A method and system for optimizing alloy bonding process parameters

Abstract

The present invention discloses a method and system for optimizing alloy bonding process parameters, which relates to the field of data processing technology, including presetting a target microstructure state and constructing an evaluation index system; obtaining actual microstructure data of the bonding interface during the alloy bonding process, and marking key evolution features to determine the diffusion layer thickness and grain size distribution; establishing a relationship model between process parameters and microstructure by comparing the actual microstructure data with the target microstructure state, and completing a first prediction; analyzing the dynamic characteristics of the diffusion layer through the results of the first prediction, and completing a second prediction in combination with the thermal-diffusion threshold; and deriving an optimal process parameter combination through the results of the second prediction to achieve the target microstructure state. The present invention effectively solves problems such as target ambiguity and insufficient model accuracy, significantly improves bonding quality and stability, reduces scrap rate and cost, and provides an innovative solution for high-performance material processing.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for optimizing alloy bonding process parameters. Background Art

[0002] Alloy bonding, a crucial component of materials science and manufacturing technology, has widespread applications in aerospace, automotive, electronics, and energy. With the increasing demand for high-performance materials in modern industry, controlling the microstructure of alloy bonding interfaces has become a research hotspot. Recent advances in multi-physics coupled modeling, machine learning algorithms, and high-precision characterization techniques (such as scanning electron microscope (SEM) and transmission electron microscope (TEM)) have provided new technical tools for optimizing alloy bonding processes. For example, finite element analysis (FEA) simulations of diffusion behavior under coupled thermal-mechanical conditions can reveal the evolution of microstructure at the bonding interface. Furthermore, deep learning-based image segmentation algorithms enable automated extraction of diffusion layer thickness and grain size distribution. Furthermore, the introduction of dynamic monitoring technology enables real-time acquisition of microstructural data during the bonding process, providing a richer experimental basis for optimizing process parameters. However, while these technologies have improved the controllability of alloy bonding processes to a certain extent, their overall optimization remains subject to numerous limitations.

[0003] The existing alloy bonding process parameter optimization methods have the following shortcomings: Traditional methods often lack a clear definition of the target microstructure state, resulting in unclear optimization direction and difficulty in meeting the needs of specific application scenarios. The existing relationship models between process parameters and microstructure are mostly based on a single physical field or static assumptions, which cannot fully reflect the complex multi-physical field coupling in the actual bonding process. The dynamic evolution characteristics of the diffusion layer thickness and grain size distribution are usually simplified, and there is a lack of in-depth analysis of the thermal-diffusion dual-drive mechanism, resulting in a large deviation between the predicted results and the actual situation. Existing optimization methods mostly rely on empirical formulas or trial-and-error experiments, which are not only time-consuming and labor-intensive, but also difficult to adapt to the rapid adjustment needs under complex process conditions. The lack of a systematic evaluation index system makes it impossible to scientifically quantify the key characteristics of the bonding interface performance, affecting the guidance and operability of process optimization.

[0004] In response to the above problems, the present invention proposes an inverse parameter optimization method based on microstructure evolution, which belongs to the field of material processing and manufacturing technology. This method significantly improves the accuracy and efficiency of process parameter optimization by presetting the target microstructure state and constructing an evaluation index system, combining actual data comparison and dual-drive evolution threshold analysis. Specifically, the present invention solves problems such as fuzzy target setting, insufficient model accuracy, and neglect of dynamic characteristics, providing an innovative solution for achieving high-quality alloy bonding interfaces. Summary of the Invention

[0005] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0006] In view of the above existing problems, the present invention is proposed.

[0007] Therefore, the present invention provides a method and system for optimizing alloy bonding process parameters, which can solve the problems mentioned in the background technology.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0009] In a first aspect, the present invention provides a method for optimizing alloy bonding process parameters, which includes presetting a target microstructure state and constructing an evaluation index system;

[0010] Obtain actual microstructural data of the bonding interface during alloy bonding and mark key evolution features to determine the diffusion layer thickness and grain size distribution;

[0011] By comparing the actual microstructure data with the target microstructure state, a relationship model between process parameters and microstructure is established, and a first prediction is completed;

[0012] The results of the first prediction are used to analyze the dynamic characteristics of the diffusion layer, and the second prediction is completed by combining the thermal-diffusion threshold;

[0013] The optimal process parameter combination is derived from the results of the second prediction to achieve the target microstructure state and complete the optimization.

[0014] As a preferred solution of the method for optimizing the alloy bonding process parameters of the present invention, the construction of the evaluation index system includes:

[0015] Obtaining target performance requirement data for alloy bonding, wherein the target performance requirement data includes strength, electrical conductivity, and corrosion resistance;

[0016] Analyzing the target performance requirement data to extract microstructural characteristics, wherein the microstructural characteristics include diffusion layer thickness, grain size distribution, and interface defect density;

[0017] Based on the microstructural characteristics, a target microstructural state is preset, and a diffusion layer thickness range and a grain size distribution range under ideal conditions are defined;

[0018] Microstructure feature weights are defined to quantify key parameters of bonding interface performance. The microstructure feature weights include diffusion layer thickness weight, grain size distribution weight, and interface defect density weight.

[0019] As a preferred solution of the method for optimizing alloy bonding process parameters of the present invention, the key evolution characteristics of the markers include:

[0020] Collecting actual microstructure data during the alloy bonding process, wherein the actual microstructure data includes a scanning electron microscope image and a transmission electron microscope image of the bonding interface;

[0021] Preprocessing the actual microstructure data;

[0022] Extracting key evolution features of the bonding interface, wherein the key evolution features include diffusion layer thickness, grain size distribution, and interface defect morphology;

[0023] Based on the key evolution characteristics, a diffusion layer thickness distribution map and a grain size distribution statistics table are generated;

[0024] The critical areas of the diffusion layer thickness and grain size distribution are marked.

[0025] As a preferred solution of the method for optimizing alloy bonding process parameters of the present invention, the first prediction includes:

[0026] Comparing and analyzing the actual microstructure data with the target microstructure state to obtain difference characteristics, wherein the difference characteristics include diffusion layer thickness deviation, grain size distribution deviation, and interface defect density deviation;

[0027] Extracting key process parameters that affect bonding interface performance based on the difference characteristics, wherein the key process parameters include bonding temperature, bonding pressure, and bonding time;

[0028] Establishing a relationship model between process parameters and microstructure, wherein the relationship model is used to characterize the influence of process parameters on diffusion layer thickness and grain size distribution;

[0029] The current process parameter combination is input into the relationship model to obtain the predicted diffusion layer thickness, thereby completing the first prediction.

[0030] As a preferred solution of the method for optimizing alloy bonding process parameters of the present invention, the second prediction includes:

[0031] Based on the results of the first prediction, the dynamic evolution characteristics of the diffusion layer thickness are analyzed to extract the correlation between the diffusion rate and the process parameters;

[0032] Combining the thermomechanical coupling effect, a thermomechanical-diffusion dual-drive evolution model is constructed. The thermomechanical-diffusion dual-drive evolution model is used to characterize the influence mechanism of temperature field and stress field on the thickness of the diffusion layer.

[0033] By introducing the thermodynamic-diffusion threshold, the critical variation range of the diffusion layer thickness under different process conditions is quantified, and the key constraints on the bonding interface performance are determined;

[0034] By using the thermal-diffusion dual-drive evolution model and the thermal-diffusion threshold, the current process parameter combination is input to obtain the optimized diffusion layer thickness and grain size distribution results, thereby completing the second prediction.

[0035] As a preferred solution of the method for optimizing alloy bonding process parameters of the present invention, achieving the target microstructural state includes:

[0036] Based on the result of the second prediction, constructing a mapping relationship model between process parameters and target microstructural state, wherein the mapping relationship model describes the influence of process parameters on diffusion layer thickness and grain size distribution;

[0037] Search for the optimal process parameter combination that meets the target microstructural state;

[0038] Verifying the optimal process parameter combination through the mapping relationship model;

[0039] The optimal process parameter combination is output and applied to the actual alloy bonding process to achieve the target microstructure state and complete the optimization.

[0040] As a preferred solution of the method for optimizing alloy bonding process parameters of the present invention, the verification of the optimal process parameter combination includes:

[0041] Calculating the diffusion layer thickness and grain size distribution of the optimal process parameter combination by substituting the optimal process parameter combination into the mapping relationship model;

[0042] Deviations from the target microstructural state were evaluated through error analysis;

[0043] If the deviation exceeds the preset threshold, the parameters are adjusted and re-validated.

[0044] In a second aspect, the present invention provides an optimization system for alloy bonding process parameters, comprising: an evaluation index system module for presetting a target microstructure state and constructing an evaluation index system;

[0045] Bonding data acquisition module, used to obtain the actual microstructure data of the bonding interface during the alloy bonding process and mark key evolution features to determine the diffusion layer thickness and grain size distribution;

[0046] a first prediction module, configured to establish a relationship model between process parameters and microstructure by comparing the actual microstructure data with the target microstructure state, and to perform a first prediction;

[0047] A second-pass prediction module is used to analyze the dynamic characteristics of the diffusion layer based on the results of the first prediction and complete the second prediction in combination with the thermal-diffusion threshold;

[0048] The optimization derivation module is used to derive the optimal process parameter combination through the results of the second prediction, achieve the target microstructure state, and complete the optimization.

[0049] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, the steps of the method for optimizing alloy bonding process parameters are implemented.

[0050] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, the steps of the method for optimizing alloy bonding process parameters are implemented.

[0051] Compared with the prior art, the beneficial effect of the present invention is to achieve significant improvement in the optimization of alloy bonding process parameters through full-process closed-loop control. First, the target microstructure state is preset and an evaluation index system is constructed to clarify the optimization direction and improve the pertinence and operability; second, high-precision actual data is collected and key features are marked to provide reliable support for modeling; third, a relationship model between process parameters and microstructure is established to complete the first prediction, revealing the influence of process parameters on the diffusion layer thickness and grain size distribution; fourth, a thermal-diffusion dual-drive evolution model and threshold analysis are introduced to complete the second prediction, solving the problem that traditional static modeling cannot reflect dynamic characteristics; finally, the optimal process parameter combination is derived and its feasibility is verified through an intelligent optimization algorithm, which significantly shortens the optimization cycle and reduces experimental costs. The modular design enhances the versatility and adaptability of the method. In summary, the present invention effectively solves problems such as target ambiguity and insufficient model accuracy, significantly improves bonding quality and stability, reduces scrap rate and cost, and provides an innovative solution for high-performance material processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0053] Figure 1A method flow chart of an optimization method and system for alloy bonding process parameters provided by one embodiment of the present invention;

[0054] Figure 2 This is a diagram of the internal structure of a computer device for a method and system for optimizing alloy bonding process parameters provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0055] To make the above-mentioned objects, features, and advantages of the present invention more easily understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0056] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0057] Unless specifically stated otherwise, the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0058] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not necessarily drawn according to the actual proportional relationship.

[0059] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0060] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0061] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0062] In addition, in the description of the present disclosure, the terms "first," "second," "third," etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance or order. Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that such operations be performed in the particular order shown or in a sequential order, or that all illustrated operations be performed to achieve the desired result. In certain circumstances, multitasking and parallel processing can be advantageous.

[0063] Example 1, with reference to Figure 1 , is an embodiment of the present invention, which provides a method for optimizing alloy bonding process parameters, comprising:

[0064] Figure 1 A method flow chart of an optimization method and system for alloy bonding process parameters is shown, including:

[0065] S1: Preset the target microstructure state and build an evaluation index system;

[0066] S2: Obtain actual microstructure data of the bonding interface during alloy bonding and mark key evolution features to determine the diffusion layer thickness and grain size distribution;

[0067] S3: By comparing the actual microstructure data with the target microstructure state, a relationship model between process parameters and microstructure is established, and the first prediction is completed;

[0068] S4: Analyze the dynamic characteristics of the diffusion layer based on the first prediction, and complete the second prediction in combination with the thermal-diffusion threshold;

[0069] S5: Based on the second prediction result, reversely deduce the optimal process parameter combination to achieve the target microstructure state.

[0070] It should be noted that alloy bonding processes must meet high-precision and high-performance requirements in the field of material processing and manufacturing. Their design must consider the evolution of the microstructure of the bonding interface, the impact of process parameters on performance, and stability during long-term use. However, existing technologies face the following challenges:

[0071] The microstructural evolution mechanism of alloy bonding interfaces is complex, and the diffusion layer thickness and grain size distribution are difficult to precisely control. Traditional methods typically rely on experience or single-physics field analysis, failing to fully reflect the multi-factor coupling effects during the actual bonding process. The selection of process parameters (such as temperature, pressure, and time) during the bonding process lacks a scientific basis, and static models struggle to accurately predict bonding quality under dynamic conditions. This results in inefficient process optimization and the susceptibility to defects (such as porosity and cracks). Existing technologies offer insufficient assessment methods for fatigue life and damage accumulation at bonding interfaces, lacking scientific prediction methods based on time-varying characteristics. This increases process instability and potential failure risks. Further complicating matters, the interplay between thermomechanical coupling and diffusion behavior decisively influences bonding performance, but traditional methods struggle to monitor and predict the dynamic changes in diffusion layer thickness in real time, leading to delayed and inaccurate process parameter adjustments.

[0072] Therefore, in response to the above-mentioned problems of microstructure control, dynamic monitoring and process optimization, through steps S1-S5, a model is constructed to simulate the microstructure evolution law in the alloy bonding process, and a relationship model between process parameters and microstructure is obtained to achieve accurate calculation of the bonding interface performance; real-time monitoring of the diffusion layer thickness is achieved, the diffusion rate is dynamically calculated and early warning of abnormal evolution characteristics is issued; at the same time, based on the thermal-diffusion dual-driven evolution threshold and fatigue damage model, the optimization design of bonding process parameters and accurate prediction of remaining life are achieved.

[0073] Example 2, reference Figure 1 , is an embodiment of the present invention, which provides a method for optimizing alloy bonding process parameters, comprising:

[0074] In the embodiment of the present application, in step S1, an evaluation index system is constructed by the following steps, including:

[0075] Obtain target performance requirements for alloy bonding, including key performance indicators such as strength, conductivity, and corrosion resistance;

[0076] Analyze target performance requirement data and extract performance-related microstructural features, including diffusion layer thickness, grain size distribution, and interface defect density;

[0077] Based on the microstructural characteristics, the target microstructural state is preset, and the diffusion layer thickness range and grain size distribution range under ideal conditions are defined;

[0078] An evaluation index system is constructed to quantify the key parameters of bonding interface performance. The evaluation index system includes the diffusion layer thickness weight, grain size distribution weight and interface defect density weight.

[0079] In an optional embodiment, target performance requirement data can be obtained through experimental testing or literature research, and these data comprehensively consider the application scenarios of alloy bonding and the performance requirements in actual use.

[0080] In one optional embodiment, target performance requirements are first obtained through experimental testing, such as tensile testing to determine strength, resistance measurement to determine conductivity, and salt spray testing to determine corrosion resistance. This data is then compared and analyzed with theoretical values ​​from literature research to ensure comprehensiveness and reliability.

[0081] In an optional embodiment, microstructure features can be extracted through material characterization technology, and there is a clear correlation between these features and target performance requirement data.

[0082] In an alternative embodiment, the microstructural feature extraction process first analyzes diffusion layer thickness and grain size distribution based on scanning electron microscopy and transmission electron microscopy data, followed by metallographic microscopy to observe interface defect density. All data are statistically analyzed to ensure representativeness.

[0083] In an optional embodiment, a machine learning algorithm can be introduced to automatically identify and classify microstructural features. For example, a convolutional neural network can be used to segment scanning electron microscope images, automatically extract diffusion layer thickness and grain size distribution, and analyze the spatial distribution characteristics of interface defect density using a clustering algorithm.

[0084] In an optional embodiment, the target microstructure state can be determined by theoretical calculation or existing experimental data, for example, by calculating the thickness range of the diffusion layer under ideal conditions according to a diffusion kinetics formula.

[0085] In one optional embodiment, the target microstructural state is defined by first calculating the diffusion layer thickness range based on the diffusion kinetics formula, and then determining the grain size distribution range in conjunction with the grain growth model. All parameters are experimentally verified to ensure their scientific and reasonableness.

[0086] In an optional embodiment, the parameter range of the target microstructural state can also be optimized through simulation. For example, finite element analysis can be used to simulate the bonding interface performance under different diffusion layer thicknesses and grain size distributions, and the parameter range with the best performance can be selected as the target state.

[0087] In an optional embodiment, the evaluation index system can be constructed through expert experience or weight distribution schemes in existing literature to ensure that the importance of each key parameter is reasonably reflected.

[0088] In an optional embodiment, the construction process of the evaluation index system first determines the initial weight distribution scheme based on expert experience, and then optimizes and adjusts the weights through the hierarchical analysis method to ensure the scientificity and consistency of the weights of each parameter.

[0089] In an optional embodiment, a multi-objective optimization algorithm can be introduced to adjust the weight distribution in the evaluation index system. For example, the optimization algorithm can adjust the weights of diffusion layer thickness, grain size distribution, and interface defect density in real time to ensure that the evaluation system can adapt to the needs of different application scenarios.

[0090] In an optional embodiment, the verification process of the evaluation index system can be completed by comparing existing experimental data or simulation results to ensure that it can accurately reflect the bonding interface performance.

[0091] In one optional embodiment, the validation process for the evaluation index system first involves comparative analysis of predicted values ​​for diffusion layer thickness, grain size distribution, and interface defect density based on existing experimental data. Simulation results are then used to verify the rationality of the weighting assignments. All validation results are documented to support subsequent optimization processes.

[0092] In an optional embodiment, the evaluation index system can be further verified by a cross-validation method. For example, the experimental data can be divided into a training set and a test set, the training set can be used to optimize the weight distribution scheme, and the test set can be used to evaluate the prediction accuracy and applicability of the evaluation system.

[0093] In the embodiment of the present application, step S2 marks the key evolution features through the following steps, including:

[0094] Collect actual microstructure data during the alloy bonding process, including scanning electron microscope images and transmission electron microscope images of the bonding interface;

[0095] Preprocessing of scanning electron microscope and transmission electron microscope images to remove noise and enhance image contrast to improve feature recognition accuracy;

[0096] Use image segmentation algorithms to extract key evolutionary features of the bonding interface, including diffusion layer thickness, grain size distribution, and interface defect morphology;

[0097] Based on key evolution characteristics, a diffusion layer thickness distribution map and grain size distribution statistics table are generated to quantify the actual microstructure data;

[0098] Mark the key areas of diffusion layer thickness and grain size distribution to provide basic data support for subsequent process parameter optimization.

[0099] In an optional embodiment, the actual microstructure data can be collected by high-resolution scanning electron microscope and transmission electron microscope equipment to ensure that the image can clearly reflect the microstructure characteristics of the bonding interface.

[0100] In an alternative embodiment, when acquiring scanning electron microscope and transmission electron microscope images, the sample is first cut and polished to ensure that the bonding interface is flat and undamaged. Subsequently, images are taken at different magnifications to cover multi-scale features from macro to micro.

[0101] In an optional embodiment, environmental control, such as constant temperature and humidity conditions, may be introduced during the collection process to prevent external factors from affecting the surface state of the sample.

[0102] In an optional embodiment, the image preprocessing can be performed by using common image processing software, such as ImageJ or MATLAB, to remove noise and adjust contrast using a filtering algorithm.

[0103] In an optional embodiment, the image preprocessing process first uses Gaussian filtering to remove background noise, and then uses a histogram equalization algorithm to enhance image contrast and highlight key features of the bonding interface.

[0104] In an optional embodiment, a deep learning algorithm, such as a convolutional neural network (CNN), can be introduced to intelligently remove noise and enhance contrast in images. For example, a CNN model can be trained to automatically identify noisy areas and optimize image quality, further improving the accuracy of subsequent feature extraction.

[0105] In an optional embodiment, the image segmentation algorithm can be implemented based on threshold segmentation or edge detection technology to extract key features such as diffusion layer thickness and grain size distribution.

[0106] In an optional embodiment, the image segmentation process first uses the Canny edge detection algorithm to locate the diffusion layer boundary, and then uses the region growing algorithm to extract the grain region. All segmentation results are manually verified to ensure accuracy.

[0107] In an optional embodiment, automated segmentation can be achieved by combining machine learning methods, such as a U-Net network. For example, a U-Net model can be trained to automatically identify diffusion layers and grain regions, and the spatial distribution characteristics of interface defects can be analyzed using a clustering algorithm.

[0108] In an optional embodiment, the diffusion layer thickness distribution graph and the grain size distribution statistics table can be generated by an image analysis tool, such as using ImageJ to measure the diffusion layer thickness and calculate the grain size distribution.

[0109] In an optional embodiment, the process of generating a diffusion layer thickness distribution map first calculates the diffusion layer thickness at each location based on the segmentation results, and then maps the data onto a two-dimensional plane to form a distribution map. A grain size distribution statistics table is generated using a statistical analysis algorithm, showing the proportion of grains of different sizes.

[0110] In an optional embodiment, finite element analysis can be introduced to simulate and verify the diffusion layer thickness distribution map. For example, finite element analysis can be used to simulate the diffusion dynamics process, verify the accuracy of the experimental measurement results, and dynamically adjust the parameter range of the distribution map.

[0111] In an optional embodiment, the marking of the key areas can be completed by manual annotation or automated algorithm to ensure that the marking results can accurately reflect the changing trends of the diffusion layer thickness and grain size distribution.

[0112] In an optional embodiment, the critical area marking process first identifies abnormal thickness areas, such as those that are too thin or too thick, based on the diffusion layer thickness distribution map. It then uses a statistical table of grain size distribution to mark abnormal grain areas, such as those that are too large or too small. All marking results are recorded to provide a basis for subsequent optimization.

[0113] In an optional embodiment, a machine learning method can be introduced to automatically classify and label key areas. For example, a K-means clustering algorithm is used to partition the diffusion layer thickness and grain size distribution, and a visual labeling map is generated based on the partitioning results.

[0114] In the embodiment of the present application, the first prediction is completed in step S3 through the following steps, including:

[0115] Compare and analyze the actual microstructure data with the target microstructure state to quantify the difference characteristics between the two, including the deviation of diffusion layer thickness, grain size distribution and interface defect density;

[0116] Based on the difference characteristics, the key process parameters affecting the performance of the bonding interface are extracted, including bonding temperature, bonding pressure and bonding time;

[0117] Use regression analysis or machine learning algorithms to establish a relationship model between process parameters and microstructure. The relationship model describes the influence of process parameters on diffusion layer thickness and grain size distribution.

[0118] Through the relational model, the current process parameter combination is input to complete the first prediction and obtain the predicted diffusion layer thickness.

[0119] In an optional embodiment, the quantification of the difference characteristics can be completed by simple mathematical calculation, such as calculating the diffusion layer thickness deviation and the grain size distribution deviation by subtraction operation.

[0120] In an optional embodiment, the differential signature quantification process first calculates the deviations in diffusion layer thickness and grain size distribution using statistical analysis methods. Then, an image comparison algorithm is used to quantify the deviations in interface defect density. All results are recorded to provide a basis for subsequent analysis.

[0121] In an optional embodiment, a machine learning algorithm may be introduced to automatically identify and quantify difference features. For example, a support vector machine (SVM) model may be trained to classify the differences between the actual data and the target state and generate a deviation distribution map.

[0122] In an optional embodiment, the extraction of key process parameters can be completed through expert experience or literature research to ensure that the extracted parameters can fully reflect the factors affecting the performance of the bonding interface.

[0123] In an optional embodiment, the key process parameter extraction process first reduces the dimensionality of the differential features based on principal component analysis to identify the parameters that have the greatest impact on the bonding interface performance, such as temperature, pressure, and time. The importance of these parameters is then verified using experimental data.

[0124] In an optional embodiment, a sensitivity analysis method can also be used to evaluate the impact of each process parameter on the differential characteristics. For example, the contribution rate of each parameter can be calculated through local sensitivity analysis or global sensitivity analysis, and the parameter priority can be dynamically adjusted.

[0125] In an optional embodiment, the relationship model can be established through multiple linear regression analysis, using experimental data to fit the mathematical relationship between process parameters and microstructure.

[0126] In an optional embodiment, the process of establishing the relationship model first fits the complex relationship based on nonlinear regression analysis, and then optimizes the model parameters through cross-validation to ensure its prediction accuracy and generalization ability.

[0127] In an optional embodiment, a deep learning algorithm can be introduced to construct a relational model. For example, a multi-layer perceptron network is designed with process parameters as input and diffusion layer thickness and grain size distribution as output, and the model is trained using large-scale experimental data.

[0128] In an optional embodiment, the first prediction can be completed by directly substituting the current process parameters into the relationship model to generate predicted diffusion layer thickness and grain size distribution results.

[0129] In an optional embodiment, the first prediction process first calculates the predicted values ​​of the diffusion layer thickness and grain size distribution based on the relationship model, and then evaluates the accuracy of the prediction results through error analysis. If the error is large, the model parameters are adjusted and the prediction is repeated.

[0130] In an optional embodiment, a real-time monitoring system can be introduced to dynamically update the prediction results. For example, process parameter data can be collected in real time during the production process, input into the relational model to generate dynamic prediction results, and the feedback data can be combined to optimize the prediction accuracy and grain size distribution results.

[0131] In the embodiment of the present application, the second prediction is completed in step S4 through the following steps, including:

[0132] Based on the first prediction results, the dynamic evolution characteristics of the diffusion layer thickness are analyzed to extract the correlation between the diffusion rate and the process parameters;

[0133] Combining the thermomechanical coupling effect, a thermomechanical-diffusion dual-driven evolution model is constructed. The model describes the influence mechanism of temperature field and stress field on the thickness of the diffusion layer.

[0134] Introducing a thermal-diffusion threshold to quantify the critical variation range of the diffusion layer thickness under different process conditions and determine the key constraints on the bonding interface performance;

[0135] Through the thermodynamic-diffusion dual-driven evolution model and thermodynamic-diffusion threshold, the current process parameter combination is input to complete the second prediction and obtain the optimized diffusion layer thickness and grain size distribution results.

[0136] In an optional embodiment, the dynamic evolution characteristics of the diffusion layer thickness can be completed by fitting experimental data, for example, using linear regression analysis to extract the relationship between the diffusion rate and process parameters such as temperature and pressure.

[0137] In one optional embodiment, the dynamic evolution analysis of the diffusion layer thickness first involves plotting a time-varying curve of the diffusion layer thickness based on experimental data. The diffusion rate is then calculated through numerical differentiation. Finally, multiple regression analysis is used to extract correlations between the diffusion rate and process parameters, such as temperature, pressure, and time.

[0138] In an optional embodiment, the thermodynamic-diffusion dual-drive evolution model can be completed by deducing theoretical formulas, for example, by combining Fourier's heat conduction equation and Fick's diffusion law to establish a mathematical model.

[0139] In an optional embodiment, the construction process of the thermodynamic-diffusion dual-driven evolution model first fits the influence coefficients of the temperature field and stress field on the diffusion layer thickness based on experimental data, and then describes the coupling between the temperature field, stress field and diffusion layer thickness through a set of partial differential equations.

[0140] In an optional embodiment, a multi-physics simulation tool, such as COMSOL Multiphysics, can be used to construct a thermal-mechanical-diffusion dual-drive evolution model. For example, a thermal-mechanical-diffusion coupling module can be set up in COMSOL, and actual process parameters can be input for simulation to generate a dynamic distribution diagram of the diffusion layer thickness as it changes with the temperature and stress fields.

[0141] In an optional embodiment, the thermo-diffusion threshold can be obtained through experimental testing or literature research to ensure that it can reflect the key constraint conditions of the bonding interface performance.

[0142] In one optional embodiment, the introduction of the thermal-diffusion threshold involves first analyzing the critical value of the diffusion layer thickness under different process conditions based on experimental data. This is then quantified using statistical analysis methods, such as confidence interval calculations. All results are documented to provide a basis for subsequent optimization.

[0143] In an optional embodiment, a machine learning algorithm can be introduced to automatically identify the thermal-diffusion threshold. For example, a K-means clustering algorithm can be used to partition the diffusion layer thickness data, extract the critical variation range under different process conditions, and adjust the threshold range based on expert experience.

[0144] In an optional embodiment, the second prediction can be completed by directly substituting the current process parameters into the thermal-diffusion dual-drive evolution model to generate optimized diffusion layer thickness and grain size distribution results.

[0145] In an optional embodiment, the second prediction process first calculates the predicted values ​​of the diffusion layer thickness and grain size distribution based on the thermal-diffusion dual-driven evolution model, and then constrains the prediction results in combination with the thermal-diffusion threshold to ensure that they meet the bonding interface performance requirements.

[0146] In an optional embodiment, a real-time monitoring system can be introduced to dynamically update the prediction results. For example, process parameter data can be collected in real time during the production process and input into the thermal-diffusion dual-drive evolution model to generate dynamic prediction results. The thermal-diffusion threshold can then be used to optimize prediction accuracy.

[0147] In the embodiment of the present application, in step S5, the optimal process parameter combination is reversely derived through the following steps, including:

[0148] Based on the second prediction result, a mapping relationship model between process parameters and target microstructure state is constructed. The mapping relationship model describes the influence of process parameters on diffusion layer thickness and grain size distribution.

[0149] Utilize optimization algorithms to search for the optimal combination of process parameters that meets the target microstructural state;

[0150] The feasibility of the optimal process parameter combination is verified through the mapping relationship model to ensure that it can achieve the target microstructure state;

[0151] Output the optimal process parameter combination and apply it to the actual alloy bonding process to achieve the target microstructure state and complete the optimization.

[0152] In an optional embodiment, the mapping relationship model can be constructed through multivariate regression analysis, and the second prediction result is used to fit the mathematical relationship between the process parameters and the diffusion layer thickness and grain size distribution.

[0153] In an optional embodiment, the mapping relationship model is constructed by first generating input-output pairs based on experimental data, and then fitting the complex relationship through nonlinear regression analysis. All parameters are cross-validated and optimized to ensure the accuracy of the model.

[0154] In an optional embodiment, the optimization algorithm can be implemented based on a genetic algorithm, by setting a fitness function to search for an optimal process parameter combination, such as minimizing the deviation of the target microstructure state.

[0155] In an optional embodiment, the optimization algorithm selection process first performs a global search in the process parameter space based on the particle swarm optimization algorithm, and then further optimizes the accuracy of the solution through a local search algorithm, such as the gradient descent method, to ensure that the optimal parameter combination is found.

[0156] In an optional embodiment, a hybrid optimization strategy can be implemented by combining multiple optimization algorithms. For example, a genetic algorithm is first used for global search, followed by a particle swarm optimization algorithm for local fine search, ultimately obtaining the optimal process parameter combination that satisfies the target microstructural state.

[0157] In an optional embodiment, the feasibility verification of the optimal process parameter combination can be completed by directly substituting it into the mapping relationship model to calculate whether the corresponding diffusion layer thickness and grain size distribution meet the target requirements.

[0158] In one optional embodiment, the feasibility verification process first calculates the diffusion layer thickness and grain size distribution for the optimal process parameter combination based on the mapping relationship model. The deviation from the target microstructure is then evaluated through error analysis. If the deviation exceeds a preset threshold, the parameters are adjusted and the verification is repeated.

[0159] In an optional embodiment, a real-time simulation tool can be used to dynamically verify the optimal process parameter combination. For example, the bonding process under different process conditions can be simulated in a simulation environment to verify whether the diffusion layer thickness and grain size distribution meet the target requirements, and then compared with experimental data for analysis.

[0160] In an optional embodiment, the output of the optimal process parameter combination can be achieved through a visual interface, for example, displaying parameters such as temperature, pressure, time, etc. in the form of a chart, and generating an operation instruction document.

[0161] In an optional embodiment, the optimal process parameter combination is first verified in a small-scale laboratory environment, and then applied on a large scale in an actual production line. All results are recorded to ensure the stability and reliability of the process parameters.

[0162] In an optional embodiment, an intelligent control system can be introduced to dynamically adjust process parameters. For example, during production, microstructure data of the bonding interface can be collected in real time, and the optimal combination of process parameters can be used as initial conditions. The process flow can then be dynamically optimized based on feedback data to ultimately achieve the target microstructure.

[0163] Example 3, reference Figure 2 , is an embodiment of the present invention, and this embodiment further provides an optimization system for alloy bonding process parameters, including:

[0164] Evaluation index system module, used to preset the target microstructure state and build an evaluation index system;

[0165] Bonding data acquisition module, used to obtain the actual microstructure data of the bonding interface during the alloy bonding process and mark key evolution features to determine the diffusion layer thickness and grain size distribution;

[0166] A first prediction module is used to establish a relationship model between process parameters and microstructure by comparing actual microstructure data with target microstructure state, and to complete a first prediction;

[0167] A second-pass prediction module is used to analyze the dynamic characteristics of the diffusion layer based on the results of the first prediction and complete the second prediction in combination with the thermal-diffusion threshold;

[0168] The optimization derivation module is used to derive the optimal process parameter combination through the results of the second prediction, achieve the target microstructure state, and complete the optimization.

[0169] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 2As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for optimizing alloy bonding process parameters is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0170] This embodiment further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the following steps are implemented:

[0171] Preset the target micro-organizational state and build an evaluation index system;

[0172] Obtain actual microstructural data of the bonding interface during alloy bonding and mark key evolution features to determine the diffusion layer thickness and grain size distribution;

[0173] By comparing the actual microstructure data with the target microstructure state, a relationship model between process parameters and microstructure is established, and the first prediction is completed;

[0174] The results of the first prediction are used to analyze the dynamic characteristics of the diffusion layer, and the second prediction is completed by combining the thermal-diffusion threshold;

[0175] The optimal process parameter combination is derived from the results of the second prediction to achieve the target microstructure state and complete the optimization.

[0176] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0177] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application may be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0178] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0179] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0180] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0181] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0182] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for optimizing alloy bonding process parameters, characterized in that: include, Preset the target micro-organizational state and build an evaluation index system; Obtain actual microstructural data of the bonding interface during alloy bonding and mark key evolution features to determine the diffusion layer thickness and grain size distribution; By comparing the actual microstructure data with the target microstructure state, a relationship model between process parameters and microstructure is established, and a first prediction is completed; The results of the first prediction are used to analyze the dynamic characteristics of the diffusion layer, and the second prediction is completed by combining the thermal-diffusion threshold; The optimal process parameter combination is derived from the results of the second prediction to achieve the target microstructure state and complete the optimization; The first prediction includes: Comparing and analyzing the actual microstructure data with the target microstructure state to obtain difference characteristics, wherein the difference characteristics include diffusion layer thickness deviation, grain size distribution deviation, and interface defect density deviation; Extracting key process parameters that affect bonding interface performance based on the difference characteristics, wherein the key process parameters include bonding temperature, bonding pressure, and bonding time; Establishing a relationship model between process parameters and microstructure, wherein the relationship model is used to characterize the influence of process parameters on diffusion layer thickness and grain size distribution; Inputting the current process parameter combination into the relationship model to obtain the predicted diffusion layer thickness, thereby completing the first prediction; The second prediction includes: Based on the results of the first prediction, the dynamic evolution characteristics of the diffusion layer thickness are analyzed to extract the correlation between the diffusion rate and the process parameters; Combining the thermomechanical coupling effect, a thermomechanical-diffusion dual-drive evolution model is constructed. The thermomechanical-diffusion dual-drive evolution model is used to characterize the influence mechanism of temperature field and stress field on the thickness of the diffusion layer. By introducing the thermodynamic-diffusion threshold, the critical variation range of the diffusion layer thickness under different process conditions is quantified, and the key constraints on the bonding interface performance are determined; By using the thermal-diffusion dual-drive evolution model and the thermal-diffusion threshold, the current process parameter combination is input to obtain the optimized diffusion layer thickness and grain size distribution results, thereby completing the second prediction.

2. The method for optimizing alloy bonding process parameters according to claim 1, wherein: The construction of the evaluation index system includes: Obtaining target performance requirement data for alloy bonding, wherein the target performance requirement data includes strength, electrical conductivity, and corrosion resistance; Analyzing the target performance requirement data to extract microstructural characteristics, wherein the microstructural characteristics include diffusion layer thickness, grain size distribution, and interface defect density; Based on the microstructural characteristics, a target microstructural state is preset, and a diffusion layer thickness range and a grain size distribution range under ideal conditions are defined; Microstructure feature weights are defined to quantify key parameters of bonding interface performance. The microstructure feature weights include diffusion layer thickness weight, grain size distribution weight, and interface defect density weight.

3. The method for optimizing alloy bonding process parameters according to claim 2, wherein: The key evolutionary features of the markers include: Collecting actual microstructure data during the alloy bonding process, wherein the actual microstructure data includes a scanning electron microscope image and a transmission electron microscope image of the bonding interface; Preprocessing the actual microstructure data; Extracting key evolution features of the bonding interface, wherein the key evolution features include diffusion layer thickness, grain size distribution, and interface defect morphology; Based on the key evolution characteristics, a diffusion layer thickness distribution map and a grain size distribution statistics table are generated; The critical areas of the diffusion layer thickness and grain size distribution are marked.

4. The method for optimizing alloy bonding process parameters according to claim 3, wherein: The target micro-organizational state is achieved by: Based on the result of the second prediction, constructing a mapping relationship model between process parameters and target microstructural state, wherein the mapping relationship model describes the influence of process parameters on diffusion layer thickness and grain size distribution; Search for the optimal process parameter combination that meets the target microstructural state; Verifying the optimal process parameter combination through the mapping relationship model; The optimal process parameter combination is output and applied to the actual alloy bonding process to achieve the target microstructure state and complete the optimization.

5. The method for optimizing alloy bonding process parameters according to claim 4, wherein: The verification of the optimal process parameter combination includes: Calculating the diffusion layer thickness and grain size distribution of the optimal process parameter combination by substituting the optimal process parameter combination into the mapping relationship model; Deviations from the target microstructural state were evaluated through error analysis; If the deviation exceeds the preset threshold, the parameters are adjusted and re-validated.

6. A system for optimizing alloy bonding process parameters, based on the method for optimizing alloy bonding process parameters according to any one of claims 1 to 5, characterized in that: include, Evaluation index system module, used to preset the target microstructure state and build an evaluation index system; Bonding data acquisition module, used to obtain the actual microstructure data of the bonding interface during the alloy bonding process and mark key evolution features to determine the diffusion layer thickness and grain size distribution; a first prediction module, configured to establish a relationship model between process parameters and microstructure by comparing the actual microstructure data with the target microstructure state, and to perform a first prediction; A second-pass prediction module is used to analyze the dynamic characteristics of the diffusion layer based on the results of the first prediction and complete the second prediction in combination with the thermal-diffusion threshold; The optimization derivation module is used to derive the optimal process parameter combination through the results of the second prediction, achieve the target microstructure state, and complete the optimization.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for optimizing the alloy bonding process parameters according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for optimizing alloy bonding process parameters according to any one of claims 1 to 5 are implemented.

Images