Simulation analysis method, device and storage medium of circuit board conductive film

Abstract

The present invention discloses a simulation analysis method, device and storage medium for a circuit board conductive film, the method comprising: obtaining historical electromagnetic wave attenuation data; performing electromagnetic field modeling according to a grid division method, boundary conditions and material properties to obtain an electromagnetic field model; performing a stress experiment according to the electromagnetic field model to obtain electromagnetic wave attenuation data; performing support vector machine classification according to the electromagnetic wave attenuation data and historical electromagnetic wave attenuation data to obtain classification data; performing model coupling according to the electromagnetic field model and a standard performance degradation model to obtain a multi-physics field model; inputting the electromagnetic wave attenuation data and the classification data into a pre-fitted standard performance degradation model to obtain predicted performance; comparing the predicted performance with the expected performance, and when it is determined that the predicted performance is lower than the expected performance, performing tree algorithm optimization to obtain optimized design parameters. The method can extend the life of the conductive film.

Description

Technical Field

[0001] The present invention relates to the technical field of conductive film simulation analysis, and in particular to a simulation analysis method, device and storage medium for a conductive film of a circuit board. Background Art

[0002] During the propagation of electromagnetic waves, the electromagnetic field distribution and propagation characteristics of the conductive film of the circuit board directly affect the integrity and reliability of the signal. However, the complex stress environment in which the conductive film is located, such as temperature, humidity, vibration, etc., will affect its electromagnetic performance, which in turn leads to problems such as signal distortion and increased attenuation. At the same time, the physical and chemical properties of the conductive film material will also change during long-term use, such as oxidation, corrosion, fatigue, etc. These changes accumulate to a certain extent, which will significantly reduce the conductive performance and mechanical strength of the conductive film, and ultimately shorten its service life.

[0003] In one existing technology, an accelerated aging test of a conductive film is performed to obtain conductive film resistance and time data, thereby establishing a life assessment model.

[0004] The existing technology lacks the ability to establish an accurate electromagnetic field model for the conductive film, and lacks an in-depth analysis of the evolution of its electromagnetic wave propagation characteristics in an actual working environment. At the same time, it does not consider the dynamic degradation process of the conductive film material performance, making it impossible to accurately evaluate its service life in a complex stress environment, and thus unable to provide an effective design improvement method to extend the life of the conductive film. Summary of the invention

[0005] The present invention provides a simulation analysis method, device and storage medium for a circuit board conductive film, so as to extend the life of the conductive film.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a simulation analysis method for a circuit board conductive film, comprising:

[0007] Obtain historical electromagnetic wave attenuation data;

[0008] Perform electromagnetic field modeling according to a preset grid division method, preset boundary conditions and preset material properties to obtain an electromagnetic field model;

[0009] According to the electromagnetic field model, a stress experiment is performed to obtain electromagnetic wave attenuation data;

[0010] Performing support vector machine classification according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain classified data;

[0011] According to the electromagnetic field model and the pre-fitted standard performance degradation model, model coupling is performed to obtain a multi-physics field model;

[0012] Inputting the electromagnetic wave attenuation data and the classification data into a pre-fitted standard performance degradation model to obtain predicted performance;

[0013] Comparing the multi-physics field model, the predicted performance and the preset expected performance, and when it is determined that the predicted performance is lower than the expected performance, performing tree algorithm optimization to obtain optimized design parameters;

[0014] The fitting process of the standard performance degradation model includes:

[0015] Obtain historical electromagnetic wave attenuation data, historical classification data, historical time data and historical initial data;

[0016] Constructing an initial performance degradation model according to the historical classification data, the historical time data and the historical initial data to obtain an initial performance degradation model;

[0017] An iterative fitting operation is performed according to the initial performance degradation model and the historical electromagnetic wave attenuation data. When it is determined that the number of iterations is greater than or equal to a preset maximum number of iterations, the iteration is terminated and a standard performance degradation model is obtained.

[0018] In an optional implementation, electromagnetic field modeling is performed according to a preset grid division method, preset boundary conditions, and preset material properties to obtain an electromagnetic field model, including:

[0019] According to the meshing method, finite element analysis is performed to obtain a finite element network model;

[0020] According to the finite element network model, the boundary conditions and the material properties, a Maxwell solution is performed to obtain an electromagnetic field model.

[0021] In an optional implementation, support vector machine classification is performed according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain classified data, including:

[0022] Performing data cleaning according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain clean attenuation data and historical clean attenuation data;

[0023] Normalizing the clean attenuation data and the historical clean attenuation data to obtain standard attenuation data and historical standard attenuation data;

[0024] According to the historical standard attenuation data, a support vector machine model is constructed to obtain an initial support vector machine model;

[0025] According to the initial support vector machine model, grid optimization training is performed to obtain an optimal support vector machine;

[0026] Classification prediction is performed according to the optimal support vector machine and the standard attenuation data to obtain classification data.

[0027] In an optional implementation, model coupling is performed according to the electromagnetic field model and the pre-fitted standard performance degradation model to obtain a multi-physics field model, including:

[0028] Extracting common parameters according to the electromagnetic field model and the standard performance degradation model to obtain common parameter data;

[0029] According to the common parameter data, multi-physics field coupling construction is performed to obtain a continuous multi-physics field model;

[0030] According to the continuous multi-physics field model, discretization processing is performed to obtain a multi-physics field model.

[0031] In an optional implementation, an initial performance degradation model is constructed according to the historical classification data, the historical time data and the historical initial data to obtain the initial performance degradation model, including:

[0032] Integrate the historical initial data, the historical classification data, and the historical time data to obtain model input data;

[0033] According to the model input data, the preset number of trees, the preset maximum tree depth and the preset number of decision features, a random forest is constructed to obtain an initial performance degradation model.

[0034] In an optional implementation, an iterative fitting operation is performed according to the initial performance degradation model and the historical electromagnetic wave attenuation data, and when it is determined that the number of iterations is greater than or equal to a preset maximum number of iterations, the iteration is terminated and a standard performance degradation model is obtained, including:

[0035] Initializing the initial performance degradation model to obtain a first performance degradation model;

[0036] Performing a theoretical calculation of electromagnetic wave attenuation according to the first performance degradation model, the historical electromagnetic wave attenuation data, the historical classification data, and the historical time data to obtain first theoretical electromagnetic wave attenuation data;

[0037] performing error calculation and updating the first performance degradation model according to the first theoretical electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain a second performance degradation model;

[0038] Continue iterating, and when it is determined that the number of iterations is greater than or equal to the preset maximum number of iterations, end the iteration and obtain the standard detection frequency estimation model.

[0039] In an optional implementation, a comparison is performed based on the multi-physics field model, the predicted performance, and the preset expected performance. When it is determined that the predicted performance is lower than the expected performance, a tree algorithm optimization is performed to obtain optimized design parameters, including:

[0040] According to the meshing method, boundary conditions, and material properties, random parameters are performed to obtain random parameters;

[0041] According to the random parameters, a gradient boosting tree is constructed to obtain a gradient boosting tree;

[0042] According to the random parameters, finite element simulation is performed to obtain a stress distribution cloud diagram;

[0043] According to the stress distribution cloud map and the gradient boosting tree, a performance qualification test is performed with the preset expected performance. When the performance is determined to be qualified, the optimization is terminated to obtain the optimized design parameters.

[0044] In a second aspect, the present invention provides a simulation analysis system for a circuit board conductive film, comprising:

[0045] An input module, used to obtain historical electromagnetic wave attenuation data;

[0046] The electromagnetic field construction module is used to perform electromagnetic field modeling according to a preset grid division method, preset boundary conditions and preset material properties to obtain an electromagnetic field model;

[0047] An electromagnetic wave simulation module, used to perform stress experiments according to the electromagnetic field model to obtain electromagnetic wave attenuation data;

[0048] An electromagnetic wave classification module, used for performing support vector machine classification according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain classification data;

[0049] A multi-physics field construction module is used to perform model coupling according to the electromagnetic field model and the pre-fitted standard performance degradation model to obtain a multi-physics field model;

[0050] A performance prediction module, used to input the electromagnetic wave attenuation data and the classification data into a pre-fitted standard performance degradation model to obtain predicted performance;

[0051] An optimization design module, for comparing the multi-physics field model, the predicted performance and the preset expected performance, and performing tree algorithm optimization to obtain optimized design parameters when it is determined that the predicted performance is lower than the expected performance;

[0052] The fitting process of the standard performance degradation model includes:

[0053] Obtain historical electromagnetic wave attenuation data, historical classification data, historical time data and historical initial data;

[0054] Constructing an initial performance degradation model according to the historical classification data, the historical time data and the historical initial data to obtain an initial performance degradation model;

[0055] An iterative fitting operation is performed according to the initial performance degradation model and the historical electromagnetic wave attenuation data. When it is determined that the number of iterations is greater than or equal to a preset maximum number of iterations, the iteration is terminated and a standard performance degradation model is obtained.

[0056] In a third aspect, the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the simulation analysis method of the conductive film of the circuit board described in any one of the above is implemented.

[0057] In a fourth aspect, the present invention further provides a computer-readable storage medium, the computer-readable storage medium comprising a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned simulation analysis methods for the conductive film of a circuit board.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] The present invention provides a simulation analysis method for a circuit board conductive film, which is executed by a computer and comprises:

[0060] Acquire historical electromagnetic wave attenuation data; perform electromagnetic field modeling according to a preset grid division method, preset boundary conditions and preset material properties to obtain an electromagnetic field model; perform stress experiments according to the electromagnetic field model to obtain electromagnetic wave attenuation data; perform support vector machine classification according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain classification data; perform model coupling according to the electromagnetic field model and a pre-fitted standard performance degradation model to obtain a multi-physics field model; input the electromagnetic wave attenuation data and the classification data into a pre-fitted standard performance degradation model to obtain predicted performance; The predicted performance is compared with the preset expected performance. When it is determined that the predicted performance is lower than the expected performance, a tree algorithm optimization is performed to obtain optimized design parameters. The fitting process of the standard performance degradation model includes: acquiring historical electromagnetic wave attenuation data, historical classification data, historical time data and historical initial data; constructing an initial performance degradation model according to the historical classification data, historical time data and the historical initial data to obtain an initial performance degradation model; performing an iterative fitting operation according to the initial performance degradation model and the historical electromagnetic wave attenuation data, and when it is determined that the number of iterations is greater than or equal to the preset maximum number of iterations, the iteration is terminated to obtain the standard performance degradation model.

[0061] The method disclosed in the present invention analyzes the interaction mechanism between electromagnetic wave propagation characteristics and material performance degradation by establishing a coupling model between electromagnetic field and material performance degradation. The propagation characteristics of electromagnetic waves in the conductive film are simulated by the finite element analysis method, and the signal integrity is classified and judged in combination with the support vector machine algorithm. At the same time, the service life of the conductive film is predicted by the random forest algorithm, and the design parameters are optimized by the gradient boosting tree algorithm. Therefore, the present invention realizes the improvement of the stability and reliability of the conductive film in a complex stress environment, and provides effective technical support for the performance optimization and life extension of the circuit board. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a schematic flow chart of a simulation analysis method of a circuit board conductive film provided by an embodiment of the present invention;

[0063] Figure 2 It is a structural schematic diagram of a simulation analysis system for a circuit board conductive film provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] Reference Figure 1 The embodiment of the present invention provides a simulation analysis method of a circuit board conductive film, comprising the following steps:

[0066] S11, obtaining historical electromagnetic wave attenuation data;

[0067] S12, performing electromagnetic field modeling according to a preset grid division method, preset boundary conditions, and preset material properties to obtain an electromagnetic field model;

[0068] S13, performing a stress experiment according to the electromagnetic field model to obtain electromagnetic wave attenuation data;

[0069] S14, performing support vector machine classification according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain classified data;

[0070] S15, performing model coupling according to the electromagnetic field model and the pre-fitted standard performance degradation model to obtain a multi-physics field model;

[0071] S16, inputting the electromagnetic wave attenuation data and the classification data into a pre-fitted standard performance degradation model to obtain predicted performance;

[0072] S17, comparing the multi-physics field model, the predicted performance and the preset expected performance, and when it is determined that the predicted performance is lower than the expected performance, performing tree algorithm optimization to obtain optimized design parameters;

[0073] The fitting process of the standard performance degradation model includes:

[0074] Obtain historical electromagnetic wave attenuation data, historical classification data, historical time data and historical initial data;

[0075] Constructing an initial performance degradation model according to the historical classification data, the historical time data and the historical initial data to obtain an initial performance degradation model;

[0076] An iterative fitting operation is performed according to the initial performance degradation model and the historical electromagnetic wave attenuation data. When it is determined that the number of iterations is greater than or equal to a preset maximum number of iterations, the iteration is terminated and a standard performance degradation model is obtained.

[0077] In step S11, historical electromagnetic wave attenuation data needs to be acquired.

[0078] It should be noted that in step S11, obtaining historical electromagnetic wave attenuation data is the basis of the entire analysis process, and the acquisition of this data is crucial for subsequent model construction and performance evaluation. The historical electromagnetic wave attenuation data includes changes in electromagnetic wave signal strength under different environmental conditions, including but not limited to temperature, humidity, distance and the like. These data can be obtained by experimental measurement. For example, in a laboratory environment, an electromagnetic wave transmitter and a receiver are used to record changes in signal strength under different set distances and environmental parameters, or historical operation data is collected from communication systems in actual applications. The present invention does not limit this. After acquiring the data, these data will be organized into a structured format for subsequent analysis and processing.

[0079] In step S12, electromagnetic field modeling is performed according to a preset grid division method, preset boundary conditions and preset material properties to obtain an electromagnetic field model, including:

[0080] According to the meshing method, finite element analysis is performed to obtain a finite element network model;

[0081] According to the finite element network model, the boundary conditions and the material properties, a Maxwell solution is performed to obtain an electromagnetic field model.

[0082] It should be noted that in step S12, the meshing method is to discretize the geometric structure of the conductive film into a finite element mesh for numerical calculation. Exemplarily, the present invention uses a tetrahedral meshing method to process a conductive film of complex shape and generate a high-quality finite element mesh model to ensure the calculation accuracy, which is not limited by the present invention. Exemplarily, for a rectangular conductive film with a size of 10cm×5cm×0.1mm, the mesh size can be set to 0.1mm to generate about 5 million mesh units. Of course, according to different application scenarios and user needs, the mesh size can also be adjusted to balance the calculation accuracy and efficiency, which is not limited by the present invention. The setting of boundary conditions reflects the actual working environment of the conductive film, which defines the physical value of the electromagnetic field on the boundary of the conductive film. These boundary conditions directly affect the distribution and propagation characteristics of the electromagnetic field, so they need to be reasonably set according to the specific application scenario. The material properties determine the electromagnetic properties of the conductive film, including parameters such as conductivity and magnetic permeability. Exemplarily, the present invention uses copper foil, whose conductivity is approximately , and the relative magnetic permeability is close to 1. These parameters directly affect the distribution and propagation characteristics of the electromagnetic field, so they need to be accurately obtained and set in the finite element model. After obtaining the finite element network model through finite element analysis, the Maxwell equations can be solved in combination with boundary conditions and material properties to obtain the electromagnetic field distribution inside the conductive film, including numerical solutions of physical quantities such as electric field intensity and magnetic field intensity. The electromagnetic field model is obtained based on the numerical solution modeling.

[0083] For example, in the experiment of the present invention, a higher electric field strength of about 0.8-1V / m is observed near the excitation end, while the electric field strength in the area far from the excitation source drops to 0.1-0.2V / m. In addition, the propagation process of electromagnetic waves in the conductive film can be simulated by the finite difference time domain method to obtain the change law of electromagnetic waves with time and space. For example, for the above conductive film, a 2.4GHz sine wave signal is input, and it can be observed that the propagation speed of the electromagnetic wave in the film is about , with a wavelength of about 6.25 cm. According to the geometric structure and boundary conditions of the conductive film, the propagation mode of the electromagnetic wave can also be determined. These analysis results not only help to understand the electromagnetic properties of the conductive film, but also provide a basis for optimizing the design. For example, the present invention can change the resonant frequency of the conductive film by adjusting the geometric dimensions of the conductive film, or improve the calculation efficiency and accuracy by optimizing the grid division.

[0084] In step S13, a stress experiment needs to be performed according to the electromagnetic field model to obtain electromagnetic wave attenuation data.

[0085] The electromagnetic field model is obtained based on finite element analysis and Maxwell's equations. It can accurately describe the electromagnetic field distribution and electromagnetic wave propagation characteristics inside the conductive film. Through this model, the propagation process of electromagnetic waves in the conductive film under different stress environments can be simulated, so as to obtain the distortion and attenuation data during the electromagnetic wave propagation process. These data are obtained through simulation methods. The simulation process needs to set different stress conditions, such as no stress, tensile stress and compressive stress, etc., to simulate the various complex environments encountered by the conductive film in actual use. The present invention does not limit this. Exemplarily, the present invention simulates three different stress states for a rectangular copper foil conductive film with a size of 10cm×5cm: no stress, 5% tensile stress and 5% compressive stress. In the stress-free state, a 2.4GHz sinusoidal wave signal is input, and the propagation speed of the electromagnetic wave in the film is approximately When a 5% tensile stress is applied, the geometric dimensions and conductivity of the conductive film change, causing the propagation speed to decrease to , while the signal amplitude attenuation increases by about 2dB. Under 5% compressive stress, the propagation speed increases to , but the signal distortion increases. These data reflect the influence of stress on the electromagnetic properties of the conductive film and are the basis for subsequent analysis. The acquired electromagnetic wave propagation distortion and attenuation data need to be cleaned and normalized by data preprocessing technology to obtain a standardized data set.

[0086] In step S14, support vector machine classification is performed according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain classified data, including:

[0087] Performing data cleaning according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain clean attenuation data and historical clean attenuation data;

[0088] Normalizing the clean attenuation data and the historical clean attenuation data to obtain standard attenuation data and historical standard attenuation data;

[0089] According to the historical standard attenuation data, a support vector machine model is constructed to obtain an initial support vector machine model;

[0090] According to the initial support vector machine model, grid optimization training is performed to obtain an optimal support vector machine;

[0091] Classification prediction is performed according to the optimal support vector machine and the standard attenuation data to obtain classification data.

[0092] It should be noted that in step S14, first of all, data cleaning is an important step in processing the original electromagnetic wave attenuation data, and its purpose is to remove outliers and process missing data. For example, among the 1000 data points collected, there are 5 data points that are obviously deviated from the normal range. The present invention can obtain clean attenuation data and historical clean attenuation data by detecting these outliers and removing them. This process ensures the quality of the data and provides a reliable foundation for subsequent analysis and modeling. Next, normalization is a key step to unify data of different dimensions to the same scale. For example, the propagation speed data is at 10 8The signal attenuation data is in the range of 0-10dB, but by dividing these data by their respective maximum values ​​so that all data fall within the range of 0-1, standard attenuation data and historical standard attenuation data can be obtained. This processing method makes the data set more conducive to subsequent machine learning algorithm processing and avoids model performance deviations caused by dimensional differences. Based on the historical standard attenuation data, a support vector machine (SVM) model is constructed for classification tasks. SVM is an effective classification tool that can build a classification model by learning the relationship between features and labels in the data. During the training process, a data set containing features such as propagation speed, signal attenuation, distortion, and corresponding signal integrity labels can be used. Exemplarily, the present invention uses three labels: good, general, and poor. Of course, other classification labeling methods can also be selected according to different application scenarios and user needs. The model performance can be optimized by adjusting the parameters γ and the penalty coefficient C of the kernel function. For example, after cross-validation, when γ=0.1 and C=10, the classification accuracy of the model on the validation set reaches 95%. Of course, other parameter combinations can be selected to further optimize the model performance according to different application scenarios and user needs, and the present invention is not limited to this.

[0093] After obtaining the initial support vector machine model, the performance of the model is further improved through grid optimization training. Grid optimization is a commonly used hyperparameter optimization method. By searching for the optimal parameter combination in the preset parameter grid, the optimal support vector machine model is obtained. This process ensures the best fitting effect of the model on the training data while avoiding the problem of overfitting or underfitting. Finally, the optimal support vector machine model and standard attenuation data are used for classification prediction to obtain classified data. This real-time monitoring and classification method can effectively prevent equipment failures caused by signal integrity problems and improve the reliability and stability of the system. Through this series of steps, not only can the electromagnetic properties of the conductive film under different conditions be deeply understood, but also an intelligent monitoring system can be built. The advantage of this method is that it combines physical models and data-driven machine learning technology, taking into account both electromagnetic principles and the advantages of big data analysis. This comprehensive method has broad application prospects in fields such as electronic equipment design, electromagnetic compatibility testing and industrial automation, and can significantly improve product quality and production efficiency.

[0094] In step S15, model coupling is performed according to the electromagnetic field model and the pre-fitted standard performance degradation model to obtain a multi-physics field model, including:

[0095] Extracting common parameters according to the electromagnetic field model and the standard performance degradation model to obtain common parameter data;

[0096] According to the common parameter data, multi-physics field coupling construction is performed to obtain a continuous multi-physics field model;

[0097] According to the continuous multi-physics field model, discretization processing is performed to obtain a multi-physics field model.

[0098] It should be noted that in step S15, first, the electromagnetic field model describes the propagation characteristics of electromagnetic waves in the conductive film, while the standard performance degradation model quantifies the performance changes of the conductive film due to factors such as oxidation, corrosion and fatigue during long-term use. By extracting the common parameters in the two models, illustratively, the present invention uses parameters related to electromagnetic characteristics such as conductivity and magnetic permeability, as well as parameters related to performance degradation such as material degradation rate and fatigue degree, common parameter data can be obtained. These parameters are the bridge connecting the electromagnetic field model and the standard performance degradation model, and provide a basis for the subsequent multi-physics field coupling construction. Next, multi-physics field coupling construction is performed based on the common parameter data to obtain a continuous multi-physics field model. This process combines the electromagnetic field model with the standard performance degradation model through mathematical methods to form a comprehensive model that can simultaneously describe the electromagnetic characteristics and material performance degradation process. The continuous multi-physics field model can more comprehensively reflect the physical behavior of the conductive film in actual use, including the propagation characteristics of electromagnetic waves and the changes in material performance over time. In order to make the multi-physics field model suitable for numerical calculation and practical application, it needs to be discretized. Discretization is the process of converting a continuous multi-physics field model into a discrete form. Exemplarily, the present invention is implemented by numerical calculation techniques such as finite element method and finite difference method. The discretized multi-physics field model can be efficiently solved and analyzed by a computer to obtain the electromagnetic characteristics and performance degradation state of the conductive film under different conditions.

[0099] It should be noted that, based on the historical classification data, the historical time data and the historical initial data, an initial performance degradation model is constructed to obtain an initial performance degradation model, including:

[0100] Integrate the historical initial data, the historical classification data, and the historical time data to obtain model input data;

[0101] According to the model input data, the preset number of trees, the preset maximum tree depth and the preset number of decision features, a random forest is constructed to obtain an initial performance degradation model.

[0102] Among them, in the process of constructing the initial performance degradation model, historical classification data, historical time data and historical initial data are integrated as model input data. These data reflect the performance status of the conductive film at different stages of use and the corresponding electromagnetic wave attenuation characteristics. Based on these input data, through the preset random forest parameters, the present invention sets the number of trees, the maximum tree depth and the number of decision features to construct an initial performance degradation model. Exemplarily, the preset number of trees can be set to 100, the maximum tree depth is set to 10, and the number of decision features is set to 3. Of course, according to different application scenarios and user needs, other parameter combinations can be selected to further optimize the model performance, and the present invention is not limited to this.

[0103] It should be noted that, according to the initial performance degradation model and the historical electromagnetic wave attenuation data, an iterative fitting operation is performed, and when it is determined that the number of iterations is greater than or equal to the preset maximum number of iterations, the iteration is terminated and a standard performance degradation model is obtained, including:

[0104] Initializing the initial performance degradation model to obtain a first performance degradation model;

[0105] Performing a theoretical calculation of electromagnetic wave attenuation according to the first performance degradation model, the historical electromagnetic wave attenuation data, the historical classification data, and the historical time data to obtain first theoretical electromagnetic wave attenuation data;

[0106] performing error calculation and updating the first performance degradation model according to the first theoretical electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain a second performance degradation model;

[0107] Continue iterating, and when it is determined that the number of iterations is greater than or equal to the preset maximum number of iterations, end the iteration and obtain the standard detection frequency estimation model.

[0108] Among them, the initial performance degradation model is optimized by iterative fitting operation. This process starts with the initialized performance degradation model, uses historical electromagnetic wave attenuation data and classification data to calculate the theoretical electromagnetic wave attenuation data, and updates the model parameters through error calculation. Each iteration recalculates the theoretical electromagnetic wave attenuation data according to the new model parameters and compares it with the historical data to evaluate the fitting accuracy of the model. When the number of iterations reaches the preset maximum number of iterations, the iterative process ends and a standard performance degradation model is obtained. Exemplarily, the preset maximum number of iterations can be set to 1000 times. Of course, according to different application scenarios and user needs, the number of iterations can also be adjusted to balance the computational efficiency and model accuracy, which is not limited in the present invention. Through this series of steps, not only a multi-physics field model that can simultaneously describe electromagnetic properties and material performance degradation can be constructed, but also an accurate performance degradation model can be obtained through random forest algorithm and iterative optimization method. The advantage of this method is that it combines physical models and data-driven machine learning technology, taking into account both electromagnetic principles and material science foundations, and taking advantage of big data analysis.

[0109] In step S16, the electromagnetic wave attenuation data and the classification data need to be input into a pre-fitted standard performance degradation model to obtain predicted performance.

[0110] The process of inputting electromagnetic wave attenuation data and classification data into a pre-fitted standard performance degradation model to obtain predicted performance. The electromagnetic wave attenuation data reflects the characteristic changes of electromagnetic wave propagation of the conductive film under different environmental conditions, including but not limited to attenuation degree, propagation speed, etc. These data can be obtained through experimental measurement or simulation. For example, the attenuation of electromagnetic waves is recorded under different stress, temperature and humidity conditions. The classification data is the result obtained after analyzing the electromagnetic wave attenuation data based on a support vector machine or other classification algorithm, which is used to identify the signal integrity status. For example, the present invention sets three levels of "good", "general" or "poor". The acquisition of these data depends on the previous electromagnetic field modeling and classification algorithm training, which provides an input basis for the performance degradation model.

[0111] The standard performance degradation model is constructed through an early iterative fitting process, and it can predict the performance state of the conductive film based on the input electromagnetic wave attenuation data and classification data. The construction of the model is based on historical data and machine learning algorithms. For example, the present invention uses random forests to quantify the performance degradation process by learning the law of changes in material performance over time and other factors. Of course, other machine learning methods can also be selected according to different application scenarios and user needs, and the present invention does not limit this.

[0112] In step S17, a comparison is made based on the multi-physics field model, the predicted performance and the preset expected performance. When it is determined that the predicted performance is lower than the expected performance, a tree algorithm optimization is performed to obtain optimized design parameters, including:

[0113] According to the meshing method, boundary conditions, and material properties, random parameters are performed to obtain random parameters;

[0114] According to the random parameters, a gradient boosting tree is constructed to obtain a gradient boosting tree;

[0115] According to the random parameters, finite element simulation is performed to obtain a stress distribution cloud diagram;

[0116] According to the stress distribution cloud map and the gradient boosting tree, a performance qualification test is performed with the preset expected performance. When the performance is determined to be qualified, the optimization is terminated to obtain the optimized design parameters.

[0117] It should be noted that in step S17, based on the multi-physics field model, the predicted performance and the preset expected performance, the comparison is performed, and the process of optimizing the design parameters is obtained by optimizing the tree algorithm. The multi-physics field model is obtained by coupling the electromagnetic field model and the material performance degradation model, and can simultaneously describe the electromagnetic characteristics of the conductive film and the changes of the material performance over time. This model provides a basic framework for the optimization design, and can be used for finite element simulation analysis after discretization. The predicted performance is obtained by the standard performance degradation model, which reflects the performance state of the conductive film under the current design parameters, including but not limited to resistivity changes, mechanical strength decreases, etc. The expected performance is a performance index preset according to the application scenario and user needs, which is used to evaluate whether the conductive film meets the design requirements. Exemplarily, the expected performance can be set to the resistivity increase of the conductive film not exceeding 20%, and the maximum stress not exceeding 80% of the material yield strength. Of course, these indicators can also be adjusted according to the application scenario and user needs, and the present invention is not limited to this.

[0118] In order to optimize the design parameters of the conductive film, the parameters are first randomized according to the meshing method, boundary conditions and material properties to obtain random parameters. The meshing method determines the accuracy and efficiency of the finite element simulation, while the boundary conditions and material properties directly affect the performance of the conductive film. Exemplarily, the meshing method can use a quadrilateral mesh, locally encrypt in the stress concentration area, and the mesh size gradually transitions from 1mm to 0.1mm; the boundary conditions can be set as fixed constraints and load application points; material properties, for example, the present invention uses Young's modulus, Poisson's ratio, conductivity, etc., which can be selected according to the actual material. Of course, these parameters can be adjusted according to specific needs, and the present invention does not limit this. Based on random parameters, a gradient boosting tree is constructed to obtain a gradient boosting tree model. The gradient boosting tree algorithm continuously improves the prediction accuracy by constructing multiple decision trees, each of which is trained on the residual of the previous tree. In the optimization of the conductive film, the mesh density, material thickness, etc. can be used as input features, and the maximum stress and deformation of the conductive film can be used as target variables. For example, in the initial design, the thickness of the conductive film is 0.5 mm and the maximum stress is 100 MPa. The optimization scheme is obtained through algorithm iteration: the thickness is increased to 0.6 mm, and the maximum stress is reduced to 80 MPa. Of course, these parameters and target variables can also be adjusted according to different application scenarios and user needs, and the present invention does not limit this. At the same time, finite element simulation is performed according to random parameters to obtain a stress distribution cloud map. Finite element simulation simulates the deformation and strain of the conductive film under different stress conditions through numerical calculation methods, providing intuitive performance evaluation for optimization design. The stress distribution cloud map can clearly show the weak areas of the conductive film, providing a basis for subsequent key optimization.

[0119] Finally, the performance qualification test is carried out according to the stress distribution cloud map and the gradient boosting tree model. If the predicted performance is judged to be lower than the expected performance, the optimization is continued; if the performance is qualified, the optimization is terminated to obtain the optimized design parameters. For example, the conductive film is subjected to a composite load of bending and tension, and the stress distribution cloud map is obtained by finite element analysis. The gradient boosting tree model identifies that when the bending stress exceeds 50MPa and the tensile stress exceeds 30MPa, the failure probability of the conductive film increases significantly. Based on this finding, these high-stress areas can be strengthened in a targeted manner, such as increasing the edge thickness from 0.5mm to 0.7mm, or using a material with a higher elastic modulus in the edge area. The optimized parameters are applied to the finite element simulation again to evaluate the performance of the conductive film under different working conditions. If the simulation results show that the maximum stress is lower than 80% of the material yield strength and the maximum deformation is less than 1% of the film thickness, it can be considered that the optimization scheme meets the requirements; otherwise, it is necessary to return to adjust the parameters for a new round of optimization.

[0120] In summary, the present invention provides a simulation analysis method for a circuit board conductive film, which is executed by a computer and includes:

[0121] Acquire historical electromagnetic wave attenuation data; perform electromagnetic field modeling according to a preset grid division method, preset boundary conditions and preset material properties to obtain an electromagnetic field model; perform stress experiments according to the electromagnetic field model to obtain electromagnetic wave attenuation data; perform support vector machine classification according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain classification data; perform model coupling according to the electromagnetic field model and a pre-fitted standard performance degradation model to obtain a multi-physics field model; input the electromagnetic wave attenuation data and the classification data into a pre-fitted standard performance degradation model to obtain predicted performance; The predicted performance is compared with the preset expected performance. When it is determined that the predicted performance is lower than the expected performance, a tree algorithm optimization is performed to obtain optimized design parameters. The fitting process of the standard performance degradation model includes: acquiring historical electromagnetic wave attenuation data, historical classification data, historical time data and historical initial data; constructing an initial performance degradation model according to the historical classification data, historical time data and the historical initial data to obtain an initial performance degradation model; performing an iterative fitting operation according to the initial performance degradation model and the historical electromagnetic wave attenuation data, and when it is determined that the number of iterations is greater than or equal to the preset maximum number of iterations, the iteration is terminated to obtain the standard performance degradation model.

[0122] The method disclosed in the present invention analyzes the interaction mechanism between electromagnetic wave propagation characteristics and material performance degradation by establishing a coupling model between electromagnetic field and material performance degradation. The propagation characteristics of electromagnetic waves in the conductive film are simulated by the finite element analysis method, and the signal integrity is classified and judged in combination with the support vector machine algorithm. At the same time, the service life of the conductive film is predicted by the random forest algorithm, and the design parameters are optimized by the gradient boosting tree algorithm. Therefore, the present invention realizes the improvement of the stability and reliability of the conductive film in a complex stress environment, and provides effective technical support for the performance optimization and life extension of the circuit board.

[0123] Reference Figure 2 The embodiment of the present invention provides a simulation analysis device for a circuit board conductive film, comprising:

[0124] An input module, used to obtain historical electromagnetic wave attenuation data;

[0125] The electromagnetic field construction module is used to perform electromagnetic field modeling according to a preset grid division method, preset boundary conditions and preset material properties to obtain an electromagnetic field model;

[0126] An electromagnetic wave simulation module, used to perform stress experiments according to the electromagnetic field model to obtain electromagnetic wave attenuation data;

[0127] An electromagnetic wave classification module, used for performing support vector machine classification according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain classification data;

[0128] A multi-physics field construction module is used to perform model coupling according to the electromagnetic field model and the pre-fitted standard performance degradation model to obtain a multi-physics field model;

[0129] A performance prediction module, used to input the electromagnetic wave attenuation data and the classification data into a pre-fitted standard performance degradation model to obtain predicted performance;

[0130] An optimization design module, for comparing the multi-physics field model, the predicted performance and the preset expected performance, and performing tree algorithm optimization to obtain optimized design parameters when it is determined that the predicted performance is lower than the expected performance;

[0131] The fitting process of the standard performance degradation model includes:

[0132] Obtain historical electromagnetic wave attenuation data, historical classification data, historical time data and historical initial data;

[0133] Constructing an initial performance degradation model according to the historical classification data, the historical time data and the historical initial data to obtain an initial performance degradation model;

[0134] An iterative fitting operation is performed according to the initial performance degradation model and the historical electromagnetic wave attenuation data. When it is determined that the number of iterations is greater than or equal to a preset maximum number of iterations, the iteration is terminated and a standard performance degradation model is obtained.

[0135] It should be noted that the simulation and analysis device for a circuit board conductive film provided in an embodiment of the present invention is used to execute all the process steps of the simulation and analysis method for a circuit board conductive film in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and thus will not be elaborated upon.

[0136] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned simulation analysis method for the conductive film of the circuit board are implemented, for example Figure 1 Alternatively, the processor implements the functions of each module / unit in the above-mentioned device embodiments when executing the computer program.

[0137] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0138] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0139] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0140] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0141] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0142] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0143] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A simulation analysis method for a circuit board conductive film, characterized in that: Executed by a computer, including: Obtain historical electromagnetic wave attenuation data; Perform electromagnetic field modeling according to a preset grid division method, preset boundary conditions and preset material properties to obtain an electromagnetic field model; According to the electromagnetic field model, a stress experiment is performed to obtain electromagnetic wave attenuation data; Performing support vector machine classification according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain classified data; According to the electromagnetic field model and the pre-fitted standard performance degradation model, model coupling is performed to obtain a multi-physics field model; Inputting the electromagnetic wave attenuation data and the classification data into a pre-fitted standard performance degradation model to obtain predicted performance; Comparing the multi-physics field model, the predicted performance and the preset expected performance, and when it is determined that the predicted performance is lower than the expected performance, performing tree algorithm optimization to obtain optimized design parameters; The fitting process of the standard performance degradation model includes: Obtain historical electromagnetic wave attenuation data, historical classification data, historical time data and historical initial data; Constructing an initial performance degradation model according to the historical classification data, the historical time data and the historical initial data to obtain an initial performance degradation model; An iterative fitting operation is performed according to the initial performance degradation model and the historical electromagnetic wave attenuation data. When it is determined that the number of iterations is greater than or equal to a preset maximum number of iterations, the iteration is terminated and a standard performance degradation model is obtained.

2. The simulation analysis method of the circuit board conductive film according to claim 1, characterized in that: According to the preset grid division method, preset boundary conditions and preset material properties, electromagnetic field modeling is performed to obtain an electromagnetic field model, including: According to the meshing method, finite element analysis is performed to obtain a finite element network model; According to the finite element network model, the boundary conditions and the material properties, a Maxwell solution is performed to obtain an electromagnetic field model.

3. The simulation analysis method of the circuit board conductive film according to claim 1, characterized in that: According to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data, support vector machine classification is performed to obtain classified data, including: Performing data cleaning according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain clean attenuation data and historical clean attenuation data; Normalizing the clean attenuation data and the historical clean attenuation data to obtain standard attenuation data and historical standard attenuation data; According to the historical standard attenuation data, a support vector machine model is constructed to obtain an initial support vector machine model; According to the initial support vector machine model, grid optimization training is performed to obtain an optimal support vector machine; Classification prediction is performed according to the optimal support vector machine and the standard attenuation data to obtain classification data.

4. The simulation analysis method of the circuit board conductive film according to claim 1, characterized in that: According to the electromagnetic field model and the pre-fitted standard performance degradation model, model coupling is performed to obtain a multi-physics field model, including: Extracting common parameters according to the electromagnetic field model and the standard performance degradation model to obtain common parameter data; According to the common parameter data, multi-physics field coupling construction is performed to obtain a continuous multi-physics field model; According to the continuous multi-physics field model, discretization processing is performed to obtain a multi-physics field model.

5. The simulation analysis method of the circuit board conductive film according to claim 1, characterized in that: An initial performance degradation model is constructed according to the historical classification data, the historical time data and the historical initial data to obtain an initial performance degradation model, including: Integrate the historical initial data, the historical classification data, and the historical time data to obtain model input data; According to the model input data, the preset number of trees, the preset maximum tree depth and the preset number of decision features, a random forest is constructed to obtain an initial performance degradation model.

6. The simulation analysis method of the circuit board conductive film according to claim 1, characterized in that: According to the initial performance degradation model and the historical electromagnetic wave attenuation data, an iterative fitting operation is performed, and when it is determined that the number of iterations is greater than or equal to a preset maximum number of iterations, the iteration is terminated and a standard performance degradation model is obtained, including: Initializing the initial performance degradation model to obtain a first performance degradation model; Performing a theoretical calculation of electromagnetic wave attenuation according to the first performance degradation model, the historical electromagnetic wave attenuation data, the historical classification data, and the historical time data to obtain first theoretical electromagnetic wave attenuation data; performing error calculation and updating the first performance degradation model according to the first theoretical electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain a second performance degradation model; Continue iterating, and when it is determined that the number of iterations is greater than or equal to the preset maximum number of iterations, end the iteration and obtain the standard detection frequency estimation model.

7. The simulation analysis method of the circuit board conductive film according to claim 1, characterized in that: According to the multi-physics field model, the predicted performance and the preset expected performance, a comparison is performed, and when it is determined that the predicted performance is lower than the expected performance, a tree algorithm optimization is performed to obtain optimized design parameters, including: According to the meshing method, boundary conditions, and material properties, random parameters are performed to obtain random parameters; According to the random parameters, a gradient boosting tree is constructed to obtain a gradient boosting tree; According to the random parameters, finite element simulation is performed to obtain a stress distribution cloud diagram; According to the stress distribution cloud map and the gradient boosting tree, a performance qualification test is performed with the preset expected performance. When the performance is determined to be qualified, the optimization is terminated to obtain the optimized design parameters.

8. A simulation analysis system for a circuit board conductive film, characterized in that: include: An input module, used to obtain historical electromagnetic wave attenuation data; The electromagnetic field construction module is used to perform electromagnetic field modeling according to a preset grid division method, preset boundary conditions and preset material properties to obtain an electromagnetic field model; An electromagnetic wave simulation module, used to perform stress experiments according to the electromagnetic field model to obtain electromagnetic wave attenuation data; An electromagnetic wave classification module, used for performing support vector machine classification according to the electromagnetic wave attenuation data and the historical electromagnetic wave attenuation data to obtain classification data; A multi-physics field construction module is used to perform model coupling according to the electromagnetic field model and the pre-fitted standard performance degradation model to obtain a multi-physics field model; A performance prediction module, used to input the electromagnetic wave attenuation data and the classification data into a pre-fitted standard performance degradation model to obtain predicted performance; An optimization design module, for comparing the multi-physics field model, the predicted performance and the preset expected performance, and performing tree algorithm optimization to obtain optimized design parameters when it is determined that the predicted performance is lower than the expected performance; The fitting process of the standard performance degradation model includes: Obtain historical electromagnetic wave attenuation data, historical classification data, historical time data and historical initial data; Constructing an initial performance degradation model according to the historical classification data, the historical time data and the historical initial data to obtain an initial performance degradation model; An iterative fitting operation is performed according to the initial performance degradation model and the historical electromagnetic wave attenuation data. When it is determined that the number of iterations is greater than or equal to a preset maximum number of iterations, the iteration is terminated and a standard performance degradation model is obtained.

9. An electronic device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the simulation analysis method of the conductive film of the circuit board as claimed in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the simulation analysis method for the conductive film of a circuit board as claimed in any one of claims 1 to 7.

Images