Wall surface boiling simulation method and device and storage medium

Abstract

The invention provides a wall boiling simulation method and device and a storage medium, and relates to the technical field of computational fluid dynamics. The wall surface boiling simulation method comprises the following steps: acquiring an initial wall surface boiling model; boiling data and experiment characteristic data of experiment measurement are obtained, the boiling data and the experiment characteristic data are processed, and experiment data are obtained; acquiring a machine learning model; training a machine learning model based on the experimental data, and predicting at least part of parameters of the wall boiling model by using the trained machine learning model; adjusting corresponding parameters in the initial wall surface boiling model based on the predicted parameters to obtain a wall surface boiling model after the parameters are adjusted; simulating a target boiling problem by using the wall surface boiling model after parameter adjustment, and evaluating the accuracy of the wall surface boiling model based on a simulation result of the target boiling problem; and under the condition that the accuracy of the wall surface boiling model meets a preset condition, performing wall surface boiling simulation by using the wall surface boiling model.

Description

Technical Field

[0001] The present application relates to the field of computational fluid dynamics technology, and in particular to a wall boiling simulation method, device, and storage medium. Background Art

[0002] Computational fluid dynamics (CFD) is a discipline that uses numerical methods and algorithms to simulate fluid flow. By solving the governing equations of fluid dynamics, the behavior of fluids is studied, analyzing flow, heat transfer, mass transfer, and other issues. CFD can be used to simulate wall boiling.

[0003] When simulating wall boiling using CFD methods, existing wall boiling models are mostly based on simplified physical assumptions and empirical formulas. These models struggle to fully capture the complex nonlinear dynamics of bubble generation, growth, and detachment, as well as the associated processes. This results in significant deviations in the models' predictions of bubble frequency, size distribution, and boiling heat transfer efficiency, impacting the accuracy and reliability of simulation results. Summary of the Invention

[0004] In order to alleviate, mitigate or eliminate the above-mentioned technical problems, the present application provides a wall boiling simulation method, device and storage medium to improve the accuracy of wall boiling simulation.

[0005] In a first aspect, the present application provides a wall boiling simulation method, comprising:

[0006] Obtain the initial wall boiling model;

[0007] Acquiring experimental characteristic data and experimentally measured boiling data, and processing the experimental characteristic data and the boiling data to obtain experimental data;

[0008] Get the machine learning model;

[0009] Training the machine learning model based on the experimental data, and using the trained machine learning model to predict at least some parameters of the wall boiling model;

[0010] Adjusting corresponding parameters in the initial wall boiling model based on the predicted parameters to obtain a wall boiling model with adjusted parameters;

[0011] simulating a target boiling problem using the parameter-adjusted wall boiling model, and evaluating the accuracy of the parameter-adjusted wall boiling model based on the simulation results of the target boiling problem;

[0012] When the accuracy of the wall boiling model after adjusting the parameters meets the preset conditions, the wall boiling simulation is performed using the wall boiling model after adjusting the parameters.

[0013] In one possible implementation, the machine learning model includes a regression model, and training the machine learning model based on the experimental data, and using the trained machine learning model to predict at least some parameters of the wall boiling model includes:

[0014] Based on the experimental data, the regression model is trained using Bayesian optimization, and the trained regression model is used to predict a first parameter of the wall boiling model, where the first parameter includes a bubble generation frequency.

[0015] In one possible implementation, the machine learning model further includes a deep neural network model, and training the machine learning model based on the experimental data and using the trained machine learning model to predict at least some parameters of the wall boiling model further includes:

[0016] The deep neural network model is trained based on the experimental data, and the trained deep neural network model is used to capture the nonlinear relationship of the boiling phenomenon to predict the second parameter of the wall boiling model, where the second parameter includes at least one of the bubble growth rate and the bubble detachment condition.

[0017] In one possible implementation, obtaining the initial wall boiling model includes:

[0018] The target wall boiling model is used to simulate the bubble generation, growth and detachment processes;

[0019] Evaluating the accuracy of the target wall boiling model based on simulation results of bubble generation, growth, and detachment processes;

[0020] When the accuracy of the target wall boiling model meets the target condition, the target wall boiling model is used as the initial wall boiling model.

[0021] In a possible implementation, the method further includes:

[0022] Adaptive mesh technology is used to refine the mesh of the bubble generation area and / or interface area of ​​the wall. The expression of the adaptive mesh technology is as follows:

[0023]

[0024] Where Δx is the grid size, L is the length of the computational domain, and m is the number of grid encryption layers.

[0025] In a possible implementation, the boiling data includes bubble generation frequency, bubble diameter or radius, bubble growth rate, and bubble detachment condition.

[0026] In a possible implementation, the experimental characteristic data includes data corresponding to the temperature field, the velocity field, and the position of the gas-liquid interface.

[0027] In a second aspect, the present application provides a computing device, comprising:

[0028] at least one processor; and

[0029] At least one memory having instructions stored thereon, which, when executed individually or collectively by the at least one processor, cause the computing device to perform the method according to the first aspect.

[0030] In a third aspect, the present application provides a computer-readable storage medium having instructions stored thereon, which, when executed individually or collectively by at least one processor of a computing device, causes the computing device to execute the method described in the first aspect.

[0031] Compared with the prior art, this application has the following advantages:

[0032] The wall boiling simulation method provided in the present application includes: obtaining an initial wall boiling model; obtaining experimentally measured boiling data and experimental characteristic data, processing the boiling data and the experimental characteristic data to obtain experimental data; obtaining a machine learning model; training the machine learning model based on the experimental data, and using the trained machine learning model to predict at least part of the parameters of the wall boiling model; adjusting the corresponding parameters in the initial wall boiling model based on the predicted parameters to obtain a wall boiling model after parameter adjustment; simulating a target boiling problem using the wall boiling model after parameter adjustment, and evaluating the accuracy of the wall boiling model after parameter adjustment based on the simulation results of the target boiling problem; and performing wall boiling simulation using the wall boiling model after parameter adjustment when the accuracy of the wall boiling model after parameter adjustment meets preset conditions. The present application trains a machine learning model with experimental data to predict at least part of the parameters of the wall boiling model, thereby improving the accuracy of the wall boiling simulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings are included to provide a further understanding of the present application. They are incorporated into and constitute a part of this application. The accompanying drawings illustrate embodiments of the present application and, together with this specification, serve to explain the principles of the present application. In the accompanying drawings:

[0034] Figure 1 1 is a flow chart of a wall boiling simulation method provided in an embodiment of the present application;

[0035] Figure 2 It is a structural diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] To more clearly illustrate the technical solutions of the embodiments of this application, the following is a brief introduction to the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0037] As used herein, unless the context clearly indicates otherwise, the terms "a," "an," "an," and / or "the" are not intended to refer to the singular but may include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0038] At the same time, this application uses specific terms to describe the embodiments of this application. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a certain feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that "one embodiment," "an embodiment," or "an alternative embodiment" mentioned twice or multiple times in different locations in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application may be appropriately combined.

[0039] Unless otherwise specified, the relative arrangement of the parts and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present application. Meanwhile, it should be understood that, for ease of description, the sizes of the various parts shown in the accompanying drawings are not drawn according to actual proportional relationships. Technology, methods and equipment known to those of ordinary skill in the relevant art may not be discussed in detail, but in appropriate cases, the technology, methods and equipment should be considered as a part of the specification. In all examples shown and discussed here, any specific value should be interpreted as being merely exemplary, rather than as a limitation. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar numbers and letters represent similar items in the following drawings, and therefore, once an item is defined in an accompanying drawing, it does not need to be further discussed in subsequent drawings.

[0040] In addition, although the terms used in this application are selected from commonly known and commonly used terms, some of the terms mentioned in this specification may be selected by the applicant at his or her discretion, and their detailed meanings are explained in the relevant parts of the description herein. In addition, it is required that this application be understood not only by the actual terms used, but also by the meaning implied by each term.

[0041] Flowcharts are used in this application to illustrate the operations performed by devices or apparatuses according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0042] Figure 1 Schematic diagram of a wall boiling simulation method provided in the embodiment of the present application. Figure 1 As shown in Figure 2, the wall boiling simulation method includes the following steps:

[0043] Step S110: Obtain an initial wall boiling model.

[0044] The initial wall boiling model is a qualified wall boiling model. The wall boiling model can be pre-stored locally or obtained remotely from a server, or a benchmark test is performed on a wall boiling model, and the qualified wall boiling model is used as the initial wall boiling model. In some embodiments, obtaining the initial wall boiling model includes: simulating the bubble generation, growth, and detachment process using a target wall boiling model; evaluating the accuracy of the target wall boiling model based on the simulation results of the bubble generation, growth, and detachment process; and using the target wall boiling model as the initial wall boiling model when the accuracy of the target wall boiling model meets the target conditions.

[0045] In one exemplary embodiment, the boiling-induced bubble dynamics and heat conduction in a wall-boiling model are analyzed to derive relevant expressions for bubble dynamics and heat conduction, such as the bubble generation frequency expression, the bubble growth rate expression, the heat flux density expression in heat conduction, and the heat transfer coefficient expression. The bubble generation frequency expression is used to predict the bubble generation rate; the bubble growth rate expression is used to predict the growth process of bubbles in the liquid, calculating the size change of bubbles from generation to separation from the wall; the heat flux density expression is used to calculate the heat conduction inside the material or at the gas-liquid interface, describing the process of heat transfer from high-temperature areas to low-temperature areas; and the heat transfer coefficient expression is used to evaluate the heat transfer efficiency between the bubble surface and the liquid, describing the rate at which heat is transferred from the bubble to the surrounding liquid.

[0046] In order to better understand the present application, a specific form of each expression is given below as an example. For example, the bubble generation frequency expression is as follows:

[0047]

[0048] Among them, f b : Bubble generation frequency, that is, the number of bubbles generated per unit time;

[0049] Δt: Bubble generation time interval, that is, the time difference between two bubble generation.

[0050] The following is an example of the bubble growth rate expression:

[0051]

[0052] Where R(t) is the change of bubble radius over time, that is, the process of bubbles gradually growing larger over time after they are generated;

[0053] R0: initial bubble radius, i.e. the initial size of the bubble when it is just generated;

[0054] σ: liquid surface tension, that is, the force of liquid surface contraction, which affects the formation and growth of bubbles;

[0055] ρl: liquid density, that is, the mass density of the liquid, which affects the behavior of bubbles in the liquid;

[0056] t: time, that is, the time after the bubble is generated.

[0057] The following is an example of heat flux expression:

[0058]

[0059] Where, q: heat flux density, that is, the heat flow per unit area, which indicates the heat transfer rate;

[0060] k: thermal conductivity, which is the ability of a material to conduct heat;

[0061] Temperature gradient, that is, the rate of change of temperature per unit distance.

[0062] An example of an expression for the heat transfer coefficient is as follows:

[0063]

[0064] Where, h: heat transfer coefficient, that is, the efficiency of heat transfer from the fluid to the solid surface;

[0065] q: heat flux density, that is, the heat flow per unit area;

[0066] ΔT: Temperature difference, that is, the temperature difference between the fluid and the solid surface.

[0067] Benchmark the Eulerian wall boiling model and analyze the simulation results, such as those for bubble generation, growth, and detachment. Compare these simulation results with experimental data or high-precision numerical results to quantify the error. If the error is less than a threshold, the wall boiling model's accuracy meets the target criteria and can be used as the initial wall boiling model.

[0068] Step S120: Acquire experimental characteristic data and experimentally measured boiling data, and process the experimental characteristic data and boiling data to obtain experimental data.

[0069] In some embodiments, boiling data includes bubble generation frequency, bubble diameter or radius, bubble growth rate, and bubble detachment conditions. Experimental characteristic data includes data corresponding to temperature field, velocity field, and gas-liquid interface position. Data processing may include data preprocessing, such as normalizing bubble generation frequency, initial bubble radius, liquid surface tension, liquid density, and temperature gradient through data standardization. Data processing may also include processing outliers and / or missing values ​​to improve the consistency and reliability of the data set.

[0070] Step S130: Obtain a machine learning model.

[0071] Machine learning models may include regression models, deep neural network models, etc., among which regression models include random forests, support vector machines or neural networks, etc.

[0072] Step S140: training a machine learning model based on experimental data, and using the trained machine learning model to predict at least some parameters of the wall boiling model.

[0073] The accuracy of the wall boiling simulation can be improved by training a machine learning model with experimental data and then using the trained machine learning model to predict at least some of the parameters of the wall boiling model, such as parameters of bubble generation, growth, and detachment. In some embodiments, training a machine learning model based on experimental data and using the trained machine learning model to predict at least some of the parameters of the wall boiling model includes: training a regression model using Bayesian optimization based on the experimental data and using the trained regression model to predict a first parameter of the wall boiling model, wherein the first parameter includes the bubble generation frequency. In some embodiments, training a machine learning model based on experimental data and using the trained machine learning model to predict at least some of the parameters of the wall boiling model also includes: training a deep neural network model based on experimental data and using the trained deep neural network model to capture the nonlinear relationship of the boiling phenomenon and predicting a second parameter of the wall boiling model, wherein the second parameter includes at least one of the bubble growth rate and the bubble detachment condition.

[0074] This embodiment of the application uses experimental data to optimize the prediction of bubble generation frequency by training a regression model, reducing the deviation of the wall boiling model. A deep neural network model is used to capture the complex nonlinear relationships in the bubble growth and / or detachment process, improving the accuracy of simulation details.

[0075] To better understand this application, a specific form of a machine learning model is given below as an example. For example, the expression of the regression model is as follows:

[0076]

[0077] in, Predicted values, which are the outputs of the regression model, such as the frequency of bubble generation;

[0078] β0: intercept, the constant term of the regression model;

[0079] βi: regression coefficient, that is, the weight of each feature, reflecting the impact of the input feature on the predicted value;

[0080] xi: input features, i.e., variables that affect the predicted value, such as initial bubble radius, liquid surface tension, liquid density, temperature gradient, etc.;

[0081] n: number of features, that is, the total number of input features.

[0082] The following are examples of expressions for deep neural network models:

[0083]

[0084] Where y: output, i.e., the prediction results of the deep neural network model, such as bubble growth rate and / or bubble detachment conditions;

[0085] f: activation function, which is a function that converts the linear combination result into a nonlinear output, such as ReLU function, Sigmoid function, etc.

[0086] wi: weight, that is, the weight of each input feature, reflecting the impact of the input feature on the output;

[0087] xi: input features, i.e., variables that affect the output, such as initial bubble radius, liquid surface tension, liquid density, temperature gradient, etc.;

[0088] b: bias, which is the constant term of the neural network and helps adjust the output of the model;

[0089] n: number of features, that is, the total number of input features.

[0090] The following is a more detailed description of parameter prediction using a regression model as an example. In this specific embodiment, the experimental conditions are as follows:

[0091] Liquid type: deionized water;

[0092] Temperature: 90℃;

[0093] Pressure: 1 atm;

[0094] Under the above experimental conditions, the bubble generation process was recorded using a high-frame-rate camera and precision measuring instruments. The frequency and initial radius of each bubble generation were recorded, and the surface tension, density, and temperature gradient of the liquid were measured. Data normalization was performed to normalize the bubble generation frequency, initial bubble radius, liquid surface tension, liquid density, and temperature gradient. Outliers and / or missing values ​​were addressed to improve the consistency and reliability of the experimental data. The resulting experimental data are shown in Table 1.

[0095] Table 1

[0096]

[0097]

[0098] Use the regression model for training. The regression model example is as follows:

[0099]

[0100] The regression coefficient βi is determined through experimental data, the model parameters are optimized, and the optimized model is used to predict the bubble generation frequency under different conditions. Through model prediction, the predicted results are compared with the experimental results to evaluate the accuracy of the model.

[0101] The present invention combines the predictions of multiple machine learning models to improve the overall accuracy and robustness of wall boiling simulations. In critical applications such as nuclear reactors and electronic cooling, the improved wall boiling model can more accurately predict and control the boiling process, reducing accident risks and improving system safety and reliability.

[0102] Step S150: adjusting corresponding parameters in the initial wall boiling model based on the predicted parameters to obtain a wall boiling model with adjusted parameters.

[0103] Step S160 : simulating a target boiling problem using the wall boiling model with adjusted parameters, and evaluating the accuracy of the wall boiling model with adjusted parameters based on the simulation results of the target boiling problem.

[0104] Typical boiling problems, such as the Bartolemei public tube boiling test and reactor core subcooled boiling, can be selected as target boiling problems to validate and evaluate the wall boiling model. In some embodiments, the wall boiling model with adjusted parameters is used to simulate typical boiling problems, covering different operating conditions. The simulation results are compared with experimental data or high-precision numerical results, and the error is statistically analyzed. The performance of the parameter-adjusted wall boiling model under different operating conditions is then analyzed. The accuracy of the parameter-adjusted wall boiling model is then evaluated based on the statistical error and performance.

[0105] Step S170 : When the accuracy of the wall boiling model after adjusting the parameters meets the preset conditions, the wall boiling model after adjusting the parameters is used to perform wall boiling simulation.

[0106] The improved wall boiling model (i.e., the model with adjusted parameters) has greater adaptability under different operating conditions and can be applied to a variety of engineering problems, such as nuclear reactor cooling and electronic component heat dissipation. In one exemplary embodiment, sensors collect real-time temperature, pressure, and other data, and the adjusted wall boiling model is used to simulate wall boiling, such as bubble generation and heat transfer in real time.

[0107] In some embodiments, during wall boiling simulations, adaptive meshing techniques can be used to refine the mesh in the bubble generation region and / or interface region of the wall, determining the degree of refinement for the local mesh, improving local computational accuracy, and enhancing local computational resolution. Alternatively, optimized time step control methods such as variable step size techniques and adaptive step size can be employed to balance computational efficiency and accuracy, and high-precision difference schemes such as central difference schemes and QUICK schemes can be used to reduce numerical dissipation and diffusion.

[0108] An example of an expression for the adaptive mesh technique is as follows:

[0109]

[0110] Where, Δx: grid size, i.e., the element size in the computational domain;

[0111] L: the length of the calculation domain, that is, the total length of the entire calculation area;

[0112] m: The number of mesh encryption layers, that is, the number of times the mesh is refined.

[0113] This embodiment of the application utilizes adaptive meshing technology to refine the mesh in key areas, improving the resolution and accuracy of local calculations. It also improves the time step control method, balancing computational efficiency and accuracy, and reducing error accumulation in numerical simulations. It also introduces a high-precision difference scheme to reduce numerical dissipation and diffusion, improving the reliability of simulation results.

[0114] The embodiments of the present application can use intelligent optimization algorithms such as genetic algorithms and particle swarm optimization to automatically adjust the parameters of the wall boiling model, find a better configuration, improve the simulation accuracy, and reduce the time and effort of manual parameter adjustment.

[0115] Figure 2 This is a schematic diagram of the structure of a computing device provided in an embodiment of the present application. Figure 2As shown, computing device 200 includes one or more processors 210 , one or more memories 220 coupled to processor 210 , and one or more communication modules 240 coupled to processor 210 .

[0116] The communication module 240 is used for two-way communication. The communication module 240 has at least one antenna to facilitate communication. The communication interface may represent any interface necessary for communicating with other network elements.

[0117] The processor 210 may be of any type suitable for the local technology network and may include, by way of non-limiting example, one or more of a general purpose computer, a special purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture. The computing device 200 may have multiple processors, such as application specific integrated circuit chips, which are driven in time to a clock that synchronizes the master processor.

[0118] The memory 220 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 224, electrically programmable read-only memory (EPROM), flash memory, hard disks, compact disks (CDs), digital video disks (DVDs), and other magnetic and / or optical memories. Examples of volatile memories include, but are not limited to, random access memory (RAM) 222 and other volatile memories that do not persist during a power outage.

[0119] The computer program 230 includes computer executable instructions that are executed by the associated processor 210. The computer program 230 may be stored in the ROM 224. The processor 210 may perform any appropriate actions and processes by loading the computer program 230 into the RAM 222.

[0120] The embodiments of the present application can be implemented by the computer program 230, so that the computing device 200 can execute the reference Figure 1 The embodiments of the present application may also be implemented by hardware or by a combination of software and hardware.

[0121] In some embodiments, the computer program 230 may be tangibly embodied in a computer-readable medium, which may be contained in the computing device 200 (e.g., memory 220) or other storage device accessible to the computing device 200. The computing device 200 may load the computer program 230 from the computer-readable medium into the RAM 222 for execution. The computer-readable medium may include any type of tangible non-volatile memory, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. The computer-readable medium has the computer program 230 stored thereon.

[0122] In general, various embodiments of the present application may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software, which may be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of the present application are shown and described as block diagrams, flow charts, or using some other graphical representations, it should be understood that, as non-limiting examples, the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0123] The present application also provides at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computer executable instructions, such as instructions included in program modules, which are executed in a device on a target real or virtual processor to perform the above-mentioned reference Figure 1 The method described. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of program modules can be combined or separated between program modules as needed. Machine-executable instructions for program modules can be executed on local or distributed devices. In distributed devices, program modules can be located in local and remote storage media.

[0124] The program code that is used to carry out the method for the present application can be written with any combination of one or more programming languages.These program codes can be provided to the processor or controller of general-purpose computer, special-purpose computer or other programmable data processing equipment, make when program code is carried out by processor or controller, the function / operation specified in flow chart and / or block diagram is realized.Program code can be carried out fully on machine as independent software package, partly on machine, partly on machine, partly on remote machine, partly on remote machine, or all on remote machine or server.

[0125] In the context of this application, computer program codes or related data may be carried by any suitable carrier to enable a device, apparatus or processor to perform various processes and operations as described above. Examples of carriers include signals, computer-readable media, etc.

[0126] The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. More specific examples of computer-readable storage media include an electrical connection having one or more wires, a portable computer floppy disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0127] In addition, although operations are described in a specific order, this should not be understood as requiring the specific order or sequence shown to perform these operations, or to perform all operations shown, to obtain the required result. In some cases, multi-tasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these details should not be interpreted as limiting the scope of the application, but can be interpreted as a description of the specific features of a particular embodiment. Some features described in the context of a separate embodiment also can be combined in a single embodiment. On the contrary, the various features described in the context of a single embodiment also can be realized individually or in any suitable sub-combination in multiple embodiments.

[0128] Although the present application has been described with reference to the current specific embodiments, ordinary technicians in this technical field should recognize that the above embodiments are only used to illustrate the present application, and various equivalent changes or substitutions can be made without departing from the spirit of the present application. Therefore, as long as the changes and modifications to the above embodiments are within the scope of the essential spirit of the present application, they will fall within the scope of the present application.

Claims

1. A wall boiling simulation method, characterized in that: include: Obtain the initial wall boiling model; Acquiring experimental characteristic data and experimentally measured boiling data, and processing the experimental characteristic data and the boiling data to obtain experimental data; Get the machine learning model; Training the machine learning model based on the experimental data, and using the trained machine learning model to predict at least some parameters of the wall boiling model; Adjusting corresponding parameters in the initial wall boiling model based on the predicted parameters to obtain a wall boiling model with adjusted parameters; simulating a target boiling problem using the parameter-adjusted wall boiling model, and evaluating the accuracy of the parameter-adjusted wall boiling model based on the simulation results of the target boiling problem; When the accuracy of the wall boiling model after adjusting the parameters meets the preset conditions, the wall boiling simulation is performed using the wall boiling model after adjusting the parameters.

2. The method according to claim 1, wherein The machine learning model includes a regression model, and the step of training the machine learning model based on the experimental data and using the trained machine learning model to predict at least some parameters of the wall boiling model includes: Based on the experimental data, the regression model is trained using Bayesian optimization, and the trained regression model is used to predict a first parameter of the wall boiling model, where the first parameter includes a bubble generation frequency.

3. The method according to claim 2, wherein The machine learning model further includes a deep neural network model. The step of training the machine learning model based on the experimental data and using the trained machine learning model to predict at least some parameters of the wall boiling model further includes: The deep neural network model is trained based on the experimental data, and the trained deep neural network model is used to capture the nonlinear relationship of the boiling phenomenon to predict the second parameter of the wall boiling model, where the second parameter includes at least one of the bubble growth rate and the bubble detachment condition.

4. The method according to claim 1, wherein The obtaining of the initial wall boiling model comprises: The target wall boiling model is used to simulate the bubble generation, growth and detachment processes; Evaluating the accuracy of the target wall boiling model based on simulation results of bubble generation, growth, and detachment processes; When the accuracy of the target wall boiling model meets the target condition, the target wall boiling model is used as the initial wall boiling model.

5. The method according to any one of claims 1 to 4, wherein Also includes: Adaptive mesh technology is used to refine the mesh of the bubble generation area and / or interface area of ​​the wall. The expression of the adaptive mesh technology is as follows: Where Δx is the grid size, L is the length of the computational domain, and m is the number of grid encryption layers.

6. The method according to any one of claims 1 to 4, wherein The boiling data includes bubble generation frequency, bubble diameter or radius, bubble growth rate and bubble detachment condition.

7. The method according to any one of claims 1 to 4, wherein The experimental characteristic data include data corresponding to the temperature field, velocity field and gas-liquid interface position.

8. A computing device, characterized in that include: at least one processor; as well as At least one memory having instructions stored thereon, which, when executed individually or collectively by the at least one processor, cause the computing device to perform the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, which, when executed individually or collectively by at least one processor of a computing device, cause the computing device to perform the method according to any one of claims 1 to 7.

Images