non-removable (or fixed) medium. In appropriate cases, 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.

[0156] The memory may include a read-only memory (ROM), a random access memory (RAM), a disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, 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 method for determining the thermophysical property parameters of a fluid according to any one embodiment of the present disclosure.

[0157] The processor 501 reads and executes the computer program instructions stored in the memory 502 to implement any one of the methods for determining the thermal physical property parameters of the fluid in the above embodiments.

[0158] In one example, the fluid thermal property parameter 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.

[0159] 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.

[0160] 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 industry standard architecture (EISA) bus, front-side bus (FSB), hypertransport (HT) interconnection, industry 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 two or more of these combinations. 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.

[0161] In addition, in combination with the method for determining the thermal physical property parameters of a fluid in the above embodiments, the embodiment of the present application may 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 the thermal physical property parameters of a fluid in the above embodiments is implemented.

[0162] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, implements any one of the methods for determining the thermal physical property parameters of a fluid in the above embodiments.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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 fluid thermal property parameters, characterized in that: include: Obtain flow field data samples and temperature field data samples of the fluid in the rod bundle channel of the nuclear power system and corresponding thermophysical property parameter labels; constructing a flow heat transfer control equation based on the flow field data samples and the temperature field data samples; Obtaining a first weight factor corresponding to the flow heat transfer control equation and a second weight factor corresponding to a preset loss function; Combining the product of the flow heat transfer control equation and the first weight factor with the product of the preset loss function and the second weight factor to obtain a target loss function; Taking the flow field data samples and the temperature field data samples as the input of the model, taking the thermophysical property parameter labels as the output of the model, taking the target loss function as the loss function of the model, training the preset model, and obtaining the fluid thermophysical property parameter determination model; Obtain the flow field data and temperature field data of the fluid in the rod bundle channel of the nuclear power system; Inputting the flow field data and the temperature field data into a preset fluid thermophysical property parameter determination model for processing to obtain the thermophysical property parameters of the fluid, wherein the loss function used in the fluid thermophysical property parameter determination model during training is determined according to the flow heat transfer control equation, and the thermophysical property parameters include at least one of fluid viscosity and fluid thermal conductivity; Wherein, the flow heat transfer control equation includes: in, represents the rate of change of the velocity component of the fluid in the x-axis direction with time t, represents the rate of change of the velocity component of the fluid in the y-axis direction with time t, represents the gradient of fluid pressure in the x-axis direction, represents the gradient of fluid pressure in the y-axis direction, and represents the thermophysical parameters of the fluid, It represents the first derivative of the velocity component of the fluid in the x-axis direction. It represents the first derivative of the velocity component of the fluid in the x-axis direction in the y-axis direction. It represents the first derivative of the velocity component of the fluid in the y-axis direction in the x-axis direction. It represents the first derivative of the velocity component of the fluid in the y-axis direction. It represents the second derivative of the velocity component of the fluid in the x-axis direction. It represents the second derivative of the velocity component of the fluid in the x-axis direction in the y-axis direction. It represents the second derivative of the velocity component of the fluid in the y-axis direction in the x-axis direction, It represents the second derivative of the velocity component of the fluid in the y-axis direction. represents the velocity component of the fluid in the x-axis direction, Represents the velocity of the fluid in the y-axis direction.

2. The method for determining fluid thermal property parameters according to claim 1, characterized in that: The method uses the flow field data samples and the temperature field data samples as the input of the model, uses the thermophysical property parameter labels as the output of the model, uses the target loss function as the loss function of the model, trains the preset model, and obtains the fluid thermophysical property parameter determination model, including: Acquire a training sample set; the training sample set includes a plurality of training samples; each of the training samples includes the flow field data sample and the temperature field data sample, and a corresponding thermophysical property parameter label; For each training sample, perform the following steps: Inputting the flow field data and temperature field data of the fluid into a preset model to determine the corresponding thermophysical property parameter prediction results; Determining the loss function value of the preset model based on the loss function of the preset model according to the prediction results of the thermophysical property parameters corresponding to each of the training samples; 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 flow field data and the temperature field data of the fluid are input into the preset model to determine the prediction results of the corresponding thermophysical property parameters; When the loss function value of the preset model meets the preset training stop condition, the training is stopped to obtain the trained fluid thermal property parameter determination model.

3. The method for determining fluid thermal property parameters according to claim 2, characterized in that: The step of determining the loss function value of the preset model based on the loss function of the preset model according to the prediction results of the thermophysical property parameters corresponding to each of the training samples includes: Calculating a first loss value according to the flow heat transfer control equation and the prediction result of the thermophysical property parameters; Obtaining a second loss value according to a difference between the thermophysical property parameter prediction result and the corresponding thermophysical property parameter label; The first loss value and the second loss value are weightedly summed to obtain the loss function value of the preset model.

4. The method for determining fluid thermal physical property parameters according to claim 2, characterized in that: When the loss function value of the preset model does not satisfy the preset training stop condition, adjusting the model parameters of the preset model includes: When the loss function value of the preset model does not satisfy the preset training stop condition, calculating the gradient relative to each parameter in the preset model based on the back propagation algorithm; According to each of the gradients, the corresponding parameters in the preset model are adjusted.

5. A device for determining fluid thermal property parameters, characterized in that: The device comprises: An acquisition module, used to acquire flow field data and temperature field data of the fluid in the rod bundle channel of the nuclear power system; A determination module, used for inputting the flow field data and the temperature field data into a preset fluid thermophysical property parameter determination model for processing to obtain the thermophysical property parameters of the fluid, wherein the loss function used by the fluid thermophysical property parameter determination model in the training process is determined according to the flow heat transfer control equation, and the thermophysical property parameters include at least one of fluid viscosity and fluid thermal conductivity; The acquisition module is also used to acquire flow field data samples and temperature field data samples of the fluid in the rod bundle channel of the nuclear power system and corresponding thermophysical property parameter labels; construct a flow heat transfer control equation based on the flow field data samples and the temperature field data samples; acquire a first weight factor corresponding to the flow heat transfer control equation and a second weight factor corresponding to a preset loss function; combine the product of the flow heat transfer control equation and the first weight factor with the product of the preset loss function and the second weight factor to obtain a target loss function; use the flow field data samples and the temperature field data samples as inputs of the model, the thermophysical property parameter labels as outputs of the model, and the target loss function as the loss function of the model to train the preset model to obtain a fluid thermophysical property parameter determination model; Wherein, the flow heat transfer control equation includes: in, represents the rate of change of the velocity component of the fluid in the x-axis direction with time t, represents the rate of change of the velocity component of the fluid in the y-axis direction with time t, represents the gradient of fluid pressure in the x-axis direction, represents the gradient of fluid pressure in the y-axis direction, and represents the thermophysical parameters of the fluid, It represents the first derivative of the velocity component of the fluid in the x-axis direction. It represents the first derivative of the velocity component of the fluid in the x-axis direction in the y-axis direction. It represents the first derivative of the velocity component of the fluid in the y-axis direction in the x-axis direction. It represents the first derivative of the velocity component of the fluid in the y-axis direction. It represents the second derivative of the velocity component of the fluid in the x-axis direction. It represents the second derivative of the velocity component of the fluid in the x-axis direction in the y-axis direction. It represents the second derivative of the velocity component of the fluid in the y-axis direction in the x-axis direction, It represents the second derivative of the velocity component of the fluid in the y-axis direction. represents the velocity component of the fluid in the x-axis direction, Represents the velocity of the fluid in the y-axis direction.

6. A device for determining fluid thermal physical property parameters, 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 method for determining the thermal physical property parameters of a fluid as described in any one of claims 1-4.

7. 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 method for determining the thermal physical property parameters of a fluid according to any one of claims 1 to 4 is implemented.

8. 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 method for determining the thermal physical property parameters of a fluid as described in any one of claims 1 to 4.

Images