Intelligent copper wire bonding data integration analysis method and system based on Internet of Things

Abstract

The invention relates to the technical field of data integration analysis, and provides an intelligent copper wire bonding data integration analysis method and system based on the Internet of Things, and the method comprises the steps: S1, collecting parameters of bonding copper wire equipment through a sensor, and obtaining original data; s2, selecting an RFID communication protocol as a gallery road for copper wire bonding data transmission; s3, preprocessing the original data to obtain preprocessed data; s4, merging the preprocessed data together and providing a unified view to obtain integrated data; s5, analyzing the integrated data by using grey correlation analysis, analyzing the relation between the copper wire bonding data, and describing the relation between the bonding copper wire data; and S6, calculating a bonding process capability index, judging whether the bonding process capability index is within a preset bonding quality standard range or not, if so, determining that the bonding process is stable, and otherwise, adjusting the process. And the comprehensive influence of the copper wire bonding data comprehensive evaluation factors on the bonding effect is analyzed by using the grey correlation, the grey correlation analysis result speed is high, and the working efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data integration and analysis, and in particular to an intelligent copper wire bonding data integration and analysis method based on the Internet of Things, and an intelligent copper wire bonding data integration and analysis system based on the Internet of Things. Background Art

[0002] The Internet of Things is an expansion and extension based on the PC Internet and mobile Internet. It collects information in real time through various sensor technologies and realizes the interconnection of all things through network connection technology. Copper wire bonding technology is an important technology in the field of electronic packaging. It is mainly used to connect the leads between the chip and the frame to realize the current and signal interaction between the chip and the outside world. Compared with traditional gold wire bonding, copper wire bonding has the advantages of low cost, excellent electrical and thermal conductivity, and high tensile strength. Copper wire bonding technology is gradually replacing gold wire bonding technology and becoming one of the mainstream technologies in the field of electronic packaging.

[0003] In existing data analysis, other data analysis methods may have higher requirements on data quality and quantity. The relationship between copper wire bonding data may be nonlinear. Existing analysis methods cannot accurately capture this nonlinear relationship, resulting in inaccurate analysis results. Grey correlation analysis not only considers the correlation between various factors, but also considers the comprehensive impact of various factors on the results, and can more comprehensively evaluate the degree of correlation between factors. Summary of the invention

[0004] The present invention provides an intelligent copper wire bonding data integration and analysis method and system based on the Internet of Things, so as to solve the defect of incomplete copper wire bonding data analysis in the prior art.

[0005] The present invention provides an intelligent copper wire bonding data integration and analysis method based on the Internet of Things, comprising: S1: Use sensors to collect parameters of the copper wire bonding equipment to obtain raw data, including welding energy, vibration frequency, pressure, temperature, and time; S2: Select RFID communication protocol as the channel for copper wire bonding data transmission; S3: preprocessing the original data to obtain preprocessed data, the preprocessing includes data standardization and data normalization; S4: Merge the preprocessed data together and provide a unified view to obtain integrated data; S5: Use grey correlation analysis to analyze the integrated data, analyze the relationship between copper wire bonding data, and describe the relationship between bonding copper wire data; S6: Calculate the bonding process capability index to determine whether it is within the preset bonding quality standard range. If so, the bonding process is stable, otherwise adjust the process.

[0006] The present invention provides an intelligent copper wire bonding data integration and analysis method based on the Internet of Things, comprising: The specific steps of data transmission are: S21: Select RFID as the communication protocol to transmit data according to the network environment and data security requirements; S22: Encrypt the original data using homomorphic encryption; S23: When the IoT system experiences signal interruption or bandwidth limitation, the RFID communication protocol is used to perform emergency caching of the original data.

[0007] The present invention provides an intelligent copper wire bonding data integration and analysis method based on the Internet of Things, comprising: The specific steps of data preprocessing are: S31: pre-processing the collected raw data to check whether there are errors or missing values ​​in the data. If so, the raw data is deleted or corrected, otherwise it remains unchanged; S32: Z-score standardization is used to convert the original data into a standard normal distribution with a mean of 0 and a standard deviation of 1.

[0008] The present invention provides an intelligent copper wire bonding data integration and analysis method based on the Internet of Things, comprising: The integrated data analysis includes: using grey correlation analysis to analyze the linear or nonlinear relationship between bonding pressure and displacement, temperature, time and bonding power parameters, and obtaining the linear relationship between bonding power and each bonding parameter.

[0009] The present invention provides an intelligent copper wire bonding data integration and analysis method based on the Internet of Things, comprising: The specific steps of using grey correlation analysis to analyze the relationship between parameters are as follows: S51: Convert integrated data into a matrix; S52: Set the optimal value in all integrated data matrices as the reference data column. The expression of the reference data column is: ; S53: The integrated data matrix is ​​dimensionless processed, and the dimensionless data sequence matrix is: ; Where m is the number of copper wire bonding data; S54: calculating the index sequence of each bonding copper wire parameter respectively, comparing the absolute value of the difference between the index sequence and the corresponding element of the reference sequence, and calculating the minimum secondary difference and the maximum secondary difference; S55: Calculate the absolute difference between the reference sequence and the comparison sequence to obtain the correlation coefficient between the elements corresponding to each comparison sequence and the reference sequence. The average value of the correlation coefficient is: ; Where, roi=(1,2,…,m)is the grey correlation degree of the mth copper wire bonding data; S56: The difference in the effect of each copper wire bonding data is eliminated by taking the weighted average of the correlation coefficient. The weighted average formula of the correlation coefficient is expressed as: ; Among them, W k is the weight of each indicator, k=1,2,…,m; S57: According to the correlation sequence of each evaluation object, the evaluation result is obtained after analysis.

[0010] The present invention provides an intelligent copper wire bonding data integration and analysis method based on the Internet of Things, comprising: The integrated data matrix formula is expressed as: ; Where m is the number of copper wire bonding data, ,i=1,2,…,n.

[0011] The present invention provides an intelligent copper wire bonding data integration and analysis method based on the Internet of Things, comprising: The minimum second-order difference formula is expressed as: ; In the formula, is the indicator sequence parameter and is the reference sequence parameter; The maximum secondary difference formula is expressed as: ; In the formula, is the indicator sequence parameter and are the reference sequence parameters.

[0012] The present invention provides an intelligent copper wire bonding data integration and analysis method based on the Internet of Things, comprising: The nonlinear relationship between bonding power and various bonding parameters is expressed as: ; Where P is the bonding power, F is the bonding pressure, A is the average vibration amplitude, and t is the welding time.

[0013] The present invention provides an intelligent copper wire bonding data integration and analysis method based on the Internet of Things, comprising: The calculation formula for the copper wire bonding ultrasonic bonding power is as follows: S521: Calculate the average vibration amplitude A, the formula is expressed as: ; Where E is the welding energy, f is the vibration frequency, and Fs is the transducer force; S522: Calculate the average value and standard deviation of the bonding pressure data using the historical bonding data to obtain the value of the current bonding pressure.

[0014] The present invention also provides an intelligent copper wire bonding data integration and analysis system based on the Internet of Things, comprising: Data acquisition module, used to collect parameters of copper wire bonding equipment; The data transmission module includes a communication protocol unit, a data encryption unit, and a data cache unit; the communication protocol unit is used to select RFID as the communication protocol to transmit data according to the network environment and data security requirements; the data encryption unit is used to encrypt the original data using homomorphic encryption; the data cache unit is used to cache and back up data when the signal is interrupted, and automatically retransmit the cached data when the network returns to normal; The data preprocessing module includes: a data correction unit and a data standardization unit; the data correction unit is used to correct errors and missing data in the original data; the data standardization unit is used to convert the original data into a standard normal distribution with a mean of 0 and a standard deviation of 1 by using Z-score standardization; A data integration module to merge pre-processed data together and provide a unified view; The data analysis module includes a linear analysis unit and a power data analysis unit. The linear analysis unit is used to use grey correlation to analyze the linear or nonlinear relationship between bonding pressure and displacement, temperature, time and bonding power parameters; the power data analysis unit is used to analyze the relationship between bonding power and various bonding parameters; The data evaluation module is used to calculate the bonding process capability index and determine whether it is within the preset bonding quality standard range. If so, the bonding process is stable, otherwise the process is adjusted.

[0015] The intelligent copper wire bonding data integration analysis method and system based on the Internet of Things provided by the present invention uses grey correlation analysis to comprehensively consider the influence of multiple influencing factors on the bonding quality of copper wire bonding data, and comprehensively evaluates the comprehensive influence of these factors on the bonding effect by calculating the correlation between each factor and the bonding quality, thereby avoiding the one-sidedness of single factor analysis. Grey correlation analysis has relatively low requirements for data and is suitable for situations with a small sample size. Grey correlation analysis can use limited data for effective analysis, extract key information, and provide strong support for decision-making. This intuitive numerical representation makes the analysis results easy to understand and interpret, which helps researchers and decision makers quickly grasp key factors and clarify optimization directions.

[0016] Grey correlation analysis not only provides the correlation between each factor and bonding quality, but also can rank and compare these correlations. This quantitative analysis method helps to determine which factors have a more significant impact on bonding quality, so as to prioritize improvements and optimizations. In addition, by comparing the changes in correlation under different conditions, the effects of improvement measures are also evaluated to provide data support for continuous optimization. The calculation process of grey correlation analysis is relatively simple and does not require complex mathematical models or advanced statistical software. This allows researchers to easily implement grey correlation analysis, quickly obtain analysis results, and improve work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 It is a flow chart of an intelligent copper wire bonding data integration and analysis method based on the Internet of Things provided by an embodiment of the present invention; Figure 2 It is a module diagram of an intelligent copper wire bonding data integration and analysis system based on the Internet of Things provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] like Figure 1 As shown, the intelligent copper wire bonding data integration and analysis method based on the Internet of Things provided by the embodiment of the present invention includes the following steps: S1: Use sensors to collect parameters of the copper wire bonding equipment to obtain raw data, which includes welding energy, vibration frequency, pressure, temperature, and time.

[0021] S11: Connect the sensors installed on the copper wire bonding equipment. Each interface is adapted to the communication protocol of different types of sensors, and the analog signal interface can accurately receive the raw data collected by the sensor.

[0022] S12: The sensor samples the copper wire bonding equipment 100-1000 times per second. Ultrasonic power and copper wire tensile force change rapidly. The ultrasonic frequency is usually between several thousand hertz and several hundred hertz. Ultrasonic power and copper wire tensile force fluctuate significantly in a short period of time. For some environmental temperature parameters that change slowly, the sampling frequency will be reduced.

[0023] S13: Connect the copper wire bonding equipment to the IoT system, manage the network configuration of the equipment and transmit the data to the central information system. Ensure that the equipment can be stable. At the same time, identify and authenticate the equipment, and assign a unique identifier to each connected device to facilitate data traceability and management.

[0024] S2: Select RFID communication protocol as the channel for copper wire bonding data transmission.

[0025] S21: Select RFID as the communication protocol to transmit data based on the network environment and data security requirements. RFID technology uses radio waves for non-contact two-way communication to automatically identify and read information from tags attached to bonding copper wires. Tags contain electronically stored information. When a tag enters the reader's effective recognition range, the reader sends a radio frequency signal through the antenna to activate the tag and read the information in it. This information is then transmitted to the central information system for data processing.

[0026] The RFID reader transmits a radio frequency signal of a specific frequency through the antenna. This signal is used to activate and identify the RFID tag that enters its effective range. When the RFID tag enters the effective identification range of the reader, the antenna of the RFID reader will receive the radio frequency signal transmitted by the reader. For passive RFID tags, the energy extracted from the radio frequency signal received by the reader is used to activate the internal circuit. Active RFID tags use their own power supply to work and do not need to obtain energy from the reader to activate. The activated tag will encode the information stored in it and reflect the encoded information back to the reader by changing the antenna reflection coefficient. After the reader receives the radio frequency signal reflected back by the tag, it will perform decoding processing to extract the information in the tag. The reader decodes the received signal and restores it to the original data format. The reader transmits the decoded data to the back-end application system through the interface. The application system executes the corresponding business logic based on the received tag information, and the RFID system triggers specific operations based on the processed data.

[0027] The data in the RFID tag is encrypted, access rights are strictly controlled, users are anonymized, and the RFID system is continuously updated and upgraded to ensure the security of data during transmission. Only authorized personnel can access the data to avoid leaking user privacy and to deal with potential security threats.

[0028] S22: To prevent data from being stolen or tampered with during transmission, the data is encrypted using homomorphic encryption.

[0029] Homomorphic encryption is an encryption method that performs specific calculations directly on encrypted data, ensuring that the decrypted result is equivalent to the same calculation performed on the original data. The homomorphic encrypted data is processed to obtain an output. After decrypting this output, the result is the same as the output obtained by processing the unencrypted original data in the same way, that is, the encrypted data is subjected to specific calculation operations like the original data without having to decrypt it first. Homomorphic encryption provides a function for processing encrypted data, so that others can process the encrypted data without revealing any of the original content. After the data processing is completed, it is decrypted and the result is exactly the result of the same processing on the original data.

[0030] Data is encrypted at the transport layer to ensure confidentiality and integrity. Identity authentication and access control are also required so that only authorized users or systems can receive and process data.

[0031] S23: When the IoT system is unstable, such as signal interruption or bandwidth limitation, the RFID communication protocol is used to cache the original data urgently. When the network returns to normal, the IoT system retransmits the cached data to ensure data integrity. The cache strategy is flexibly adjusted according to the data priority and storage space, for example, key device operation status data is cached first.

[0032] S3: Preprocess the collected data, including data standardization and data normalization.

[0033] S31: Preprocess the collected data to check whether there are errors or missing values ​​in the data. For obviously erroneous data, delete or correct them. For example, if the pressure value output by the pressure sensor is significantly higher than the maximum value that the device can withstand, it may be abnormal data caused by sensor failure, which needs to be deleted or corrected according to empirical values. For missing data, interpolation is performed according to the distribution law of the data and adjacent data points, such as linear interpolation, polynomial interpolation and other methods.

[0034] S32: Since the data collected by different sensors may have different units and orders of magnitude, in order to facilitate subsequent integration and analysis, the data needs to be standardized to eliminate the differences in attribute characteristics such as properties, dimensions, and orders of magnitude between different variables, and convert them into dimensionless standardized values ​​to ensure that the values ​​of each indicator are at the same order of magnitude, thereby facilitating comprehensive analysis and comparison between indicators.

[0035] Z-score standardization is used to convert the data into a standard normal distribution with a mean of 0 and a standard deviation of 1. The formula for Z-score standardization is expressed as: ; In the formula, Z is the standardized value, X is the original value, is the mean of the overall data, is the standard deviation of the overall data.

[0036] Data normalization maps the data to the interval [0,1] to eliminate the quantitative differences between different features and make the data comparable between different features. This eliminates the impact of data dimension and enables different types of data to be compared and analyzed on the same scale.

[0037] S4: Combine the preprocessed data into a common view and aggregate the data from heterogeneous data sources into a central location to obtain integrated data.

[0038] S41: Unify the data formats from different sensors and devices. Different sensors will output data in different formats, such as text format, binary format, and specific database format. These different formats of data need to be converted into a unified format, usually by organizing the data into a table in a relational database, defining a clear name, type, and length for each data field to facilitate data storage and query.

[0039] S42: Data of different dimensions are associated and fused according to key information such as timestamp and equipment number. For example, pressure data, temperature data and displacement data collected at the same time are associated together to construct a complete data record of the copper wire bonding process. At the same time, other related data are also bonded and fused, such as equipment maintenance records, operator information, etc. Through data fusion, bonding can have a more comprehensive understanding of the copper wire bonding process and provide richer information for subsequent analysis and decision-making.

[0040] Data integration unifies the bonded data standards and formats, eliminates the data island problem between different systems, and ensures the consistency and accuracy of data. Data integration merges and deduplicates data from different systems, eliminating data redundancy and duplication, which not only saves storage space, but also reduces the complexity and cost of data management. By eliminating redundant data, enterprises simplify data maintenance processes and improve overall efficiency.

[0041] S5: Analyze the integrated data to see if there is any relationship between the copper wire bonding data. Data analysis includes: using grey correlation to analyze the linear or nonlinear relationship between bonding pressure and displacement, temperature, time and bonding power parameters, and obtaining the linear relationship between bonding power and each bonding parameter.

[0042] S51: Convert the integrated data into a matrix: ; In the formula, m is the number of indicators, ,i=1,2,…,n.

[0043] S52: Set the optimal value in all integrated data matrices as the reference data column, denoted as , when two data columns are closer to each other, the higher the degree of correlation between them.

[0044] S53: The integrated data matrix is ​​dimensionally processed. Since each influencing factor in the evaluation object represents different things, the dimensions of the collected data are also different. The mean method and initialization method are used for dimensionless processing.

[0045] The mean transformation formula is: ; The initialization transformation formula is: ; In the formula, i=1,2,…,n;k=1,2,…,m.

[0046] The dimensionless data sequence matrix is: ; S54: Calculate the index sequence of each bonding copper wire parameter respectively, compare the absolute value of the difference between the sequence and the corresponding element of the reference sequence, and calculate the minimum secondary difference and the maximum secondary difference.

[0047] The minimum second-order difference formula is expressed as: ; In the formula, i=1,2,…,n;k=1,2,…,m, and the number of bonding wire parameters is n.

[0048] The maximum secondary difference formula is expressed as: ; In the formula, i=1,2,…,n;k=1,2,…,m, and the number of bonding wire parameters is n.

[0049] S55: Grey correlation coefficient is an important coefficient reflecting the correlation between the reference sequence and the comparison sequence. The absolute difference between the reference sequence and the comparison sequence is used to calculate the correlation coefficient between the elements corresponding to each comparison sequence and the reference sequence. The formula is: ; In the formula, is the correlation coefficient of the kth evaluation factor of the i-th evaluation unit, k=1,2,…,m, ρ∈(0,1) represents the resolution coefficient. The strength is determined by the value, usually ρ is 0.5 to ensure (0,1].

[0050] The correlation sequence reflects the correlation between each evaluation object and the reference sequence. By calculating the correlation coefficient corresponding to the comparison sequence and the reference sequence, the average value formula of the correlation coefficient is expressed as: ; In the formula, r oi =(1,2,…,m)is the grey relational degree of the mth evaluation parameter.

[0051] S56: The difference in the role played by each indicator is eliminated by taking the weighted average of the correlation coefficient. The formula of the weighted average of the correlation coefficient is expressed as: ; Among them, W k is the weight of each indicator, k=1,2,…,m.

[0052] S57: According to the correlation sequence of each evaluation object, the evaluation result is obtained after analysis.

[0053] The nonlinear relationship between bonding power and various bonding parameters is expressed as: ; Where P is the bonding power, F is the bonding pressure, A is the average vibration amplitude, and t is the welding time.

[0054] The calculation formula of the average vibration amplitude A is expressed as: ; Where E is the welding energy, f is the vibration frequency, and F s is the transducer force.

[0055] The mean and standard deviation of the copper wire bonding pressure parameters are calculated using historical bonding data. The mean μ reflects the average pressure of the bonding pressure data, and the standard deviation measures the dispersion of the bonding pressure data relative to the mean.

[0056] The formula for the mean is: ; In the formula, x i is each data point, and n is the total number of data points.

[0057] The expression formula of standard deviation σ is: ; By calculating the mean and standard deviation of the pressure data, the bonding process can be understood with respect to the average level and fluctuation of pressure, thereby determining the stability of the bonding process.

[0058] The current bonding pressure data is calculated using the mean and standard deviation obtained from historical copper wire bonding data: The formula for calculating the current bonding pressure using the cumulative distribution function is expressed as: ; Where erf is the error function, σ is the standard deviation of the bonding process, and μ is the mean.

[0059] There is a significant positive correlation between temperature and bonding strength, so in process control, the bonding temperature should be appropriately increased to improve the bonding strength; ; Wherein, T is temperature, A and B are arbitrary real numbers, and A>0.

[0060] S6: Evaluate whether the copper wire bonding process meets the quality requirements. By calculating the process capability index, the production capacity and quality stability of the bonding process are judged according to the pre-set bonding quality standards. If the process capability index is low, it means that there is a large variation in the bonding process and the process needs to be adjusted, such as optimizing equipment parameters and improving operating methods.

[0061] The process capability index includes the Cp index and the Cpk index. The Cp index measures the potential capability of the process, and the Cpk index measures the actual capability of the process, taking into account the degree of deviation between the center position of the process and the target value.

[0062] The formula of Cp index is: ; Where USL is the upper specification limit, LSL is the lower specification limit, and σ is the standard deviation of the bonding process.

[0063] The formula for the Cpk index is: ; Where μ is the mean of the bonding process, USL is the upper specification limit, LSL is the lower specification limit, and σ is the standard deviation of the bonding process.

[0064] like Figure 2 As shown, based on the same general inventive concept, the present invention also protects an intelligent copper wire bonding data integration and analysis system based on the Internet of Things, comprising: The data acquisition module is used to collect the parameters of the bonding copper wire equipment.

[0065] The data transmission module includes a communication protocol unit, a data encryption unit, and a data cache unit. The communication protocol unit is used to select RFID as a communication protocol to transmit data according to the network environment and data security requirements. The data encryption unit is used to encrypt the original data using homomorphic encryption. The data cache unit is used to cache and back up data when the signal is interrupted, and automatically retransmit the cached data when the network returns to normal.

[0066] The data preprocessing module includes: a data correction unit and a data standardization unit. The data correction unit is used to correct errors and missing data in the original data. The data standardization unit is used to convert the original data into a standard normal distribution with a mean of 0 and a standard deviation of 1 by using Z-score standardization.

[0067] A data integration module is used to merge the pre-processed data together and provide a unified view.

[0068] The data analysis module includes a linear analysis unit and a power data analysis unit. The linear analysis unit is used to use grey correlation to analyze the linear or nonlinear relationship between bonding pressure and displacement, temperature, time and bonding power parameters. The power data analysis unit is used to analyze the relationship between bonding power and various bonding parameters.

[0069] The data evaluation module is used to calculate the bonding process capability index and determine whether it is within the preset bonding quality standard range. If so, the bonding process is stable, otherwise the process is adjusted.

[0070] These modules together form a complete IoT system, ensuring interoperability between devices and effective data processing.

[0071] The intelligent copper wire bonding data integration analysis method and system based on the Internet of Things provided by the present invention uses grey correlation analysis to comprehensively consider the influence of multiple influencing factors on the bonding quality of copper wire bonding data, and comprehensively evaluates the comprehensive influence of these factors on the bonding effect by calculating the correlation between each factor and the bonding quality, thereby avoiding the one-sidedness of single factor analysis. Grey correlation analysis has relatively low requirements for data and is suitable for situations with a small sample size. Grey correlation analysis can use limited data for effective analysis, extract key information, and provide strong support for decision-making. This intuitive numerical representation makes the analysis results easy to understand and interpret, which helps researchers and decision makers quickly grasp key factors and clarify optimization directions.

[0072] Grey correlation analysis not only provides the correlation between each factor and bonding quality, but also can rank and compare these correlations. This quantitative analysis method helps to determine which factors have a more significant impact on bonding quality, so as to prioritize improvements and optimizations. In addition, by comparing the changes in correlation under different conditions, the effects of improvement measures are also evaluated to provide data support for continuous optimization. The calculation process of grey correlation analysis is relatively simple and does not require complex mathematical models or advanced statistical software. This allows researchers to easily implement grey correlation analysis, quickly obtain analysis results, and improve work efficiency.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments are still modified, or some of the technical features thereof are replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent copper wire bonding data integration and analysis method based on the Internet of Things, characterized in that: include: S1: using sensors to collect parameters of the copper wire bonding equipment to obtain raw data, wherein the raw data includes welding energy, vibration frequency, pressure, temperature, and time; S2: Select RFID communication protocol as the channel for copper wire bonding data transmission; S3: preprocessing the original data to obtain preprocessed data, wherein the preprocessing includes data standardization and data normalization; S4: merging the preprocessed data together and providing a unified view to obtain integrated data; S5: Analyze the integrated data using grey correlation analysis, analyze the relationship between the copper wire bonding data, and describe the relationship between the bonding copper wire data; S6: Calculate the bonding process capability index to determine whether it is within the preset bonding quality standard range. If so, the bonding process is stable, otherwise adjust the process.

2. The intelligent copper wire bonding data integration and analysis method based on the Internet of Things according to claim 1 is characterized in that: In step S2, the specific steps of data transmission are: S21: Select RFID as the communication protocol to transmit data according to the network environment and data security requirements; S22: Encrypting the original data using homomorphic encryption; S23: When the IoT system experiences signal interruption or bandwidth limitation, the original data is urgently cached using the RFID communication protocol.

3. The intelligent copper wire bonding data integration and analysis method based on the Internet of Things according to claim 1 is characterized in that: In step S3, the specific steps of data preprocessing are: S31: pre-processing the collected raw data to check whether there are errors or missing values ​​in the data, and if so, deleting or correcting the raw data, otherwise keeping it unchanged; S32: Convert the original data into a standard normal distribution with a mean of 0 and a standard deviation of 1 by using Z-score standardization.

4. The intelligent copper wire bonding data integration and analysis method based on the Internet of Things according to claim 1 is characterized in that: In step S5, the integrated data analysis includes: using grey correlation analysis to analyze the linear or nonlinear relationship between bonding pressure and displacement, temperature, time and bonding power parameters, and obtaining the linear relationship between bonding power and each bonding parameter.

5. The intelligent copper wire bonding data integration and analysis method based on the Internet of Things according to claim 4 is characterized in that: In step S5, the specific steps of using grey correlation analysis to analyze the relationship between parameters are as follows: S51: Convert integrated data into a matrix; S52: Set the optimal value in all integrated data matrices as the reference data column. The expression of the reference data column is: ; S53: The integrated data matrix is ​​dimensionless processed, and the dimensionless data sequence matrix is: ; In the formula, m is the number of copper wire bonding data; S54: calculating the index sequence of each bonding copper wire parameter respectively, comparing the absolute value of the difference between the index sequence and the corresponding element of the reference sequence, and calculating the minimum secondary difference and the maximum secondary difference; S55: Calculate the absolute difference between the reference sequence and the comparison sequence to obtain the correlation coefficient between the elements corresponding to each comparison sequence and the reference sequence, and the average value of the correlation coefficient is: ; In the formula, r oi = (1, 2, ..., m) is the grey correlation degree of the mth copper wire bonding data; S56: The difference in the effect of each copper wire bonding data is eliminated by taking the weighted average of the correlation coefficient. The weighted average formula of the correlation coefficient is expressed as: ; Among them, W k is the weight of each indicator, k=1,2,…,m; S57: According to the correlation sequence of each evaluation object, the evaluation result is obtained after analysis.

6. The method for integrated analysis of intelligent copper wire bonding data based on the Internet of Things according to claim 5, characterized in that: In step S51, the integrated data matrix formula is expressed as: ; Where m is the number of copper wire bonding data, ,i=1,2,…,n.

7. The method for integrated analysis of intelligent copper wire bonding data based on the Internet of Things according to claim 5, characterized in that: In step S54, the minimum secondary difference formula is expressed as: ; In the formula, is the indicator sequence parameter and is the reference sequence parameter, i=1,2,…,n; k=1,2,…,m, the number of bonding wire parameters is n; The maximum secondary difference formula is expressed as: ; In the formula, is the indicator sequence parameter and are reference sequence parameters, i=1,2,…,n; k=1,2,…,m, and the number of bonding wire parameters is n.

8. The method for integrated analysis of intelligent copper wire bonding data based on the Internet of Things according to claim 4, characterized in that: In step S5, the nonlinear relationship between the bonding power and each bonding parameter is expressed as: ; Where P is the bonding power, F is the bonding pressure, A is the average vibration amplitude, and t is the welding time.

9. The method for integrated analysis of intelligent copper wire bonding data based on the Internet of Things according to claim 8, characterized in that: In step S5, the average vibration amplitude and bonding pressure in the copper wire bonding ultrasonic bonding power calculation formula are calculated as follows: S521: Calculate the average vibration amplitude A, the formula is expressed as: ; Where E is the welding energy, f is the vibration frequency, and F s is the transducer force; S522: Calculate the average value and standard deviation of the bonding pressure data using the historical bonding data to obtain the value of the current bonding pressure.

10. An intelligent copper wire bonding data integration and analysis system based on the Internet of Things, applied to the intelligent copper wire bonding data integration and analysis method based on the Internet of Things as claimed in any one of claims 1 to 9, characterized in that: include: Data acquisition module, used to collect parameters of copper wire bonding equipment; The data transmission module includes a communication protocol unit, a data encryption unit, and a data cache unit; the communication protocol unit is used to select RFID as the communication protocol to transmit data according to the network environment and data security requirements; the data encryption unit is used to encrypt the data using homomorphic encryption; the data cache unit is used to cache and back up data when the signal is interrupted, and automatically retransmit the cached data when the network returns to normal; The data preprocessing module includes: a data correction unit and a data standardization unit; the data correction unit is used to correct errors and missing data in the original data; the data standardization unit is used to convert the original data into a standard normal distribution with a mean of 0 and a standard deviation of 1 by using Z-score standardization; A data integration module for merging the pre-processed data together and providing a unified view; The data analysis module includes a linear analysis unit and a power data analysis unit. The linear analysis unit is used to use grey correlation to analyze the linear or nonlinear relationship between bonding pressure and displacement, temperature, time and bonding power parameters; the power data analysis unit is used to analyze the relationship between bonding power and various bonding parameters; The data evaluation module is used to calculate the bonding process capability index and determine whether it is within the preset bonding quality standard range. If so, the bonding process is stable, otherwise the process is adjusted.

Images