CN114781201A - Method, system, device and medium for calculating PCB temperature field in radiator - Google Patents

Abstract

The invention discloses a method, a system, a device and a medium for calculating a PCB temperature field in a radiator, wherein the method comprises the following steps: acquiring training data, wherein the training data comprises radiator fin distribution, chip layout and temperature field distribution; preprocessing the training data, and combining corresponding temperature field distribution as a label to form matching data; generating a countering neural network based on deep convolution, training to obtain a strong mapping relation between radiator fin distribution and chip layout, and constructing an agent model for quickly calculating a PCB (printed Circuit Board) steady-state temperature field under the heat dissipation condition according to the radiator fin distribution and the chip layout; inputting input data consisting of radiator fin distribution and chip layout into the trained proxy model, and rapidly calculating the steady-state PCB temperature cloud chart. According to the invention, through history acquisition, a proxy model is obtained through training and is used for helping a thermal design engineer to improve the design efficiency under the condition of ensuring the prediction precision; can be widely applied to the technical field of numerical heat transfer science calculation.

Description

Method, system, device and medium for calculating PCB temperature field in radiator

technical field

The invention relates to the technical field of numerical heat transfer calculation, in particular to a calculation method, system, device and medium of a PCB temperature field in a heat sink.

Background technique

At present, the degree of automatic driving of automobiles is increasing, and the number of electronic control units in automobiles is rapidly increasing, which poses challenges to the integration capability of integrated circuits, and at the same time puts forward higher requirements for the heat dissipation capability of electronic devices such as controllers. Generally speaking, the temperature field calculation of electronic equipment is a complex process of multi-physics coupling. When performing finite element simulation, it is necessary to divide a large number of meshes for entities such as fins and chips, and set boundary conditions in combination with fluid mechanics and heat transfer. and iterative conditions to solve.

However, when solving the above-mentioned heat-flow coupling problem, the occupied computing resources are relatively high, the time-consuming process is relatively long, and the user requirements are relatively high. Therefore, how to simplify the numerical simulation process and reduce the design cost of thermal simulation schemes will be an urgent problem to be solved in the new generation of design and research.

SUMMARY OF THE INVENTION

In order to solve one of the technical problems existing in the prior art at least to a certain extent, the purpose of the present invention is to provide a method, system, device and medium for calculating the temperature field of a PCB in a heat sink.

The technical scheme adopted in the present invention is:

A method for calculating the temperature field of a PCB in a heat sink, comprising the following steps:

acquiring training data, the training data including the fin distribution of the radiator, the chip layout and the temperature field distribution;

Preprocessing the training data, and combining the corresponding temperature field distributions as labels to form matching data;

Based on a deep convolutional generative adversarial neural network, a strong mapping relationship between the fin distribution of the heat sink and the chip layout is obtained through training, and a proxy for quickly calculating the steady-state temperature field of the PCB under this heat dissipation condition is constructed based on the distribution of the heat sink fins and the chip layout. Model;

Input the input data consisting of the fin distribution of the heat sink and the chip layout into the trained surrogate model to quickly calculate the steady-state PCB temperature nephogram.

Further, the surrogate model is trained by a generative adversarial network, and the training process consists of two different models, a generator and a discriminator. The generator is used to convert the input fin distribution and chip distribution to the PCB steady-state temperature. Field cloud map, the discriminator is used to distinguish the temperature field cloud map generated by the generator from the actual label cloud map. The final training balance point is when the temperature cloud map generated by the generator is consistent or very similar to the corresponding label of the dataset, and the discriminator can distinguish the generated data. The probability of the generated cloud map is 50%.

Further, the input data of the surrogate model is obtained in the following manner:

Step 1: Determine the fin distribution and fin height, the chip distribution and chip heating power, the bump distribution and bump height connecting the chip and the heat sink;

Step 2: Create a three-channel image with the same proportion as the radiator under study, and perform a linear mapping between the fin height, chip heating power, and bump height with the image channel values to obtain model training data;

Step 3: Create a corresponding thermal model in ANSYS software according to the height of the fin, the heating power of the chip, and the height of the bump and perform numerical simulation to obtain the PCB temperature field distribution as a training label, and compare the training label with the model training data in step 2 one by one. pair.

Further, the calculation method also includes a fine-tuning step:

Migrate the data training weights of historical application scenarios to the current specific application scenario weights.

Another technical scheme adopted by the present invention is:

A computing system for PCB temperature field in a heat sink, comprising:

a data acquisition module for acquiring training data, where the training data includes fin distribution of the radiator, chip layout and temperature field distribution;

A label generation module is used to preprocess the training data, and combine the corresponding temperature field distributions as labels to form matching data;

The data training module is used to generate an adversarial neural network based on deep convolution. The training obtains a strong mapping relationship between the fin distribution of the radiator and the layout of the chip, and builds a rapid calculation of the PCB stability under this heat dissipation condition according to the distribution of the fins of the radiator and the layout of the chip. surrogate model of the temperature field of the state;

The temperature calculation module is used to input the input data consisting of the radiator fin distribution and the chip layout into the trained surrogate model, and quickly calculate the steady-state PCB temperature cloud map.

Further, the surrogate model is trained by a generative adversarial network, and the training process consists of two different models, a generator and a discriminator. The generator is used to convert the input fin distribution and chip distribution to the PCB steady-state temperature. Field cloud map, the discriminator is used to distinguish the temperature field cloud map generated by the generator from the actual label cloud map. The final training balance point is when the temperature cloud map generated by the generator is consistent or very similar to the corresponding label of the dataset, and the discriminator can distinguish the generated data. The probability of the generated cloud map is 50%.

Further, the input data of the surrogate model is obtained in the following manner:

Determine fin distribution and fin height, chip distribution and chip heating power, bump distribution and bump height connecting chip and heat sink;

Create a three-channel image with the same scale as the studied radiator, and perform a linear mapping with the image channel value with the height of the fin, the heating power of the chip, and the height of the bump, respectively, to obtain the model training data;

According to the height of the fin, the heating power of the chip, and the height of the bump, the corresponding thermal model is created in ANSYS software and numerical simulation is performed, and the PCB temperature field distribution is obtained as a training label, and the training label is paired with the model training data one by one.

Further, the computing system further includes a fine-tuning module, and the fine-tuning module is configured to migrate the data training weights of historical application scenarios to the current specific application scenario weights.

Another technical scheme adopted by the present invention is:

A computing device for PCB temperature field in a heat sink, comprising:

at least one processor;

at least one memory for storing at least one program;

When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

Another technical scheme adopted by the present invention is:

A computer-readable storage medium in which a processor-executable program is stored, the processor-executable program, when executed by the processor, is used to perform the method as described above.

The beneficial effects of the present invention are as follows: the present invention obtains a proxy model capable of quickly calculating the PCB temperature field corresponding to the corresponding scene structure data by collecting historical related thermal design scene structure data and corresponding PCB temperature field distribution data as training data for generating a confrontation network, Using surrogate models can help thermal design engineers improve design efficiency while ensuring prediction accuracy.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following descriptions are given to the accompanying drawings of the embodiments of the present invention or the related technical solutions in the prior art. It should be understood that the drawings in the following introduction are only In order to facilitate and clearly express some embodiments of the technical solutions of the present invention, for those skilled in the art, other drawings can also be obtained from these drawings without creative work.

Fig. 1 is the schematic diagram of the PCB temperature field fast calculation system in the radiator in the embodiment of the present invention;

2 is a schematic diagram of a thermal simulation model used for generating labels in an embodiment of the present invention;

3 is an initial label diagram obtained in the step of generating a label in an embodiment of the present invention;

4 is a schematic diagram of several pairs of matching data obtained in an embodiment of the present invention;

5 is a schematic diagram of the structure and training process of a generative adversarial network model selected in an embodiment of the present invention;

6 is a comparison diagram of model training results and simulation results in the embodiment of the present invention;

FIG. 7 is a flow chart of steps of a method for calculating a temperature field of a PCB in a heat sink according to an embodiment of the present invention.

Detailed ways

The following describes in detail the embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, only used to explain the present invention, and should not be construed as a limitation of the present invention. The numbers of the steps in the following embodiments are only set for the convenience of description, and the sequence between the steps is not limited in any way, and the execution sequence of each step in the embodiments can be adapted according to the understanding of those skilled in the art Sexual adjustment.

In the description of the present invention, it should be understood that the azimuth description, such as the azimuth or position relationship indicated by up, down, front, rear, left, right, etc., is based on the azimuth or position relationship shown in the drawings, only In order to facilitate the description of the present invention and simplify the description, it is not indicated or implied that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore should not be construed as limiting the present invention.

In the description of the present invention, the meaning of several is one or more, the meaning of multiple is two or more, greater than, less than, exceeding, etc. are understood as not including this number, above, below, within, etc. are understood as including this number. If it is described that the first and the second are only for the purpose of distinguishing technical features, it cannot be understood as indicating or implying relative importance, or indicating the number of the indicated technical features or the order of the indicated technical features. relation.

In the description of the present invention, unless otherwise clearly defined, words such as setting, installation, connection should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above words in the present invention in combination with the specific content of the technical solution.

This embodiment provides a rapid calculation system for the PCB temperature field in the heat sink. The system includes a model preparation module and a front-end usage module. The system architecture diagram is shown in FIG. 1 . The model preparation module includes steps such as data sampling, generating labels, data training, and storing weights.

The data sampling step includes model training data preparation and thermal model structure parameter preparation. First, a thermal model is established for common passive cooling scenarios, as shown in Figure 2. The upper cover 100 includes fins 110 and bumps 120 in contact with the chips. A number of chip sets 140 are distributed on the PCB module 130. The lower cover 150 is used to form a closed link where the PCB module 130 is located. , and other modules that are consistent with the actual heat dissipation, such as thermal grease, etc. Then generate several parameters within a specified range for random sampling within a certain range, including fin type, fin thickness, number of fins, fin height, substrate height, bump position parameters, bump height, chip Position parameters, chip power consumption. The thermal model is parameterized according to random parameter values, and ICEPAK is used to calculate the steady-state temperature field to derive the temperature nephogram distribution on the PCB under steady-state conditions. In order to facilitate the loading and processing of subsequent model training, each parameter value is represented by an image with the same scale as the PCB. The fin position distribution information such as fin type and fin thickness is represented by different pixel values R of the red channel of the image. The specific pixel value is obtained by linear mapping of the fin height h1 and the substrate height h2 by the following formula (1); the bump position information is expressed by the green channel pixel value G of the image, and the specific pixel value is determined by the bump height h3 through the following Formula (2) is obtained by linear mapping; the chip position information is represented by the pixel value B of the blue channel of the image, and the specific pixel value is obtained by the linear mapping of the chip power value P and size r1, r2 by the following formula (3), pay attention to h1, h2, h3, P, r1, r2 are not constant and depend on the parameters of the image corresponding to the radiator position.

其中

代表图像中翅片对应位置的点构成的集合，

代表图像中无翅片仅有凸台对应位置的点构成的集合，h1,h2单位为mm。Formula 1):

in

the set of points representing the corresponding positions of the fins in the image,

Represents the set of points in the image that have no fins but only the corresponding positions of the bosses. The unit of h1 and h2 is mm.

其中

代表图像中凸块对应位置的点构成的集合，h3单位为mm。Formula (2):

in

The set of points that represent the corresponding positions of the bumps in the image, and the unit of h3 is mm.

其中

代表图像中芯片对应位置的点构成的集合，P单位为W，r1，r2单位为mm。Formula (3):

in

A set of points representing the corresponding position of the chip in the image, P is in W, r1, r2 is in mm.

In the step of generating labels, the ICEPAK module in the ANSYS workbench platform is used to establish a model method for parametric simulation. This embodiment uses the CFD solver inside ANSYS and the Boussineske approximation model to simulate the temperature field of the radiator model in the natural cooling state, while taking into account the radiation heat transfer phenomenon in natural convection. Taking into account the calculation speed and accuracy, the Discrete Ordinates (DO) radiation model is used. Assuming that the fluid states in the computational domain are all turbulent, because it is a simulation of an electronic product radiator, a cost-effective zero-equation turbulence model is used. In order to ensure the calculation accuracy, 1.5 times the model feature length L is set for the calculation domain except the Ymax direction at the top of the radiator, while the Ymax direction is set to 2 times the model feature length L, and the area attributes in the six directions are all Set to Opening, and set the ambient temperature in the computing domain to 85°C. The chip is simulated using two copper blocks with intermediate doping and no thickness heat sources. Parameterize the shape parameters and power parameters of the chip. The shell is built using the enclosure cavity module, and the six boundary surfaces are set as thin shell features with a thickness of 2mm (thickness actually participates in the calculation of the temperature field, but does not participate in the meshing of the model), and the overall shell is made of aluminum alloys Material. Because the chip on the PCB has a certain distance from the upper end of the cavity shell, establishing bumps (blcoks) of a corresponding number and size to link the cavity shell and the chip is conducive to effective heat dissipation. A plate structure with a thickness of 1 mm is set at the contact position between the bump and the chip to simulate the thermal conductive silica gel in the actual object, and the thermal conductivity of the thermal conductive silica gel is set to 5W/m·k. After completing the basic modeling of the electronics, an aluminum extrusion heat sink is added to the upper end of the cavity housing. The radiator is made of an aluminum alloy material with a thermal conductivity of 240W/m·k. Parameters are set for the overall height of the radiator, the height of the substrate, the number of fins, and the thickness of the fins, which can be achieved by changing the parameter values. Simulation of the temperature field of various heat sinks.

After completing the establishment of the overall model, the model needs to be meshed. Because the shapes contained in the model are all regular, the Hexa Cartesian structured mesh is used, and all the meshes are vertically orthogonal. After dividing the mesh, check the quality of the mesh, and judge it according to the face alignment rate, the mesh volume value, and the skewness of the mesh. The values of the three are close to the expected values, so for this model, the mesh quality is good, and it can conform to the body. In addition to good meshing quality, good meshing accuracy is also required. The number of meshes directly affects the speed and accuracy of the solution to the final result. For the overall model, the maximum mesh size for the X, Y, and Z directions is limited to 10mm, 5mm, and 15mm. This is limited by 1/20 to 1/40 of the feature size of the computational domain. However, because the part size of the chip model and the fin model is much smaller than the feature size of the computational domain, it is necessary to perform mesh refinement independently to achieve the required computational accuracy. In order to test the grid independence, the number of grids of the chip and fin models is increased in stages, and the changes of the temperature field of the model under different grid numbers are tested. According to the results of six different mesh refinement models, when the number of meshes is 1,161,576, the model can ensure better calculation accuracy and at the same time calculate the temperature field of the model with less calculation time, so this is the final choice. A way of meshing.

Because it is a finite element analysis simulation, the exact value of the result is required, so it is necessary to set the corresponding number of iteration steps and the residual standard of the corresponding parameter, and set the standard of the coupling residual - Flow residual is 1e-3, energy The energy residual value is 1e-7. As long as the three residual error criteria are met, the calculation result is considered to meet the accuracy requirements. In the early stage, a small number of parameters were calculated and solved, and it was found that most of the model calculations converged within 250 steps, so the number of iteration steps was set to 250.

The original image of the data obtained by ICEPAK is shown in Figure 3. The PCB area is cropped by digital image technology and saved as a label.

In the training data, a variety of fin types are selected for data collection, and several matching data are selected as shown in Figure 4. Figure 4 shows six pairs of matching data, the left half is the combined image calculated by the above formula, and the right half is captured from the cloud image results obtained by the simulation software.

In the data training part, the paired data is put into the conditional generative adversarial network as shown in Figure 5 to start the training process. The model used is a Spatially-Adaptive Pixelwise Networks (ASAP-Net). There are two training modes: no pre-training data and fine-tuning on scene data. No training data means that no relevant historical data is used for pre-training, and only the current scene data is used for training. When training without pre-training data, select 16 to 32 paired data to train the model, and use the set-out method to test the prediction quality of the model to obtain weights and store them. Scene data fine-tuning refers to selecting some historical data for training in the presence of similar historical databases. The number of historical data is not limited here. Generally, the more data, the more accurate it is. After obtaining the pre-training weights, use a small learning rate for fine-tuning under a small amount of scene data to obtain accurate weight storage. An example of the results obtained after training without pre-training data is shown in Figure 6, which are shown respectively. The input, model calculation results and corresponding labels of 4 randomly selected data from the test set are presented.

Front-end usage modules include deployment weights and display parts. By deploying the above stored weights in cloud resources, the fast computing function can be provided in the WeChat applet through services such as WeChat cloud hosting, and the user can simply design the fin structure and chip position in the WeChat applet and other interfaces to achieve fast computing; also In view of the light weight of the model, the model can be used offline on a personal computer without spending a lot of computing power to complete the fast calculation process.

In this embodiment, a proxy model that can quickly calculate the PCB temperature field corresponding to the corresponding scene structure data is obtained by collecting historical related thermal design scene structure data and corresponding PCB temperature field distribution data as training data for the generative adversarial network. The proxy model can help thermal design engineers to improve design efficiency while ensuring the prediction accuracy. In addition, the model weight transfer of historical data can be realized based on a small amount of new data to meet the thermal design accuracy requirements of the corresponding scenario. And it can help engineers quickly estimate the PCB temperature field when they need to quickly evaluate the peripheral selection of thermal solutions. Compared with the complete CFD numerical simulation process in the traditional design process, the calculation cost is greatly reduced, the calculation time and the user's learning cost are reduced, and manpower and material resources are saved.

As shown in FIG. 7 , this embodiment also provides a method for calculating the temperature field of a PCB in a heat sink, including the following steps:

S1. Obtain training data, where the training data includes fin distribution of the radiator, chip layout and temperature field distribution;

S2, preprocessing the training data, and combining the corresponding temperature field distribution as a label to form matching data;

S3. Based on the deep convolutional generative adversarial neural network, the strong mapping relationship between the fin distribution of the radiator and the chip layout is obtained by training, and the stable temperature field of the PCB under this heat dissipation condition is quickly calculated according to the distribution of the fins of the radiator and the chip layout. Proxy model;

S4. Input the input data consisting of the fin distribution of the radiator and the chip layout into the surrogate model after training, and quickly calculate the steady-state PCB temperature cloud map.

The method for calculating the PCB temperature field in the heat sink in this embodiment has a corresponding relationship with the calculation system for the PCB temperature field in the heat sink shown in FIG. 1 , and thus has the functions and beneficial effects of the system.

This embodiment also provides a computing device for the PCB temperature field in the heat sink, including:

at least one processor;

at least one memory for storing at least one program;

When the at least one program is executed by the at least one processor, the at least one processor implements the method shown in FIG. 7 .

The device for calculating the temperature field of the PCB in the heat sink in this embodiment can execute the method for calculating the temperature field of the PCB in the heat sink provided by the method embodiment of the present invention, and can execute any combination of the implementation steps of the method embodiment, and has The corresponding functions and beneficial effects of the method.

Embodiments of the present application further disclose a computer program product or computer program, where the computer program product or computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method shown in FIG. 7 .

This embodiment also provides a storage medium storing an instruction or a program for executing a method for calculating a temperature field of a PCB in a heat sink provided by the method embodiment of the present invention. When the instruction or program is executed, the method can be executed. Any combination of the implementation steps of the embodiments has the corresponding functions and beneficial effects of the method.

In some alternative implementations, the functions/operations noted in the block diagrams may occur out of the order noted in the operational diagrams. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/operations involved. Furthermore, the embodiments presented and described in the flowcharts of the present invention are provided by way of example in order to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of the various operations are altered and in which sub-operations described as part of larger operations are performed independently.

Furthermore, while the invention is described in the context of functional modules, it is to be understood that, unless stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or or software modules, or one or more functions and/or features may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to understand the present invention. Rather, given the attributes, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the modules will be within the routine skill of the engineer. Accordingly, those skilled in the art, using ordinary skill, can implement the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are illustrative only and are not intended to limit the scope of the invention, which is to be determined by the appended claims along with their full scope of equivalents.

The functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

The logic and/or steps represented in flowcharts or otherwise described herein, for example, may be considered an ordered listing of executable instructions for implementing the logical functions, may be embodied in any computer-readable medium, For use with, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from and execute instructions from an instruction execution system, apparatus, or apparatus) or equipment. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in connection with an instruction execution system, apparatus, or apparatus.

More specific examples (non-exhaustive list) of computer readable media include the following: electrical connections with one or more wiring (electronic devices), portable computer disk cartridges (magnetic devices), random access memory (RAM), Read Only Memory (ROM), Erasable Editable Read Only Memory (EPROM or Flash Memory), Fiber Optic Devices, and Portable Compact Disc Read Only Memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program may be printed, as the paper or other medium may be optically scanned, for example, followed by editing, interpretation, or other suitable medium as necessary process to obtain the program electronically and then store it in computer memory.

It should be understood that various parts of the present invention may be implemented in hardware, software, firmware or a combination thereof. In the above-described embodiments, various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or a combination of the following techniques known in the art: Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.

In the above description of the present specification, reference to the description of the terms "one embodiment/example", "another embodiment/example" or "certain embodiments/examples" etc. means the description in conjunction with the embodiment or example. Particular features, structures, materials, or characteristics are included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Although embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, The scope of the invention is defined by the claims and their equivalents.

The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above-mentioned embodiments, and those skilled in the art can also make various equivalent deformations or replacements on the premise of not violating the spirit of the present invention. Equivalent modifications or substitutions are included within the scope defined by the claims of the present application.

Claims (10)

1. a calculation method of PCB temperature field in a radiator, is characterized in that, comprises the following steps: acquiring training data, the training data including the fin distribution of the radiator, the chip layout and the temperature field distribution; Preprocessing the training data, and combining the corresponding temperature field distributions as labels to form matching data; Based on the deep convolutional generative adversarial neural network, the strong mapping relationship between the fin distribution of the heat sink and the chip layout is obtained by training, and a proxy for quickly calculating the steady-state temperature field of the PCB under this heat dissipation condition is constructed according to the distribution of the heat sink fins and the chip layout. Model; Input the input data consisting of the fin distribution of the heat sink and the chip layout into the trained surrogate model to quickly calculate the steady-state PCB temperature nephogram. 2. the calculation method of PCB temperature field in a kind of radiator according to claim 1, is characterized in that, described surrogate model is trained by way of generative confrontation network, and training process is made up of two different models of generator and discriminator , the generator is used to convert the input radiator fin distribution and chip distribution into the temperature field cloud map of the PCB steady state, the discriminator is used to distinguish the temperature field cloud map generated by the generator and the actual label cloud map, and the final training balance point is when the generator The generated temperature cloud map is consistent with the corresponding label of the dataset, and the probability that the discriminator can identify the cloud map generated by the generator is 50%. 3. the calculation method of PCB temperature field in a kind of radiator according to claim 1, is characterized in that, the input data of described proxy model is obtained by the following way: Determine fin distribution and fin height, chip distribution and chip heating power, bump distribution and bump height connecting chip and heat sink; Create a three-channel image with the same scale as the studied radiator, and perform a linear mapping with the image channel value with the height of the fin, the heating power of the chip, and the height of the bump, respectively, to obtain the model training data; According to the height of the fin, the heating power of the chip, and the height of the bump, the corresponding thermal model is created in ANSYS software and numerical simulation is performed, and the PCB temperature field distribution is obtained as a training label, and the training label is paired with the model training data one by one. 4. the calculation method of PCB temperature field in a kind of radiator according to claim 1, is characterized in that, described calculation method also comprises fine-tuning step: Migrate the data training weights of historical application scenarios to the current specific application scenario weights. 5. A computing system for PCB temperature field in a radiator, comprising: a data acquisition module for acquiring training data, where the training data includes fin distribution of the radiator, chip layout and temperature field distribution; A label generation module is used to preprocess the training data, and combine the corresponding temperature field distributions as labels to form matching data; The data training module is used to generate an adversarial neural network based on deep convolution. The training obtains a strong mapping relationship between the fin distribution of the radiator and the layout of the chip, and builds a rapid calculation of the PCB stability under this heat dissipation condition according to the distribution of the fins of the radiator and the layout of the chip. surrogate model of the temperature field of the state; The temperature calculation module is used to input the input data consisting of the fin distribution of the radiator and the chip layout into the surrogate model after training, and quickly calculate the steady-state PCB temperature cloud map. 6. The computing system of a PCB temperature field in a radiator according to claim 5, wherein the surrogate model is trained by a generative confrontation network, and the training process is composed of two different models of a generator and a discriminator , the generator is used to convert the input radiator fin distribution and chip distribution into the PCB steady-state temperature field cloud map, the discriminator is used to distinguish the temperature field cloud map generated by the generator and the actual label cloud map, and the final training balance point is when the generator The generated temperature cloud map is consistent with the corresponding label of the dataset, and the probability that the discriminator can identify the cloud map generated by the generator is 50%. 7. The computing system of a PCB temperature field in a heat sink according to claim 5, wherein the input data of the surrogate model is obtained in the following manner: Determine fin distribution and fin height, chip distribution and chip heating power, bump distribution and bump height connecting chip and heat sink; Create a three-channel image with the same scale as the studied radiator, and perform a linear mapping with the image channel value with the height of the fin, the heating power of the chip, and the height of the bump, respectively, to obtain the model training data; According to the height of the fin, the heating power of the chip, and the height of the bump, the corresponding thermal model is created in ANSYS software and numerical simulation is performed, and the PCB temperature field distribution is obtained as a training label, and the training label is paired with the model training data one by one. 8 . The computing system for a PCB temperature field in a heat sink according to claim 5 , wherein the computing system further comprises a fine-tuning module, and the fine-tuning module is used for migrating the data training weight of historical application scenarios to the current one. 9 . Specific application scenario weights. 9. A computing device for a PCB temperature field in a radiator, comprising: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method of any one of claims 1-4. 10. A computer-readable storage medium in which a processor-executable program is stored, wherein the processor-executable program is used to execute any one of claims 1-4 when executed by the processor the method.

Images