Method and system for testing tensile property of electronic connecting wire

Abstract

The invention discloses a method and system for testing the tensile property of an electronic connecting wire, and relates to the technical field of performance test.The method comprises the steps that electronic connecting wire test samples are grouped according to an equal proportion mode, and labels are pasted; processing the grouped samples in different modes, and recording a processing mode corresponding to each label; testing the processed sample, recording corresponding tensile property data, and establishing a data sample set; drawing a tensile property change scatter diagram; establishing a mathematical model between the tensile property and the single processing mode; establishing a mathematical model between the tensile property and a plurality of processing modes; and judging whether the sample has representativeness or not according to a comparison result of prediction and actual measurement. The method has the advantages that the tensile property data of different processing degrees under different processing conditions is predicted through machine learning, and is compared with the measured value to judge whether the tensile property data has representativeness, so that the test process is simplified, and the test accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of performance testing, and in particular to a method and system for testing the tensile strength of electronic connecting wires. Background Art

[0002] Tensile strength testing is a key quality indicator for electronic cables. This testing assesses the mechanical strength, durability, and service life of cables, ensuring they meet design requirements and quality standards. In electronic devices, cables are frequently subjected to forces such as stretching and bending. Inadequate tensile strength can lead to connection failure, impacting the normal operation of the device. Therefore, it is crucial to prioritize and strengthen tensile strength testing and optimization during the design and production of electronic products.

[0003] The existing technology mainly focuses on the device for testing the tensile performance of electronic connecting wires and the optimization of various data collected during the tensile performance test of electronic connecting wires through various monitoring equipment. Although it can improve the precision and accuracy of the test results, it is difficult to adapt to the tensile performance test under the influence of various environmental factors. When testing the tensile performance with required environmental factors, a large number of group tests are required, which has problems such as complicated processes, waste of resources and low testing efficiency. Summary of the Invention

[0004] In order to solve the above technical problems, a method and system for testing the tensile performance of electronic connecting wires are provided. This technical solution solves the problem raised in the above background technology that it is difficult to adapt to the tensile performance test under the influence of various environmental factors. When testing the tensile performance with required environmental factors, a large number of group tests are required, which has problems of complicated procedures, waste of resources and low testing efficiency.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is:

[0006] A method for testing the tensile strength of an electronic connecting wire, comprising:

[0007] Group the electronic connecting wire test samples in equal proportions and label them;

[0008] Process the grouped electronic connecting wire test samples in different ways and record the processing method corresponding to each label;

[0009] Testing the processed electronic connecting wire test samples, and recording the corresponding tensile performance data, to establish a tensile performance data sample set;

[0010] Based on the tensile performance data sample set, a scatter plot of tensile performance changes is drawn;

[0011] Based on machine learning algorithms, a mathematical model is established between tensile properties and individual treatment methods;

[0012] Based on machine learning algorithms, a mathematical model is established between tensile strength and multiple treatment methods;

[0013] The tensile strength of the sample after treatment is predicted based on the mathematical model and compared with the actual test results. The representativeness of the electronic connecting wire test sample is judged through the comparison results.

[0014] Preferably, the grouping of the electronic connecting wire test samples in equal proportions and labeling them specifically includes:

[0015] The electronic connecting wire test sample group obtained by sampling is divided into several small groups in equal proportion, and the corresponding processing methods and numbers are affixed to the small groups. Then, the small groups are divided into several subgroups in equal proportion, and the corresponding electronic connecting wire test sample processing degrees and numbers are affixed to the subgroups, where the order of the numbers is consistent with the processing degrees.

[0016] Preferably, the processing of the grouped electronic connecting wire test samples in different ways and recording the processing method corresponding to each label specifically includes:

[0017] According to the grouping situation, the electronic connecting wire test samples are processed in sequence according to the processing method recorded on the label, and the processing situation of each group and sub-group is recorded during the processing process. The processing and recording of each group of electronic connecting wire test samples are completed according to the test standards established by the enterprise;

[0018] Among them, a special group and subgroup that integrates all treatment methods and all different treatment degrees is set up to test the tensile performance data of electronic connecting wire test samples under various treatment methods and different degrees.

[0019] Preferably, the testing of the processed electronic connecting wire test sample and recording the corresponding tensile performance data to establish a tensile performance data sample set specifically includes:

[0020] Test the tensile properties of the electronic connecting wire test samples under different treatment methods and treatment degrees in sequence according to the numbering order of each group and subgroup, record the corresponding tensile performance data, and establish a tensile performance data sample set;

[0021] The tensile performance data sample set includes: labels of each group and subgroup, processing methods corresponding to each group label, processing degrees corresponding to each subgroup label, and tensile performance data at different processing degrees;

[0022] When establishing a sample set of tensile performance data, the tensile performance data of each electronic connecting wire test sample in the same subgroup are tested, and the average value of the tensile performance data of the subgroup is calculated using the truncated mean method, wherein the truncated mean method is a method of removing a maximum value and a minimum value and averaging the remaining data.

[0023] Preferably, drawing a scatter plot of changes in tensile properties based on the tensile properties data sample set specifically includes:

[0024] Based on the tensile performance data sample set obtained from the test, MATLAB software was used to draw a scatter plot of the changes in the tensile performance test results under different treatment methods and treatment degrees, and an electronic connecting line was used to test the scatter plot of the changes in the tensile performance of the samples under a single treatment method and different treatment degrees, and the impact of a single treatment method and different treatment degrees on the tensile performance was analyzed.

[0025] Preferably, the establishment of a mathematical model between tensile strength and a single treatment method based on a machine learning algorithm specifically includes:

[0026] Based on the tensile performance data sample set, a linear regression equation between tensile performance and a single treatment method is established;

[0027] Based on the standard value of tensile strength established by the enterprise standard, a loss function of the parameters of a single treatment method is established;

[0028] Based on the loss function of a single processing method parameter, a parameter update equation is established;

[0029] Using machine learning tools to predict tensile performance data for a single treatment at different levels;

[0030] The linear regression equation of the tensile strength and the single treatment method is:

[0031] y θ (x) = θ0 + θ1x

[0032] Among them, y θ (x) is the tensile strength result corresponding to different degrees under a certain treatment method, x is a certain treatment method, θ0 is the error term, and θ1 is the parameter of a certain treatment method;

[0033] The loss function of the single processing parameter is:

[0034]

[0035] Among them, Y θ It represents the relationship between the measured value and the standard value, m is the number of samples with different treatment levels, y θ (xi ) is the tensile strength result corresponding to the i-th treatment degree under a certain treatment method, and y is the standard value of tensile strength established by the enterprise standard;

[0036] The single processing mode parameter update equation is:

[0037]

[0038] in, For the i-th updated parameter of a certain processing method, θ i is the i-th parameter of a certain processing method, and β is the step size.

[0039] Preferably, the establishment of a mathematical model between tensile strength and multiple treatment methods based on a machine learning algorithm specifically includes:

[0040] Based on the tensile performance data sample set, a linear regression equation between tensile performance and multiple treatment methods is established;

[0041] Based on the standard values ​​of tensile properties established by the enterprise standard, loss functions of multiple treatment parameters are established;

[0042] Based on the loss function of multiple processing parameters, a parameter update equation is established;

[0043] Using machine learning tools, we can predict tensile performance data for multiple treatments at different levels.

[0044] The linear regression equation between the tensile properties and the multiple treatment methods is:

[0045]

[0046] in, is the tensile strength data corresponding to the jth treatment degree under the i-th treatment method, α0 is the error term, α i is the parameter of the i-th processing method, X i is the data of the jth processing degree under the i-th processing method, n is the number of processing methods, and m is the number of samples with different processing degrees;

[0047] The loss function of the multiple processing parameters is:

[0048]

[0049] Among them, Y α It is a relationship between the difference between the measured values ​​and the standard values ​​of multiple treatment methods, m is the number of samples with different treatment degrees, and y is the standard value of tensile strength established by the enterprise standard;

[0050] The multiple processing method parameter update equations are:

[0051]

[0052] in, is the update parameter in the i-th processing method, α i is the parameter of the i-th processing method, m is the number of samples with different processing levels, γ is the step size, is the jth processing level data under the i-th processing method.

[0053] Preferably, the tensile strength of the next sample after treatment predicted by the mathematical model is compared with the actual test, and judging whether the electronic connecting wire test sample is representative through the comparison results specifically includes:

[0054] After the processed sample data is imported into the system, a predicted value is obtained, and the predicted value is compared with the actual test. Based on the comparison results, it is judged whether the electronic connecting wire test sample is representative. The evaluation rules are as follows:

[0055] When the absolute value of the difference between the predicted value and the actual test value is less than or equal to a, it means that the electronic connecting wire test sample is representative, indicating that the tensile strength of the electronic connecting wire test sample under different conditions is consistent with the value predicted by the system, and there is no need to conduct multiple sets of tensile strength tests;

[0056] When the absolute value of the difference between the predicted value and the actual test value is greater than a, it means that the electronic connecting wire test sample is not representative and it is necessary to re-evaluate by adding test data of several more sets of electronic connecting wire test samples;

[0057] By judging whether more than b% of the added test data meet the requirement that the absolute value of the difference between the predicted value and the actual test value is less than a, if so, it means that the tensile properties of the electronic connecting wire test samples under different conditions are consistent with the values ​​predicted by the system. If not, it is necessary to test this batch of electronic connecting wire test samples more times.

[0058] Furthermore, the present invention proposes a system for testing the tensile strength of electronic connecting wires, which is used to implement the above-mentioned method for testing the tensile strength of electronic connecting wires, including:

[0059] A sample set establishment module is used to group the electronic connecting wire test samples in equal proportions and label them; process the grouped electronic connecting wire test samples in different ways and record the processing method corresponding to each label; test the processed electronic connecting wire test samples and record the corresponding tensile performance data to establish a tensile performance data sample set;

[0060] A data processing module, the data processing module is used to draw a scatter plot of the change in tensile performance based on the tensile performance data sample set; establish a mathematical model between the tensile performance and a single treatment method based on a machine learning algorithm; establish a mathematical model between the tensile performance and multiple treatment methods based on a machine learning algorithm;

[0061] The judging module is used to predict the tensile strength of the next sample after treatment based on the mathematical model and compare it with the actual test, and judge whether the electronic connecting wire test sample is representative through the comparison result.

[0062] Preferably, the sample set establishment module includes:

[0063] A sample grouping unit, which is used to group the electronic connecting wire test samples in equal proportions and label them;

[0064] A sample processing unit, the sample processing unit is used to process the grouped electronic connecting wire test samples in different ways and record the processing method corresponding to each label;

[0065] The sample testing unit is used to test the processed electronic connecting wire test sample, record the corresponding tensile performance data, and establish an tensile performance data sample set.

[0066] The data processing module includes:

[0067] A scatter plot drawing unit, wherein the scatter plot drawing unit is used to draw a scatter plot of changes in tensile properties according to a sample set of tensile properties data;

[0068] A single processing model unit, wherein the single processing model unit is used to establish a mathematical model between tensile strength and a single processing method based on a machine learning algorithm;

[0069] A multi-processing model unit is used to establish a mathematical model between tensile strength and multiple processing methods based on a machine learning algorithm.

[0070] Compared with the prior art, the present invention has the following beneficial effects:

[0071] Through the preliminary preparation work of grouping, processing and testing the electronic connecting wire test samples, a sample set of tensile performance data was established. The tensile performance data of different treatment conditions and different treatment degrees were predicted based on machine learning, and the predicted values ​​were compared with the actual test values. Through the comparison results, it was judged whether the group of electronic connecting wire test samples was representative, thereby simplifying the testing process, reducing resource waste, and improving test efficiency and test accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 This is a flow chart of a method for testing the tensile strength of an electronic connecting wire according to the present invention;

[0073] Figure 2 The present invention establishes a mathematical model flow chart between tensile strength and treatment methods according to enterprise requirements;

[0074] Figure 3 This is a flow chart of the present invention for judging whether the electronic connecting wire test sample is representative based on the comparison results between the predicted value and the actual test value. DETAILED DESCRIPTION

[0075] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0076] Reference Figure 1 As shown, a method for testing the tensile strength of an electronic connecting wire comprises:

[0077] Group the electronic connecting wire test samples in equal proportions and label them;

[0078] Process the grouped electronic connecting wire test samples in different ways and record the processing method corresponding to each label;

[0079] Testing the processed electronic connecting wire test samples, and recording the corresponding tensile performance data, to establish a tensile performance data sample set;

[0080] Based on the tensile performance data sample set, a scatter plot of tensile performance changes is drawn;

[0081] Based on machine learning algorithms, a mathematical model is established between tensile properties and individual treatment methods;

[0082] Based on machine learning algorithms, a mathematical model is established between tensile strength and multiple treatment methods;

[0083] The tensile strength of the sample after treatment is predicted based on the mathematical model and compared with the actual test results. The representativeness of the electronic connecting wire test sample is judged through the comparison results.

[0084] It can be explained that this scheme establishes a sample set of tensile performance data through the preliminary preparation work of grouping, processing and testing of electronic connecting wire test samples, predicts the tensile performance data of different treatment conditions and different treatment degrees based on machine learning, and compares the predicted values ​​with the actual test values. By comparing the results, it is judged whether the group of electronic connecting wire test samples is representative. Among them, this scheme conducts complex and comprehensive testing and modeling on a certain type of electronic connecting wire products in advance. When testing such samples later, it directly predicts through the system's mathematical model, and judges the tensile performance of such samples by comparing the results, thereby reducing subsequent testing processes and improving test accuracy.

[0085] Reference Figure 2 As shown, the mathematical model between tensile properties and treatment methods established according to enterprise requirements specifically includes:

[0086] According to the enterprise's test environment requirements for electronic connecting wire test samples, mathematical models between tensile strength and a single treatment method and between tensile strength and multiple treatment methods are established;

[0087] The mathematical model between the tensile properties and the individual treatment methods specifically includes:

[0088] Based on the tensile performance data sample set, a linear regression equation between tensile performance and a single treatment method is established;

[0089] Based on the standard value of tensile strength established by the enterprise standard, a loss function of the parameters of a single treatment method is established;

[0090] Based on the loss function of a single processing method parameter, a parameter update equation is established;

[0091] Using machine learning tools to predict tensile performance data for a single treatment at different levels;

[0092] The linear regression equation of the tensile strength and the single treatment method is:

[0093] y θ (x) = θ0 + θ1x

[0094] Among them, y θ (x) is the tensile strength result corresponding to different degrees under a certain treatment method, x is a certain treatment method, θ0 is the error term, and θ1 is the parameter of a certain treatment method;

[0095] The loss function of the single processing parameter is:

[0096]

[0097] Among them, Yθ It represents the relationship between the measured value and the standard value, m is the number of samples with different treatment levels, y θ (x i ) is the tensile strength result corresponding to the i-th treatment degree under a certain treatment method, and y is the standard value of tensile strength established by the enterprise standard;

[0098] The single processing mode parameter update equation is:

[0099]

[0100] in, For the i-th updated parameter of a certain processing method, θ i is the i-th parameter of a certain processing method, and β is the step size.

[0101] The mathematical model between the tensile strength and the multiple treatment methods specifically includes:

[0102] Based on the tensile performance data sample set, a linear regression equation between tensile performance and multiple treatment methods is established;

[0103] Based on the standard values ​​of tensile properties established by the enterprise standard, loss functions of multiple treatment parameters are established;

[0104] Based on the loss function of multiple processing parameters, a parameter update equation is established;

[0105] Using machine learning tools, we can predict tensile performance data for multiple treatments at different levels.

[0106] The linear regression equation between the tensile properties and the multiple treatment methods is:

[0107]

[0108] in, is the tensile strength data corresponding to the jth treatment degree under the i-th treatment method, α0 is the error term, α i is the parameter of the i-th processing method, X i is the data of the jth processing degree under the i-th processing method, n is the number of processing methods, and m is the number of samples with different processing degrees;

[0109] The loss function of the multiple processing parameters is:

[0110]

[0111] Among them, Y α It is a relationship between the difference between the measured values ​​and the standard values ​​of multiple treatment methods, m is the number of samples with different treatment degrees, and y is the standard value of tensile strength established by the enterprise standard;

[0112] The multiple processing method parameter update equations are:

[0113]

[0114] in, is the update parameter in the i-th processing method, α i is the parameter of the i-th processing method, m is the number of samples with different processing levels, γ is the step size, is the jth processing level data under the i-th processing method.

[0115] What can be explained is that, based on the company's requirements for tensile performance testing of electronic connecting wires, a mathematical model between tensile performance and a single processing method and a mathematical model between tensile performance and multiple processing methods are established. Both models are based on establishing a large data sample before the test, and then using machine learning to predict tensile performance data of various processing degrees under different processing methods. Among them, when using machine learning tools, the gradient descent iterative method is adopted to iteratively update each parameter. After the two mathematical models are established, in order to ensure the accuracy of the model's predicted values, several additional groups of tests with different processing degrees under different processing methods are required to compare and correct the data with the predicted data, so as to ensure the accuracy of subsequent predictions.

[0116] Reference Figure 3 As shown, the comparison between the predicted value and the standard value is used to judge whether the electronic connecting wire test sample is representative, specifically including:

[0117] After the processed sample data is imported into the system, a predicted value is obtained, and the predicted value is compared with the actual test. Based on the comparison results, it is judged whether the electronic connecting wire test sample is representative. The evaluation rules are as follows:

[0118] When the absolute value of the difference between the predicted value and the actual test value is less than or equal to a, it means that the electronic connecting wire test sample is representative, indicating that the tensile strength of the electronic connecting wire test sample under different conditions is consistent with the value predicted by the system, and there is no need to conduct multiple sets of tensile strength tests;

[0119] When the absolute value of the difference between the predicted value and the actual test value is greater than a, it means that the electronic connecting wire test sample is not representative and it is necessary to re-evaluate by adding test data of several more sets of electronic connecting wire test samples;

[0120] By judging whether more than b% of the added test data meet the requirement that the absolute value of the difference between the predicted value and the actual test value is less than a, if so, it means that the tensile properties of the electronic connecting wire test samples under different conditions are consistent with the values ​​predicted by the system. If not, it is necessary to test this batch of electronic connecting wire test samples more times.

[0121] It is understandable that it is very important to test whether the tensile strength of electronic connecting wires meets the requirements of the enterprise and whether the tensile strength can remain good under the influence of different environmental factors. This plan obtains sample data and mathematical modeling in the early stage in order to compare the predicted values ​​derived from the system model with the actual values ​​of several groups of on-site different treatment methods and different degrees of treatment. By comparison, if the absolute value of the difference between the predicted value and the actual value is less than a, it means that this batch of test samples meets the requirements and is within the standard range. Then, based on the system's derivation and prediction ability, it can be judged whether this batch of samples can obtain the tensile strength of this batch of samples under the influence of different treatment degrees under other treatment methods. If not, it is necessary to add a few more groups of tests and then make comparative judgments to prevent the presence of a large number of defective products in this batch of samples from affecting the tensile strength of the actual electronic connecting wires. Among them, the environmental factors refer to different treatment methods, including: temperature, humidity, pH, and oxygen concentration.

[0122] Furthermore, based on the same inventive concept as the above-mentioned method for testing the tensile strength of electronic connecting wires, this solution also proposes a system for testing the tensile strength of electronic connecting wires, comprising:

[0123] A sample set establishment module is used to group the electronic connecting wire test samples in equal proportions and label them; process the grouped electronic connecting wire test samples in different ways and record the processing method corresponding to each label; test the processed electronic connecting wire test samples and record the corresponding tensile performance data to establish a tensile performance data sample set;

[0124] A data processing module, the data processing module is used to draw a scatter plot of the change in tensile performance based on the tensile performance data sample set; establish a mathematical model between the tensile performance and a single treatment method based on a machine learning algorithm; establish a mathematical model between the tensile performance and multiple treatment methods based on a machine learning algorithm;

[0125] The judging module is used to predict the tensile strength of the next sample after treatment based on the mathematical model and compare it with the actual test, and judge whether the electronic connecting wire test sample is representative through the comparison result.

[0126] The sample set creation module includes:

[0127] A sample grouping unit, which is used to group the electronic connecting wire test samples in equal proportions and label them;

[0128] A sample processing unit, the sample processing unit is used to process the grouped electronic connecting wire test samples in different ways and record the processing method corresponding to each label;

[0129] The sample testing unit is used to test the processed electronic connecting wire test sample, record the corresponding tensile performance data, and establish an tensile performance data sample set.

[0130] The data processing module includes:

[0131] A scatter plot drawing unit, wherein the scatter plot drawing unit is used to draw a scatter plot of changes in tensile properties according to a sample set of tensile properties data;

[0132] A single processing model unit, wherein the single processing model unit is used to establish a mathematical model between tensile strength and a single processing method based on a machine learning algorithm;

[0133] A multi-processing model unit is used to establish a mathematical model between tensile strength and multiple processing methods based on a machine learning algorithm.

[0134] In summary, the advantages of the present invention are: through the preliminary preparation work of grouping, processing and testing of electronic connecting wire test samples, a tensile performance data sample set is established, and the tensile performance data of different treatment degrees under different treatment conditions are predicted based on machine learning, and the predicted values ​​are compared with the actual test values. Through the comparison results, it is judged whether the group of electronic connecting wire test samples is representative, thereby simplifying the testing process, reducing resource waste, and improving testing efficiency and test accuracy.

[0135] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for testing the tensile strength of electronic connecting wires, characterized in that: include: Group the electronic connecting wire test samples in equal proportions and label them; Process the grouped electronic connecting wire test samples in different ways and record the processing method corresponding to each label; Testing the processed electronic connecting wire test samples, and recording the corresponding tensile performance data, to establish a tensile performance data sample set; Based on the tensile performance data sample set, a scatter plot of tensile performance changes is drawn; Based on machine learning algorithms, a mathematical model is established between tensile properties and individual treatment methods; Based on machine learning algorithms, a mathematical model is established between tensile strength and multiple treatment methods; The tensile strength of the sample after treatment is predicted based on the mathematical model and compared with the actual test results. The representativeness of the electronic connecting wire test sample is judged through the comparison results.

2. The method for testing the tensile strength of an electronic connecting wire according to claim 1, wherein: The electronic connecting wire test samples are grouped in equal proportions and labeled, specifically including: The electronic connecting wire test sample group obtained by sampling is divided into several small groups in equal proportion, and the corresponding processing methods and numbers are affixed to the small groups. Then, the small groups are divided into several subgroups in equal proportion, and the corresponding electronic connecting wire test sample processing degrees and numbers are affixed to the subgroups, where the order of the numbers is consistent with the processing degrees.

3. The method for testing the tensile strength of an electronic connecting wire according to claim 2, wherein: The processing of the grouped electronic connecting wire test samples in different ways and recording the processing method corresponding to each label specifically includes: According to the grouping situation, the electronic connecting wire test samples are processed in sequence according to the processing method recorded on the label, and the processing situation of each group and sub-group is recorded during the processing process. The processing and recording of each group of electronic connecting wire test samples are completed according to the test standards established by the enterprise; Among them, a special group and subgroup that integrates all treatment methods and all different treatment degrees is set up to test the tensile performance data of electronic connecting wire test samples under various treatment methods and different degrees.

4. The method for testing the tensile strength of an electronic connecting wire according to claim 3, wherein: The testing of the processed electronic connecting wire test sample and recording the corresponding tensile performance data to establish a tensile performance data sample set specifically includes: Test the tensile properties of the electronic connecting wire test samples under different treatment methods and treatment degrees in sequence according to the numbering order of each group and subgroup, record the corresponding tensile performance data, and establish a tensile performance data sample set; The tensile performance data sample set includes: labels of each group and subgroup, processing methods corresponding to each group label, processing degrees corresponding to each subgroup label, and tensile performance data at different processing degrees; When establishing a sample set of tensile performance data, the tensile performance data of each electronic connecting wire test sample in the same subgroup are tested, and the average value of the tensile performance data of the subgroup is calculated using the truncated mean method, wherein the truncated mean method is a method of removing a maximum value and a minimum value and averaging the remaining data.

5. The method for testing the tensile strength of an electronic connecting wire according to claim 4, wherein: Drawing a scatter plot of changes in tensile performance according to the tensile performance data sample set specifically includes: Based on the tensile performance data sample set obtained from the test, MATLAB software was used to draw a scatter plot of the changes in the tensile performance test results under different treatment methods and treatment degrees, and an electronic connecting line was used to test the scatter plot of the changes in the tensile performance of the samples under a single treatment method and different treatment degrees, and the impact of a single treatment method and different treatment degrees on the tensile performance was analyzed.

6. The method for testing the tensile strength of an electronic connecting wire according to claim 5, wherein: The mathematical model between tensile strength and a single treatment method based on the machine learning algorithm specifically includes: Based on the tensile performance data sample set, a linear regression equation between tensile performance and a single treatment method is established; Based on the standard value of tensile strength established by the enterprise standard, a loss function of the parameters of a single treatment method is established; Based on the loss function of a single processing method parameter, a parameter update equation is established; Using machine learning tools to predict tensile performance data for a single treatment at different levels; The linear regression equation of the tensile strength and the single treatment method is: y θ (x)=θ0+θ1x Among them, y θ (x) is the tensile strength result corresponding to different degrees under a certain treatment method, x is a certain treatment method, θ0 is the error term, and θ1 is the parameter of a certain treatment method; The loss function of the single processing parameter is: Among them, Y θ It represents the relationship between the measured value and the standard value, m is the number of samples with different treatment levels, y θ (x i ) is the tensile strength result corresponding to the i-th treatment degree under a certain treatment method, and y is the standard value of tensile strength established by the enterprise standard; The single processing mode parameter update equation is: in, For the i-th updated parameter of a certain processing method, θ i is the i-th parameter of a certain processing method, and β is the step size.

7. A method for testing the tensile strength of an electronic connecting wire according to claim 6, characterized in that: The mathematical model between tensile strength and multiple treatment methods based on the machine learning algorithm specifically includes: Based on the tensile performance data sample set, a linear regression equation between tensile performance and multiple treatment methods is established; Based on the standard values ​​of tensile properties established by the enterprise standard, loss functions of multiple treatment parameters are established; Based on the loss function of multiple processing parameters, a parameter update equation is established; Using machine learning tools, we can predict tensile performance data for multiple treatments at different levels. The linear regression equation between the tensile properties and the multiple treatment methods is: in, is the tensile strength data corresponding to the jth treatment degree under the i-th treatment method, α0 is the error term, α i is the parameter of the i-th processing method, X i is the data of the jth processing degree under the i-th processing method, n is the number of processing methods, and m is the number of samples with different processing degrees; The loss function of the multiple processing parameters is: Among them, Y α It is a relationship between the difference between the measured values ​​and the standard values ​​of multiple treatment methods, m is the number of samples with different treatment degrees, and y is the standard value of tensile strength established by the enterprise standard; The multiple processing method parameter update equations are: in, is the update parameter in the i-th processing method, α i is the parameter of the i-th processing method, m is the number of samples with different processing levels, γ is the step size, is the jth processing level data under the i-th processing method.

8. The method for testing the tensile strength of an electronic connecting wire according to claim 7, wherein: The tensile properties of the sample after treatment predicted by the mathematical model are compared with the actual test results. The representativeness of the electronic connecting wire test sample is judged by comparing the results. Specifically, the following are included: After the processed sample data is imported into the system, a predicted value is obtained, and the predicted value is compared with the actual test. Based on the comparison results, it is judged whether the electronic connecting wire test sample is representative. The evaluation rules are as follows: When the absolute value of the difference between the predicted value and the actual test value is less than or equal to a, it means that the electronic connecting wire test sample is representative, indicating that the tensile strength of the electronic connecting wire test sample under different conditions is consistent with the value predicted by the system, and there is no need to conduct multiple sets of tensile strength tests; When the absolute value of the difference between the predicted value and the actual test value is greater than a, it means that the electronic connecting wire test sample is not representative and it is necessary to re-evaluate by adding test data of several more sets of electronic connecting wire test samples; By judging whether more than b% of the added test data meet the requirement that the absolute value of the difference between the predicted value and the actual test value is less than a, if so, it means that the tensile properties of the electronic connecting wire test samples under different conditions are consistent with the values ​​predicted by the system. If not, it is necessary to test this batch of electronic connecting wire test samples more times.

9. A system for testing the tensile strength of electronic connecting wires, for implementing the method for testing the tensile strength of electronic connecting wires according to any one of claims 1 to 8, characterized in that: include: A sample set establishment module is used to group the electronic connecting wire test samples in equal proportions and label them; Processing the grouped electronic connecting wire test samples in different ways and recording the processing method corresponding to each label; testing the processed electronic connecting wire test samples and recording the corresponding tensile performance data to establish an tensile performance data sample set; A data processing module, the data processing module is used to draw a scatter plot of changes in tensile properties based on a sample set of tensile properties data; Based on machine learning algorithms, a mathematical model is established between tensile strength and a single treatment method; based on machine learning algorithms, a mathematical model is established between tensile strength and multiple treatment methods; The judging module is used to predict the tensile strength of the next sample after treatment based on the mathematical model and compare it with the actual test, and judge whether the electronic connecting wire test sample is representative through the comparison result.

10. The electronic connecting wire tensile strength testing system according to claim 9, characterized in that: The sample set establishment module specifically includes: A sample grouping unit, which is used to group the electronic connecting wire test samples in equal proportions and label them; A sample processing unit, the sample processing unit is used to process the grouped electronic connecting wire test samples in different ways and record the processing method corresponding to each label; A sample testing unit, the sample testing unit is used to test the processed electronic connecting wire test sample and record the corresponding tensile performance data to establish an tensile performance data sample set; The data processing module specifically includes: A scatter plot drawing unit, wherein the scatter plot drawing unit is used to draw a scatter plot of changes in tensile properties according to a sample set of tensile properties data; A single processing model unit, wherein the single processing model unit is used to establish a mathematical model between tensile strength and a single processing method based on a machine learning algorithm; A multi-processing model unit is used to establish a mathematical model between tensile strength and multiple processing methods based on a machine learning algorithm.

Images