Intelligent bonding silver wire material judgment method and system based on big data

Abstract

The invention discloses an intelligent bonding silver wire material judgment method and system based on big data, and relates to the technical field of material judgment. A current characteristic curve is monitored in real time; analyzing and processing the current characteristic data to form a quantitative index set of the surface damage degree of the intelligent bonding silver wire; based on the quantitative indexes, combining standard test data of the same batch of intelligent bonding silver wires, and constructing a performance degradation model; on the basis of a performance degradation model, predicting performance degradation, damage and aging conditions of the intelligent bonding silver wire in a long-term use process, and calculating the service life of the intelligent bonding silver wire in an actual working environment; and generating a material quality evaluation report of the intelligent bonding silver wire, and giving a material judgment result of the intelligent bonding silver wire. According to the invention, through dynamic adjustment of test conditions, multi-dimensional feature extraction and environmental factor correction, the precision and adaptability of silver wire performance evaluation are improved, and the problem that damage and service life are difficult to accurately evaluate due to complex working conditions in the prior art is effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of material determination, and in particular to an intelligent bonding silver wire material determination method and system based on big data. Background Art

[0002] With the rapid development of microelectronics technology, semiconductor manufacturing and integrated circuit packaging technology, bonding wires, as core interconnect materials, play a vital role in the efficient operation and stability of electronic devices. Silver bonding wires have become an important choice to replace traditional gold and copper bonding wires due to their excellent conductivity, thermal stability and anti-oxidation properties.

[0003] However, when smart bonding silver wire is used for a long time in a complex working environment, it may be affected by factors such as oxidation, corrosion and stress fatigue, which may cause performance degradation and shortened life.

[0004] Existing bonding wire material evaluation technologies are mainly based on macroscopic physical measurement methods, such as tensile testing and optical microscopy analysis. Although these methods can reflect the surface state of bonding wires to a certain extent, they lack timeliness, accuracy and pertinence, and are particularly difficult to quantify and reflect the dynamic process of material microstructure degradation and performance decline. In addition, research on the laws of damage and aging during long-term use is not in-depth and cannot meet the needs of increasingly complex application scenarios.

[0005] In addition, existing research usually focuses on a single test condition and fails to effectively integrate diverse data from different batches or different environmental conditions, making it difficult to build a performance degradation model with high adaptability and reliability. These shortcomings restrict the scientificity and practicality of smart silver bonding wire quality assessment, and also indirectly affect the overall reliability and production efficiency of high-precision electronic packaging. Summary of the invention

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

[0007] Therefore, the problem to be solved by the present invention is how to identify the damage of the smart bonding silver wire during long-term use, evaluate its performance and predict its reliability.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, an embodiment of the present invention provides a method for determining the material of a smart bonding silver wire based on big data, which includes placing the smart bonding silver wire in an electrochemical testing device, applying current on the surface, monitoring the current characteristic curve in real time, and synchronously recording multi-channel data; analyzing and processing the current characteristic data, extracting key characteristic parameters in the electrochemical reaction, and forming a set of quantitative indicators for the degree of surface damage of the smart bonding silver wire; constructing a performance degradation model based on the quantitative indicators and combining the standard test data of the same batch of smart bonding silver wires; predicting the performance degradation, damage and aging of the smart bonding silver wire during long-term use based on the performance degradation model; generating a material quality assessment report for the smart bonding silver wire, and giving a material judgment result of the smart bonding silver wire.

[0009] As a preferred solution of the intelligent bonding silver wire material judgment method based on big data described in the present invention, the electrochemical testing process includes: dynamically adjusting the frequency of applied current according to the real-time changes in the surface state of the intelligent bonding silver wire by setting the automatic adjustment function of the electrochemical testing equipment.

[0010] As a preferred solution of the intelligent bonding silver wire material judgment method based on big data described in the present invention, wherein: the adjustment of the frequency of the current is performed by considering the surface potential change rate, and the frequency of the applied current is set to , which is proportional to the rate of change of surface potential, and the calculation formula is: ; in, is the rate of change of surface potential, is the proportionality coefficient.

[0011] As a preferred solution of the intelligent bonding silver wire material judgment method based on big data described in the present invention, wherein: the analysis and processing of the current characteristic data to extract the key characteristic parameters in the electrochemical reaction include the following: the key characteristic parameters include current peak value, corrosion resistance time and oxidation reaction rate; Kalman filtering is performed on the current signal to obtain a smoothed current signal; the current peak value in the current characteristic curve is extracted through a local extreme value detection algorithm; the corrosion resistance time is the time period during the electrochemical reaction when the current characteristic curve remains stable and has no significant corrosion. By detecting the relatively stable interval of current change, the duration of the stable interval is defined as the corrosion resistance time; the oxidation reaction rate is calculated by the slope of the current curve to reflect the rate change of the electrochemical reaction.

[0012] As a preferred solution of the intelligent bonding silver wire material judgment method based on big data described in the present invention, the calculation process of the corrosion resistance time is as follows: ; in, is the baseline value of the current, indicating the reference value of the stable period, For corrosion resistance time, is the smoothed current signal, is the threshold value of current change.

[0013] As a preferred solution of the intelligent bonding silver wire material judgment method based on big data described in the present invention, the construction of the performance degradation model includes: using a machine learning method to input quantitative indicators and standard test data into the model to predict the performance degradation trend of the intelligent bonding silver wire. The specific formula is as follows: ; in, For time The performance degradation prediction value at time is the total number of decision trees in the random forest, For the The weight of a decision tree, For the A decision tree based on The output value of It is a feature in the quantitative indicator set.

[0014] As a preferred solution of the material judgment method of the intelligent bonding silver wire based on big data described in the present invention, the prediction of the performance degradation, damage and aging of the intelligent bonding silver wire during long-term use includes the following steps: combining the performance degradation model, introducing environmental factors to correct the performance prediction results; based on the damage accumulation theory, calculating the cumulative damage value of the intelligent bonding silver wire.

[0015] In a second aspect, an embodiment of the present invention provides a smart bonding silver wire material judgment system based on big data, which includes: an electrochemical reaction monitoring module, which is used to place the smart bonding silver wire in an electrochemical testing device, apply current on the surface, monitor the current characteristic curve in real time, and perform multi-channel data synchronous recording; The data analysis and processing module is used to analyze and process the current characteristic data, extract the key characteristic parameters in the electrochemical reaction, and form a quantitative indicator set of the surface damage degree of the smart bonding silver wire; A performance model building module, used to build a performance degradation model based on the quantitative indicators and in combination with standard test data of the same batch of smart bonding silver wires; A performance evaluation module, used to predict the performance degradation, damage and aging of the smart bonding silver wire during long-term use based on the performance degradation model; The material evaluation report generation module is used to generate a material quality evaluation report for the smart bonding silver wire and provide the material judgment result of the smart bonding silver wire.

[0016] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the intelligent bonding silver wire material judgment method based on big data as described in the first aspect of the present invention are implemented.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the intelligent bonding silver wire material judgment method based on big data as described in the first aspect of the present invention are implemented.

[0018] The beneficial effects of the present invention are as follows: the present invention uses an electrochemical sensor to detect the oxide layer or corrosion signs on the surface of the silver wire in real time, and uses the surface potential change rate as the basis for dynamically adjusting the applied current frequency, thereby improving the efficiency and accuracy of the test; through quantitative indicators and standard test data of the same batch, a machine learning method is used to construct a performance degradation model, thereby realizing the prediction of the performance degradation trend of the silver wire, solving the limitations of the traditional linear prediction method when facing nonlinear data, and improving the prediction accuracy of the performance change of the silver wire. The present invention improves the accuracy and adaptability of the performance evaluation of the silver wire by dynamically adjusting the test conditions, extracting multidimensional features, and correcting environmental factors, effectively solving the problem in the prior art that it is difficult to accurately evaluate damage and life due to complex working conditions, and providing a generalizable technical framework for intelligent material evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] 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.

[0020] Figure 1 This is a flow chart of the intelligent bonding silver wire material judgment method based on big data.

[0021] Figure 2 This is the structural diagram of the intelligent bonding silver wire material judgment system based on big data. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and 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.

[0024] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0025] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0026] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0027] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0028] Example 1 Reference Figure 1~Figure 2 , which is the first embodiment of the present invention, and provides an intelligent bonding silver wire material judgment method based on big data, such as Figure 1 As shown, including, S1: Place the smart bonding silver wire in an electrochemical testing device, apply a small current on the surface, and monitor the current characteristic curve in real time.

[0029] S1.1: By setting the automatic adjustment function of the electrochemical test equipment, the frequency of the applied current is dynamically adjusted according to the real-time changes in the surface state of the smart bonding silver wire. First, the oxide layer or corrosion signs on the surface of the smart bonding silver wire are detected in real time by the electrochemical sensor. This information will serve as the basis for adjusting the current amplitude and frequency.

[0030] The frequency of the current can be adjusted by considering the rate of change of the surface potential to optimize the test efficiency and accuracy. The applied current frequency is set to , which is proportional to the rate of change of surface potential, and the calculation formula is: ; in, is the rate of change of surface potential, is the proportionality coefficient, which indicates the sensitivity of potential change to frequency adjustment.

[0031] S1.2: Use high-frequency sampling technology to obtain the current characteristic curve in real time and record multi-channel data synchronously.

[0032] For example, a high-frequency sampling rate (e.g., above 1 MHz) is used to capture the characteristic curve of current changing over time, ensuring that the subtle fluctuations of current generated during the electrochemical reaction process can be accurately captured.

[0033] Data is collected at multiple sensor locations simultaneously to ensure that the signal collection during the electrochemical reaction can cover the overall reaction of the smart silver bonding wire. For example, multiple electrochemical sensors can be set to measure the current signals at different locations to ensure that the data of each channel is recorded synchronously, and the current data of each channel is synchronized using timestamps.

[0034] S2: Analyze and process the current characteristic data, extract key characteristic parameters in the electrochemical reaction, such as current peak, corrosion resistance time, oxidation reaction rate, etc., and form a set of quantitative indicators for the degree of surface damage of the smart bonding silver wire.

[0035] Firstly, according to the current characteristic data collected in S1, the data is subjected to noise suppression through an adaptive filtering algorithm, that is, a Kalman filter is performed on the current signal to obtain a smoothed current signal, thereby removing the noise in the original data.

[0036] Based on the time-frequency domain analysis method, key parameters such as current peak value and corrosion resistance time are extracted from the current characteristic curve segment to generate preliminary damage indexes, including: The current peak value in the current characteristic curve is extracted through the local extreme value detection algorithm; The corrosion resistance time is defined as the period of time during the electrochemical reaction when the current characteristic curve remains stable and there is no significant corrosion. The duration of the stable interval is defined by detecting the relatively stable interval of current change. , That is, when the current fluctuation amplitude is less than the threshold Duration of time: ; in, is the baseline value of the current, indicating the reference value of the stable period, For corrosion resistance time, is the smoothed current signal, is the threshold value of current change.

[0037] The oxidation reaction rate is calculated by the slope of the current curve, reflecting the change in the rate of the electrochemical reaction. The oxidation reaction rate is related to the rate of change of the current and can be calculated by the following formula: ; in, is the rate of oxidation reaction, which reflects the intensity of surface oxidation reaction. is the rate of change of current.

[0038] The extracted current peak value, corrosion resistance time and oxidation reaction rate are used as quantitative indicators of damage degree, and the final set of damage degree indicators is generated.

[0039] S3: Based on the quantitative indicators obtained in step S2 and combined with the standard test data of the same batch of smart bonding silver wires, a performance degradation model is constructed.

[0040] It should be noted that the standard test data is taken from the long-term performance records of the same batch of samples in an experimental environment.

[0041] The performance degradation model uses machine learning methods (such as random forests or long short-term memory networks LSTM) to convert quantitative indicators The standard test data is input into the model to predict the performance degradation trend of the smart bonding silver wire. The specific formula is as follows: ; in, For time The performance degradation prediction value at time is the total number of decision trees in the random forest, For the The weight of a decision tree, For the A decision tree based on The output value of It is a feature in the quantitative indicator set.

[0042] Furthermore, the model parameters are adjusted through cross-validation to ensure the accuracy of the prediction results.

[0043] S4: Based on the performance degradation model, predict the performance degradation, damage and aging of the smart bonding silver wire during long-term use. The specific steps are as follows: First, combined with the performance degradation model, environmental factors are introduced to correct the performance prediction results. The formula is: ; in, The corrected time The performance degradation prediction value at time is the environmental factor sensitivity coefficient, The revised performance degradation prediction value is a weighted sum of the comprehensive environmental factor influence values, including temperature, current density and humidity, which can reflect the performance changes of smart bonding silver wire in actual environment.

[0044] It can be seen that by introducing environmental factors and sensitivity coefficients, the coupling of multiple factors such as temperature is effectively incorporated into the calculation, which enhances the robustness and adaptability of the model. The value can be modified dynamically This makes the prediction results more consistent with the actual situation. This design improves the performance evaluation accuracy of silver wire under different working conditions and lays a reliable foundation for subsequent life prediction.

[0045] Secondly, based on the damage accumulation theory, the cumulative damage value of the smart bonding silver wire is calculated using the formula: ; in, is the cumulative damage value, is the number of total load cases, For the Actual working time under working conditions; For the Theoretical fatigue life under working conditions.

[0046] It should be noted that the use of Miner damage theory to accurately calculate the cumulative damage under multiple working conditions solves the problem that material properties are difficult to quantify under complex load conditions. For example, under high temperature and high pressure conditions, the damage rate of silver wire may increase exponentially. The calculation effectively quantifies this change. In addition, the damage contribution of multiple working conditions is comprehensively considered to avoid dependence on a single working condition and improve the reliability of the predicted life.

[0047] Furthermore, based on the cumulative damage value and performance correction model, the service life of the silver wire is predicted as follows: ; in, To predict the service life of smart bonding silver wire, is the long-term aging coefficient, determined by experimental fitting; is the total forecast time interval.

[0048] It should be noted that the present invention can predict the aging speed and damage type of silver wire under different working environments and usage conditions, and further evaluate the service life and long-term reliability.

[0049] S5: Generate a material quality assessment report for the smart bonding silver wire and provide a material judgment result for the smart bonding silver wire.

[0050] Specifically, the key quantitative indicators (current peak value, corrosion resistance time, oxidation reaction rate) extracted from S2 are summarized to form a characteristic data table for each smart bonding silver wire; Integrate the prediction results of the performance degradation model constructed in S3, quantify the performance change trend of each silver wire during long-term use into a performance degradation curve, and apply the long-term use prediction results calculated in the performance degradation model to fit the performance change trend with the standard trend curve to determine whether its change rate is within the expected range.

[0051] The cumulative damage value is calculated by applying the damage accumulation theory, and combined with the long-term aging coefficient, the reliability of the silver wire is comprehensively evaluated, and the smart bonding silver wire is divided into the following quality categories: High quality (Class A): The cumulative damage value is less than 10%, the long-term performance degradation trend is stable, and the expected life span meets industry standards.

[0052] Available (Class B): The cumulative damage value is between 10% and 20%, and the performance degradation rate is slightly higher than the standard. It is recommended to be used in low-risk environments.

[0053] Poor quality (Class C): The cumulative damage value is higher than 20%, there is a significant risk of performance degradation, and it is not recommended for use in key components.

[0054] The quality category of each silver thread must be clearly marked in the evaluation report, and recommended application scenarios must be attached.

[0055] Furthermore, this embodiment also provides an intelligent bonding silver wire material judgment system based on big data, including: The electrochemical reaction monitoring module is used to place the smart bonding silver wire in the electrochemical testing equipment, apply current on the surface, monitor the current characteristic curve in real time, and perform multi-channel data synchronous recording; The data analysis and processing module is used to analyze and process the current characteristic data, extract the key characteristic parameters in the electrochemical reaction, and form a quantitative indicator set of the surface damage degree of the smart bonding silver wire; A performance model building module, used to build a performance degradation model based on the quantitative indicators and in combination with standard test data of the same batch of smart bonding silver wires; A performance evaluation module, used to predict the performance degradation, damage and aging of the smart bonding silver wire during long-term use based on the performance degradation model; The material evaluation report generation module is used to generate a material quality evaluation report for the smart bonding silver wire and provide the material judgment result of the smart bonding silver wire.

[0056] This embodiment also provides a computer device, which is suitable for the case of an intelligent bonding silver wire material judgment method based on big data, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the intelligent bonding silver wire material judgment method based on big data proposed in the above embodiment.

[0057] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, 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. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0058] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for intelligently determining the material of silver bonding wire based on big data as proposed in the above embodiment is implemented.

[0059] In summary, the present invention uses electrochemical sensors to detect the oxide layer or corrosion signs on the surface of the silver wire in real time, and uses the surface potential change rate as the basis for dynamically adjusting the applied current frequency, thereby improving the efficiency and accuracy of the test; through quantitative indicators and standard test data of the same batch, a machine learning method is used to construct a performance degradation model, which realizes the prediction of the performance degradation trend of the silver wire, solves the limitations of the traditional linear prediction method when facing nonlinear data, and improves the prediction accuracy of the performance change of the silver wire. The present invention improves the accuracy and adaptability of the performance evaluation of the silver wire by dynamically adjusting the test conditions, multi-dimensional feature extraction and environmental factor correction, effectively solving the problem in the prior art that it is difficult to accurately evaluate damage and life due to complex working conditions, and provides a generalizable technical framework for intelligent material evaluation.

[0060] Example 2 Referring to Table 1, which is the second embodiment of the present invention, this embodiment provides an intelligent bonding silver wire material judgment method based on big data. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0061] First, the selected smart bonding silver wire sample is placed in an electrochemical testing device. The functional settings of the electrochemical testing device include applying a small current and real-time monitoring of the current characteristic curve. By applying an electrochemical sensor to monitor the oxide layer or corrosion signs on the surface of the silver wire, data is acquired in real time and dynamic analysis is performed.

[0062] During the implementation process, the automatic adjustment function of the electrochemical test equipment is first enabled to adjust the frequency of the applied current according to the rate of change of the surface potential monitored in real time. The adjustment of the current frequency is based on the calculation of the rate of change of the surface potential. This dynamic adjustment helps to optimize the test efficiency and accuracy.

[0063] Next, high-frequency sampling technology (such as above 1 MHz) is used to obtain the current characteristic curve in real time to ensure that the subtle fluctuations of current during the electrochemical reaction can be accurately captured. Multiple sensors collect data at different locations at the same time to ensure the synchronous recording of data in each channel, and use timestamps to synchronize the current data of each channel.

[0064] After the current characteristic data is collected, an adaptive filtering algorithm (such as Kalman filtering) is used to remove noise and obtain a smoothed current signal. Then, key parameters such as current peak value, corrosion resistance time and oxidation reaction rate are extracted from the current characteristic curve segment through time-frequency domain analysis method to form a quantitative indicator set of damage degree.

[0065] Based on data processing, the performance degradation model is constructed and combined with standard test data to predict the performance degradation trend of smart silver bonding wire. The influence of environmental factors (such as temperature, humidity, etc.) is introduced into the model to further correct the performance prediction value to ensure its accuracy in the actual environment.

[0066] Finally, according to the damage accumulation theory, combined with the actual working time and theoretical fatigue life under different working conditions, the cumulative damage value of the silver wire is calculated to predict its service life. Based on these data, a quality assessment report for smart bonding silver wire is generated, the material judgment results are given, and its application in different scenarios is recommended. Some experimental data are as follows: Table 1 Experimental data table Smart bonding silver wire sample Current peak(mA) Corrosion resistance time (hours) Oxidation reaction rate (mA / s) Damage degree (index) Performance degradation prediction value (%) Cumulative damage value (%) Sample 1 12.5 80 0.05 8.2 5.3 8.0 Sample 2 13.0 75 0.04 7.5 6.0 9.0 Sample 3 12.8 85 0.06 8.0 4.8 7.5 Sample 4 11.9 72 0.03 6.5 6.3 9.2 Sample 5 14.1 90 0.05 9.0 5.2 7.0 Sample 6 13.5 88 0.04 8.1 5.5 8.5 Through the analysis of the above table data, it can be clearly seen that the intelligent bonding silver wire material judgment method based on big data adopted by the present invention has advantages in improving test accuracy and evaluating reliability. First of all, by real-time monitoring of the current characteristic curve and dynamically adjusting the current frequency, the present invention can optimize the test conditions under different silver wire states and accurately capture subtle changes in surface corrosion or oxidation. For example, the oxidation reaction rate of sample 3 is 0.06 mA / s, indicating that its oxidation reaction is relatively strong, and the corrosion resistance time is 85 hours, showing a longer stable period, and it is speculated that the material of the sample is relatively good.

[0067] Compared with traditional methods, the present invention significantly improves the acquisition accuracy of current signals through multi-channel synchronous data acquisition and high-frequency sampling technology. In terms of data processing, after denoising using the Kalman filter algorithm, key parameters (such as current peak value, oxidation reaction rate, etc.) can be accurately extracted. The quantitative extraction of these parameters effectively reflects the damage degree and corrosion state of the smart bonding silver wire.

[0068] By applying the performance degradation prediction model and combining it with the correction of environmental factors, the long-term service life of silver wire can be predicted more accurately. For example, the cumulative damage value of sample 4 is 9.2%, indicating that it is close to the critical value of performance degradation under a harsh working environment, while the damage value of sample 1 is lower, only 8.0%, and its service life is expected to be relatively long. Introducing the influence of environmental factors (such as humidity, temperature, etc.) further enhances the adaptability of the model and ensures the accuracy of performance prediction under different working conditions.

[0069] In general, the method of the present invention can not only monitor and analyze the electrochemical properties of the smart bonding silver wire in real time, but also build a more accurate life prediction model based on long-term performance data and environmental factors, thereby improving the accuracy and reliability of the smart bonding silver wire material judgment.

[0070] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. 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.

Claims

1. An intelligent bonding silver wire material judgment method based on big data, characterized by: include, The smart bonding silver wire is placed in an electrochemical testing device, current is applied to the surface, the current characteristic curve is monitored in real time, and multi-channel data is recorded synchronously; Analyze and process the current characteristic data, extract the key characteristic parameters in the electrochemical reaction, and form a quantitative index set of the surface damage degree of the smart bonding silver wire; Based on the quantitative indicators and combined with the standard test data of the same batch of smart bonding silver wires, a performance degradation model is constructed; Based on the performance degradation model, predict the performance degradation, damage and aging of the smart bonding silver wire during long-term use; Generate a material quality assessment report for the smart bonding silver wire and give the material judgment result of the smart bonding silver wire.

2. The intelligent bonding silver wire material determination method based on big data as claimed in claim 1 is characterized by: The electrochemical test process includes: By setting the automatic adjustment function of the electrochemical testing equipment, the frequency of the applied current is dynamically adjusted according to the real-time changes in the surface state of the smart bonding silver wire.

3. The intelligent bonding silver wire material determination method based on big data as claimed in claim 2, characterized in that: The frequency of the current is adjusted by taking into account the rate of change of the surface potential, and the frequency of the applied current is set to , which is proportional to the rate of change of surface potential, and the calculation formula is: ； in, is the rate of change of surface potential, is the proportionality coefficient.

4. The intelligent bonding silver wire material determination method based on big data as claimed in claim 3 is characterized by: The analysis and processing of the current characteristic data to extract the key characteristic parameters in the electrochemical reaction includes the following: The key characteristic parameters include current peak value, corrosion resistance time, and oxidation reaction rate; Perform Kalman filtering on the current signal to obtain a smoothed current signal; The current peak value in the current characteristic curve is extracted through the local extreme value detection algorithm; The corrosion resistance time is the time period during which the current characteristic curve remains stable and there is no significant corrosion during the electrochemical reaction. By detecting the relatively stable interval of current change, the duration of the stable interval is defined as the corrosion resistance time; The oxidation reaction rate is calculated by the slope of the current curve, reflecting the change in the rate of the electrochemical reaction.

5. The intelligent bonding silver wire material determination method based on big data as claimed in claim 4 is characterized by: The calculation process of the corrosion resistance time is as follows: ； in, is the baseline value of the current, indicating the reference value of the stable period, For corrosion resistance time, is the smoothed current signal, is the threshold value of current change.

6. The intelligent bonding silver wire material determination method based on big data as claimed in claim 5, characterized in that: The construction of the performance degradation model includes: The machine learning method is used to input quantitative indicators and standard test data into the model to predict the performance degradation trend of smart bonding silver wire. The specific formula is as follows: ； in, For time The performance degradation prediction value at time is the total number of decision trees in the random forest, For the The weight of a decision tree, For the A decision tree based on The output value of It is a feature in the quantitative indicator set.

7. The intelligent bonding silver wire material determination method based on big data as claimed in claim 6 is characterized by: The method for predicting the performance degradation, damage and aging of the smart silver bonding wire during long-term use includes the following steps: Combined with the performance degradation model, environmental factors are introduced to correct the performance prediction results; Based on the damage accumulation theory, the cumulative damage value of the smart bonding silver wire is calculated.

8. An intelligent bonding silver wire material judgment system based on big data, based on the intelligent bonding silver wire material judgment method based on big data according to any one of claims 1 to 7, characterized in that: Also includes, The electrochemical reaction monitoring module is used to place the smart bonding silver wire in the electrochemical testing equipment, apply current on the surface, monitor the current characteristic curve in real time, and perform multi-channel data synchronous recording; The data analysis and processing module is used to analyze and process the current characteristic data, extract the key characteristic parameters in the electrochemical reaction, and form a quantitative indicator set of the surface damage degree of the smart bonding silver wire; A performance model building module, used to build a performance degradation model based on the quantitative indicators and in combination with standard test data of the same batch of smart bonding silver wires; A performance evaluation module, used to predict the performance degradation, damage and aging of the smart bonding silver wire during long-term use based on the performance degradation model; The material evaluation report generation module is used to generate a material quality evaluation report for the smart bonding silver wire and provide the material judgment result of the smart bonding silver wire.

9. 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 intelligent bonding silver wire material judgment method based on big data described in any one of claims 1 to 7 are implemented.

10. 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 intelligent bonding silver wire material judgment method based on big data described in any one of claims 1 to 7 are implemented.

Images