A method, apparatus, and device for optimizing three-dimensional heat pipe capillary structures.

Abstract

This application discloses a method, apparatus, device, and readable storage medium for optimizing the capillary structure of a three-dimensional heat pipe, relating to the fields of artificial intelligence and thermal management technology. The method includes: first, acquiring initial capillary structure data of the three-dimensional heat pipe and establishing a simulation model of the three-dimensional heat pipe based on the initial capillary structure data; then, performing mesh discretization processing on the simulation model of the three-dimensional heat pipe to obtain simulation elements of the three-dimensional heat pipe; then, inputting the simulation elements of the three-dimensional heat pipe into a three-dimensional heat pipe parameter optimization model to obtain the optimization parameters of the simulation elements; and finally, optimizing the capillary structure of the three-dimensional heat pipe based on the optimization parameters. This method reduces the cost and workload of parameter optimization and avoids the blindness of global optimization, resulting in a better performance of the optimized three-dimensional heat pipe.

Description

Technical Field

[0001] This invention relates to the fields of artificial intelligence and thermal management technology, and more specifically to a method, apparatus, device, and readable storage medium for optimizing a three-dimensional heat pipe capillary structure. Background Technology

[0002] A three-dimensional heat pipe is an advanced heat transfer device based on the traditional heat pipe principle. It utilizes the phase change process of the working fluid to achieve efficient multi-directional heat transfer and diffusion in three-dimensional space. Compared with traditional one-dimensional linear heat pipes, three-dimensional heat pipes have advantages such as flexible structure, multiple heat transfer paths, and strong heat dissipation capabilities. They can adapt to the thermal management needs of multiple heat source coupling, high heat flux density, and complex spatial layouts. They are widely used in mobile terminal devices, data centers, LED lighting, 5G base stations, and aerospace, and represent an important development direction for next-generation high-efficiency heat dissipation technology.

[0003] The core technology of 3D heat pipes lies in the design of their capillary structures. In traditional technology, the design of 3D heat pipe capillary structures relies on engineers' experience and verifies the performance of 3D heat pipes through physical experiments. This method is too time-consuming and costly. To improve this situation, fluid dynamics and heat transfer simulation technology were introduced to replace some physical experiments with simulation, reducing the cost of trial and error. However, simulation technology cannot completely reproduce the structure of 3D heat pipes, resulting in certain errors in the experimental results. To further improve this, gradient descent, genetic algorithms, and optimization tools were introduced to optimize the structural parameters of 3D heat pipes. However, this method requires manual parameter tuning, and the number of high-dimensional parameters is too large, resulting in a huge amount of manual work and difficulty in finding the optimal solution for structural parameters.

[0004] Therefore, there is an urgent need for an optimization method for three-dimensional heat pipe capillary structures that can overcome the above problems. Summary of the Invention

[0005] The purpose of this invention is to provide a method, apparatus, device, and readable storage medium for optimizing the capillary structure of a three-dimensional heat pipe. This invention utilizes a three-dimensional heat pipe parameter optimization model to optimize the capillary structure of the three-dimensional heat pipe. Compared to traditional methods that optimize the capillary structure through physical experiments, this significantly reduces the cost of parameter optimization. Compared to traditional methods that involve manual parameter tuning, it greatly reduces the workload of parameter optimization. Furthermore, since the optimization does not directly target the entire three-dimensional heat pipe but rather optimizes the parameters of a simulation unit, each part of the three-dimensional heat pipe can be optimized locally, rather than being uniformly optimized globally. This avoids the blindness of global optimization and allows the optimized three-dimensional heat pipe to achieve better results.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for optimizing a three-dimensional heat pipe capillary structure, the method comprising:

[0008] Acquire the initial capillary structure data of the three-dimensional heat pipe, and establish a simulation model of the three-dimensional heat pipe based on the initial capillary structure data;

[0009] The simulation model of the three-dimensional heat pipe is discretized into a mesh to obtain the simulation unit of the three-dimensional heat pipe;

[0010] The simulation unit of the three-dimensional heat pipe is input into the three-dimensional heat pipe parameter optimization model to obtain the optimized parameters of the simulation unit;

[0011] The three-dimensional heat pipe capillary structure is optimized based on the aforementioned optimization parameters.

[0012] In some embodiments, establishing a simulation model of the three-dimensional heat pipe based on the initial capillary structure data includes:

[0013] An initial model of the three-dimensional heat pipe is established based on the initial capillary structure data;

[0014] The initial model of the three-dimensional heat pipe was experimentally optimized to obtain a transitional model of the three-dimensional heat pipe.

[0015] The parameters to be optimized in the three-dimensional heat pipe transition model are normalized and denoised to obtain the simulation model of the three-dimensional heat pipe; the parameters to be optimized include thermal resistance, temperature standard deviation and liquid reflux velocity.

[0016] In some embodiments, the simulation model of the three-dimensional heat pipe is discretized into a mesh to obtain the simulation unit of the three-dimensional heat pipe, including:

[0017] Obtain the mesh discretization parameters; the mesh discretization parameters include the length, width, and height of the simulation cell;

[0018] Based on the mesh discretization parameters, the simulation model of the three-dimensional heat pipe is divided to obtain at least two simulation units.

[0019] In some embodiments, the training process of the three-dimensional heat pipe parameter optimization model includes:

[0020] Obtain a training dataset; the training dataset includes simulation units of unoptimized 3D heat pipes;

[0021] The three-dimensional heat pipe parameter optimization model is trained based on the training dataset.

[0022] In some embodiments, training the three-dimensional heat pipe parameter optimization model based on the training dataset includes:

[0023] The training dataset is input into the three-dimensional heat pipe parameter optimization model;

[0024] The reward value of each simulation unit in the training dataset is calculated based on the reward function;

[0025] If the reward value does not meet the preset reward threshold, the model parameters of the three-dimensional heat pipe parameter optimization model are adjusted, and the operation of inputting the training dataset into the three-dimensional heat pipe parameter optimization model is re-executed until the reward value meets the preset reward threshold or the number of iterations reaches the preset number.

[0026] In some embodiments, the reward function is constructed based on the thermal resistance, temperature standard deviation, liquid reflux rate, cost, and defects of the simulation unit of the three-dimensional heat pipe.

[0027] Secondly, the present invention also provides an optimization device for a three-dimensional heat pipe capillary structure, the device comprising:

[0028] The model simulation module is used to acquire the initial capillary structure data of the three-dimensional heat pipe and to establish a simulation model of the three-dimensional heat pipe based on the initial capillary structure data.

[0029] The discrete processing module is used to perform mesh discretization processing on the simulation model of the three-dimensional heat pipe to obtain the simulation unit of the three-dimensional heat pipe;

[0030] The parameter solving module is used to input the simulation unit of the three-dimensional heat pipe into the three-dimensional heat pipe parameter optimization model to obtain the optimized parameters of the simulation unit;

[0031] The structure optimization module is used to optimize the three-dimensional heat pipe capillary structure based on the optimization parameters.

[0032] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the optimization method for the three-dimensional heat pipe capillary structure provided in the first aspect.

[0033] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the optimization method for the three-dimensional heat pipe capillary structure provided in the first aspect.

[0034] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the optimization method for the three-dimensional heat pipe capillary structure provided in the first aspect.

[0035] The beneficial effects of this invention are as follows:

[0036] The optimization method for the capillary structure of a three-dimensional heat pipe provided in this invention first obtains initial capillary structure data of the three-dimensional heat pipe and establishes a simulation model of the three-dimensional heat pipe based on the initial capillary structure data; then, the simulation model of the three-dimensional heat pipe is discretized into a mesh to obtain simulation units of the three-dimensional heat pipe; then, the simulation units of the three-dimensional heat pipe are input into a three-dimensional heat pipe parameter optimization model to obtain the optimization parameters of the simulation units; finally, the capillary structure of the three-dimensional heat pipe is optimized based on the optimization parameters. Using a three-dimensional heat pipe parameter optimization model to optimize the capillary structure of the three-dimensional heat pipe significantly reduces the cost of parameter optimization compared to the traditional method of optimizing the capillary structure of the three-dimensional heat pipe through physical experiments. Compared to the traditional method of manually adjusting parameters, it significantly reduces the workload of parameter optimization. Furthermore, since the parameter optimization is not performed directly on the entire three-dimensional heat pipe, but rather on the simulation units, each part of the three-dimensional heat pipe can be optimized locally to its best effect, rather than being optimized globally. This avoids the blindness of global optimization and allows the optimized three-dimensional heat pipe to achieve better results.

[0037] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Attached Figure Description

[0038] Figure 1 This is a flowchart illustrating an optimization method for a three-dimensional heat pipe capillary structure according to an embodiment of the present invention.

[0039] Figure 2 This is a flowchart illustrating another method for optimizing a three-dimensional heat pipe capillary structure according to an embodiment of the present invention.

[0040] Figure 3 This is a schematic diagram of the structure of an optimization device for a three-dimensional heat pipe capillary structure according to an embodiment of the present invention;

[0041] Figure 4 This is a schematic diagram of the structure of an optimized device for a three-dimensional heat pipe capillary structure according to an embodiment of the present invention;

[0042] Figure 5 This is a schematic diagram of the structure of an optimization device for a three-dimensional heat pipe capillary structure according to an embodiment of the present invention;

[0043] Figure 6 This is a schematic diagram of the structure of an optimization device for a three-dimensional heat pipe capillary structure according to an embodiment of the present invention;

[0044] Figure 7This is a schematic diagram of an electronic device structure provided in an embodiment of this application. Detailed Implementation

[0045] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] It should be noted that references to "an embodiment," "embodiment," "example embodiment," etc., in this specification refer to the described embodiment including specific features, structures, or characteristics; however, not every embodiment must include these specific features, structures, or characteristics. Furthermore, such expressions do not refer to the same embodiment. Moreover, when describing specific features, structures, or characteristics in conjunction with embodiments, whether or not explicitly described, it is indicated that incorporating such features, structures, or characteristics into other embodiments is within the knowledge of those skilled in the art.

[0047] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0048] In some embodiments, such as Figure 1 As shown, an optimization method for a three-dimensional heat pipe capillary structure is provided, the specific method including:

[0049] S101: Obtain the initial capillary structure data of the three-dimensional heat pipe, and establish a simulation model of the three-dimensional heat pipe based on the initial capillary structure data.

[0050] The initial capillary structure data consists of the unprocessed capillary structure data of the three-dimensional heat pipe. This data can be manually set based on human experience or randomly generated. There are various types of initial capillary structure data, which can be used to simulate three-dimensional heat pipe simulation models with different structures.

[0051] Specifically, ANSYS Fluent or OpenFOAM can be used to construct multiple different simulation models of three-dimensional heat pipes based on the initial capillary structure data of the three-dimensional heat pipe. These simulation models include indicators such as thermal resistance, temperature standard deviation, and liquid reflux rate.

[0052] Optionally, the method for establishing the simulation model of the three-dimensional heat pipe can also be as follows: establishing an initial model of the three-dimensional heat pipe based on the initial capillary structure data; performing experimental optimization on the initial model of the three-dimensional heat pipe to obtain a transitional model of the three-dimensional heat pipe; performing normalization and denoising processing on the parameters to be optimized in the transitional model of the three-dimensional heat pipe to obtain the simulation model of the three-dimensional heat pipe; the parameters to be optimized include thermal resistance, temperature standard deviation, and liquid reflux velocity.

[0053] Specifically, ANSYS Fluent or OpenFOAM can be used to construct multiple different initial models of a 3D heat pipe based on the initial capillary structure data. Since these initial models are constructed based on initial capillary structure data set by human experience or randomly generated initial capillary structure data, there are significant differences between the initial models and the ideal models. Therefore, it is necessary to conduct experimental optimization on these initial models. For example, experimental testing can be carried out on the structure of these initial models (such as sintered powder, grooved type) to achieve preliminary optimization of these initial models and obtain transitional models. Then, the parameters to be optimized in these transitional models are normalized (such as mapping thermal resistance, temperature standard deviation, liquid reflux velocity, porosity, and channel width to between 0 and 1) and denoised (such as removing outlier data and supplementing missing data) to obtain a more standardized simulation model of the 3D heat pipe.

[0054] S102, the simulation model of the three-dimensional heat pipe is discretized into a mesh to obtain the simulation elements of the three-dimensional heat pipe.

[0055] Among them, mesh discretization is the process of dividing the simulation model into multiple smaller parts.

[0056] Specifically, the more parts the simulation model of the three-dimensional heat pipe is divided into during mesh discretization, the more simulation units are obtained. The subsequent optimization of the capillary structure of the three-dimensional heat pipe will be more refined and specific, but the time and workload required for optimization will also be greater. Therefore, based on the mesh discretization requirements, the simulation model of the three-dimensional heat pipe needs to be divided into appropriate sizes, that is, multiple simulation units of the three-dimensional heat pipe are obtained.

[0057] Optionally, the method for mesh discretization of the simulation model of the three-dimensional heat pipe can also be to obtain mesh discretization parameters; the mesh discretization parameters include the length, width and height of the simulation unit; based on the mesh discretization parameters, the simulation model of the three-dimensional heat pipe is divided to obtain at least two simulation units.

[0058] For example, the length, width and height of the simulation unit can be 50*50*50, and the simulation model of the three-dimensional hot end can be divided into multiple 50*50*50 simulation units.

[0059] S103, input the simulation unit of the three-dimensional heat pipe into the three-dimensional heat pipe parameter optimization model to obtain the optimized parameters of the simulation unit.

[0060] Among them, the three-dimensional heat pipe parameter optimization model is a neural network model that can optimize the parameters of each simulation unit of the three-dimensional heat pipe.

[0061] Specifically, the simulation unit of the three-dimensional heat pipe can be directly input into the three-dimensional heat pipe parameter optimization model, and the three-dimensional heat pipe parameter optimization model can directly output the optimized parameters of the simulation unit.

[0062] It should be noted that the training process of the three-dimensional heat pipe parameter optimization model includes: obtaining a training dataset; the training dataset includes simulation units of unoptimized three-dimensional heat pipes; and training the three-dimensional heat pipe parameter optimization model based on the training dataset.

[0063] The method for training the three-dimensional heat pipe parameter optimization model based on the training dataset includes: inputting the training dataset into the three-dimensional heat pipe parameter optimization model; calculating the reward value of each simulation unit in the training dataset based on the reward function; if the reward value does not meet the preset reward threshold, adjusting the model parameters of the three-dimensional heat pipe parameter optimization model, and re-executing the operation of inputting the training dataset into the three-dimensional heat pipe parameter optimization model until the reward value meets the preset reward threshold or the number of iterations reaches the preset number; the reward function is constructed based on the thermal resistance, temperature standard deviation, liquid reflux rate, cost, and defects of the simulation unit of the three-dimensional heat pipe.

[0064] For example, the training dataset consists of unoptimized simulation units of a 3D heat pipe. The training dataset is first input into the policy network of the 3D heat pipe parameter optimization model to obtain the action probability distribution. Then, it passes through the value network of the 3D heat pipe parameter optimization model, and the reward value of each simulation unit is calculated using the reward function. When the reward value of each simulation unit does not meet the preset reward threshold, the policy network can be updated using the POO algorithm, thus completing one iteration. The reward value of each simulation unit is then calculated again. When the reward value meets the preset reward threshold or the number of iterations reaches the preset number, it indicates that the 3D heat pipe parameter optimization model has completed training. Since the reward function is constructed based on the thermal resistance, temperature standard deviation, liquid reflux rate, cost, and defects of the 3D heat pipe simulation units, the optimized parameters obtained based on the 3D heat pipe parameter optimization model can ensure that the thermal resistance, temperature standard deviation, and liquid reflux rate of the 3D heat pipe capillary structure are all handled ideally, while also minimizing cost and defects.

[0065] S104, the capillary structure of the three-dimensional heat pipe is optimized based on the optimized parameters.

[0066] Specifically, based on the optimized parameters, the parameters of the three-dimensional heat pipe capillary structure are adjusted, for example, by directly adjusting the parameters of the three-dimensional heat pipe capillary structure to the optimized parameters.

[0067] It should be noted that since the input of the 3D heat pipe parameter optimization model is the simulation unit of the 3D heat pipe, the output of the 3D heat pipe parameter optimization model is the optimization parameters of each simulation unit. In the process of optimizing the 3D heat pipe capillary structure based on the optimization parameters, the structure of each simulation unit is actually optimized based on the optimization parameters of each simulation unit. The 3D heat pipe capillary structure is composed of each simulation unit. After optimizing each simulation unit, the global optimization of the multi-3D heat pipe capillary structure is completed.

[0068] The optimization method for the capillary structure of a three-dimensional heat pipe in the above embodiments first obtains initial capillary structure data of the three-dimensional heat pipe and establishes a simulation model of the three-dimensional heat pipe based on the initial capillary structure data; then, the simulation model of the three-dimensional heat pipe is discretized into a mesh to obtain simulation units of the three-dimensional heat pipe; then, the simulation units of the three-dimensional heat pipe are input into a three-dimensional heat pipe parameter optimization model to obtain the optimization parameters of the simulation units; finally, the capillary structure of the three-dimensional heat pipe is optimized based on the optimization parameters. Using a three-dimensional heat pipe parameter optimization model to optimize the capillary structure of the three-dimensional heat pipe significantly reduces the cost of parameter optimization compared to the traditional method of optimizing the capillary structure of the three-dimensional heat pipe through physical experiments. Compared to the traditional method of manually adjusting parameters, it significantly reduces the workload of parameter optimization. Furthermore, since the parameter optimization is not performed directly on the entire three-dimensional heat pipe, but rather on the simulation units, each part of the three-dimensional heat pipe can be optimized locally to its best effect, rather than being optimized globally. This avoids the blindness of global optimization and allows the optimized three-dimensional heat pipe to achieve better results.

[0069] To more comprehensively demonstrate this solution, this embodiment presents an optional method for optimizing a three-dimensional heat pipe capillary structure, such as... Figure 2 As shown:

[0070] S201, Obtain the training dataset.

[0071] The training dataset includes simulation cells of unoptimized 3D heat pipes.

[0072] S202, input the training dataset into the three-dimensional heat pipe parameter optimization model.

[0073] S203 calculates the reward value of each simulation unit in the training dataset based on the reward function.

[0074] S204. If the reward value does not meet the preset reward threshold, adjust the model parameters of the three-dimensional heat pipe parameter optimization model and re-execute the operation of inputting the training dataset into the three-dimensional heat pipe parameter optimization model until the reward value meets the preset reward threshold or the number of iterations reaches the preset number.

[0075] The reward function is constructed based on the thermal resistance, temperature standard deviation, liquid reflux rate, cost, and defects of the simulation unit of the three-dimensional heat pipe.

[0076] S205, acquire the initial capillary structure data of the three-dimensional heat pipe.

[0077] S206, an initial model of a three-dimensional heat pipe is established based on initial capillary structure data.

[0078] S207, experimental optimization of the initial model of the three-dimensional heat pipe was carried out to obtain the transitional model of the three-dimensional heat pipe.

[0079] S208 normalizes and denoises the parameters to be optimized in the three-dimensional heat pipe transition model to obtain the simulation model of the three-dimensional heat pipe.

[0080] The parameters to be optimized include thermal resistance, temperature standard deviation, and liquid reflux rate.

[0081] S209, obtain the grid discretization processing parameters.

[0082] The parameters for mesh discretization include the length, width, and height of the simulation cells.

[0083] S210, based on the mesh discretization processing parameters, divides the simulation model of the three-dimensional heat pipe into at least two simulation units.

[0084] S211, input the simulation unit of the three-dimensional heat pipe into the three-dimensional heat pipe parameter optimization model to obtain the optimized parameters of the simulation unit.

[0085] S212, The three-dimensional heat pipe capillary structure is optimized based on the optimization parameters.

[0086] The specific processes of S201-S212 described above can be found in the description of the above method embodiments. Their implementation principles and technical effects are similar, and will not be repeated here.

[0087] Based on the same inventive concept, this application also provides an optimization apparatus for a three-dimensional heat pipe capillary structure for implementing the optimization method for the three-dimensional heat pipe capillary structure described above. The solution provided by this apparatus is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the optimization apparatus for a three-dimensional heat pipe capillary structure provided below can be found in the limitations of the optimization method for a three-dimensional heat pipe capillary structure described above, and will not be repeated here.

[0088] In one embodiment, such as Figure 3 As shown, an optimization device for a three-dimensional heat pipe capillary structure is provided, the device comprising:

[0089] The model simulation module 30 is used to acquire the initial capillary structure data of the three-dimensional heat pipe and establish a simulation model of the three-dimensional heat pipe based on the initial capillary structure data.

[0090] Discrete processing module 31 is used to perform mesh discretization processing on the simulation model of the three-dimensional heat pipe to obtain the simulation unit of the three-dimensional heat pipe;

[0091] The parameter solving module 32 is used to input the simulation unit of the three-dimensional heat pipe into the three-dimensional heat pipe parameter optimization model to obtain the optimized parameters of the simulation unit;

[0092] The structure optimization module 33 is used to optimize the three-dimensional heat pipe capillary structure based on the optimization parameters.

[0093] In another embodiment, such as Figure 4 As shown above, Figure 3 The model simulation module 30 includes:

[0094] The model building unit 300 is used to build an initial model of the three-dimensional heat pipe based on the initial capillary structure data.

[0095] The model optimization unit 301 is used to perform experimental optimization on the initial model of the three-dimensional heat pipe to obtain the transition model of the three-dimensional heat pipe.

[0096] The parameter processing unit 302 is used to normalize and denoise the parameters to be optimized in the three-dimensional heat pipe transition model to obtain the simulation model of the three-dimensional heat pipe; the parameters to be optimized include thermal resistance, temperature standard deviation and liquid reflux velocity.

[0097] In another embodiment, such as Figure 5 As shown above, Figure 3 The discrete processing module 31 in the middle includes:

[0098] The parameter acquisition unit 310 is used to acquire the mesh discretization processing parameters; the mesh discretization processing parameters include the length, width and height of the simulation unit;

[0099] Model segmentation unit 311 is used to segment the simulation model of the three-dimensional heat pipe based on the mesh discretization processing parameters to obtain at least two simulation units.

[0100] In another embodiment, such as Figure 6 As shown above, Figure 3The optimization device for the three-dimensional heat pipe capillary structure also includes:

[0101] Data acquisition module 34 acquires a training dataset; the training dataset includes simulation units of an unoptimized three-dimensional heat pipe;

[0102] The model training module 35 is used to train the three-dimensional heat pipe parameter optimization model based on the training dataset.

[0103] In another embodiment, the above Figure 6 The model training module 35 is specifically used for: inputting the training dataset into the three-dimensional heat pipe parameter optimization model; calculating the reward value of each simulation unit in the training dataset based on the reward function; if the reward value does not meet the preset reward threshold, adjusting the model parameters of the three-dimensional heat pipe parameter optimization model, and re-executing the operation of inputting the training dataset into the three-dimensional heat pipe parameter optimization model until the reward value meets the preset reward threshold or the number of iterations reaches the preset number.

[0104] In another embodiment, the reward function is constructed based on the thermal resistance, temperature standard deviation, liquid reflux rate, cost, and defects of the simulation unit of the three-dimensional heat pipe.

[0105] This application also provides an electronic device, in some embodiments, referring to... Figure 7 As shown, the electronic device 700 includes an input unit 710, a memory 720, a processor 730, and an output unit 740. The memory 720 stores program instructions that can be executed on the processor 730. The processor 730 can execute the optimization method and / or technical solution based on the three-dimensional heat pipe capillary structure in the foregoing embodiments by calling the program instructions. The electronic device 700 can be a mobile terminal device such as a mobile phone or a computer.

[0106] Furthermore, embodiments of this application also provide a computer-readable storage medium for storing a computer program that performs an optimization method for a three-dimensional heat pipe capillary structure. For example, computer program instructions, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. The program instructions that invoke the methods of this application may be stored in a fixed or removable storage medium, and / or transmitted via data streams in broadcast or other signal carrying media, and / or stored in a storage medium that operates according to the program instructions.

[0107] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0108] The technical features of the above embodiments can be arbitrarily integrated. For the sake of brevity, not all possible integrations of the technical features in the above embodiments are described. However, as long as the integration of these technical features does not contradict each other, they should be considered to be within the scope of this specification.

[0109] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method of optimizing a capillary structure of a three-dimensional heat pipe, characterized by, The method comprises: acquiring initial capillary structure data of a three-dimensional heat pipe, and establishing an initial model of the three-dimensional heat pipe based on the initial capillary structure data; experimentally optimizing the initial model of the three-dimensional heat pipe to obtain a transition model of the three-dimensional heat pipe; performing normalization processing and denoising processing on to-be-optimized parameters of the transition model of the three-dimensional heat pipe to obtain a simulation model of the three-dimensional heat pipe; the to-be-optimized parameters include thermal resistance, temperature standard deviation, and liquid backflow velocity; performing grid discretization processing on the simulation model of the three-dimensional heat pipe to obtain a simulation unit of the three-dimensional heat pipe; inputting the simulation unit of the three-dimensional heat pipe into a three-dimensional heat pipe parameter optimization model to obtain optimization parameters of the simulation unit; the training process of the three-dimensional heat pipe parameter optimization model comprises: acquiring a training data set; the training data set includes simulation units of unoptimized three-dimensional heat pipes; inputting the training data set into the three-dimensional heat pipe parameter optimization model; calculating reward values of simulation units in the training data set based on a reward function; the reward function is constructed based on thermal resistance, temperature standard deviation, liquid backflow velocity, cost, and defects of the simulation unit of the three-dimensional heat pipe; if the reward value does not meet a preset reward threshold, adjusting model parameters of the three-dimensional heat pipe parameter optimization model, re-executing the operation of inputting the training data set into the three-dimensional heat pipe parameter optimization model, until the reward value meets the preset reward threshold or the number of iterations reaches a preset number of times; optimizing the capillary structure of the three-dimensional heat pipe based on the optimization parameters.

2. The optimization method of a capillary structure of a three-dimensional heat pipe according to claim 1, wherein The grid discretization processing on the simulation model of the three-dimensional heat pipe to obtain a simulation unit of the three-dimensional heat pipe comprises: acquiring grid discretization processing parameters; the grid discretization processing parameters include the length, width, and height of the simulation unit; based on the grid discretization processing parameters, cutting the simulation model of the three-dimensional heat pipe to obtain at least two simulation units.

3. An apparatus for optimizing a capillary structure of a three-dimensional heat pipe, characterized by comprising: The device comprises: a model simulation module configured to acquire initial capillary structure data of a three-dimensional heat pipe, and establish an initial model of the three-dimensional heat pipe based on the initial capillary structure data; experimentally optimize the initial model of the three-dimensional heat pipe to obtain a transition model of the three-dimensional heat pipe; perform normalization processing and denoising processing on to-be-optimized parameters of the transition model of the three-dimensional heat pipe to obtain a simulation model of the three-dimensional heat pipe; the to-be-optimized parameters include thermal resistance, temperature standard deviation, and liquid backflow velocity; a discretization processing module configured to perform grid discretization processing on the simulation model of the three-dimensional heat pipe to obtain a simulation unit of the three-dimensional heat pipe; a parameter solving module configured to input the simulation unit of the three-dimensional heat pipe into a three-dimensional heat pipe parameter optimization model to obtain optimization parameters of the simulation unit; the training process of the three-dimensional heat pipe parameter optimization model comprises: acquiring a training data set; the training data set includes simulation units of unoptimized three-dimensional heat pipes; inputting the training data set into the three-dimensional heat pipe parameter optimization model; calculating a reward value of each simulation unit in the training data set based on a reward function; the reward function is constructed based on thermal resistance, temperature standard deviation, liquid backflow velocity, cost and defect of the simulation unit of the three-dimensional heat pipe; if the reward value does not meet a preset reward threshold, adjusting model parameters of the three-dimensional heat pipe parameter optimization model, re-executing the operation of inputting the training data set into the three-dimensional heat pipe parameter optimization model until the reward value meets the preset reward threshold or the number of iterations reaches a preset number; a structure optimization module configured to optimize the capillary structure of the three-dimensional heat pipe based on the optimization parameters.

4. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the optimization method of the capillary structure of the three-dimensional heat pipe in any one of claims 1 to 2.

5. A computer readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the optimization method of the capillary structure of the three-dimensional heat pipe in any one of claims 1 to 2.

6. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the optimization method of the capillary structure of the three-dimensional heat pipe in any one of claims 1 to 2.

Images