Copper wire stretching quality detection method and system for elongation analysis

Abstract

The invention provides a copper wire stretching quality detection method and system for elongation analysis. The method comprises the following steps: obtaining production process record data of a copper wire sample meeting an elongation threshold; on the basis of a preset production process, traversing the production process record data for comparison to obtain a production process deviation parameter; according to the deviation parameters, extracting record data with the deviation parameters smaller than or equal to a threshold value for centralized value evaluation to obtain a production process reference space; when the production process monitoring data of the to-be-detected copper wire falls into the reference space, judging that the copper wire is qualified; when the monitoring data does not fall into the reference space, extracting a single-attribute deviation matrix; and retrieving an elongation threshold value of an abnormal sample meeting the deviation matrix, and executing targeted tensile quality actual measurement. By establishing a production process reference space, accurate prediction and targeted detection of the drawing quality of the copper wire are realized, and the omission ratio is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of copper wire quality detection, and in particular to a copper wire tensile quality detection method and system for elongation analysis. Background Art

[0002] Copper wire, as a common conductive material, is widely used in electrical, electronic, and communication fields. The elongation of copper wire is an important indicator for evaluating its mechanical properties, which affects the service life and reliability of the product. In traditional copper wire production quality control, tensile quality testing mainly relies on average sampling, that is, randomly sampling samples from batch-produced copper wire for elongation testing. This random sampling lacks specificity and cannot effectively identify quality problems that may occur under specific production process conditions; at the same time, the number of random inspections is limited, and it is difficult to fully cover various variables and parameter combinations in the production process, resulting in a high missed detection rate, which makes it possible for unqualified copper wire products to flow into the market, bringing safety hazards and economic losses. Summary of the invention

[0003] The present invention aims to solve the technical problem that copper wire stretching quality detection in the prior art relies on average sampling and lacks specificity, thus leading to a high missed detection rate, and provides a copper wire stretching quality detection method and system for elongation analysis to solve the problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a copper wire stretching quality detection method for elongation analysis, comprising: obtaining a plurality of production process record data of a plurality of copper wire samples that meet an elongation threshold; based on a preset production process, traversing the plurality of production process record data for comparison to obtain a plurality of production process deviation parameters; based on the plurality of production process deviation parameters, extracting selected production process record data whose production process deviation parameters are less than or equal to the deviation parameter threshold from the plurality of production process record data for centralized value evaluation to obtain a production process reference space; when the production process monitoring data of the copper wire to be tested falls into the production process reference space, marking the copper wire to be tested as qualified in quality; when the production process monitoring data of the copper wire to be tested does not fall into the production process reference space, extracting a production process single attribute deviation matrix based on a preset deviation threshold of a single attribute of the production process; retrieving the minimum value of the concentrated copper wire elongation of abnormal copper wire samples that meet the production process single attribute deviation matrix, and sending it to the copper wire stretching control end to set the stretching parameters and perform actual stretching quality measurement.

[0005] In a second aspect, the present invention provides a copper wire stretching quality detection system for elongation analysis, comprising: a sample acquisition module, used to obtain a number of production process record data of a number of copper wire samples that meet the elongation threshold; a process parameter comparison module, used to traverse the number of production process record data for comparison based on a preset production process, and obtain a number of production process deviation parameters; a reference space construction module, used to extract selected production process record data with production process deviation parameters less than or equal to the deviation parameter threshold from the number of production process record data according to the number of production process deviation parameters, and perform centralized value evaluation to obtain a production process reference space; a qualified identification determination module, used to mark the quality of the copper wire to be tested as qualified when the production process monitoring data of the copper wire to be tested falls into the production process reference space; a deviation matrix extraction module, used to extract the production process single attribute deviation matrix based on the production process single attribute preset deviation threshold when the production process monitoring data of the copper wire to be tested does not fall into the production process reference space; a stretching quality measurement module, used to retrieve the minimum value of the concentrated copper wire elongation of abnormal copper wire samples that meet the production process single attribute deviation matrix, and send it to the copper wire stretching control end to set the stretching parameters and perform stretching quality measurement.

[0006] The beneficial effects of the present invention are: Obtain several production process record data of several copper wire samples that meet the elongation threshold, and establish a basic data set for subsequent analysis by collecting the production process record data of copper wire samples that have been proven to meet the elongation quality requirements in history; based on the preset production process, traverse several production process record data for comparison, obtain several production process deviation parameters, compare and analyze the preset production process under ideal conditions with the process record data in actual production, calculate the deviation value of each process parameter, and quantify the fluctuation in the production process; according to several production process deviation parameters, extract selected production process record data with production process deviation parameters less than or equal to the deviation parameter threshold from several production process record data for centralized value evaluation, obtain the production process benchmark space, and construct the process benchmark space that characterizes the production conditions of qualified products by screening out the production process record data with deviation parameters within an acceptable range and performing centralized value evaluation on these data, so as to provide a reference standard for subsequent quality judgment; by judging when Whether the process monitoring data of the copper wire produced before is within the established process reference space, if it is within the space, it can be directly determined to be of qualified quality without the need for actual tensile testing, thereby improving detection efficiency; when the production process monitoring data of the copper wire to be tested does not fall into the production process reference space, the single attribute deviation matrix of the production process is extracted based on the preset deviation threshold of the single attribute of the production process, and in the case where the process monitoring data is not within the reference space, the deviation of each individual process attribute is further analyzed to construct a deviation matrix to provide a basis for accurately locating potential quality problems; the minimum value of the concentrated copper wire elongation of the abnormal copper wire samples that meet the single attribute deviation matrix of the production process is retrieved, and sent to the copper wire stretching control end to set the stretching parameters and perform stretching quality measurement, and by retrieving abnormal sample records similar to the current deviation matrix in the historical data, a suitable elongation threshold is determined, and applied to the stretching test equipment to perform targeted stretching quality measurement to ensure that the test parameters match the potential problems and improve the accuracy of detection.

[0007] Through the above technical solution, a technical upgrade from general sampling to accurate prediction and targeted testing has been achieved, effectively reducing the missed detection rate of copper wire tensile quality testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic flow chart of a copper wire stretching quality detection method for elongation analysis provided by the present invention; Figure 2 A schematic structural diagram of a copper wire stretching quality detection system for elongation analysis provided by the present invention.

[0009] In the accompanying drawings, the components represented by the reference numerals are as follows: Sample acquisition module 11, process parameter comparison module 12, reference space construction module 13, qualified identification determination module 14, deviation matrix extraction module 15, stretching quality measurement module 16. DETAILED DESCRIPTION

[0010] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0011] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0012] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0013] Embodiment 1, as Figure 1 As shown, an embodiment of the present invention provides a copper wire tensile quality detection method for elongation analysis, comprising: S100: Obtaining a plurality of production process record data of a plurality of copper wire samples meeting an elongation threshold.

[0014] Specifically, as a key indicator for measuring the quality of copper wire, elongation directly reflects the deformation ability and material toughness of copper wire under stress, and has a decisive influence on the performance of copper wire. The elongation threshold refers to the minimum allowable value of the ratio of the elongation of the copper wire before breaking to the original gauge length in a tensile test, usually expressed as a percentage. Among them, the elongation threshold is determined based on the statistical analysis of a large amount of historical production data, combined with product standard requirements and actual application needs.

[0015] By screening historical production data and selecting samples whose elongation test results meet or exceed the elongation threshold, several copper wire samples are obtained. These samples represent copper wire products that meet the elongation threshold. For each copper wire sample that meets the elongation threshold, its complete production process data is recorded, including but not limited to key parameters such as copper wire raw material ratio, copper wire rolling process, copper wire stretching process and heat treatment process. Among them, the copper wire raw material ratio data contains information such as the purity of the raw materials and the alloy composition ratio; the copper wire rolling process data records the temperature, pressure, speed and other parameters during the rolling process; the copper wire stretching process data covers factors such as stretching equipment, stretching rate, tension control, etc.; the heat treatment process data includes process elements such as heat treatment temperature curve, holding time, and cooling method.

[0016] The obtained data of several production process records of several copper wire samples provide necessary data support for subsequent process parameter analysis and quality assessment. By collecting these sample data that meet the elongation threshold, the production process reference space of copper wire can be determined, providing an accurate reference basis for subsequent quality inspection, thereby achieving targeted quality inspection, effectively reducing the missed detection rate, and improving the accuracy and efficiency of inspection.

[0017] S200: Based on a preset production process, traverse the plurality of production process record data for comparison to obtain a plurality of production process deviation parameters.

[0018] Specifically, the preset production process refers to a combination of standard process parameters determined based on the technical specifications and production experience of copper wire products, which is usually formulated by the technical department of the enterprise as a benchmark process for copper wire production. The preset production process includes a standard formula for the proportion of copper wire raw materials, standard parameters for the rolling process, standard settings for the stretching process, and standard conditions for the heat treatment process.

[0019] The production process record data of each copper wire sample that meets the elongation threshold is traversed in turn, and it is compared with the parameters of the preset production process one by one. During the comparison process, the difference between the actual production process parameters in the production process record data and the preset parameters in the preset production process is calculated to form a number of production process deviation parameters. The production process deviation parameter is a quantitative indicator to measure the degree of difference between the actual production process and the preset production process. It can be an absolute deviation value, a relative deviation rate, or a comprehensive deviation index calculated by a specific mathematical model. These deviation parameters reflect the allowable fluctuation range of the production process under the premise of ensuring the qualified elongation of the copper wire.

[0020] By obtaining several production process deviation parameters, quantifying the potential impact of production process changes on the elongation of copper wire, and establishing a correlation model between the copper wire production process and elongation, a data basis is provided for the subsequent determination of the process reference space and deviation threshold, thereby effectively improving the accuracy and reliability of copper wire stretching quality detection.

[0021] S300: According to the plurality of production process deviation parameters, selected production process record data having production process deviation parameters less than or equal to a deviation parameter threshold are extracted from the plurality of production process record data for centralized value evaluation to obtain a production process reference space.

[0022] Specifically, on the basis of obtaining several production process deviation parameters, by setting the deviation parameter threshold, the production process record data with small deviation is screened out, and these data are evaluated by centralized value to construct the production process benchmark space of copper wire. Among them, the deviation parameter threshold refers to the allowable upper limit value of the production process deviation parameter. The threshold is determined by comprehensively considering the process stability requirements, product quality fluctuation tolerance and actual production conditions. For example, through statistical analysis methods, combined with historical production experience, a reasonable deviation parameter threshold is determined, which can not only ensure that the screened data is representative, but also ensure that the number of samples meets the needs of subsequent analysis.

[0023] First, the production process deviation parameters of each production process record data are evaluated, and the record data with production process deviation parameters less than or equal to the set deviation parameter threshold are screened out and marked as selected production process record data. These selected production process record data represent the process parameter combination with a small deviation from the preset production process under the premise of ensuring the qualified elongation of the copper wire. Next, the selected production process record data are evaluated for the concentration value. Concentration value evaluation is a data analysis method that aims to determine the concentrated distribution area of ​​multidimensional data. Among them, the concentration value evaluation can use a variety of statistical methods, such as principal component analysis, cluster analysis, kernel density estimation, etc., to identify the main distribution characteristics and concentration trends of the selected production process record data. Through the concentration value evaluation, the production process benchmark space is finally obtained. The production process benchmark space is a multidimensional parameter space that defines the range of process parameter combinations that ensure the qualified elongation of the copper wire. The space can be a geometric area composed of multiple process parameters, or it can be a set of parameter relationships described by a mathematical model.

[0024] By establishing a production process reference space, a basis is provided for subsequent copper wire quality testing. By judging whether the production process monitoring data of the copper wire to be tested falls into this reference space, it is possible to effectively predict whether the elongation of the copper wire meets the requirements, thereby achieving efficient testing of the copper wire tensile quality and overcoming the shortcomings of traditional sampling methods, such as lack of pertinence and high missed detection rate.

[0025] S400: When the production process monitoring data of the copper wire to be tested falls into the production process reference space, the copper wire to be tested is marked as qualified in quality.

[0026] Specifically, in the copper wire production process, various sensors, detection instruments and production control systems are used to collect process parameter data in real time, including copper wire raw material ratio, rolling process parameters, stretching process parameters and heat treatment process parameters, etc., to obtain the production process monitoring data of the copper wire to be tested, which comprehensively reflects the process conditions of the copper wire to be tested in the production process and provides an important basis for evaluating the quality of the copper wire. Subsequently, the production process monitoring data of the copper wire to be tested is compared with the established production process reference space. The comparison process can use a variety of mathematical methods, such as Euclidean distance calculation, Mahalanobis distance evaluation, multivariate statistical analysis, etc., to determine whether the data point to be tested falls into the production process reference space.

[0027] When the judgment result shows that the production process monitoring data of the copper wire to be tested falls into the production process reference space, it means that the production process conditions of the copper wire to be tested are similar or consistent with the process conditions of the known high-quality copper wire samples, and it can be inferred that the elongation of the copper wire to be tested meets the quality requirements. At this time, the copper wire to be tested is given a quality certification mark. Among them, the quality certification mark can be an electronic mark in the production management system, or it can be a physical mark on the actual production line, such as a qualified label, a specific color mark or a barcode. The quality certification mark indicates that the copper wire to be tested does not need to undergo additional elongation testing and can directly enter the next production link or finished product inventory, thereby greatly improving production efficiency and reducing unnecessary quality inspection costs.

[0028] By marking the copper wires to be tested whose production process monitoring data fall into the production process reference space as qualified, the copper wire elongation quality can be quickly determined based on the production process parameters, avoiding the cumbersome process of physical sampling testing of the copper wires to be tested in the traditional method, and improving the efficiency and accuracy of quality inspection. Especially for mass-produced copper wire products, this method can significantly reduce the time and labor costs of the quality inspection link, while ensuring the reliability of product quality.

[0029] S500: When the production process monitoring data of the copper wire to be tested does not fall into the production process reference space, extracting a production process single attribute deviation matrix based on a preset deviation threshold of a production process single attribute.

[0030] Specifically, when it is determined that the production process monitoring data of the copper wire to be tested does not fall into the production process reference space, it indicates that the production process conditions of the copper wire are somewhat different from the known high-quality copper wire samples, and its elongation may not meet the quality requirements. At this point, it is necessary to further analyze which specific process parameters have deviated from the reference range and the degree of deviation.

[0031] Each production process monitoring data of the copper wire to be tested is compared with the preset standard value in the preset production process, the actual deviation value of each parameter is calculated, and these deviation values ​​are compared with the corresponding single attribute preset deviation threshold in the single attribute preset deviation threshold of the production process, so as to determine which parameters exceed the allowable range and the degree of excess. This information is organized into a single attribute deviation matrix of the production process. Among them, the single attribute preset deviation threshold of the production process refers to the upper limit of the allowable deviation set separately for each production process parameter. These deviation thresholds are determined based on historical production data analysis and professional experience, reflecting the sensitivity of each process parameter to the elongation of the copper wire. For example, the deviation threshold of the purity of the copper wire raw material may be set to ±0.5%, the deviation threshold of the rolling temperature may be set to ±10℃, and the deviation threshold of the heat treatment time may be set to ±5 minutes, etc. The single attribute deviation matrix of the production process is a data structure used to store and display the deviation of each process parameter in the production process monitoring data of the copper wire to be tested. The matrix can contain information such as parameter name, preset standard value, actual monitoring value, deviation value, single attribute preset deviation threshold, and whether it exceeds the threshold. Through the single attribute deviation matrix of the production process, it is possible to intuitively identify which process parameters are potential factors causing quality abnormalities.

[0032] By constructing a production process single attribute deviation matrix for the copper wires to be tested whose production process monitoring data do not fall into the production process benchmark space, data support is provided for subsequent quality assessment and process adjustment.

[0033] S600: Retrieve the minimum value of the concentrated copper wire elongation of the abnormal copper wire samples that meet the single attribute deviation matrix of the production process, and send it to the copper wire stretching control end to set the stretching parameters and perform stretching quality measurement.

[0034] Specifically, after obtaining the single-attribute deviation matrix of the production process, the abnormal copper wire sample library is searched to find the abnormal copper wire samples with similar process deviation characteristics to the current copper wire to be tested, and their elongation data are obtained. The stretching parameters are set accordingly to achieve targeted quality measurement.

[0035] First, historical samples matching the single attribute deviation matrix characteristics of the production process of the current copper wire to be tested are retrieved from the abnormal copper wire sample library to obtain abnormal copper wire samples. These abnormal copper wire samples refer to copper wire samples whose production process parameters and preset standard value deviation patterns are similar to those of the current copper wire to be tested in the previous production process. Among them, the matching process can use methods such as pattern recognition or similarity calculation to ensure that the most representative similar samples are found. Since these abnormal copper wire samples are similar to the current copper wire to be tested in terms of production process deviation characteristics, their elongation performance has reference value for predicting the elongation of the current copper wire to be tested.

[0036] Then, the copper wire elongation data of these abnormal copper wire samples are extracted, and the distribution characteristics of the obtained copper wire elongation data are analyzed, such as using statistical methods such as box plot method, probability density analysis or cluster analysis to identify the concentrated distribution interval of these elongation data, and the concentrated copper wire elongation is obtained after removing the outliers, and the minimum value of the concentrated copper wire elongation is used as the minimum elongation level that the current copper wire to be tested may reach. The minimum value of the concentrated copper wire elongation refers to the lowest level of elongation in the abnormal copper wire samples produced under similar process conditions. Then, the minimum value of the concentrated copper wire elongation is sent to the copper wire stretching control end as the basis for setting the stretching parameters. The copper wire stretching control end adjusts the parameter settings of the stretching test equipment, such as stretching rate, initial tension, test temperature, etc., according to the received minimum value of the concentrated copper wire elongation, to ensure the accuracy and reliability of the actual measurement of the stretching quality.

[0037] By obtaining the minimum value of the concentrated copper wire elongation and setting the stretching parameters based on it, targeted quality inspection of copper wire produced under abnormal process conditions is achieved, avoiding the inaccurate inspection problem caused by using uniform stretching parameters in traditional methods. At the same time, since the stretching parameter setting is more in line with the actual characteristics of the copper wire to be tested, the reliability of the inspection results is improved, providing more accurate data support for production process control and quality improvement.

[0038] Furthermore, based on the preset production process, the plurality of production process record data are traversed for comparison to obtain a plurality of production process deviation parameters, including: S210: Obtaining first production process record data of the plurality of production process record data; S220: Obtaining a weight set of production process attribute elongation influencing factors; S230: performing a same-attribute comparison between the first production process record data and the preset production process to obtain a same-attribute deviation set; S240: Performing weighted Euclidean distance evaluation on the same-attribute deviation set according to the production process attribute elongation rate influence weight set, obtaining a first production process deviation parameter, and adding it to the plurality of production process deviation parameters.

[0039] In a feasible implementation, first, a piece of production process record data is selected from several production process record data that have been obtained, and is processed as the first production process record data. The first production process record data refers to any complete production process record data selected from multiple copper wire samples that meet the elongation threshold according to a predetermined sorting rule (such as production time sequence, batch number sequence, etc.). The first production process record data contains complete parameter information such as the proportion of copper wire raw materials, rolling process, stretching process and heat treatment process, and is the basic data for subsequent comparison and analysis. At the same time, a preset production process attribute elongation influence weight set is obtained. The production process attribute elongation influence weight set refers to a quantitative indicator set of the influence degree of each process parameter on the elongation of the copper wire. In the copper wire production process, different process parameters have different influences on the elongation of the final copper wire product. For example, the heat treatment temperature may have a more significant effect on the elongation than the cooling rate. The production process attribute elongation influence weight set can be determined based on historical data analysis and expert experience, reflecting the sensitivity of each process parameter change to the elongation.

[0040] Then, each process parameter in the first production process record data is compared one by one with the corresponding standard parameters in the preset production process. The comparison process follows the principle of same attribute comparison, that is, the purity of the copper wire raw material is compared with the standard purity, the actual rolling temperature is compared with the standard rolling temperature, the actual stretching rate is compared with the standard stretching rate, etc. Through the same attribute comparison, the deviation value of each process parameter is calculated to form a same attribute deviation set. The set contains the deviation information of all process parameters and can be expressed as a vector or matrix, in which each element corresponds to the deviation value of a specific process parameter. The deviation value can be an absolute difference, a relative difference, or other difference measurement suitable for specific parameter characteristics.

[0041] Subsequently, the obtained production process attribute elongation influence weight set is used to perform weighted processing on the same attribute deviation set. Specifically, the weighted Euclidean distance evaluation can be used to consider the product of the sum of the squares of the deviations of each process parameter and the weight of the elongation influence of its production process attribute, thereby comprehensively reflecting the degree of overall process deviation.

[0042] The mathematical expression of weighted Euclidean distance evaluation can be: ; in, It represents the influence weight of the elongation of the production process attribute of the i-th process parameter, Pi represents the actual value of the i-th process parameter, and Si represents the standard value of the i-th process parameter.

[0043] Through the above calculation, the comprehensive deviation parameter of the first production process record data is obtained, that is, the first production process deviation parameter. The first production process deviation parameter is a comprehensive indicator that quantifies the overall difference between the first production process record data and the preset production process. This parameter is added to several production process deviation parameters as the basic data for subsequent analysis.

[0044] The above steps S210 to S240 constitute a loop processing flow, which processes each production process record data in turn, calculates the corresponding production process deviation parameters, and forms several production process deviation parameters to provide data support for the subsequent construction of the production process reference space.

[0045] Furthermore, the weight set of the elongation influencing factors of the production process attributes is obtained, including: S221: Obtaining a first production process attribute; S222: extracting a first attribute preset deviation threshold from the single attribute preset deviation threshold of the production process; S223: searching the abnormal copper wire sample library for the number of first abnormal samples in which only the first production process attribute is greater than a preset deviation threshold of the first attribute; S224: until the Nth production process attribute is obtained; S225: extracting the Nth attribute preset deviation threshold from the single attribute preset deviation threshold of the production process; S226: searching the abnormal copper wire sample library for the number of Nth abnormal samples having only the Nth production process attribute greater than the preset deviation threshold of the Nth attribute; S227: Calculate the sum of abnormal samples from the first abnormal sample number to the Nth abnormal sample number, traverse the first abnormal sample number to the Nth abnormal sample number, compare it with the sum of abnormal samples, and obtain the production process attribute elongation influence weight set.

[0046] In a preferred embodiment, there are multiple production process attributes in the production process of the copper wire, and the multiple production process attributes are traversed, and one production process attribute is selected each time as the first production process attribute, such as copper wire raw material purity, rolling temperature, stretching rate, heat treatment time, etc. At the same time, for the determined first production process attribute, the corresponding preset deviation threshold is extracted from the pre-established production process single attribute preset deviation threshold as the first attribute preset deviation threshold. The production process single attribute preset deviation threshold refers to the maximum deviation range allowed for each production process attribute, which is determined based on production experience and quality standards. The first attribute preset deviation threshold is the standard line for judging whether the first production process attribute is abnormal. If it exceeds this threshold, it is regarded as an abnormal factor that may affect the elongation.

[0047] Then, perform precise search in the abnormal copper wire sample library to screen out those samples whose only first production process attribute exceeds the preset deviation threshold of the first attribute, while all other process attributes are within the normal range. Count their number and record it as the number of first abnormal samples, which reflects the frequency of unqualified elongation caused by the abnormality of the first production process attribute alone, and is an important data for quantifying the weight of the attribute. According to a similar method, process the second, third, to the Nth production process attributes in turn, where N is the number of all production process attributes involved in the copper wire production process. For each production process attribute, execute the operation process of obtaining the production process attribute, extracting the preset deviation threshold of the attribute, and retrieving the number of single factor abnormal samples, and finally obtain the number of abnormal samples from the first to the Nth.

[0048] After obtaining the number of abnormal samples of all production process attributes, first calculate the sum of these numbers, that is, the sum of abnormal samples, which represents the total number of unqualified elongation samples caused by all single-factor abnormalities. Then, traverse the number of abnormal samples of each production process attribute, divide it by the sum of abnormal samples, and obtain the relative frequency of the abnormal elongation caused by the attribute, as the influence weight of the attribute on the elongation. These weight values ​​together constitute the elongation influence weight set of production process attributes.

[0049] Through the statistical method based on abnormal samples, the objective quantification of the weights of the influence of various production process attributes is achieved, avoiding the uncertainty of subjective experience judgment. These elongation influence weights provide a reliable basis for the subsequent comprehensive evaluation of process deviations and improve the accuracy and reliability of copper wire drawing quality detection.

[0050] Further, selected production process record data with production process deviation parameters less than or equal to the deviation parameter threshold are extracted from the plurality of production process record data for centralized value evaluation to obtain a production process reference space, including: S310: performing pairwise comparison on the selected production process record data to obtain a plurality of selected production process deviation parameters; S320: Based on the multiple selected production process deviation parameters, traverse the selected production process record data to perform outlier factor statistics to obtain an outlier factor statistical value set; S330: Based on the outlier factor threshold and in combination with the outlier factor statistical value set, the selected production process record data is sorted to obtain concentrated production process record data and construct the production process benchmark space.

[0051] Specifically, first, from a number of production process record data, extract the data whose production process deviation parameters are less than or equal to the deviation parameter threshold, and mark them as selected production process record data. These selected data represent qualified process parameter combinations within a certain deviation tolerance range. Next, perform pairwise comparison analysis on these selected production process record data. Pairwise comparison refers to comparing each selected production process record data with each other selected production process record data one by one, and calculating the parameter differences between them. The specific comparison method can use Euclidean distance, Mahalanobis distance or other distance measurement methods suitable for multidimensional data comparison. Through comprehensive pairwise comparison, multiple selected production process deviation parameters are obtained, and the similarities or differences between different process records are quantified, providing basic data for subsequent outlier factor analysis.

[0052] After obtaining multiple selected production process deviation parameters, the outlier factor is calculated for each selected production process record data. The outlier factor is a statistical indicator used to measure the degree of abnormality or dispersion of a data point compared with other data points. In specific implementation, each selected production process record data is traversed, and the distribution characteristics of its deviation parameters from other selected production process record data, such as average deviation, maximum deviation, deviation standard deviation, etc., are counted to obtain the outlier factor statistical value of the selected production process record data. This process is repeated until all selected production process record data are processed, and finally a set of outlier factor statistical values ​​is formed. This set contains quantitative indicators of the degree of outlier of each selected production process record data, which can reflect which process records are more consistent with the mainstream process mode and which have large deviations.

[0053] Subsequently, an outlier factor threshold is first determined, which is determined by a statistical analysis method, such as percentiles based on the outlier factor distribution, cluster analysis results, or expert experience values. Then, the outlier factor statistics of each selected production process record data are compared with the set outlier factor threshold. If the outlier factor statistics of a selected production process record data is less than or equal to the outlier factor threshold, it is judged as a concentrated process record data; if it is greater than the outlier factor threshold, it is regarded as an outlier and is not included in the data set constructed by the production process benchmark space. Through this sorting process, process record data with smaller outlier factors and stronger representativeness are screened out and defined as concentrated production process record data. These data have high mutual consistency and can more accurately reflect the process characteristics of high-quality production of copper wire. Afterwards, a production process benchmark space is constructed based on the concentrated production process record data. The production process benchmark space is a region in a multidimensional parameter space, which is defined by the distribution range of concentrated data points.

[0054] By constructing a production process benchmark space, the interference of abnormal or atypical process records is eliminated, and the process conditions for ensuring the qualified elongation of copper wire are more accurately reflected, providing a reliable reference standard for subsequent quality inspections.

[0055] Furthermore, when the production process monitoring data of the copper wire to be tested does not fall into the production process reference space, the production process single attribute deviation matrix is ​​extracted based on the preset deviation threshold of the production process single attribute, including: S510: Obtaining a first production process attribute; S520: Retrieving a set of copper wire samples with abnormal elongation that have deviations in the first production process attribute; S530: extracting a first production process attribute deviation value set between a first production process attribute record value and a first production process attribute preset value of the elongation abnormal copper wire sample set; S540: Perform box plot analysis on the first production process attribute deviation value set to obtain a box deviation value set, extract the minimum value, set it as the first production process attribute deviation threshold, and add it to the production process single attribute preset deviation threshold.

[0056] In a preferred embodiment, first, a production process attribute is selected from multiple production process attributes of the copper wire production process as the first production process attribute. Then, copper wire samples with unqualified elongation and deviations in the first production process attribute are retrieved from the abnormal copper wire sample library to obtain a set of copper wire samples with abnormal elongation. These samples represent historical cases that lead to abnormal elongation when the first production process attribute deviates. By screening these specific abnormal samples, a correlation between process deviation and abnormal elongation can be established.

[0057] For the screened copper wire sample set with abnormal elongation, the actual recorded value of the first production process attribute is extracted and compared with the preset value of the first production process attribute in the preset production process to calculate the deviation value. These deviation values ​​can be absolute deviations, relative deviations or other difference measures suitable for the attribute characteristics. The deviation values ​​of all samples together constitute the first production process attribute deviation value set, which reflects the distribution of the attribute deviation that causes the abnormal elongation.

[0058] After obtaining the deviation value set of the first production process attribute, the box plot analysis method is used to perform statistical processing on the data. The box plot is a statistical graph that intuitively displays the distribution characteristics of data and can effectively identify the central trend and outliers of the data. Through the box plot analysis, a set of box deviation values ​​is obtained, that is, the distribution interval of the main data after removing the outliers. The minimum value is extracted from this interval as the deviation threshold of the first production process attribute. Selecting the minimum value as the threshold reflects the conservative strategy of quality control, that is, as long as the attribute deviation reaches or exceeds the minimum deviation level in the historical abnormal samples, it may lead to abnormal elongation. The determined first production process attribute deviation threshold is added to the preset deviation threshold of the single attribute of the production process as a reference standard for subsequent quality evaluation. Through the same method, other production process attributes are processed in turn, and finally a complete preset deviation threshold of the single attribute of the production process is constructed.

[0059] Further, retrieving the minimum value of the concentrated copper wire elongation of the abnormal copper wire samples that meet the single attribute deviation matrix of the production process also includes: S610: Obtaining a weight set of production process attribute elongation influence; S620: extracting a normalized eigenvalue set of production process single attribute deviations from the production process single attribute deviation matrix; S630: weighting the normalized eigenvalue set of the single attribute deviation of the production process according to the elongation influence weight set of the production process attribute to obtain a weighted eigenvalue set; S640: sorting the production process deviation attribute set from large to small according to the weighted feature value set to obtain a production process deviation attribute sorting result; S650: Processing the production process deviation attribute sorting result and the production process single attribute deviation value set by a copper wire elongation abnormality probability evaluator bound to the copper wire model to obtain an elongation abnormality probability; S660: When the abnormal probability of the elongation is greater than or equal to the abnormal probability threshold, the copper wire to be tested is fully inspected and marked; S670: When the abnormal probability of the elongation is less than the abnormal probability threshold, spot-check and mark the copper wire to be tested; S680: Combine the full inspection mark or the random inspection mark and store it in association with the minimum value of the concentrated copper wire elongation.

[0060] In a preferred embodiment, first, the production process attribute elongation influence weight set is obtained to reflect the influence of each process parameter on the elongation of the copper wire, which is the basic data for subsequent weighted analysis. Then, the deviation value of each process attribute is extracted from the production process single attribute deviation matrix, and normalized to obtain the production process single attribute deviation normalized eigenvalue set. The purpose of normalization is to eliminate the influence of different process attributes due to differences in dimensions and numerical ranges, so that the deviation values ​​of each attribute are comparable. Among them, the normalization method can be maximum and minimum value normalization, Z-score standardization, etc., and a normalization method suitable for each attribute characteristic is selected to ensure the rationality of data conversion.

[0061] Next, the normalized deviation values ​​of each production process attribute in the normalized eigenvalue set of the production process single attribute deviation are multiplied by their corresponding influence weights in the production process attribute elongation influence weight set to obtain the weighted eigenvalues. These weighted eigenvalues ​​comprehensively consider the degree of process deviation and the importance of the influence of the production process attribute on the elongation, and can more accurately reflect the actual influence of each deviation factor on the elongation of the copper wire. All weighted eigenvalues ​​constitute a weighted eigenvalue set, which provides a basis for the subsequent ranking of the importance of process parameters.

[0062] Subsequently, according to the weighted eigenvalue set, each production process attribute is sorted from large to small according to its weighted eigenvalue to form the production process deviation attribute sorting result. The production process attribute with a higher ranking has a greater potential impact on the elongation of the copper wire, and is a factor that needs to be focused on in quality control. The production process deviation attribute sorting result helps to identify the key process parameters that are most likely to cause abnormal elongation of the copper wire to be tested, and provides guidance for targeted quality inspection. Then, using a dedicated copper wire elongation abnormality probability estimator bound to the copper wire model to be tested, the obtained production process deviation attribute sorting results and the production process single attribute deviation value set are comprehensively analyzed to evaluate the abnormal elongation probability. Among them, the production process single attribute deviation value set records the actual deviation value of each production process single attribute. The copper wire elongation abnormality probability estimator is a data model, which can be a prediction model constructed based on machine learning methods such as random forests, support vector machines or neural networks, and can output the probability prediction of abnormal elongation based on the input process parameter deviation characteristics. Since different types of copper wires differ in material properties, structural design and application requirements, and their sensitivities to process deviations are also different, the copper wire elongation anomaly probability evaluator is bound to a specific copper wire model to ensure the pertinence and accuracy of the prediction results.

[0063] According to the obtained abnormal probability of elongation, a differentiated quality inspection strategy is adopted. When the abnormal probability of elongation is greater than or equal to the preset abnormal probability threshold, the copper wire to be tested is marked with a full inspection, indicating that the batch of copper wires needs to undergo 100% elongation testing to ensure quality safety. When the abnormal probability of elongation is less than the abnormal probability threshold, the copper wire to be tested is marked with a random inspection, indicating that a sampling inspection method can be used to reduce the inspection workload. This differentiated inspection strategy based on risk probability not only ensures the reliability of quality control, but also optimizes the configuration of inspection resources and improves the overall quality management efficiency. Afterwards, the full inspection mark or random inspection mark is associated with the minimum value of the concentrated copper wire elongation obtained and stored. This minimum value can be used as a reference indicator to set the control parameters of the tensile test. The purpose of the associated storage is to establish a corresponding relationship between the inspection strategy and the expected quality level, which is convenient for subsequent tensile quality measurement and data analysis, and provides a basis for continuous improvement of quality control methods.

[0064] Through the above steps, the intelligent assessment of the abnormal risk of copper wire elongation and the formulation of targeted detection strategies are realized, which effectively solves the problems of insufficient targeting and waste of resources in traditional copper wire quality detection and improves the scientificity and efficiency of quality control.

[0065] Furthermore, the abnormal probability of elongation of the copper wire bound to the copper wire model to be tested is processed on the production process deviation attribute sorting result and the production process single attribute deviation value set to obtain the abnormal probability of elongation, including: S651: Based on the preset deviation threshold of the single attribute of the production process, the single attribute deviation record matrix of the production process is retrieved, and the proportion of the number of abnormal elongation samples in the index samples that meet the single attribute deviation record matrix of the production process is retrieved; S652: Processing the production process single attribute deviation record matrix to obtain a production process deviation attribute sorting record result; S653: Taking the proportion of the number of abnormal elongation samples as supervision, and taking the single attribute deviation record matrix of the production process and the sorted record results of the production process deviation attributes as input, the random forest is configured to obtain the copper wire elongation abnormality probability evaluator.

[0066] In a preferred embodiment, first, the range of specific copper wire models is limited, and data retrieval and analysis are performed on the specific models of the copper wire to be tested. This model limitation ensures that the copper wire elongation abnormality probability estimator constructed subsequently has strong pertinence and can accurately reflect the quality characteristics of the specific model of copper wire. Then, based on the established single attribute preset deviation threshold of the production process, sample records with similar process deviation patterns to the current copper wire to be tested are retrieved and screened in the historical database to form a single attribute deviation record matrix for the production process. This matrix contains the deviation data of each process attribute in the historical samples and is the basic data set for model training. At the same time, the number of samples with unqualified elongation and their proportion in the total samples in these index samples that meet the conditions of the deviation record matrix are counted. This proportion data reflects the historical probability of abnormal elongation under specific process deviation conditions, which will be used as a supervisory signal for model training.

[0067] Subsequently, the single attribute deviation record matrix of the production process was processed, including data cleaning, feature extraction, feature selection and other operations, to improve data quality and model training effect. After processing, the process attributes were ranked in importance according to the statistical characteristics of the deviation of each process attribute, such as the deviation mean, deviation variance, and the correlation between the deviation and elongation abnormality, and the production process deviation attribute ranking record results were obtained. This ranking result reflects the degree of influence of different process attributes on elongation, and provides prior knowledge of feature importance for subsequent model construction.

[0068] Next, the random forest algorithm is used to construct a copper wire elongation abnormality probability estimator. Random forest is an integrated learning method that can effectively process high-dimensional features, resist overfitting, and provide good prediction performance by constructing multiple decision trees and combining the obtained prediction results. The single attribute deviation record matrix of the production process is used as the input feature, the proportion of the number of abnormal elongation samples is used as the supervisory signal or label, and the feature optimization is combined with the sorting record results of the production process deviation attribute to train and configure the random forest model. The configuration process includes determining parameters such as the number of decision trees, tree depth, and node splitting criteria. These parameters can be optimized by cross-validation and other methods to improve model performance. Through the above training and configuration process, a copper wire elongation abnormality probability estimator for a specific copper wire model is finally obtained. The copper wire elongation abnormality probability estimator can receive new process deviation data as input and output the probability prediction of elongation abnormality, providing a basis for the formulation of quality inspection strategies.

[0069] By constructing an evaluator based on a data-driven approach, an accurate assessment of the abnormal risk of copper wire elongation is achieved, which overcomes the subjectivity and uncertainty of traditional empirical judgment, improves the accuracy and reliability of quality prediction, and provides intelligent technical support for copper wire tensile quality detection.

[0070] Embodiment 2, as Figure 2 As shown, based on the same inventive concept as the copper wire stretching quality detection method for elongation analysis provided in Example 1, an embodiment of the present invention also provides a copper wire stretching quality detection system for elongation analysis, including: A sample acquisition module 11 is used to obtain a number of production process record data of a number of copper wire samples that meet the elongation threshold; A process parameter comparison module 12 is used to traverse the plurality of production process record data for comparison based on a preset production process to obtain a plurality of production process deviation parameters; A reference space construction module 13 is used to extract selected production process record data whose production process deviation parameters are less than or equal to the deviation parameter threshold from the production process record data according to the production process deviation parameters, and perform centralized value evaluation to obtain a production process reference space; A qualified identification determination module 14 is used to identify the quality of the copper wire to be tested as qualified when the production process monitoring data of the copper wire to be tested falls into the production process reference space; The deviation matrix extraction module 15 is used to extract the production process single attribute deviation matrix based on the production process single attribute preset deviation threshold when the production process monitoring data of the copper wire to be tested does not fall into the production process reference space; The stretching quality measurement module 16 is used to retrieve the minimum value of the concentrated copper wire elongation of the abnormal copper wire samples that meet the single attribute deviation matrix of the production process, and send it to the copper wire stretching control end to set the stretching parameters and perform stretching quality measurement.

[0071] Furthermore, the process parameter comparison module 12 includes the following execution steps: Obtaining first production process record data of the plurality of production process record data; Obtaining a weight set of elongation influencing factors of production process attributes; Performing a same-attribute comparison between the first production process record data and the preset production process to obtain a same-attribute deviation set; According to the elongation influence weight set of the production process attribute, a weighted Euclidean distance evaluation is performed on the deviation set with the same attribute to obtain a first production process deviation parameter, which is added to the plurality of production process deviation parameters.

[0072] Furthermore, the process parameter comparison module 12 also includes the following execution steps: Obtaining a first production process attribute; Extracting a first attribute preset deviation threshold from the single attribute preset deviation threshold of the production process; Retrieving in the abnormal copper wire sample library the number of first abnormal samples in which only the first production process attribute is greater than a preset deviation threshold of the first attribute; Until the Nth production process attribute is obtained; Extracting the Nth attribute preset deviation threshold from the single attribute preset deviation threshold of the production process; Retrieve the number of Nth abnormal samples in the abnormal copper wire sample library, where only the Nth production process attribute is greater than the preset deviation threshold of the Nth attribute; Calculate the sum of abnormal samples from the first abnormal sample number to the Nth abnormal sample number, traverse the first abnormal sample number to the Nth abnormal sample number, compare it with the sum of abnormal samples, and obtain the production process attribute elongation influence weight set.

[0073] Furthermore, the reference space construction module 13 includes the following execution steps: Comparing the selected production process record data in pairs to obtain a plurality of selected production process deviation parameters; Based on the multiple selected production process deviation parameters, traverse the selected production process record data to perform outlier factor statistics to obtain an outlier factor statistical value set; Based on the outlier factor threshold and in combination with the outlier factor statistical value set, the selected production process record data is sorted to obtain concentrated production process record data and construct the production process benchmark space.

[0074] Furthermore, the deviation matrix extraction module 15 includes the following execution steps: Obtaining a first production process attribute; Retrieving a set of copper wire samples with abnormal elongation that have deviations in the first production process attribute; Extracting a first production process attribute deviation value set of the first production process attribute record value and the first production process attribute preset value of the elongation abnormal copper wire sample set; A box plot analysis is performed on the first production process attribute deviation value set to obtain a box deviation value set, and the minimum value is extracted and set as the first production process attribute deviation threshold, which is added to the production process single attribute preset deviation threshold.

[0075] Furthermore, the stretching quality measuring module 16 also includes the following execution steps: Obtaining a weight set of elongation influencing factors of production process attributes; Extracting a normalized eigenvalue set of production process single attribute deviations from the production process single attribute deviation matrix; After weighting the normalized characteristic value set of the single attribute deviation of the production process according to the elongation influence weight set of the production process attribute, a weighted characteristic value set is obtained; According to the weighted characteristic value set, the production process deviation attribute set is sorted from large to small to obtain the production process deviation attribute sorting result; The copper wire elongation abnormality probability evaluator bound to the copper wire model to be tested is used to process the production process deviation attribute sorting result and the production process single attribute deviation value set to obtain the elongation abnormality probability; When the abnormal probability of elongation is greater than or equal to the abnormal probability threshold, the copper wire to be tested is fully inspected and marked; When the abnormal probability of the elongation is less than the abnormal probability threshold, spot-checking and marking the copper wire to be tested; Combined with the full inspection mark or the random inspection mark, it is associated with the minimum value of the concentrated copper wire elongation rate and stored.

[0076] Furthermore, the stretching quality measuring module 16 also includes the following execution steps: Limiting the copper wire model to be tested, based on the preset deviation threshold of the single attribute of the production process, searching the single attribute deviation record matrix of the production process, and the proportion of the number of abnormal elongation samples in the index samples that meet the single attribute deviation record matrix of the production process; Processing the production process single attribute deviation record matrix to obtain a production process deviation attribute sorting record result; Taking the proportion of the number of abnormal elongation samples as supervision, and taking the single attribute deviation record matrix of the production process and the sorted record results of the production process deviation attributes as input, the random forest is configured to obtain the copper wire elongation abnormality probability estimator.

[0077] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0078] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0082] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0083] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A copper wire tensile quality testing method for elongation analysis, characterized in that: include: Obtaining a number of production process record data of a number of copper wire samples that meet an elongation threshold; Based on the preset production process, traverse the plurality of production process record data for comparison to obtain a plurality of production process deviation parameters; According to the plurality of production process deviation parameters, selected production process record data having production process deviation parameters less than or equal to a deviation parameter threshold are extracted from the plurality of production process record data for centralized value evaluation to obtain a production process reference space; When the production process monitoring data of the copper wire to be tested falls into the production process reference space, the copper wire to be tested is marked as qualified in quality; When the production process monitoring data of the copper wire to be tested does not fall into the production process reference space, extracting the production process single attribute deviation matrix based on the production process single attribute preset deviation threshold; The minimum value of the concentrated copper wire elongation of the abnormal copper wire samples that meet the single attribute deviation matrix of the production process is retrieved and sent to the copper wire stretching control end to set the stretching parameters and perform the actual measurement of the stretching quality.

2. The method according to claim 1, characterized in that Based on the preset production process, the plurality of production process record data are traversed for comparison to obtain a plurality of production process deviation parameters, including: Obtaining first production process record data of the plurality of production process record data; Obtaining a weight set of elongation influencing factors of production process attributes; Performing a same-attribute comparison between the first production process record data and the preset production process to obtain a same-attribute deviation set; According to the elongation influence weight set of the production process attribute, a weighted Euclidean distance evaluation is performed on the deviation set with the same attribute to obtain a first production process deviation parameter, which is added to the plurality of production process deviation parameters.

3. The method according to claim 2, characterized in that Obtain the production process attribute elongation influence weight set, including: Obtaining a first production process attribute; Extracting a first attribute preset deviation threshold from the single attribute preset deviation threshold of the production process; Retrieving in the abnormal copper wire sample library the number of first abnormal samples in which only the first production process attribute is greater than a preset deviation threshold of the first attribute; Until the Nth production process attribute is obtained; Extracting the Nth attribute preset deviation threshold from the single attribute preset deviation threshold of the production process; Retrieve the number of Nth abnormal samples in the abnormal copper wire sample library, where only the Nth production process attribute is greater than the preset deviation threshold of the Nth attribute; Calculate the sum of abnormal samples from the first abnormal sample number to the Nth abnormal sample number, traverse the first abnormal sample number to the Nth abnormal sample number, compare it with the sum of abnormal samples, and obtain the production process attribute elongation influence weight set.

4. The method according to claim 1, characterized in that Extracting selected production process record data whose production process deviation parameters are less than or equal to the deviation parameter threshold from the plurality of production process record data for centralized value evaluation to obtain a production process reference space, including: Comparing the selected production process record data in pairs to obtain a plurality of selected production process deviation parameters; Based on the multiple selected production process deviation parameters, traverse the selected production process record data to perform outlier factor statistics to obtain an outlier factor statistical value set; Based on the outlier factor threshold and in combination with the outlier factor statistical value set, the selected production process record data is sorted to obtain concentrated production process record data and construct the production process benchmark space.

5. The method according to claim 1, characterized in that When the production process monitoring data of the copper wire to be tested does not fall into the production process reference space, a single attribute deviation matrix of the production process is extracted based on a preset deviation threshold of a single attribute of the production process, including: Obtaining a first production process attribute; Retrieving a set of copper wire samples with abnormal elongation that have deviations in the first production process attribute; Extracting a first production process attribute deviation value set of the first production process attribute record value and the first production process attribute preset value of the elongation abnormal copper wire sample set; A box plot analysis is performed on the first production process attribute deviation value set to obtain a box deviation value set, and the minimum value is extracted and set as the first production process attribute deviation threshold, which is added to the production process single attribute preset deviation threshold.

6. The method according to claim 1, characterized in that Retrieving the minimum value of the concentrated copper wire elongation of the abnormal copper wire samples that meet the single attribute deviation matrix of the production process, further comprising: Obtaining a weight set of elongation influencing factors of production process attributes; Extracting a normalized eigenvalue set of production process single attribute deviations from the production process single attribute deviation matrix; After weighting the normalized characteristic value set of the single attribute deviation of the production process according to the elongation influence weight set of the production process attribute, a weighted characteristic value set is obtained; According to the weighted characteristic value set, the production process deviation attribute set is sorted from large to small to obtain the production process deviation attribute sorting result; The copper wire elongation abnormality probability evaluator bound to the copper wire model to be tested is used to process the production process deviation attribute sorting result and the production process single attribute deviation value set to obtain the elongation abnormality probability; When the abnormal probability of elongation is greater than or equal to the abnormal probability threshold, the copper wire to be tested is fully inspected and marked; When the abnormal probability of the elongation is less than the abnormal probability threshold, spot-checking and marking the copper wire to be tested; Combined with the full inspection mark or the random inspection mark, it is associated with the minimum value of the concentrated copper wire elongation rate and stored.

7. The method according to claim 6, characterized in that The abnormal probability of elongation of a copper wire bound to the copper wire model to be tested is processed on the production process deviation attribute sorting result and the production process single attribute deviation value set to obtain the abnormal probability of elongation, including: Limiting the copper wire model to be tested, based on the preset deviation threshold of the single attribute of the production process, searching the single attribute deviation record matrix of the production process, and the proportion of the number of abnormal elongation samples in the index samples that meet the single attribute deviation record matrix of the production process; Processing the production process single attribute deviation record matrix to obtain a production process deviation attribute sorting record result; Taking the proportion of the number of abnormal elongation samples as supervision, and taking the single attribute deviation record matrix of the production process and the sorted record results of the production process deviation attributes as input, the random forest is configured to obtain the copper wire elongation abnormality probability estimator.

8. A copper wire tensile quality detection system for elongation analysis, characterized in that: For implementing the method according to any one of claims 1 to 7, comprising: A sample acquisition module, used to obtain a number of production process record data of a number of copper wire samples that meet the elongation threshold; A process parameter comparison module is used to traverse the plurality of production process record data for comparison based on a preset production process to obtain a plurality of production process deviation parameters; A reference space construction module is used to extract selected production process record data whose production process deviation parameters are less than or equal to the deviation parameter threshold from the production process record data according to the production process deviation parameters, and perform centralized value evaluation to obtain a production process reference space; A qualified identification determination module is used to identify the quality of the copper wire to be tested as qualified when the production process monitoring data of the copper wire to be tested falls into the production process reference space; A deviation matrix extraction module, used for extracting a single attribute deviation matrix of a production process based on a preset deviation threshold of a single attribute of a production process when the production process monitoring data of the copper wire to be tested does not fall into the production process reference space; The stretching quality measurement module is used to retrieve the minimum value of the concentrated copper wire elongation of abnormal copper wire samples that meet the single attribute deviation matrix of the production process, and send it to the copper wire stretching control end to set the stretching parameters and perform stretching quality measurement.

Images