Solid crystal glue performance optimization method and system based on filling technology

Abstract

The invention provides a solid crystal glue performance optimization method and system based on a filling technology, and relates to the technical field of data processing, and the method comprises the steps: taking packaging quality and a filling mode as guidance, determining a performance optimization index, carrying out clustering and correlation evaluation based on an optimization type, determining an optimization constraint condition, and reading a solid crystal glue production technology. Performing traceability positioning based on performance optimization indexes, determining optimization process points, performing hierarchical multi-target optimization, determining an initialization optimization scheme, performing forward derivation evaluation and reverse derivation verification, performing determination verification addition, and determining a performance optimization scheme. According to the invention, the technical problem that the overall performance and reliability of the product are further influenced due to poor packaging quality and filling effect caused by insufficient adaptation degree of die attach adhesive production process parameter setting in the prior art can be solved, the packaging quality and the filling effect are improved, and the overall performance and reliability of the product are ensured to reach expected standards.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for optimizing the performance of a die-bonding adhesive based on a filling technology. Background Art

[0002] Bonding adhesives are widely used in semiconductor packaging, LED packaging and other fields. With the continuous development of the electronics industry, the performance requirements for bonding adhesives are getting higher and higher. For example, in the field of LED packaging, with the growing demand for small-size chip packaging, the market has put forward higher requirements for the viscosity, stability, anti-poisoning ability, curing speed and thrust of bonding adhesives.

[0003] At present, the parameter setting in the production process of the die-bonding adhesive is crucial to the packaging quality and filling method. However, in the prior art, due to the lack of scientific parameter setting methods and precise optimization targets, the process parameter settings are often unreasonable. Such unreasonable parameter settings will directly affect the packaging quality and filling effect of the die-bonding adhesive, causing gaps, unevenness or other defects in the packaging layer. These problems will further affect the overall performance and reliability of the product, such as reducing the mechanical strength, electrical performance and durability of the product.

[0004] In summary, the prior art has technical problems in which the process parameters of the die-bonding adhesive production process are not sufficiently adapted, resulting in poor packaging quality and filling effects, further affecting the overall performance and reliability of the product. Summary of the invention

[0005] The purpose of this application is to provide a method and system for optimizing the performance of a die-bonding adhesive based on filling technology, so as to solve the technical problem that the prior art die-bonding adhesive production process parameter settings are insufficiently adaptable, resulting in poor packaging quality and filling effect, further affecting the overall performance and reliability of the product.

[0006] In view of the above problems, the present application provides a method and system for optimizing the performance of a die-bonding adhesive based on filling technology.

[0007] In a first aspect, the present application provides a method for optimizing the performance of a die-bonding adhesive based on a filling technology, and the method is implemented by a die-bonding adhesive performance optimization system based on a filling technology, wherein the method includes: determining performance optimization indicators guided by packaging quality and filling method, wherein the performance optimization indicators include a solid performance dimension based on scene adaptability and a fluid performance dimension based on dynamic curing quality; clustering and correlation evaluation of the performance optimization indicators based on the optimization type to determine optimization constraints; reading the die-bonding adhesive production process, performing traceability positioning based on the performance optimization indicators, and determining the optimization process points; determining the performance optimization type, and combining the optimization process points, performing hierarchical multi-objective optimization based on the finite element analysis principle in a performance optimization module to determine an initial optimization scheme; combining the optimization verification module, performing forward deduction evaluation and reverse deduction verification on the initial optimization scheme to determine the verification result, and the optimization verification module is obtained based on the information system training of the entire life cycle of the die-bonding adhesive; identifying the verification result, and determining the performance optimization scheme, and the performance optimization scheme includes optimization point-optimization direction-optimization step.

[0008] In the second aspect, the present application also provides a system for optimizing the performance of a die-bonding adhesive based on filling technology, which is used to execute the method for optimizing the performance of a die-bonding adhesive based on filling technology as described in the first aspect, wherein the system includes: an optimization index determination module, which is used to determine the performance optimization index based on packaging quality and filling method, wherein the performance optimization index includes a solid performance dimension based on scene adaptability and a fluid performance dimension based on dynamic curing quality; an optimization constraint determination module, which is used to cluster and evaluate the correlation of the performance optimization index based on the optimization type to determine the optimization constraint; a traceability positioning module, which is used to read the die-bonding adhesive production process and execute the basic The performance optimization index is traced and located to determine the optimization process point; a multi-objective optimization module is used to determine the performance optimization type, and in combination with the optimization process point, a hierarchical multi-objective optimization based on the finite element analysis principle is performed in the performance optimization module to determine the initial optimization plan; a deduction and verification module is used to perform forward deduction evaluation and reverse deduction verification on the initial optimization plan in combination with the optimization verification module to determine the verification result, and the optimization verification module is based on the information system training acquisition of the entire life cycle of the solid crystal glue; an optimization plan acquisition module is used to identify the verification result and determine the performance optimization plan, and the performance optimization plan includes optimization point-optimization direction-optimization step.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By taking packaging quality and filling method as the guide, performance optimization indicators are determined, wherein the performance optimization indicators include a solid performance dimension based on scenario adaptability and a fluid performance dimension based on dynamic curing quality; clustering and correlation evaluation are performed on the performance optimization indicators based on the optimization type to determine optimization constraints; the solid crystal glue production process is read, traceability positioning based on the performance optimization indicators is performed, and the optimization process points are determined; the performance optimization type is determined, and in combination with the optimization process points, hierarchical multi-objective optimization based on the finite element analysis principle is performed in the performance optimization module to determine the initial optimization plan; in combination with the optimization verification module, the initial optimization plan is forward deduced and evaluated and reversely deduced and verified to determine the verification result, and the optimization verification module is obtained based on the information system training of the entire life cycle of the solid crystal glue; the verification result is identified to determine the performance optimization plan, and the performance optimization plan includes optimization point-optimization direction-optimization step, which effectively solves the technical problem that the adaptation of the existing solid crystal glue production process parameter setting is insufficient, resulting in poor packaging quality and filling effect, and further affecting the overall performance and reliability of the product, improves the packaging quality and filling effect, and ensures that the overall performance and reliability of the product meet the expected standards.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 This is a flow chart of a method for optimizing the performance of a die-bonding adhesive based on a filling technology in this application;

[0014] Figure 2 This is a schematic diagram of the structure of the die-bonding adhesive performance optimization system based on the filling technology of this application.

[0015] Description of reference numerals:

[0016] Optimization index determination module 11, optimization constraint determination module 12, source tracing and positioning module 13, multi-objective optimization search module 14, deduction and verification module 15, optimization plan acquisition module 16. DETAILED DESCRIPTION

[0017] The present application provides a method and system for optimizing the performance of a die-bonding adhesive based on filling technology, thereby solving the technical problem that the prior art die-bonding adhesive production process parameter settings are insufficiently adaptable, resulting in poor packaging quality and filling effects, and further affecting the overall performance and reliability of the product. The application improves the packaging quality and filling effects, and ensures that the overall performance and reliability of the product meet the expected standards.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] Embodiment 1

[0020] Please refer to the attached Figure 1 The present application provides a method for optimizing the performance of a die-bonding adhesive based on a filling technology, wherein the method is applied to a die-bonding adhesive performance optimization system based on a filling technology, and the method specifically comprises the following steps:

[0021] S1: Determine performance optimization indicators guided by packaging quality and filling method, wherein the performance optimization indicators include solid performance dimensions based on scene adaptability and fluid performance dimensions based on dynamic solidification quality;

[0022] Specifically, solid performance dimensions include structural strength. The packaged product should have sufficient structural strength to cope with physical shock and vibration in different scenarios. Thermal stability. The packaged product should be able to maintain stable performance under different temperature environments. Including parameters such as the thermal expansion coefficient and thermal conductivity of the material. Scenario adaptability. The packaged product should be able to adapt to different usage scenarios, including harsh environments such as high temperature, low temperature, and high humidity. Performance stability under different environmental conditions such as temperature, humidity, and vibration. For example, thermal conductivity, electrical conductivity, etc., for performance and environmental tolerance characteristics in actual applications. Fluid performance dimensions include fluidity to ensure that it can be evenly filled to the required position during the packaging process. Curing speed. The filling material should be able to cure quickly after encapsulation. Performance after curing, such as hardness, strength, corrosion resistance, etc.

[0023] S2: performing clustering and correlation evaluation on the performance optimization indicators based on the optimization type to determine the optimization constraints;

[0024] Specifically, collect historical data related to each performance optimization indicator. Clean and standardize the data. K-means and hierarchical clustering can be used for clustering. The performance optimization indicators are used as clustering features for clustering analysis. Through the clustering results, identify the similarities and differences between the indicators. Classify similar indicators into one category. Use methods such as Pearson correlation coefficient and Spearman rank correlation coefficient to calculate the correlation between the various performance optimization indicators. Evaluate the linear relationship or rank correlation between the indicators. According to the size and positive and negative correlation coefficients, judge the degree and direction of association between the indicators. Identify highly correlated indicators, which may need special attention to their mutual influence during optimization. Based on the clustering results and correlation evaluation, identify groups of indicators that need to be optimized simultaneously or maintain a certain relationship. For highly correlated indicators, set their relative relationship or ratio during optimization to ensure the synergy of optimization. For different types of indicators in the clustering results, set their optimization priorities and weights.

[0025] S3: Read the die-bonding adhesive production process, perform traceability positioning based on the performance optimization index, and determine the optimized process point;

[0026] Specifically, the production process includes material preparation, mixing, filling, curing and other links. Identify the specific operations, equipment used, process parameters and factors that may affect product performance in each link. Compare performance optimization indicators such as scene adaptability, generalization ability, dynamic curing quality, durability and reliability with each link of the production process. Analyze the impact that each link may have on the performance optimization indicators. Through comparative analysis, locate the key process points that affect the performance optimization indicators. These key process points may be material selection, mixing ratio, filling method, curing temperature and time, etc. Based on traceability and positioning, determine the specific process points that need to be optimized. These optimized process points should be links that have a significant impact on the performance optimization indicators, and it is expected to achieve the purpose of performance improvement by adjusting process parameters or operating methods.

[0027] S4: Determine the performance optimization type, combine the optimization process points, perform hierarchical multi-objective optimization based on the finite element analysis principle in the performance optimization module, and determine the initial optimization plan;

[0028] Specifically, in the production process of bonding adhesive, the optimization types include improving the thermal conductivity of bonding adhesive, enhancing mechanical strength, improving curing speed, and improving weather resistance. Combine the optimization process point with the optimization type. In the performance optimization module, a hierarchical multi-objective optimization method is used to determine the initial optimization plan. The method can help balance multiple performance optimization indicators and find the best combination of process parameters. A multi-objective optimization model is established based on the performance optimization indicators and the optimization process points. The model should contain all performance indicators and corresponding process parameters to be optimized. Set an objective function for each performance indicator and define constraints. The objective function should reflect the optimization direction of the performance indicator, such as maximization or minimization, while the constraints ensure that the process parameters change within a feasible range. The performance of bonding adhesive is simulated and analyzed using the principle of finite element analysis. By changing the values ​​of process parameters and observing the change trend of performance indicators, the best combination of process parameters can be found. Since multiple performance indicators may conflict with each other, such as improving thermal conductivity may reduce mechanical strength, a hierarchical optimization method is used. First, optimize the most important performance indicator, and then gradually optimize other indicators on this basis until a solution that is relatively satisfactory in all indicators is found.

[0029] S5: Combined with the optimization verification module, the initial optimization scheme is evaluated by forward deduction and verified by reverse deduction to determine the verification result, wherein the optimization verification module is obtained based on the information system training of the entire life cycle of the die-bonding adhesive;

[0030] Specifically, the optimization and verification module is an intelligent system based on the training of the information system of the entire life cycle of the C-bonding adhesive. It uses a large amount of historical data through machine learning and data analysis technology to predict and verify the performance of the C-bonding adhesive. This module can simulate the performance of the C-bonding adhesive in actual applications and provide an evaluation of the optimization scheme. The process parameters in the initial optimization scheme are input into the optimization and verification module. The prediction algorithm and model in the module are used to predict the performance of the C-bonding adhesive under the initial optimization scheme. Including thermal conductivity, mechanical strength, curing speed and other aspects. According to the prediction results, evaluate whether the initial optimization scheme can achieve the expected performance improvement. According to the performance indicators in the initial optimization scheme, set the reverse deduction target. Using the optimization and verification module, starting from the target performance, reversely deduce the process parameters required to achieve these performances. Compare the process parameters obtained by reverse deduction with the parameters in the initial optimization scheme. If the two are consistent or similar, it means that the initial optimization scheme is reasonable and effective. Compare and analyze the results of the forward deduction evaluation and the reverse deduction verification. Check the consistency and difference between the two. If the results of both the forward derivation evaluation and the backward derivation verification indicate that the initial optimization plan is effective, then it can be determined that the plan is feasible. If there are large differences or inconsistencies, the initial optimization plan needs to be reviewed and adjusted.

[0031] S6: Identify the verification result and determine a performance optimization solution, wherein the performance optimization solution includes an optimization point, an optimization direction, and an optimization step.

[0032] Specifically, based on the verification results, the specific points that need to be optimized can be determined. These points are certain specific process parameters, such as temperature, time, material ratio, etc., which have a key impact on the performance of the final product. The optimization points should be those parameters that show large differences in the verification results or do not meet the expected performance indicators. For each optimization point, determine the direction of optimization. Decide whether to increase or decrease the value of a process parameter, or change a certain characteristic, such as changing the material type to achieve better performance. The optimization direction is obtained based on the comparative analysis of the verification results. Finally, set a reasonable optimization step for each optimization point. This includes determining the magnitude of each adjustment of the process parameters to ensure that the target performance can be steadily approached during the gradual optimization process. The setting of the optimization step should take into account the stability of the production process, the feasibility of adjustment, and potential risks.

[0033] Furthermore, step S2 of the present application also includes:

[0034] Identify the performance optimization index, and determine the modification index category and the strengthening index category;

[0035] Conduct compatibility analysis between the modified index and the original performance index, and determine the optimization avoidance principle based on performance priority and modification range;

[0036] Performing mutual influence analysis on the modification index class and the strengthening index class to determine a synergistic influence relationship, wherein the synergistic influence relationship includes multiple ones and is marked with an influence coefficient;

[0037] Based on the optimization avoidance principle and the coordinated influence relationship, the optimization constraint condition is determined.

[0038] Specifically, the performance optimization indicators include the thermal conductivity, mechanical strength, weather resistance, and curing speed of the solid crystal adhesive. The modified indicator category includes improvements or adjustments to the original performance of the product, such as changing the physical properties of the solid crystal adhesive, such as viscosity and hardness. The enhanced indicator category is to improve certain performance of the product, such as enhancing the bonding strength of the solid crystal adhesive and improving heat resistance. Analyze the compatibility between the modified indicators and the original performance indicators. It is found that certain modifications may have a negative impact on the original performance indicators. Determine which performance indicators are primary and which are secondary. Evaluate the possible range of changes in the modified indicators and their impact on the overall performance of the product. Based on the above analysis, the optimization avoidance principle can be determined, that is, in the modification process, the negative impact on the primary performance indicators should be avoided or minimized as much as possible. Analyze the mutual influence between the modified indicator category and the enhanced indicator category, and determine the synergistic effect between them. Synergistic influence relationship, identify which indicators' optimization will promote each other and which may restrict each other. Determine an influence coefficient for each synergistic influence relationship to quantify the degree of interaction between them. Based on the optimization avoidance principle and synergistic influence relationship, optimization constraints can be formulated. These conditions will guide subsequent process optimization work to ensure that while certain performance indicators are improved, other key indicators will not be unacceptably negatively impacted.

[0039] Furthermore, step S4 of the present application also includes:

[0040] Determining the type of performance optimization, which includes component optimization, structure optimization and process optimization;

[0041] Based on the performance optimization type, randomly determine a first preset number of first-layer optimization targets, and randomly determine a second preset number of second-layer optimization targets within the first-layer optimization targets, wherein the first preset number is a positive integer greater than or equal to 1 and less than or equal to 3, the second preset number is a positive integer greater than or equal to 1, and the second-layer optimization targets belong to the performance optimization index;

[0042] The first-layer optimization objective and the second-layer optimization objective are combined to determine a first optimization solution set.

[0043] Specifically, the types of performance optimization may include component optimization, structural optimization, and process optimization. Component optimization refers to the chemical composition of the solid crystal adhesive, and the performance is improved by adjusting the ratio of raw materials or using new materials. Structural optimization refers to designing the internal structure of the solid crystal adhesive to improve its mechanical and thermal properties. Process optimization refers to improving the production process, including parameters such as temperature, pressure, and time, to improve production efficiency and product quality. According to the performance optimization type, a first preset number of first-layer optimization targets are randomly selected. These first-layer optimization targets are macro optimization directions, such as improving thermal conductivity and enhancing mechanical strength. The first preset number may be a positive integer between 1 and 3. Within the selected first-layer optimization target, a second preset number of second-layer optimization targets are randomly determined. The second-layer optimization target is a specific executable optimization point, such as adjusting the proportion of a certain component, changing the parameters of a certain process flow, etc. The second preset number is a positive integer greater than or equal to 1, and its number should take into account the feasibility and cost-effectiveness of the experiment. The selected first-layer optimization target and the second-layer optimization target are combined to form a comprehensive set of optimization solutions. Orthogonal experimental design, response surface method, etc. can be used to find the best performance improvement solution. Through data analysis, the performance improvement effects of different optimization solutions are evaluated. Based on the evaluation results, the solution with the most significant performance improvement is selected as the first optimization solution set.

[0044] Furthermore, the present application also includes:

[0045] Traversing the first optimization solution set to determine a taboo column, wherein the taboo column is determined based on an optimization direction of an indicator with the highest frequency of occurrence;

[0046] The taboo column is locked, and iterative optimization is continued until the convergence condition is met, and the global optimal solution is selected as the initial optimization solution, wherein the taboo column is unlocked after satisfying a preset number of iterations.

[0047] Specifically, each scheme in the first optimization scheme set is evaluated, and the frequency of occurrence of each indicator optimization direction in each scheme is recorded. According to the indicator optimization direction with the highest frequency, one or more taboo columns are determined. Taboo columns refer to optimization directions that need to be avoided or restricted in the next iterative optimization. The setting of taboo columns is to prevent the algorithm from converging to the local optimal solution too early. By temporarily prohibiting certain frequently occurring optimization directions, the search process is prompted to explore other optimization spaces. In the next iterative optimization process, the taboo columns are locked, that is, no optimization attempts are made in these directions, or they are given a lower priority. After locking the taboo columns, the iterative optimization process continues. In each iteration, according to the current optimization scheme and performance indicator evaluation results, other optimization directions that are not locked are adjusted. In the iterative process, it is constantly checked whether the preset convergence conditions are met. The convergence conditions can be reaching the preset maximum number of iterations, the improvement of the performance indicator is less than a certain threshold, or the optimal solution that meets all constraints is found. When the convergence conditions are met, the iterative optimization is stopped. From the schemes generated in all iterative processes, the global optimal scheme with the best performance is selected as the initial optimization scheme. If the taboo column has met the preset number of iterations or reached a specific unlocking condition, it can be unlocked. The unlocked taboo column can be reconsidered in the subsequent optimization process.

[0048] Furthermore, the present application also includes:

[0049] The optimization verification module includes a forward deduction branch and a reverse deduction branch configured in parallel, and there is lateral interaction between the branches;

[0050] Identifying a bidirectional analysis target, wherein the bidirectional analysis target is an optimization solution-performance optimization standard;

[0051] Based on the bidirectional analysis target, the verification result is determined in combination with the forward deduction branch and the reverse deduction branch.

[0052] Specifically, the optimization verification module includes a forward derivation branch and a reverse derivation branch configured in parallel. The two branches can work independently, but there is also lateral interaction between the branches, so that information can flow and share between the two branches. The forward derivation branch predicts the performance of the die-bonding adhesive based on the known process parameters and optimization scheme. The prediction model trained by historical data and expert knowledge is used. The reverse derivation branch reversely infers the required process parameters and optimization scheme based on the set performance optimization standard. The optimization algorithm and reverse engineering methods are used to find the best process parameter combination that can achieve the expected performance. Information is shared and mutually verified through lateral interaction. For example, the prediction result of the forward derivation branch can be used as the input of the reverse derivation branch, and the optimization scheme obtained by the reverse derivation branch can be used by the forward derivation branch to verify its effectiveness. The bidirectional analysis target refers to the two directions considered simultaneously when performing optimization analysis, namely, the optimization scheme and the performance optimization standard. The optimization scheme is the improvement measure implemented, and the performance optimization standard is the performance indicator that is expected to be achieved. The performance of the proposed optimization scheme is predicted through the forward derivation branch to see whether it can achieve the expected performance optimization standard. Next, the backward deduction branch is used to derive the optimization solution that should be adopted in theory based on the performance optimization standard. Finally, the results of the forward deduction are compared and analyzed with the results of the backward deduction. If the two are consistent or similar, it means that the proposed optimization solution is feasible and has a high probability of achieving the expected performance improvement. If they are inconsistent, the optimization solution needs to be reviewed and adjusted.

[0053] Furthermore, step S6 of the present application also includes:

[0054] If the verification result meets the standard, the initial optimization plan is used as the performance optimization plan;

[0055] If the verification result does not meet the standard, identifying a first correction point based on a forward deduction chain and a second correction point based on a backward deduction chain;

[0056] Performing consistency comparison between the first calibration point and the second calibration point to determine scheme compensation data;

[0057] Based on the scheme compensation data, the initial optimization scheme is corrected to determine the performance optimization scheme.

[0058] Specifically, if the verification result is up to standard, it means that the initial optimization scheme can meet the performance optimization standard, so the initial optimization scheme is directly used as the performance optimization scheme. If the verification result is not up to standard, it means that the initial optimization scheme needs to be further adjusted. In the case of not meeting the standard, identify the first correction point in the forward deduction chain and the second correction point in the reverse deduction chain. These correction points refer to the key links that deviate or do not meet expectations during the deduction or deduction process. Compare the first correction point and the second correction point for consistency, and analyze the differences and commonalities between the two. Based on the comparison results, determine the data that needs to be compensated or adjusted. Including adjustments in process parameters, raw material ratios, production processes, etc. Use the scheme compensation data to correct the initial optimization scheme. Including adjusting the order, time, temperature and other parameters of certain process steps, or changing the ratio and type of raw materials. The corrected scheme will be used as the final performance optimization scheme. This scheme should be able to meet the previously set performance optimization standards and be feasible and stable in actual operation.

[0059] Furthermore, the present application also includes:

[0060] Determining a parameter control matrix based on the performance optimization solution;

[0061] Based on stability, the distribution of the expansion interval is determined, wherein the stability includes control stability and performance stability, wherein the expansion standard is optimal;

[0062] Based on the distribution of the external expansion intervals, the performance optimization scheme and the parameter control matrix are adjusted.

[0063] Specifically, the parameter control matrix is ​​a tool for describing and optimizing the relationship between various parameters in the production process. According to the key process parameters determined in the performance optimization plan, a matrix is ​​constructed in which the rows and columns represent different process parameters. The elements in the matrix can represent the correlation, degree of influence or optimization weight between the parameters. Stability includes control stability and performance stability. Control stability refers to the reliability of parameter control in the production process, that is, the parameter fluctuation range is small and the production process is easy to control. Performance stability refers to the consistency and reliability of product performance. Based on these two stabilities, the external expansion interval distribution of each parameter is determined, that is, the range in which the parameter can be adjusted. This range should be optimal, and adjusting the parameters within this range can improve or at least maintain the current stability. According to the range and limitations of the external expansion interval, the parameters in the performance optimization plan are adjusted, and at the same time, the parameter control matrix is ​​updated to reflect the impact of these adjustments on the relationship between the parameters.

[0064] In summary, the method for optimizing the performance of die-bonding adhesive based on filling technology provided in this application has the following technical effects:

[0065] By taking packaging quality and filling method as the guide, performance optimization indicators are determined, wherein the performance optimization indicators include a solid performance dimension based on scenario adaptability and a fluid performance dimension based on dynamic curing quality; clustering and correlation evaluation are performed on the performance optimization indicators based on the optimization type to determine optimization constraints; the solid crystal glue production process is read, traceability positioning based on the performance optimization indicators is performed, and the optimization process points are determined; the performance optimization type is determined, and in combination with the optimization process points, hierarchical multi-objective optimization based on the finite element analysis principle is performed in the performance optimization module to determine the initial optimization plan; in combination with the optimization verification module, the initial optimization plan is forward deduced and evaluated and reversely deduced and verified to determine the verification result, and the optimization verification module is obtained based on the information system training of the entire life cycle of the solid crystal glue; the verification result is identified to determine the performance optimization plan, and the performance optimization plan includes optimization point-optimization direction-optimization step, which effectively solves the technical problem that the adaptation of the existing solid crystal glue production process parameter setting is insufficient, resulting in poor packaging quality and filling effect, and further affecting the overall performance and reliability of the product, improves the packaging quality and filling effect, and ensures that the overall performance and reliability of the product meet the expected standards.

[0066] Embodiment 2

[0067] Based on the same inventive concept as the method for optimizing the performance of a die-bonding adhesive based on the filling technology in the aforementioned embodiment, the present application also provides a system for optimizing the performance of a die-bonding adhesive based on the filling technology. Figure 2 , the system comprising:

[0068] An optimization index determination module 11, the optimization index determination module 11 is used to determine the performance optimization index based on the packaging quality and the filling method, wherein the performance optimization index includes a solid performance dimension based on scene adaptability and a fluid performance dimension based on dynamic solidification quality;

[0069] An optimization constraint determination module 12, the optimization constraint determination module 12 is used to perform clustering and correlation evaluation on the performance optimization indicators based on the optimization type, and determine the optimization constraint conditions;

[0070] A traceability positioning module 13, which is used to read the production process of the die-bonding adhesive, perform traceability positioning based on the performance optimization index, and determine the optimized process point;

[0071] A multi-objective optimization module 14, which is used to determine the performance optimization type, and to perform hierarchical multi-objective optimization based on the finite element analysis principle in the performance optimization module in combination with the optimization process point, to determine an initial optimization solution;

[0072] A deduction and verification module 15, which is used to perform forward deduction evaluation and reverse deduction verification on the initial optimization scheme in combination with the optimization verification module to determine the verification result. The optimization verification module is based on the information system training acquisition of the entire life cycle of the die-bonding adhesive;

[0073] The optimization scheme acquisition module 16 is used to identify the verification result and determine the performance optimization scheme, and the performance optimization scheme includes optimization point-optimization direction-optimization step.

[0074] Furthermore, the optimization constraint condition determination module 12 in the system is also used for:

[0075] Identify the performance optimization index, and determine the modification index category and the strengthening index category;

[0076] Conduct compatibility analysis between the modified index and the original performance index, and determine the optimization avoidance principle based on performance priority and modification range;

[0077] Performing mutual influence analysis on the modification index class and the strengthening index class to determine a synergistic influence relationship, wherein the synergistic influence relationship includes multiple ones and is marked with an influence coefficient;

[0078] Based on the optimization avoidance principle and the coordinated influence relationship, the optimization constraint condition is determined.

[0079] Furthermore, the multi-objective optimization module 14 in the system is also used for:

[0080] Determining the type of performance optimization, which includes component optimization, structure optimization and process optimization;

[0081] Based on the performance optimization type, randomly determine a first preset number of first-layer optimization targets, and randomly determine a second preset number of second-layer optimization targets within the first-layer optimization targets, wherein the first preset number is a positive integer greater than or equal to 1 and less than or equal to 3, the second preset number is a positive integer greater than or equal to 1, and the second-layer optimization targets belong to the performance optimization index;

[0082] The first-layer optimization objective and the second-layer optimization objective are combined to determine a first optimization solution set.

[0083] Furthermore, the system further comprises a global optimal solution acquisition module, and the global optimal solution acquisition module is used to:

[0084] Traversing the first optimization solution set to determine a taboo column, wherein the taboo column is determined based on an optimization direction of an indicator with the highest frequency of occurrence;

[0085] The taboo column is locked, and iterative optimization is continued until the convergence condition is met, and the global optimal solution is selected as the initial optimization solution, wherein the taboo column is unlocked after satisfying a preset number of iterations.

[0086] Furthermore, the system further comprises a deduction branch module, wherein the deduction branch module is used for:

[0087] The optimization verification module includes a forward deduction branch and a reverse deduction branch configured in parallel, and there is lateral interaction between the branches;

[0088] Identifying a bidirectional analysis target, wherein the bidirectional analysis target is an optimization solution-performance optimization standard;

[0089] Based on the bidirectional analysis target, the verification result is determined in combination with the forward deduction branch and the reverse deduction branch.

[0090] Furthermore, the optimization solution acquisition module 16 in the system is also used for:

[0091] If the verification result meets the standard, the initial optimization plan is used as the performance optimization plan;

[0092] If the verification result does not meet the standard, identifying a first correction point based on a forward deduction chain and a second correction point based on a backward deduction chain;

[0093] Performing consistency comparison between the first calibration point and the second calibration point to determine scheme compensation data;

[0094] Based on the scheme compensation data, the initial optimization scheme is corrected to determine the performance optimization scheme.

[0095] Furthermore, the system further comprises a matrix adjustment module, wherein the matrix adjustment module is used for:

[0096] Determining a parameter control matrix based on the performance optimization solution;

[0097] Based on stability, the distribution of the expansion interval is determined, wherein the stability includes control stability and performance stability, wherein the expansion standard is optimal;

[0098] Based on the distribution of the external expansion intervals, the performance optimization scheme and the parameter control matrix are adjusted.

[0099] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1The method and specific examples for optimizing the performance of the solid crystal glue based on the filling technology in the first embodiment are also applicable to the system for optimizing the performance of the solid crystal glue based on the filling technology in the present embodiment. Through the above detailed description of the method for optimizing the performance of the solid crystal glue based on the filling technology, those skilled in the art can clearly know the system for optimizing the performance of the solid crystal glue based on the filling technology in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0100] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0101] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for optimizing the performance of a die-bonding adhesive based on a filling technology, characterized in that: The method comprises: Based on the packaging quality and filling method, performance optimization indicators are determined, wherein the performance optimization indicators include a solid performance dimension based on scene adaptability and a fluid performance dimension based on dynamic solidification quality; Performing clustering and correlation evaluation on the performance optimization indicators based on the optimization type to determine the optimization constraints; Read the die-bonding adhesive production process, perform traceability positioning based on the performance optimization index, and determine the optimized process point; Determine the performance optimization type, combine the optimization process points, perform hierarchical multi-objective optimization based on the finite element analysis principle in the performance optimization module, and determine the initial optimization plan; Combined with the optimization verification module, the initial optimization scheme is evaluated by forward deduction and verified by reverse deduction to determine the verification result. The optimization verification module is obtained through training based on the information system of the entire life cycle of the die-bonding adhesive; Identify the verification result and determine a performance optimization solution, wherein the performance optimization solution includes an optimization point, an optimization direction, and an optimization step.

2. The method according to claim 1, characterized in that The determining of the optimization constraint conditions comprises: Identify the performance optimization index, and determine the modification index category and the strengthening index category; Conduct compatibility analysis between the modified index and the original performance index, and determine the optimization avoidance principle based on performance priority and modification range; Performing mutual influence analysis on the modification index class and the strengthening index class to determine a synergistic influence relationship, wherein the synergistic influence relationship includes multiple ones and is marked with an influence coefficient; Based on the optimization avoidance principle and the coordinated influence relationship, the optimization constraint condition is determined.

3. The method according to claim 1, characterized in that The hierarchical multi-objective optimization based on the finite element analysis principle includes: Determining the type of performance optimization, which includes component optimization, structure optimization and process optimization; Based on the performance optimization type, randomly determine a first preset number of first-layer optimization targets, and randomly determine a second preset number of second-layer optimization targets within the first-layer optimization targets, wherein the first preset number is a positive integer greater than or equal to 1 and less than or equal to 3, the second preset number is a positive integer greater than or equal to 1, and the second-layer optimization targets belong to the performance optimization index; The first-layer optimization objective and the second-layer optimization objective are combined to determine a first optimization solution set.

4. The method according to claim 3, characterized in that Iteration criteria include superior replacement and inferior fallback, including: Traversing the first optimization solution set to determine a taboo column, wherein the taboo column is determined based on an optimization direction of an indicator with the highest frequency of occurrence; The taboo column is locked, and iterative optimization is continued until the convergence condition is met, and the global optimal solution is selected as the initial optimization solution, wherein the taboo column is unlocked after satisfying a preset number of iterations.

5. The method according to claim 1, characterized in that The optimization verification module includes a forward deduction branch and a reverse deduction branch configured in parallel, and there is lateral interaction between the branches; Identifying a bidirectional analysis target, wherein the bidirectional analysis target is an optimization solution-performance optimization standard; Based on the bidirectional analysis target, the verification result is determined in combination with the forward deduction branch and the reverse deduction branch.

6. The method according to claim 1, characterized in that Identify the verification result and determine a performance optimization solution, including: If the verification result meets the standard, the initial optimization plan is used as the performance optimization plan; If the verification result does not meet the standard, identifying a first correction point based on a forward deduction chain and a second correction point based on a backward deduction chain; Performing consistency comparison between the first calibration point and the second calibration point to determine scheme compensation data; Based on the scheme compensation data, the initial optimization scheme is corrected to determine the performance optimization scheme.

7. The method according to claim 1, characterized in that After the performance optimization scheme is determined, the following steps are included: Determining a parameter control matrix based on the performance optimization solution; Based on stability, the distribution of the expansion interval is determined, wherein the stability includes control stability and performance stability, wherein the expansion standard is optimal; Based on the distribution of the external expansion intervals, the performance optimization scheme and the parameter control matrix are adjusted.

8. The die-bonding adhesive performance optimization system based on filling technology is characterized by: For implementing the steps of the method according to any one of claims 1 to 7, the system comprises: An optimization index determination module, the optimization index determination module is used to determine the performance optimization index based on the packaging quality and the filling method, wherein the performance optimization index includes a solid performance dimension based on scene adaptability and a fluid performance dimension based on dynamic solidification quality; An optimization constraint determination module, the optimization constraint determination module is used to perform clustering and correlation evaluation on the performance optimization indicators based on the optimization type to determine the optimization constraint conditions; A traceability and positioning module, which is used to read the production process of the die-bonding adhesive, perform traceability and positioning based on the performance optimization index, and determine the optimized process point; A multi-objective optimization module, wherein the multi-objective optimization module is used to determine the performance optimization type, and in combination with the optimization process points, a hierarchical multi-objective optimization based on the finite element analysis principle is performed in the performance optimization module to determine an initial optimization plan; A deduction and verification module, which is used to perform forward deduction evaluation and reverse deduction verification on the initial optimization scheme in combination with the optimization verification module to determine the verification result. The optimization verification module is based on the information system training acquisition of the entire life cycle of the die-bonding adhesive; The optimization scheme acquisition module is used to identify the verification result and determine the performance optimization scheme, and the performance optimization scheme includes optimization point-optimization direction-optimization step.

Images