An Internet of Things-supported intelligent monitoring method and system for the production status of bonded copper wires

Abstract

The present invention relates to the technical field of bonded copper wires, and discloses an Internet of Things-supported intelligent bonded copper wire production status monitoring method and system, including: evaluating the equipment operating conditions performance corresponding to the copper wire manufacturing equipment; querying the bonding process flow corresponding to the bonded copper wire, calculating the quality variability corresponding to the bonding process flow, evaluating the craftsmanship corresponding to the bonding process flow, and evaluating the process stability performance corresponding to the bonding process flow; performing physical and chemical tests on the bonded copper wire samples to obtain physical and chemical test data, and respectively calculating the sample yield strength and conductivity value corresponding to the bonded copper wire samples; analyzing the bonding performance of the bonded copper wire, and combining with a preset Internet of Things database, equipment operating conditions performance, process stability performance and sample bonding performance to generate a production status monitoring report of the bonded copper wire. The main purpose of the present invention is to solve the problem of low accuracy in monitoring the production status of bonded copper wires.

Description

Technical Field

[0001] The invention relates to an intelligent bonding copper wire production status monitoring method and system supported by the Internet of Things, belonging to the technical field of bonding copper wires. Background Art

[0002] Bonding copper wire plays an extremely critical role in the field of electronic equipment manufacturing. It is widely used in many key links such as semiconductor packaging and integrated circuits. Its quality and performance are directly related to the overall reliability and operation effect of electronic equipment. With the rapid development of the electronics industry, the quality requirements for bonding copper wire are becoming increasingly stringent, and the production scale is also expanding. In order to ensure the production quality of bonding copper wire, improve production efficiency and optimize the production process, it is urgently necessary to use advanced Internet of Things technology to intelligently monitor and accurately control its production status.

[0003] The existing production status monitoring of bonding copper wire mainly relies on traditional manual inspections and simple manual analysis after sensor data collection. This method has many disadvantages. Due to its reliance on manual operation and experience judgment, it is difficult to quickly and accurately identify subtle changes in production abnormalities when faced with complex and changeable production conditions. In addition, the data processing speed of manual analysis is slow, and real-time dynamic monitoring and instant feedback of the production process cannot be achieved, resulting in limited production efficiency. At the same time, differences in analysis levels among different staff members may lead to inaccurate judgments on the production status, which in turn affects the stability and consistency of product quality, thereby reducing the accuracy of bonding copper wire production status monitoring. Summary of the invention

[0004] The present invention provides an intelligent bonding copper wire production status monitoring method and system supported by the Internet of Things, the main purpose of which is to solve the problem of low accuracy in the bonding copper wire production status monitoring.

[0005] To achieve the above object, the present invention provides an Internet of Things-supported intelligent bonding copper wire production status monitoring method, comprising:

[0006] Obtaining a copper wire manufacturing device corresponding to the bonding copper wire, recording device operating condition data and device maintenance data corresponding to the copper wire manufacturing device, and evaluating device operating condition performance corresponding to the copper wire manufacturing device in combination with the device operating condition data and the device maintenance data;

[0007] Query the bonding process flow corresponding to the bonding copper wire, collect the raw material bonding monitoring image and the finished copper wire image of the bonding copper wire in the bonding process flow in real time, calculate the quality variability corresponding to the bonding process flow based on the raw material bonding monitoring image, evaluate the process sophistication corresponding to the bonding process flow based on the finished copper wire image, and evaluate the process stability performance corresponding to the bonding process flow in combination with the quality variability and the process sophistication;

[0008] During the bonding process flow, the bonded copper wire is sampled to obtain a bonded copper wire sample, and the bonded copper wire sample is subjected to physical and chemical tests to obtain physical and chemical test data. The physical and chemical test data includes sample force test data and sample electrical test data. Combining the sample force test data and the sample electrical test data, the sample yield strength and conductivity value corresponding to the bonded copper wire sample are calculated respectively;

[0009] Combining the conductivity value and the sample yield strength, the bonding performance of the bonded copper wire is analyzed. Combining the preset Internet of Things database, the equipment working condition performance, the process stability performance and the sample bonding performance, a production status monitoring report of the bonded copper wire is generated.

[0010] Optionally, the evaluating the equipment working condition performance corresponding to the copper wire manufacturing equipment by combining the equipment working condition data and the equipment maintenance data includes:

[0011] Identifying the data tags corresponding to the equipment working condition data to obtain equipment working condition tags;

[0012] Extracting the working condition characterization parameters from the equipment working condition data, and based on the equipment working condition tags, selecting the key characterization parameters from the working condition characterization parameters;

[0013] Calculating the equipment health degree corresponding to the copper wire manufacturing equipment according to the key characterization parameters and the equipment working condition tags;

[0014] Calculating the failure risk rate corresponding to the copper wire manufacturing equipment according to the equipment maintenance data;

[0015] Combining the equipment health degree and the failure risk rate, the equipment working condition performance corresponding to the copper wire manufacturing equipment is evaluated.

[0016] Optionally, the selecting the key characterization parameters from the working condition characterization parameters based on the equipment working condition tags includes:

[0017] Calculating the mean value of the characterization parameters corresponding to the working condition characterization parameters, and according to the mean value of the characterization parameters, calculating the characterization variance value corresponding to the working condition characterization parameters;

[0018] Analyzing the semantic meaning of the working condition tags corresponding to the equipment working condition tags, and based on the semantic meaning of the working condition tags, calculating the tag correlation degree between the equipment working condition tags;

[0019] Combining the characterization variance value and the tag correlation degree, selecting the key characterization parameters from the working condition characterization parameters.

[0020] Optionally, calculating the failure risk rate corresponding to the copper wire manufacturing equipment based on the equipment maintenance data includes:

[0021] Extracting the equipment maintenance frequency corresponding to the copper wire manufacturing equipment from the equipment maintenance data;

[0022] Counting the number of equipment units corresponding to the copper wire manufacturing equipment and querying the maintenance time span corresponding to the copper wire manufacturing equipment;

[0023] Combining the equipment maintenance frequency, the number of equipment units, and the maintenance time span, the failure risk rate corresponding to the copper wire manufacturing equipment can be calculated through the following formula:

[0024] ;

[0025] Where A represents the failure risk rate corresponding to the copper wire manufacturing equipment, B represents the equipment maintenance frequency, D represents the maintenance time span, and E represents the number of equipment units.

[0026] Optionally, calculating the quality variation degree corresponding to the bonding process based on the raw material bonding monitoring image includes:

[0027] Obtaining the process processing purpose corresponding to the bonding process and querying the bonding target quality corresponding to the process processing purpose;

[0028] Performing image denoising processing on the raw material bonding monitoring image to obtain a denoised bonding monitoring image;

[0029] Extracting the bonding color characterization attribute corresponding to the denoised bonding monitoring image and analyzing the actual bonding quality corresponding to the bonding color characterization attribute;

[0030] Calculating the quality difference value between the bonding target quality and the actual bonding quality;

[0031] Based on the quality difference value, obtaining the quality variation degree corresponding to the bonding process.

[0032] Optionally, evaluating the process sophistication corresponding to the bonding process based on the copper wire finished product image includes:

[0033] Scheduling the reference copper wire finished product image corresponding to the bonding process;

[0034] Extracting the finished product shape feature and the finished product texture feature in the copper wire finished product image;

[0035] Extracting the reference shape feature and the reference texture feature in the reference copper wire finished product image;

[0036] Combining the finished product morphological features and the reference morphological features, calculate the process defect index corresponding to the bonding process flow;

[0037] Combining the finished product texture features and the reference texture features, calculate the process deviation coefficient corresponding to the bonding process flow;

[0038] Combining the process defect index and the process deviation coefficient, evaluate the process sophistication corresponding to the bonding process flow.

[0039] Optionally, the combining the finished product morphological features and the reference morphological features, calculating the process defect index corresponding to the bonding process flow includes:

[0040] Perform vectorization processing on the finished product morphological features and the reference morphological features respectively to obtain a first morphological feature vector and a second morphological feature vector;

[0041] Combining the first morphological feature vector and the second morphological feature vector, calculate the feature deviation degree between the finished product morphological features and the reference morphological features;

[0042] According to the feature deviation degree, calculate the process defect index corresponding to the bonding process flow through the following formula:

[0043] ;

[0044] Wherein, G represents the process defect index corresponding to the bonding process flow, represents the feature deviation degree corresponding to the a-th feature in the finished product morphological features, a represents the feature serial number of the finished product morphological features, Q represents the number of features of the finished product morphological features, represents the maximum value in the feature deviation degrees.

[0045] Optionally, the combining the finished product texture features and the reference texture features, calculating the process deviation coefficient corresponding to the bonding process flow includes:

[0046] Calculate the texture entropy corresponding to the finished product texture features and the reference texture features respectively to obtain a first texture entropy and a second texture entropy;

[0047] Calculate the texture weighting factor corresponding to the finished product texture features;

[0048] Combining the texture weighting factor, the first texture entropy and the second texture entropy, the process deviation coefficient corresponding to the bonding process flow can be calculated through the following formula:

[0049] ;

[0050] Wherein, F represents the process deviation coefficient corresponding to the bonding process flow, The texture weighting factor representing the d-th feature in the finished product texture features, where d represents the serial number corresponding to the finished product texture features, and r represents the number of features corresponding to the finished product texture features. Represents the texture entropy corresponding to the d-th feature of the finished product texture features in the first texture entropy. Represents the texture entropy corresponding to the d-th feature of the reference texture features in the second texture entropy.

[0051] Optionally, combining the sample force measurement data and the sample electrical measurement data, and respectively calculating the sample yield strength and the conductivity value corresponding to the bonded copper wire sample, including:

[0052] Performing data calibration processing on the sample force measurement data and the sample electrical measurement data respectively to obtain calibrated force measurement data and calibrated electrical measurement data;

[0053] Measuring the sample length and the sample cross-sectional area corresponding to the bonded copper wire sample;

[0054] Reading the sample yield force value corresponding to the bonded copper wire sample in the calibrated force measurement data, and combining the sample yield force value and the sample cross-sectional area to calculate the sample yield strength corresponding to the bonded copper wire sample;

[0055] Determining the sample resistance value corresponding to the bonded copper wire sample from the calibrated electrical measurement data;

[0056] Combining the sample length, the sample cross-sectional area and the sample resistance value to calculate the conductivity value corresponding to the bonded copper wire sample.

[0057] An Internet of Things-supported intelligent bonded copper wire production status monitoring system, the system includes:

[0058] A working condition performance evaluation module, used to obtain the copper wire manufacturing equipment corresponding to the bonded copper wire, record the equipment working condition data and the equipment maintenance data corresponding to the copper wire manufacturing equipment, and combine the equipment working condition data and the equipment maintenance data to evaluate the equipment working condition performance corresponding to the copper wire manufacturing equipment;

[0059] A process performance evaluation module, used to query the bonding process flow corresponding to the bonded copper wire, collect in real time the raw material bonding monitoring images and the copper wire finished product images in the bonding process flow, calculate the quality variation degree corresponding to the bonding process flow based on the raw material bonding monitoring images, evaluate the process sophistication degree corresponding to the bonding process flow based on the copper wire finished product images, and combine the quality variation degree and the process sophistication degree to evaluate the process stability performance corresponding to the bonding process flow;

[0060] A parameter calculation module is used to sample the bonded copper wire during the bonding process flow to obtain a bonded copper wire sample, perform physical and chemical tests on the bonded copper wire sample to obtain physical and chemical test data, where the physical and chemical test data includes sample force measurement data and sample electrical measurement data, and combine the sample force measurement data and the sample electrical measurement data to calculate the sample yield strength and conductivity value corresponding to the bonded copper wire sample respectively;

[0061] A report production module is used to analyze the bonding performance of the bonded copper wire by combining the conductivity value and the sample yield strength, and generate a production status monitoring report of the bonded copper wire by combining a preset Internet of Things database, the equipment operating conditions performance, the process stability performance, and the sample bonding performance.

[0062] Compared with the problems in the background art, the present invention evaluates the equipment operating conditions performance corresponding to the copper wire manufacturing equipment by combining the equipment operating condition data and the equipment maintenance data, can understand the overall performance of the equipment corresponding to the copper wire manufacturing equipment, and further obtains the equipment status monitoring result of the bonded copper wire. The present invention calculates the quality variation degree corresponding to the bonding process flow based on the raw material bonding monitoring image, can understand the fluctuation degree of the processing quality of the raw material of the bonded copper wire in the processing process, and further provides a basis for the evaluation of the process stability performance corresponding to the subsequent bonding process flow. The present invention combines the sample force measurement data and the sample electrical measurement data to calculate the sample yield strength and conductivity value corresponding to the bonded copper wire sample respectively, can understand the characteristic performance of the bonded copper wire in terms of mechanics and electricity, and provides a basis for the analysis of the sample bonding performance of the subsequent bonded copper wire sample. The present invention analyzes the bonding performance of the bonded copper wire by combining the conductivity value and the sample yield strength, can comprehensively analyze the comprehensive performance of the bonded copper wire sample in the processing process, combines a preset Internet of Things database, the equipment operating conditions performance, the process stability performance, and the bonding performance, generates a production status monitoring report of the bonded copper wire, and further obtains a more accurate production status monitoring result of the bonded copper wire. Therefore, the present invention proposes an Internet of Things-supported intelligent bonded copper wire production status monitoring method and system to improve the accuracy of the bonded copper wire production status monitoring. Brief Description of the Drawings

[0063] Figure 1 It is a schematic flow chart of an Internet of Things-supported intelligent bonded copper wire production status monitoring method provided by an embodiment of the present invention;

[0064] Figure 2 It is a functional module diagram of an Internet of Things-supported intelligent bonded copper wire production status monitoring system provided by an embodiment of the present invention.

[0065] The implementation, functional features, and advantages of the present invention will be further described in conjunction with embodiments with reference to the accompanying drawings. Specific Embodiments

[0066] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0067] The embodiments of the present application provide a method for monitoring the production status of Internet of Things-supported intelligent bonding copper wires. The execution subjects of the method for monitoring the production status of Internet of Things-supported intelligent bonding copper wires include, but are not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiments of the present application. In other words, the method for monitoring the production status of Internet of Things-supported intelligent bonding copper wires can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc. Embodiment 1:

[0068] Refer to Figure 1 As shown, it is a flowchart of the method for monitoring the production status of Internet of Things-supported intelligent bonding copper wires provided by an embodiment of the present invention. In this embodiment, the method for monitoring the production status of Internet of Things-supported intelligent bonding copper wires includes:

[0069] S1. Obtain the copper wire manufacturing equipment corresponding to the bonding copper wire, record the equipment working condition data and equipment maintenance data corresponding to the copper wire manufacturing equipment, and combine the equipment working condition data and the equipment production capacity data to evaluate the equipment working condition performance corresponding to the copper wire manufacturing equipment.

[0070] By combining the equipment working condition data and the equipment maintenance data of the present invention to evaluate the equipment working condition performance corresponding to the copper wire manufacturing equipment, the overall performance of the equipment corresponding to the copper wire manufacturing equipment can be understood, and then the equipment status monitoring result of the bonding copper wire can be obtained. It should be explained that the bonding copper wire is a key material used in electronic devices to achieve functions such as electrical connection, the copper wire manufacturing equipment is a professional production device for producing the bonding copper wire, the equipment working condition data is various parameter information reflecting the working state of the copper wire manufacturing equipment during operation, the equipment maintenance data is relevant records and parameters involved in the maintenance and repair of the copper wire manufacturing equipment, and the equipment working condition performance is the comprehensive performance of the copper wire manufacturing equipment. Exemplarily, the recording of the equipment working condition data and equipment maintenance data corresponding to the copper wire manufacturing equipment can be realized through the recording system in the equipment.

[0071] Specifically, the combining the equipment working condition data and the equipment maintenance data to evaluate the equipment working condition performance corresponding to the copper wire manufacturing equipment includes:

[0072] Identify the data tags corresponding to the device condition data to obtain device condition tags;

[0073] Extract the condition characterization parameters from the device condition data, and based on the device condition tags, select the key characterization parameters from the condition characterization parameters;

[0074] Calculate the device health degree corresponding to the copper wire manufacturing device according to the key characterization parameters and the device condition tags;

[0075] Calculate the failure risk rate corresponding to the copper wire manufacturing device according to the device maintenance data;

[0076] Combine the device health degree and the failure risk rate to evaluate the device condition performance corresponding to the copper wire manufacturing device.

[0077] It should be explained that the data tags are category information corresponding to the device condition data for classifying and identifying different operating states of the device, the condition characterization parameters are relevant parameters in the device condition data that can reflect the operating characteristics and conditions of the device, the key characterization parameters are the core parameters in the condition characterization parameters that play a key role in judging the overall condition of the device, the device health degree represents a quantitative index of the overall operating goodness and performance state corresponding to the copper wire manufacturing device, and the failure risk rate represents a quantitative measurement value of the probability of failure of the copper wire manufacturing device within a certain period.

[0078] Furthermore, the identification of the data tags corresponding to the device condition data can be achieved through a tag identification tool, and the tag identification tool is compiled by the JAVA language; the extraction of the condition characterization parameters in the device condition data can be achieved through the principal component analysis method; the key characterization parameters are normalized according to the corresponding standard characterization parameters to obtain normalized parameters. Assuming that the normal range of the bonding temperature in the standard characterization parameters is 200 - 250 degrees Celsius and the current measured value is 230 degrees Celsius, then the normalized parameter is (230 - 200) / (250 - 200) = 0.6, and the tag weight corresponding to the device condition tags is calculated. The tag weight and the corresponding normalized parameter are multiplied and summed to obtain the device health degree corresponding to the copper wire manufacturing device; combine the device health degree and the failure risk rate to evaluate the device condition performance corresponding to the copper wire manufacturing device. If the device health degree is 0.8 and the failure risk rate is 0.2, generally speaking, the device condition performance is excellent.

[0079] Furthermore, as an optional embodiment of the present invention, the selection of the key characterization parameters from the condition characterization parameters based on the device condition tags includes:

[0080] Calculate the mean value of the characterization parameters corresponding to the working condition characterization parameters, and calculate the characterization variance value corresponding to the working condition characterization parameters according to the mean value of the characterization parameters;

[0081] Analyze the semantics of the working condition labels corresponding to the equipment working conditions, and calculate the label correlation degree between the equipment working condition labels based on the semantics of the working condition labels;

[0082] Combine the characterization variance value and the label correlation degree to select the key characterization parameters in the working condition characterization parameters.

[0083] It should be explained that the mean value of the characterization parameters is the average value of all data corresponding to the working condition characterization parameters, which is used to reflect the average level of the parameters; the characterization variance value represents the degree of data dispersion corresponding to the working condition characterization parameters and reflects the fluctuation of the parameters; the semantics of the working condition labels is the actual meaning contained in the literal expression corresponding to the equipment working condition labels; the label correlation degree is a quantitative index representing the semantic similarity degree between the equipment working condition labels.

[0084] Exemplarily, the mean value of the characterization parameters corresponding to the working condition characterization parameters can be calculated through an average function; the characterization variance value corresponding to the working condition characterization parameters can be calculated through a variance function; the semantics of the working condition labels corresponding to the equipment working condition labels can be analyzed through a semantic analysis method; calculate the semantic similarity degree between the semantics of the working condition labels, and use the semantic similarity degree as the label correlation degree between the equipment working condition labels; calculate the sum value of the characterization variance value and the label correlation degree corresponding to the working condition characterization parameters, and select the key characterization parameters in the working condition characterization parameters according to the size of the sum value.

[0085] Further, as an optional embodiment of the present invention, the calculation of the failure risk rate corresponding to the copper wire manufacturing equipment according to the equipment maintenance data includes:

[0086] Extract the equipment maintenance frequency corresponding to the copper wire manufacturing equipment from the equipment maintenance data;

[0087] Count the number of equipment corresponding to the copper wire manufacturing equipment, and query the maintenance time span corresponding to the copper wire manufacturing equipment;

[0088] Combined with the equipment maintenance frequency, the number of equipment and the maintenance time span, the failure risk rate corresponding to the copper wire manufacturing equipment can be calculated through the following formula:

[0089] ;

[0090] Wherein, A represents the failure risk rate corresponding to the copper wire manufacturing equipment, B represents the equipment maintenance frequency, D represents the maintenance time span, and E represents the number of equipment.

[0091] It should be explained that the equipment maintenance frequency is the number of repairs corresponding to the copper wire manufacturing equipment, and the maintenance time span is a span description of the equipment failure data in the time dimension. For example, in years, if it is one month, D is 1 / 12, and if it is one quarter, D is 1 / 4.

[0092] S2. Query the bonding process flow corresponding to the bonded copper wire, and collect in real time the raw material bonding monitoring images and copper wire finished product images of the bonded copper wire in the bonding process flow. Based on the raw material bonding monitoring images, calculate the quality variation degree corresponding to the bonding process flow. Based on the copper wire finished product images, evaluate the craftsmanship degree corresponding to the bonding process flow. Combine the quality variation degree and the craftsmanship degree to evaluate the process stability performance corresponding to the bonding process flow.

[0093] In the present invention, by calculating the quality variation degree corresponding to the bonding process flow based on the raw material bonding monitoring images, it is possible to understand the fluctuation degree of the processing quality of the raw materials of the bonded copper wire in the bonding process flow, thereby providing a basis for the subsequent evaluation of the process stability performance corresponding to the bonding process flow. It should be explained that the bonding process flow is the processing process corresponding to the bonded copper wire, the raw material bonding monitoring images are the images of the raw material processing process of the bonded copper wire in the bonding process flow, the copper wire finished product images are the formed products in each process obtained by processing the bonded copper wire in the bonding process flow, and the quality variation degree represents a description of the quality fluctuation of the raw material processing corresponding to each process in the bonding process flow. Exemplarily, the bonding process flow corresponding to the bonded copper wire can be obtained by querying from the manufacturer; the collection of the raw material bonding monitoring images and copper wire finished product images of the bonded copper wire in the bonding process flow can be achieved by an industrial camera.

[0094] Specifically, calculating the quality variation degree corresponding to the bonding process flow based on the raw material bonding monitoring images includes:

[0095] Obtain the process processing purpose corresponding to the bonding process flow, and query the bonding target quality corresponding to the process processing purpose;

[0096] Perform image denoising processing on the raw material bonding monitoring images to obtain denoised bonding monitoring images;

[0097] Extract the bonding color characterization attributes corresponding to the denoised bonding monitoring images, and analyze the actual bonding quality corresponding to the bonding color characterization attributes;

[0098] Calculate the quality difference value between the bonding target quality and the actual bonding quality;

[0099] Based on the quality difference value, the quality variability corresponding to the bonding process flow is obtained.

[0100] It should be explained that the purpose of the process processing is the task direction to be achieved corresponding to the bonding process flow, the bonding target quality is the quality standard expected to be achieved corresponding to the purpose of the process processing, the denoised bonding monitoring image is an image that is more conducive to analysis obtained after removing noise interference from the raw material bonding monitoring image, the bonding color characterization attribute is a property description reflecting the color-related characteristics of the bonding area corresponding to the denoised bonding monitoring image, the actual bonding quality is the bonding effect quality level reflected based on the actual presentation situation corresponding to the bonding color characterization attribute, and the quality difference value is a quantitative difference reflecting the deviation degree between the bonding target quality and the actual bonding quality.

[0101] Furthermore, the acquisition of the purpose of the process processing corresponding to the bonding process flow can be achieved by consulting relevant process documents; the query of the bonding target quality corresponding to the purpose of the process processing can be achieved by referring to industry quality standard specifications; the image denoising process of the raw material bonding monitoring image can be achieved by applying a median filtering algorithm; the extraction of the bonding color characterization attribute corresponding to the denoised bonding monitoring image can be achieved by spectral analysis technology; the analysis of the actual bonding quality corresponding to the bonding color characterization attribute can be achieved by combining material science knowledge and comparing with standard samples; the quality difference value can be obtained by calculating the difference between the bonding target quality and the actual bonding quality; the quality difference value is converted into a percentage form to obtain the quality variability corresponding to the bonding process flow.

[0102] In the present invention, by evaluating the craftsmanship corresponding to the bonding process flow based on the copper wire finished product image, the execution precision of each link in the bonding process flow can be understood, and further, the evaluation stability of the process stability performance corresponding to the subsequent bonding process flow can be improved. It should be explained that the craftsmanship represents the execution precision of each link in the bonding process flow.

[0103] Specifically, the evaluation of the craftsmanship corresponding to the bonding process flow based on the copper wire finished product image includes:

[0104] Dispatch the reference copper wire finished product image corresponding to the bonding process flow;

[0105] Extract the finished product shape features and finished product texture features in the copper wire finished product image;

[0106] Extract the reference shape features and reference texture features in the reference copper wire finished product image;

[0107] Calculate the process defect index corresponding to the bonding process by combining the finished product morphological features and the reference morphological features;

[0108] Calculate the process deviation coefficient corresponding to the bonding process by combining the finished product texture features and the reference texture features;

[0109] Evaluate the process proficiency corresponding to the bonding process by combining the process defect index and the process deviation coefficient.

[0110] It should be explained that the reference copper wire finished product image is the standard reference image corresponding to the bonding process for measuring the quality of the actual production results. The finished product morphological features and the finished product texture features are respectively the attribute descriptions reflecting the characteristics of the actually produced copper wire finished product in terms of shape, appearance, and surface texture in the copper wire finished product image. The reference morphological features and the reference texture features are respectively the attribute descriptions of the shape, appearance, and surface texture characteristics that the copper wire finished product should possess in the ideal state in the reference copper wire finished product image. The process defect index represents the degree of process defects reflected by the differences in morphology and other aspects between the actual and the ideal state corresponding to the bonding process. The process deviation coefficient represents the degree of process deviation reflected by the deviation of the actual texture features from the ideal texture features corresponding to the bonding process.

[0111] Exemplarily, the reference copper wire finished product image corresponding to the bonding process can be retrieved from the standard image database established within the enterprise or the archived qualified product image data. The finished product morphological features and the finished product texture features in the copper wire finished product image can be extracted by applying image analysis algorithms, such as geometric feature extraction algorithms based on shape recognition and texture analysis algorithms such as gray-level co-occurrence matrix, in combination with computer vision technology. The extraction principles of the reference morphological features and the reference texture features are the same as those of the finished product morphological features and the finished product texture features, and will not be elaborated here. Evaluate the process proficiency corresponding to the bonding process by combining the process defect index and the process deviation coefficient. If the process defect index is relatively high, it indicates that there are significant deviations between the finished product and the reference in terms of morphology, such as irregular bonding point shapes and abnormal copper wire bending. At the same time, if the process deviation coefficient is also large, it means that the texture features deviate significantly from the standard, such as poor texture uniformity and abnormal directionality. Considering both, it can be determined that the process proficiency of this bonding process is relatively low.

[0112] Furthermore, as an optional embodiment of the present invention, the step of calculating the process defect index corresponding to the bonding process by combining the finished product morphological features and the reference morphological features includes:

[0113] Perform vectorization processing on the finished product morphological features and the reference morphological features respectively to obtain a first morphological feature vector and a second morphological feature vector;

[0114] Combine the first morphological feature vector and the second morphological feature vector to calculate the feature deviation degree between the finished product morphological features and the reference morphological features;

[0115] According to the feature deviation degree, calculate the process defect index corresponding to the bonding process flow through the following formula:

[0116] ;

[0117] where G represents the process defect index corresponding to the bonding process flow, represents the feature deviation degree corresponding to the a-th feature in the finished product morphological features, a represents the feature serial number of the finished product morphological features, Q represents the number of features of the finished product morphological features, represents the maximum value in the feature deviation degrees.

[0118] It should be explained that the first morphological feature vector and the second morphological feature vector are respectively the vector expression forms corresponding to the finished product morphological features and the reference morphological features, and the feature deviation degree represents the degree of difference between the finished product morphological features and the reference morphological features. Exemplarily, the vectorization processing of the finished product morphological features and the reference morphological features can be realized through an encoding algorithm; calculate the similarity between the first morphological feature vector and the second morphological feature vector, and 1 - similarity gives the feature deviation degree between the finished product morphological features and the reference morphological features.

[0119] Further, as an optional embodiment of the present invention, the combining the finished product texture features and the reference texture features to calculate the process deviation coefficient corresponding to the bonding process flow includes:

[0120] Calculate the texture entropies corresponding to the finished product texture features and the reference texture features respectively to obtain a first texture entropy and a second texture entropy;

[0121] Calculate the texture weighting factor corresponding to the finished product texture features;

[0122] Combine the texture weighting factor, the first texture entropy and the second texture entropy, and calculate the process deviation coefficient corresponding to the bonding process flow through the following formula:

[0123] ;

[0124] where F represents the process deviation coefficient corresponding to the bonding process flow, The texture weighting factor representing the d-th feature in the finished product texture features, where d represents the serial number corresponding to the finished product texture features, and r represents the number of features corresponding to the finished product texture features. The texture entropy corresponding to the d-th feature of the finished product texture features in the first texture entropy. The texture entropy corresponding to the d-th feature of the reference texture features in the second texture entropy.

[0125] It should be explained that the first texture entropy and the second texture entropy respectively represent the quantization indexes reflecting the texture complexity corresponding to the finished product texture features and the reference texture features. The texture weighting factor represents the quantization coefficient corresponding to the finished product texture features based on its importance degree in aspects such as the overall process or quality. Exemplarily, the calculation of the texture entropy corresponding to the finished product texture features and the reference texture features can be achieved by extracting energy feature parameters based on the gray-level co-occurrence matrix and then calculating the energy feature parameters using the Shannon entropy formula; the calculation of the texture weighting factor corresponding to the finished product texture features can be determined by analyzing the influence degree of the texture features on the key performance indexes of the bonding process (such as strength, conductivity, etc.).

[0126] By combining the quality variability and the process fineness, the present invention can evaluate the process stability performance corresponding to the bonding process flow, obtain the production performance monitoring of the bonding process flow, and improve the accuracy of the stability analysis of the bonding process flow. It should be explained that the process stability performance is a description of the stability corresponding to the bonding process flow. Exemplarily, if both the quality variability and the process fineness are high, it indicates that the process stability performance corresponding to the bonding process flow is poor.

[0127] S3. Sampling the bonding copper wire in the bonding process flow to obtain a bonding copper wire sample, performing physical and chemical tests on the bonding copper wire sample to obtain physical and chemical test data. The physical and chemical test data includes sample force test data and sample electrical test data. Combining the sample force test data and the sample electrical test data, respectively calculate the sample yield strength and conductivity value corresponding to the bonding copper wire sample.

[0128] By combining the sample force measurement data and the sample electrical measurement data, the sample yield strength and the conductivity performance value corresponding to the bonded copper wire sample are calculated respectively, so as to understand the mechanical and electrical characteristics of the bonded copper wire, providing a basis for the subsequent analysis of the sample bonding performance of the bonded copper wire sample. It should be explained that the bonded copper wire sample is a physical sample obtained after the actual processing operation of the bonded copper wire in the bonding process flow for subsequent performance testing. The sample force measurement data and the sample electrical measurement data are data obtained from the physical and chemical test data regarding the bonded copper wire sample through mechanical testing and electrical testing respectively, which can reflect its force-bearing and conductivity-related characteristics. The sample yield strength and the conductivity performance value respectively represent the strength index at which the bonded copper wire sample starts to produce plastic deformation when subjected to an external force and the performance index of the current conduction ability. Exemplarily, the physical and chemical testing of the bonded copper wire sample can be realized by a universal material testing machine and an impedance analyzer.

[0129] Specifically, the combination of the sample force measurement data and the sample electrical measurement data to calculate the sample yield strength and the conductivity performance value corresponding to the bonded copper wire sample respectively includes:

[0130] Perform data calibration processing on the sample force measurement data and the sample electrical measurement data respectively to obtain calibrated force measurement data and calibrated electrical measurement data;

[0131] Measure the sample length and sample cross-sectional area corresponding to the bonded copper wire sample;

[0132] Read the sample yield force value corresponding to the bonded copper wire sample from the calibrated force measurement data, and combine the sample yield force value and the sample cross-sectional area to calculate the sample yield strength corresponding to the bonded copper wire sample;

[0133] Determine the sample resistance value corresponding to the bonded copper wire sample from the calibrated electrical measurement data;

[0134] Combine the sample length, the sample cross-sectional area and the sample resistance value to calculate the conductivity performance value corresponding to the bonded copper wire sample.

[0135] It should be explained that the calibrated force measurement data and the calibrated electrical measurement data are respectively the data obtained after calibration operations such as correcting deviations and removing errors from the sample force measurement data and the sample electrical measurement data. The sample yield force value is the value of the force borne by the bonded copper wire sample corresponding to the calibrated force measurement data when the material begins to exhibit obvious plastic deformation. Exemplarily, the data calibration processing of the sample force measurement data and the sample electrical measurement data can be achieved by the mean substitution method, using the average value to replace the error data; the measurement of the sample length and sample cross-sectional area corresponding to the bonded copper wire sample can be achieved by measuring tools such as vernier calipers and laser diameter gauges.

[0136] Further, as an optional embodiment of the present invention, calculating the conductivity value corresponding to the bonded copper wire sample by combining the sample length, the sample cross-sectional area, and the sample resistance value includes:

[0137] Combining the sample length, the sample cross-sectional area, and the sample resistance value, calculating the conductivity value corresponding to the bonded copper wire sample through the following formula:

[0138] ;

[0139] wherein, N represents the conductivity value corresponding to the bonded copper wire sample, P represents the sample length, R represents the sample resistance value, and S represents the sample cross-sectional area.

[0140] S4. Analyze the bonding performance of the bonded copper wire by combining the conductivity value and the sample yield strength, and generate a production status monitoring report for the bonded copper wire by combining a preset Internet of Things database, the equipment operating conditions, the process stability performance, and the bonding performance.

[0141] By combining the conductivity value and the sample yield strength, the bonding performance of the bonded copper wire is analyzed, and the comprehensive performance of the bonded copper wire sample during the processing can be comprehensively analyzed. By combining the preset Internet of Things database, the equipment working condition performance, the process stability performance, and the bonding performance, a production status monitoring report of the bonded copper wire is generated, and then a more accurate production status monitoring result of the bonded copper wire is obtained. It should be noted that the bonding performance is the comprehensive performance of the bonded copper wire during the bonding production process. The preset Internet of Things database is a data storage and management system specifically designed and configured for Internet of Things applications, used to collect, store, manage, and analyze various data generated by Internet of Things devices and related business processes. Exemplarily, by combining the conductivity value and the sample yield strength, the bonding performance of the bonded copper wire is analyzed. If the conductivity value is high and the sample yield strength meets the standard, it indicates that the resistance at the bonding point is small, which is beneficial to current conduction, and at the same time, it can withstand a certain mechanical stress, then the bonding performance is good; conversely, if the conductivity value is low and the sample yield strength is insufficient, the bonding performance is low. By combining the preset Internet of Things database, the equipment working condition performance, the process stability performance, and the sample bonding performance, a production status monitoring report of the bonded copper wire is generated. The equipment working condition performance, the process stability performance, and the sample bonding performance are compared with the data recorded in the preset Internet of Things database to obtain an evaluation report corresponding to the equipment working condition performance, the process stability performance, and the sample bonding performance. The evaluation reports are summarized to obtain the production status monitoring report of the bonded copper wire.

[0142] Compared with the problems described in the background art, the present invention combines the equipment operating conditions data and the equipment maintenance data to evaluate the equipment operating conditions performance corresponding to the copper wire manufacturing equipment, so as to understand the overall performance of the equipment corresponding to the copper wire manufacturing equipment, and further obtain the equipment status monitoring results of the bonded copper wire. The present invention calculates the quality variation degree corresponding to the bonding process flow based on the raw material bonding monitoring image, so as to understand the fluctuation degree of the processing quality of the raw materials of the bonded copper wire in the processing process, and further provides a basis for the evaluation of the process stability performance corresponding to the subsequent bonding process flow. The present invention combines the sample force measurement data and the sample electrical measurement data to calculate the sample yield strength and the conductivity value corresponding to the bonded copper wire sample respectively, so as to understand the characteristic performance of the bonded copper wire in terms of mechanics and electricity, and provides a basis for the analysis of the sample bonding performance of the subsequent bonded copper wire sample. The present invention analyzes the bonding performance of the bonded copper wire by combining the conductivity value and the sample yield strength, and can comprehensively analyze the comprehensive performance of the bonded copper wire sample in the processing process. Combining the preset Internet of Things database, the equipment operating conditions performance, the process stability performance and the bonding performance, a production status monitoring report of the bonded copper wire is generated, and further a more accurate production status monitoring result of the bonded copper wire is obtained. Therefore, the present invention proposes an Internet of Things-supported intelligent bonded copper wire production status monitoring method to improve the accuracy of the bonded copper wire production status monitoring. Embodiment 2:

[0143] As Figure 2 shown, it is a functional module diagram of an Internet of Things-supported intelligent bonded copper wire production status monitoring system provided by an embodiment of the present invention.

[0144] The Internet of Things-supported intelligent bonded copper wire production status monitoring system 100 of the present invention can be installed in an electronic device. According to the functions achieved, the Internet of Things-supported intelligent bonded copper wire production status monitoring system 100 can include an operating conditions performance evaluation module 101, a process performance evaluation module 102, a parameter calculation module 103, and a report production module 104. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and are stored in the memory of the electronic device.

[0145] In this embodiment, the functions of each module / unit are as follows:

[0146] The operating conditions performance evaluation module 101 is used to obtain the copper wire manufacturing equipment corresponding to the bonded copper wire, record the equipment operating conditions data and the equipment maintenance data corresponding to the copper wire manufacturing equipment, and combine the equipment operating conditions data and the equipment maintenance data to evaluate the equipment operating conditions performance corresponding to the copper wire manufacturing equipment;

[0147] The process performance evaluation module 102 is used to query the bonding process flow corresponding to the bonded copper wire, collect in real time the raw material bonding monitoring images and copper wire finished product images of the bonded copper wire in the bonding process flow, calculate the quality variation degree corresponding to the bonding process flow based on the raw material bonding monitoring images, evaluate the craftsmanship degree corresponding to the bonding process flow based on the copper wire finished product images, and evaluate the process stability performance corresponding to the bonding process flow by combining the quality variation degree and the craftsmanship degree;

[0148] The parameter calculation module 103 is used to take samples of the bonded copper wire in the bonding process flow to obtain a bonded copper wire sample, perform physical and chemical tests on the bonded copper wire sample to obtain physical and chemical test data, where the physical and chemical test data includes sample force measurement data and sample electrical measurement data, and calculate the sample yield strength and conductivity value corresponding to the bonded copper wire sample by combining the sample force measurement data and the sample electrical measurement data;

[0149] The report production module 104 is used to analyze the bonding performance of the bonded copper wire by combining the conductivity value and the sample yield strength, and generate a production status monitoring report of the bonded copper wire by combining a preset Internet of Things database, the equipment operating conditions, the process stability performance, and the sample bonding performance.

[0150] Specifically, each module in the intelligent bonded copper wire production status monitoring system 100 supported by the Internet of Things described in the embodiments of the present application adopts the same technical means as those in the above Figure 1 a kind of intelligent bonded copper wire production status monitoring method supported by the Internet of Things described, and can produce the same technical effects, which will not be elaborated here.

[0151] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0152] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for monitoring the production status of intelligent bonding copper wire supported by the Internet of Things, characterized in that: The method comprises: Obtaining a copper wire manufacturing device corresponding to the bonding copper wire, recording device operating condition data and device maintenance data corresponding to the copper wire manufacturing device, and evaluating device operating condition performance corresponding to the copper wire manufacturing device in combination with the device operating condition data and the device maintenance data; Query the bonding process flow corresponding to the bonding copper wire, collect the raw material bonding monitoring image and the finished copper wire image of the bonding copper wire in the bonding process flow in real time, calculate the quality variability corresponding to the bonding process flow based on the raw material bonding monitoring image, wherein the quality variability represents the description of the quality fluctuation of the raw material processing corresponding to each process in the bonding process flow, and evaluate the process sophistication corresponding to the bonding process flow based on the finished copper wire image, wherein the process sophistication represents the execution accuracy of each link in the bonding process flow, and evaluate the process stability performance corresponding to the bonding process flow in combination with the quality variability and the process sophistication; In the bonding process, the bonding copper wire is sampled to obtain a bonding copper wire sample, and the bonding copper wire sample is subjected to physical and chemical tests to obtain physical and chemical test data, wherein the physical and chemical test data includes sample force measurement data and sample electrical measurement data, and the sample yield strength and the conductive performance value corresponding to the bonding copper wire sample are calculated in combination with the sample force measurement data and the sample electrical measurement data, respectively, wherein the sample yield strength and the conductive performance value respectively represent the strength index corresponding to the bonding copper wire sample at which plastic deformation begins to occur when subjected to an external force and the performance index of the ability to conduct current; The bonding performance of the bonding copper wire is analyzed in combination with the conductive performance value and the yield strength of the sample, wherein the bonding performance is the comprehensive performance of the bonding copper wire in the bonding production process. A production status monitoring report of the bonding copper wire is generated in combination with a preset Internet of Things database, the equipment operating performance, the process stability performance and the bonding performance of the bonding copper wire.

2. The method for monitoring the production status of the intelligent bonding copper wire supported by the Internet of Things according to claim 1, characterized in that: The combining of the equipment operating condition data and the equipment maintenance data to evaluate the equipment operating condition performance corresponding to the copper wire manufacturing equipment includes: Identify the data tag corresponding to the equipment operating condition data to obtain the equipment operating condition tag; Extracting operating condition characterization parameters from the equipment operating condition data, and selecting key characterization parameters from the operating condition characterization parameters based on the equipment operating condition label; Calculating the equipment health corresponding to the copper wire manufacturing equipment according to the key characterization parameters and the equipment operating condition label; Calculating the failure risk rate corresponding to the copper wire manufacturing equipment according to the equipment maintenance data; In combination with the equipment health and the failure risk rate, the equipment operating performance corresponding to the copper wire manufacturing equipment is evaluated.

3. The method for monitoring the production status of the intelligent bonding copper wire supported by the Internet of Things according to claim 2, characterized in that: The selecting, based on the equipment operating condition label, key characterization parameters from among the operating condition characterization parameters comprises: Calculate the characterization parameter mean corresponding to the operating condition characterization parameter, and calculate the characterization variance value corresponding to the operating condition characterization parameter based on the characterization parameter mean; Analyze the semantics of the working condition labels corresponding to the equipment working condition labels, and calculate the label association degree between the equipment working condition labels based on the semantics of the working condition labels; In combination with the characterization variance value and the label association degree, a key characterization parameter among the operating condition characterization parameters is selected.

4. The method for monitoring the production status of the intelligent bonding copper wire supported by the Internet of Things according to claim 2, characterized in that: The calculating, according to the equipment maintenance data, a failure risk rate corresponding to the copper wire manufacturing equipment comprises: Extracting the equipment maintenance frequency corresponding to the copper wire manufacturing equipment from the equipment maintenance data; Counting the number of devices corresponding to the copper wire manufacturing equipment, and querying the maintenance time span corresponding to the copper wire manufacturing equipment; Combined with the equipment maintenance frequency, the number of equipment and the maintenance time span, the failure risk rate corresponding to the copper wire manufacturing equipment is calculated by the following formula: ； Among them, A represents the failure risk rate corresponding to the copper wire manufacturing equipment, B represents the equipment maintenance frequency, D represents the maintenance time span, and E represents the number of equipment.

5. The method for monitoring the production status of the intelligent bonding copper wire supported by the Internet of Things according to claim 1, characterized in that: The calculating the quality variability corresponding to the bonding process flow based on the raw material bonding monitoring image includes: Obtaining a process processing purpose corresponding to the bonding process flow, and querying a bonding target quality corresponding to the process processing purpose; Performing image denoising processing on the raw material bonding monitoring image to obtain a denoised bonding monitoring image; Extracting a bonding color representation attribute corresponding to the denoised bonding monitoring image, and analyzing an actual bonding quality corresponding to the bonding color representation attribute; Calculating a mass difference value between the bonding target mass and the actual bonding mass; Based on the quality difference value, the quality variability corresponding to the bonding process flow is obtained.

6. The method for monitoring the production status of the intelligent bonding copper wire supported by the Internet of Things according to claim 1, characterized in that: The step of evaluating the process sophistication of the bonding process based on the finished copper wire image includes: Dispatching a reference copper wire finished product image corresponding to the bonding process flow; Extracting finished product morphological features and finished product texture features from the finished copper wire image; Extracting reference morphological features and reference texture features from the reference copper wire finished product image; Calculating a process defect index corresponding to the bonding process flow by combining the finished product morphological features and the reference morphological features, wherein the process defect index indicates the degree of process defects reflected by the morphological difference between the actual state and the ideal state corresponding to the bonding process flow; Calculating a process deviation coefficient corresponding to the bonding process flow by combining the finished product texture features and the reference texture features, wherein the process deviation coefficient represents a degree of process deviation due to deviation between actual texture features and ideal texture features corresponding to the bonding process flow; The process sophistication of the bonding process flow is evaluated by combining the process defect index and the process deviation coefficient.

7. The method for monitoring the production status of the intelligent bonding copper wire supported by the Internet of Things according to claim 6, characterized in that: The step of calculating the process defect index corresponding to the bonding process flow by combining the finished product morphological features and the reference morphological features includes: Performing vectorization processing on the finished product morphological features and the reference morphological features respectively to obtain a first morphological feature vector and a second morphological feature vector; Calculate the characteristic deviation between the finished product morphological feature and the reference morphological feature by combining the first morphological feature vector and the second morphological feature vector; According to the characteristic deviation, the process defect index corresponding to the bonding process flow is calculated by the following formula: ； Among them, G represents the process defect index corresponding to the bonding process flow, It represents the feature deviation corresponding to the ath feature in the finished product morphological features, a represents the feature sequence number of the finished product morphological features, Q represents the number of features of the finished product morphological features, Indicates the maximum value in the feature deviation.

8. The method for monitoring the production status of the intelligent bonding copper wire supported by the Internet of Things according to claim 6, characterized in that: The step of calculating the process deviation coefficient corresponding to the bonding process flow by combining the finished product texture feature and the reference texture feature includes: Calculating the texture entropies corresponding to the finished product texture feature and the reference texture feature respectively to obtain a first texture entropy and a second texture entropy; Calculating a texture weighting factor corresponding to the texture feature of the finished product; In combination with the texture weighting factor, the first texture entropy and the second texture entropy, the process deviation coefficient corresponding to the bonding process flow is calculated by the following formula: ； Where F represents the process deviation coefficient corresponding to the bonding process flow, represents the texture weighting factor of the dth feature in the finished product texture feature, d represents the serial number corresponding to the finished product texture feature, r represents the number of features corresponding to the finished product texture feature, represents the texture entropy corresponding to the dth feature of the finished product texture feature in the first texture entropy, Represents the texture entropy corresponding to the dth feature of the reference texture feature in the second texture entropy.

9. The method for monitoring the production status of the intelligent bonding copper wire supported by the Internet of Things according to claim 1, characterized in that: The combining the sample force measurement data and the sample electrical measurement data to respectively calculate the sample yield strength and the conductivity value corresponding to the bonding copper wire sample comprises: Respectively performing data calibration processing on the sample force measurement data and the sample electrical measurement data to obtain calibrated force measurement data and calibrated electrical measurement data; Measuring the sample length and sample cross-sectional area corresponding to the bonding copper wire sample; Reading the sample yield force value corresponding to the bonding copper wire sample in the calibration force measurement data, wherein the sample yield force value is the value of the force corresponding to the bonding copper wire sample in the calibration force measurement data when the material begins to produce obvious plastic deformation, and combining the sample yield force value and the sample cross-sectional area to calculate the sample yield strength corresponding to the bonding copper wire sample; Determining a sample resistance value corresponding to the bonding copper wire sample from the calibration electrical measurement data; The conductivity value corresponding to the bonding copper wire sample is calculated based on the sample length, the sample cross-sectional area and the sample resistance value.

10. The intelligent bonding copper wire production status monitoring system supported by the Internet of Things is characterized by: The system comprises: A working condition performance evaluation module, used for obtaining the copper wire manufacturing equipment corresponding to the bonding copper wire, recording the equipment working condition data and equipment maintenance data corresponding to the copper wire manufacturing equipment, and evaluating the equipment working condition performance corresponding to the copper wire manufacturing equipment in combination with the equipment working condition data and the equipment maintenance data; A process performance evaluation module is used to query the bonding process flow corresponding to the bonding copper wire, collect the raw material bonding monitoring image and the finished copper wire image of the bonding copper wire in the bonding process flow in real time, calculate the quality variability corresponding to the bonding process flow based on the raw material bonding monitoring image, wherein the quality variability represents the description of the quality fluctuation of the raw material processing corresponding to each process in the bonding process flow, and evaluate the process sophistication corresponding to the bonding process flow based on the finished copper wire image, wherein the process sophistication represents the execution accuracy of each link in the bonding process flow, and evaluate the process stability performance corresponding to the bonding process flow in combination with the quality variability and the process sophistication; A parameter calculation module, used for sampling the bonding copper wire in the bonding process to obtain a bonding copper wire sample, performing physical and chemical tests on the bonding copper wire sample to obtain physical and chemical test data, wherein the physical and chemical test data includes sample force measurement data and sample electrical measurement data, and combining the sample force measurement data and the sample electrical measurement data to respectively calculate the sample yield strength and the conductivity performance value corresponding to the bonding copper wire sample, wherein the sample yield strength and the conductivity performance value respectively represent the strength index corresponding to the bonding copper wire sample at which plastic deformation begins to occur when subjected to an external force and the performance index of the ability to conduct current; A report production module is used to analyze the bonding performance of the bonding copper wire in combination with the conductive performance value and the yield strength of the sample, wherein the bonding performance is the comprehensive performance of the bonding copper wire in the bonding production process, and generates a production status monitoring report of the bonding copper wire in combination with a preset Internet of Things database, the equipment operating performance, the process stability performance and the bonding performance of the bonding copper wire.

Images