Cable conductor resistance detection method and system applied to cable production line

By collecting resistance and temperature data of cable conductors in the cable production line, calculating resistance change indicators and interference rates, and correcting abnormal detection results, the error problem caused by temperature fluctuations is solved, and the accuracy of resistance detection of cable conductors is improved.

CN118759230BActive Publication Date: 2024-11-22ZHONGLIANSHENG (QINGDAO) INTELLIGENT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411244654.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-06
Publication Date
2024-11-22
Estimated Expiration
2044-09-06

AI Technical Summary

Technical Problem

The cable conductor resistance detection method in the existing cable production lines has a large error in the detection results due to temperature fluctuations, which affects the accuracy of the detection results.

Method used

By collecting resistance and temperature data of cable conductors, the resistance change index and interference rate are calculated, and the abnormal detection results are corrected based on these indicators, interference from temperature factors is eliminated, and the corrected abnormal detection results are obtained.

Benefits of technology

Reduce the error of the detection result, improve the accuracy of the resistance detection of cable conductors, and ensure that the cable operates normally within the design specifications.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118759230B_ABST
    Figure CN118759230B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of resistance detection technology, and provides a method and system for detecting the resistance of a cable conductor applied to a cable production line. After obtaining an abnormal detection result using a LOF algorithm, the abnormal detection result is corrected. The method includes: collecting resistance data of each production batch and its corresponding temperature data; determining resistance change indicators of different production batches based on the resistance data of the same production batch and its corresponding temperature data; determining the interference rate of each production batch to other production batches based on the resistance data, temperature data and resistance change index of each production batch; and correcting the abnormal detection result based on the interference rate to obtain a corrected abnormal detection result. The method can eliminate the interference of temperature factors on the detection result, reduce errors, and ensure the accuracy of the final detection result. The present invention also provides a cable conductor resistance detection system applied to a cable production line.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of resistance detection, and in particular to a method and system for detecting the resistance of a cable conductor applied to a cable production line. Background Art

[0002] Cable conductor resistance detection in cable production lines is an important part of ensuring cable quality and performance, because the resistance of cable conductors directly affects the electrical conductivity of the cable. If the resistance is too high, it will cause power loss, overheating and even failure of the cable during use. Therefore, resistance detection is very important to ensure that the cable is within the design specifications and can operate normally.

[0003] At present, the cable conductor resistance detection of cable production lines generally uses the double-bridge detection method to monitor the abnormal resistance of each cable conductor produced. After taking several sections of cable conductors produced each time and calculating the average value of their resistance, the LOF algorithm can be used to detect abnormalities and identify abnormal production batches. However, since the double-bridge detection method has extremely high requirements for temperature fluctuations in the detection process, temperature fluctuations are prone to cause resistance changes during the actual detection process, which in turn makes the detection results obtained by the LOF algorithm have large errors. Summary of the invention

[0004] In order to solve the technical problem of large error in detection results, the purpose of the present invention is to provide a cable conductor resistance detection method and system applied to a cable production line. The technical solution adopted is as follows:

[0005] A cable conductor resistance detection method applied to a cable production line, after obtaining an abnormal detection result by using a LOF algorithm, correcting the abnormal detection result, the method comprises:

[0006] Collecting resistance data and corresponding temperature data of each production batch, wherein the resistance data includes resistances of multiple cable conductor segments, and the temperature data includes multiple temperatures when the resistances are collected;

[0007] Determine the resistance variation index of different production batches based on the resistance data of the same production batch and its corresponding temperature data;

[0008] Determine the interference rate of each production batch to other production batches based on the resistance data, temperature data and resistance change index of each production batch;

[0009] The abnormality detection result is corrected based on the interference rate to obtain a corrected abnormality detection result.

[0010] Preferably, determining the resistance change index of different production batches according to the resistance data of the same production batch and its corresponding temperature data includes:

[0011] Determine the overall resistance variation index of each production batch based on the resistance of multiple cable conductor segments of the same production batch;

[0012] Determine multiple inter-segment resistance variation indicators based on the resistance of every two segments of cable conductors in the same production batch to form an inter-segment resistance variation data set;

[0013] Determine multiple inter-segment temperature fluctuation indices based on multiple temperatures of every two segments of cable conductors in the same production batch to form an inter-segment temperature fluctuation data set;

[0014] The resistance change index of each production batch is obtained according to the inter-segment resistance change data set, the inter-segment temperature fluctuation data set and the overall resistance change index of each production batch.

[0015] Preferably, the calculation formula of the resistance change index is:

[0016]

[0017] in, represents the resistance change index of production batch A, LW represents the temperature fluctuation data set between segments, LR represents the resistance change data set between segments, represents the Pearson correlation coefficient between the data sets LW and LR, Indicates the overall resistance change index of production batch A.

[0018] Preferably, in the step of determining the interference rate of each production batch to other production batches according to the resistance data, temperature data and resistance change index of each production batch, the interference rate of each production batch to any other production batch is determined by the following steps:

[0019] Perform linear fitting based on the resistance data and temperature data of all production batches to obtain the slope parameter;

[0020] Obtaining a theoretical resistance difference between the two production batches based on the slope parameter and the temperature data of the two production batches;

[0021] Obtaining a resistance change impact index based on the resistance change index and resistance data of two production batches and the theoretical resistance difference;

[0022] The interference rate is obtained according to the resistance change impact index and the batch difference between two production batches.

[0023] Preferably, the linear fitting is to perform optimal linear fitting using the least square method according to a function model, wherein the function model is:

[0024]

[0025] in, Indicates the size of the resistor, represents the intercept parameter, represents the slope parameter, Indicates the temperature.

[0026] Preferably, the calculation formula of the theoretical resistance difference is:

[0027]

[0028] in, Indicates the theoretical resistance difference between production batch A and production batch B, represents the slope parameter, It represents the average temperature of all segments collected in production batch A. It represents the average temperature of all segments collected in production batch B.

[0029] Preferably, the calculation formula of the resistance change impact index is:

[0030]

[0031] in, It indicates the impact index of production batch B on the resistance change of production batch A. Indicates the resistance change index of production batch A, Indicates the resistance change index of production batch B, It represents the average value of all segment resistances collected from production batch A. It represents the average value of all segment resistances collected from production batch B. represents the theoretical resistance difference between production batch A and interference batch B, Indicates preset parameters.

[0032] Preferably, the calculation formula of the interference rate is:

[0033]

[0034] in, It represents the interference rate of the interference batch B to the production batch A, represents the maximum and minimum normalized function, It indicates the influence index of the interference batch B on the resistance change of the production batch A. Indicates the batch difference between production batch A and interference batch B.

[0035] Preferably, the method of obtaining the abnormality detection result by using the LOF algorithm is to obtain the local abnormality factor of each production batch by using the LOF algorithm, and determine whether each production batch is abnormal based on the local abnormality factor;

[0036] The correcting the abnormality detection result based on the interference rate is to reconstruct the calculation formula of the local abnormality factor based on the interference rate.

[0037] A cable conductor resistance detection system applied to a cable production line, comprising:

[0038] A data acquisition module, used to collect resistance data of each production batch and its corresponding temperature data, wherein the resistance data includes the resistance of multiple sections of cable conductors, and the temperature data includes multiple temperatures when the resistance is collected;

[0039] A data processing module, used to determine the resistance change index of different production batches based on the resistance data of the same production batch and its corresponding temperature data, and to determine the interference rate of each production batch on other production batches based on the resistance data, temperature data and resistance change index of each production batch;

[0040] The correction module corrects the abnormality detection result based on the interference rate to obtain a corrected abnormality detection result.

[0041] The present invention has the following beneficial effects: the cable conductor resistance detection method and system proposed by the present invention for cable production lines, by determining the resistance change index of different production batches, that is, the resistance change caused by temperature fluctuations in the same production batch during the acquisition process, and then determining the interference rate of multiple interference batches on each production batch, that is, the interference caused by multiple interference batches in the neighborhood of each production batch due to temperature changes between different production batches, and then correcting the abnormal detection result according to the interference rate, and finally obtaining the corrected abnormal detection result. This method can eliminate the interference of temperature factors on the detection result, reduce errors, and ensure the accuracy of the final detection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A schematic diagram of a flow chart of a cable conductor resistance detection method applied to a cable production line provided in Embodiment 1 of the present invention;

[0044] Figure 2 This is a schematic diagram of a sub-flow chart of step S2 in the cable conductor resistance detection method applied to a cable production line provided in the first embodiment of the present invention;

[0045] Figure 3A schematic diagram of a flow chart of determining the interference rate of each production batch to any other production batch in a cable conductor resistance detection method applied to a cable production line provided in Embodiment 1 of the present invention;

[0046] Figure 4 This is a module schematic diagram of a cable conductor resistance detection system applied to a cable production line provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the cable conductor resistance detection method and system applied to a cable production line according to the present invention, its specific implementation, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0048] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0049] A specific scheme of a cable conductor resistance detection method and system applied to a cable production line provided by the present invention is described in detail below in conjunction with the accompanying drawings.

[0050] Embodiment 1

[0051] An embodiment of the present invention provides a cable conductor resistance detection method applied to a cable production line, which uses a LOF algorithm to obtain an abnormal detection result and then corrects the abnormal detection result. Figure 1 , the method comprising:

[0052] Step S1, collecting resistance data of each production batch and its corresponding temperature data, wherein the resistance data includes the resistance of multiple sections of cable conductors, and the temperature data includes multiple temperatures when the resistance is collected;

[0053] Step S2, determining the resistance change index of different production batches according to the resistance data of the same production batch and its corresponding temperature data;

[0054] Step S3, determining the interference rate of each production batch to other production batches according to the resistance data, temperature data and resistance change index of each production batch;

[0055] Step S4, correcting the abnormality detection result based on the interference rate to obtain a corrected abnormality detection result.

[0056] The cable conductor resistance detection method applied to the cable production line proposed by the present invention determines the resistance change index of different production batches, that is, the resistance change caused by the temperature fluctuation of the same production batch during the acquisition process, and then determines the interference rate of multiple interference batches on each production batch, that is, the interference caused by multiple interference batches in the neighborhood of each production batch due to the temperature change between different production batches, and then corrects the abnormal detection result according to the interference rate, and finally obtains the corrected abnormal detection result. This method can eliminate the interference of temperature factors on the detection result, reduce errors, and ensure the accuracy of the final detection result.

[0057] The main purpose of the present invention is to eliminate the interference of temperature factors on the resistance detection of cable conductors and determine the production batches of cable conductors with truly abnormal resistance in the cable production line.

[0058] The specific scenario targeted by the present invention is: on the basis of the existing abnormality detection method, that is, directly using the average value of the cable conductor resistance in each production process and using the LOF algorithm for abnormality detection, the present invention takes into account the interference of temperature factors on the resistance detection of the cable conductor, thereby correcting the detection result to make the abnormality detection result more accurate.

[0059] The following is a detailed description of each step:

[0060] In step S1, it can be understood that a collection method is designed and data is collected.

[0061] Collection plan: Cut a section of cable conductor for testing from each production batch on the cable production line, and divide it into n sections according to the set length (this can be done through automatic cutting equipment or manual operation to ensure that the length of each section is consistent for accurate resistance measurement). Each section is tested for resistance using the double-bridge detection method to obtain resistance data, and a temperature sensor is used to monitor the temperature data during the double-bridge detection process.

[0062] Data collection: The cable conductors cut from a production batch are evenly divided into segments, and the resistance value of each segment is tested using the double-bridge detection method. A 100 Hz temperature sensor is used to collect the time-series temperature data during the double-bridge detection process.

[0063] In step S2, since the temperature fluctuation before and after the double bridge detection method is required not to exceed 1° during the resistance detection process, otherwise it will cause errors, the error caused by the temperature fluctuation during the resistance detection process is considered in this step. For cable conductors of different segments of the same batch, the positive correlation between temperature fluctuation and resistance change can be used to determine the resistance difference caused by temperature fluctuation in each batch, that is, to determine the resistance change of n segments of resistance detection results in the same production batch due to temperature, first determine the resistance change, and then determine how much of the resistance change is caused by temperature fluctuation. Since temperature fluctuation and resistance change are positively correlated, the resistance change affected by temperature in each batch detection process is obtained.

[0064] Preferably, if Figure 2 As shown, step S2 includes:

[0065] Step S21, determining the overall resistance change index of each production batch according to the resistance of multiple cable conductor segments of the same production batch;

[0066] Step S22, determining a plurality of inter-segment resistance change indices based on the resistance of every two segments of cable conductors in the same production batch to form an inter-segment resistance change data set;

[0067] Step S23, determining a plurality of inter-segment temperature fluctuation indices based on a plurality of temperatures of every two segments of cable conductors in the same production batch, to form an inter-segment temperature fluctuation data set;

[0068] Step S24, obtaining the resistance change index of each production batch according to the inter-segment resistance change data set, the inter-segment temperature fluctuation data set and the overall resistance change index of each production batch.

[0069] In step S21, the calculation formula of the overall resistance change index is:

[0070]

[0071] in, It represents the overall resistance change index of production batch A, a and b represent segment a and segment b of the n segments into which production batch A is divided. It represents the resistance measured in segment a of production batch A. Represents the resistance measured in segment b of the production batch. represents the permutation and combination formula, that is n(n-1) / 2. It means that from the n segments divided into production batch A, any two segments (denoted by segment a and segment b) are selected as a group, and the absolute value of the difference between the resistances of the two segments in each group is calculated and summed.

[0072] That is, the n resistors cut from production batch A are connected two by two (a total of ) to obtain the average resistance difference as the overall resistance change indicator of production batch A.

[0073] In step S22, the inter-segment resistance change index is specifically the absolute value of the difference between the resistances of every two segments of the cable conductor, that is, the specific formula of the inter-segment temperature fluctuation index is:

[0074]

[0075] in, It indicates the resistance change index between segments a and b taken from production batch A. a and b indicate segments a and b among the n segments into which production batch A is divided. It represents the resistance measured in segment a of production batch A. Represents the resistance measured in segment b of the production batch.

[0076] Then, the n cable conductors obtained from batch A are produced, and every two ( The resistance change index obtained by the method forms the inter-segment resistance change data set LR.

[0077] In step S23, because multiple temperature data are measured for both segments when measuring their resistance, the temperature difference between segments a and b is calculated to obtain the inter-segment temperature fluctuation index. In some specific embodiments, the calculation formula of the inter-segment temperature fluctuation index is:

[0078]

[0079] in, It represents the temperature fluctuation index between segments a and b in production batch A. m represents the total m temperatures measured in each segment when measuring resistance. It indicates the i-th temperature when measuring the resistance of section a of production batch A. It indicates the i-th temperature when measuring the resistance of section b taken from production batch A.

[0080] Then, the n cable conductors obtained from batch A are produced, and every two ( The temperature fluctuation index obtained by (a) forms the inter-segment temperature fluctuation data set LW.

[0081] In step S24, preferably, the calculation formula of the resistance change index is:

[0082]

[0083] in, represents the resistance change index of production batch A, LW represents the temperature fluctuation data set between segments, LR represents the resistance change data set between segments, represents the Pearson correlation coefficient between the data sets LW and LR, Indicates the overall resistance change index of production batch A.

[0084] Since temperature fluctuation is positively correlated with resistance change, There is a positive correlation The higher the value, the greater the effect of temperature fluctuation on the overall resistance change. The higher the degree of influence, the calculation formula of the above resistance change index is constructed.

[0085] So far, the detection interference caused by temperature fluctuations during the detection process has been determined.

[0086] In step S3, since the resistance change between the two production batches is not necessarily caused by temperature fluctuations, it may be caused by normal temperature changes (for example, the detection process temperature of one production batch is constant at 20°, and the detection process temperature of the other production batch is constant at 15°), therefore in this step, the error caused by temperature changes is further combined to determine the interference rate of one production batch to the LOF algorithm due to temperature fluctuations relative to another production batch.

[0087] Since there is a linear relationship between temperature and resistance in theory, the resistance difference between two production batches caused by temperature change can be calculated in theory, and the detection interference caused by temperature fluctuation between the two production batches can be further obtained.

[0088] Therefore, in some preferred embodiments, Figure 3 As shown, the interference rate of each production batch to any other production batch is determined by the following steps:

[0089] Step T1, performing linear fitting based on the resistance data and temperature data of all production batches to obtain a slope parameter;

[0090] Step T2, obtaining a theoretical resistance difference between the two production batches based on the slope parameter and the temperature data of the two production batches;

[0091] Step T3, obtaining a resistance change impact index based on the resistance change index and resistance data of two production batches and the theoretical resistance difference;

[0092] Step T4, obtaining the interference rate according to the resistance change impact index and the batch difference between two production batches.

[0093] In step T1, preferably, the linear fitting is to perform optimal linear fitting using the least square method according to a function model, wherein the function model is:

[0094]

[0095] in, Indicates the size of the resistor, represents the intercept parameter, represents the slope parameter, Indicates the temperature.

[0096] That is, the average resistance value of all batches tested and the average temperature value of the testing process are used to perform optimal linear fitting on the above function model using the least squares method, so as to obtain a more accurate fitting formula.

[0097] In step T2, it can be understood that this step is to calculate the theoretical resistance difference between the two production batches based on the obtained slope parameter, that is, the theoretical positive correlation between temperature and resistance. In some specific embodiments, the calculation formula of the theoretical resistance difference is:

[0098]

[0099] in, Indicates the theoretical resistance difference between production batch A and production batch B, represents the slope parameter, It represents the average temperature of all segments collected in production batch A. It represents the average temperature of all segments collected in production batch B.

[0100] In step T3, preferably, the calculation formula of the resistance change impact index is:

[0101]

[0102] in, It indicates the impact index of production batch B on the resistance change of production batch A. Indicates the resistance change index of production batch A, Indicates the resistance change index of production batch B, It represents the average value of all segment resistances collected from production batch A. It represents the average value of all segment resistances collected from production batch B. Indicates the theoretical resistance difference between production batch A and production batch B, Indicates preset parameters. That is, the average resistance difference between the two production batches A and B. That is, the resistance difference between the two production batches A and B is not caused by normal temperature changes. This is a preset parameter to prevent the denominator from being 0.

[0103] Because here we need to find the resistance change rate between the two production batches A and B due to the temperature factor affecting the test results. For example, it is not necessarily the actual change, but may be the measurement error caused by normal temperature change. Here, the actual change is obtained by removing the measurement error caused by the actual temperature. Finally, the resistance change caused by the relative temperature fluctuation between production batches A and B is used Compare the actual changes , the above formula can be constructed to obtain the resistance change rate of the test results caused by temperature fluctuation between the two production batches A and B.

[0104] In step T4, since the LOF algorithm uses the information of neighboring points to perform anomaly detection, the closer the distance is when the resistance change rate of the detection result caused by temperature fluctuation is higher, the more important it is for accurately calculating the LOF value. Therefore, in some preferred embodiments, the calculation formula of the interference rate is:

[0105]

[0106] in, It represents the interference rate of production batch B to production batch A, represents the maximum and minimum normalized function, It indicates the impact index of production batch B on the resistance change of production batch A. Indicates the batch difference between production batch A and production batch B.

[0107] Generally speaking, the interference rate of production batch B on production batch A is required. If the resistance change rate of the test results due to temperature fluctuation between the two production batches A and B is greater, the impact of temperature fluctuation on production batch B relative to production batch A will be greater, and the interference rate will be greater; and, if the batch difference between the two production batches is smaller when the interference rate is large, then the degree of their proximity will be higher. The LOF algorithm performs anomaly detection through neighboring points, so its interference rate will be further improved compared to non-neighboring points. Therefore, the above formula can be constructed to obtain the actual interference rate of production batch B on production batch A due to temperature fluctuations.

[0108] Thus, the interference rate of each production batch to other production batches can be obtained.

[0109] In step S4, it can be understood that the present invention is corrected on the basis of the existing LOF algorithm, and this step is the final correction step. The abnormality detection result obtained by using the LOF algorithm is to obtain the local abnormality factor of each production batch through the LOF algorithm, and judge whether each production batch is abnormal based on the local abnormality factor.

[0110] Specifically, the LOF algorithm detects outliers by calculating the local density of each point. Local density refers to the point density of a point in its neighborhood. The local density of a point is estimated by the neighboring distance of the point (such as K nearest neighbors). Generally, points with higher local density have more neighbors, while points with lower local density may be outliers.

[0111] The correction is to use the interference rate of k neighbors to the monitoring point to correct the gain of each of the k neighbors to the local abnormality factor, so that the interference rate is higher (large temperature fluctuations have a smaller impact on the results, and thus the abnormal detection results obtained are truly caused by the production and preparation process, rather than inaccurate detection results caused by temperature fluctuations. Therefore, the correction of the abnormal detection results based on the interference rate is to reconstruct the calculation formula of the local abnormality factor based on the interference rate. Preferably, the calculation formula of the reconstructed local abnormality factor is:

[0112]

[0113] in, represents the real local abnormal factor of production batch A, represents the number of k-distance neighborhood samples, Represents the production batch within the k-distance neighborhood , Represents the production batch within the k-distance neighborhood The k-reachable density, It represents the interference rate of O production batch to A production batch in the k-distance neighborhood. In this reconstructed formula, the parameters belonging to the original formula are: , , , .

[0114] Here, the calculation formula for the local anomaly factor of production batch A using the LOF algorithm is as follows:

[0115]

[0116] However, if the production batches within the k-distance neighborhood are disturbed by temperature fluctuations, the local abnormality factor obtained will be extremely inaccurate. Here, the high interference rate is used to lower the gain rate of the abnormality factor, and then the above formula is constructed, so that the local abnormality factor obtained is truly caused by the production and preparation process, rather than by inaccurate detection results caused by temperature fluctuations.

[0117] The final test result is judged based on the true local anomaly factor obtained. If the true local anomaly factor not affected by temperature fluctuation is greater than 1, it means that the production batch may be an abnormal production batch, and the larger the true local anomaly factor is, the more likely it is an abnormal production batch.

[0118] Embodiment 2

[0119] The present invention also provides a cable conductor resistance detection system for a cable production line, such as Figure 4 As shown, the system includes:

[0120] The data acquisition module 10 is used to collect the resistance data of each production batch and its corresponding temperature data, wherein the resistance data includes the resistance of multiple sections of cable conductors, and the temperature data includes multiple temperatures when the resistance is collected;

[0121] The data processing module 20 is used to determine the resistance change index of different production batches according to the resistance data of the same production batch and its corresponding temperature data, and to determine the interference rate of each production batch on other production batches according to the resistance data, temperature data and resistance change index of each production batch;

[0122] The correction module 30 corrects the abnormality detection result based on the interference rate to obtain a corrected abnormality detection result.

[0123] In the embodiment of the cable conductor resistance detection system applied to the cable production line of the present invention, all the technical features of the above-mentioned embodiments of the cable conductor resistance detection method applied to the cable production line are included, and the description and explanation content are basically the same as those of the above-mentioned embodiments of the data processing method, and will not be repeated here.

[0124] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0125] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A cable conductor resistance detection method applied to a cable production line, characterized in that: After obtaining the abnormal detection result by using the LOF algorithm, the abnormal detection result is corrected, and the method includes: Collecting resistance data and corresponding temperature data of each production batch, wherein the resistance data includes resistances of multiple cable conductor segments, and the temperature data includes multiple temperatures when the resistances are collected; Determine the resistance variation index of different production batches based on the resistance data of the same production batch and its corresponding temperature data; Determine the interference rate of each production batch on other production batches based on the resistance data, temperature data and resistance change index of each production batch; Correcting the abnormality detection result based on the interference rate to obtain a corrected abnormality detection result; Wherein, determining the resistance change index of different production batches according to the resistance data of the same production batch and its corresponding temperature data includes: Determine the overall resistance variation index of each production batch based on the resistance of multiple cable conductor segments of the same production batch; Determine multiple inter-segment resistance variation indicators based on the resistance of every two segments of cable conductors in the same production batch to form an inter-segment resistance variation data set; Determine multiple inter-segment temperature fluctuation indices based on multiple temperatures of every two segments of cable conductors in the same production batch to form an inter-segment temperature fluctuation data set; Obtaining a resistance change index for each production batch according to the inter-segment resistance change data set, the inter-segment temperature fluctuation data set, and the overall resistance change index for each production batch; Wherein, the calculation formula of the resistance change index is: in, represents the resistance change index of production batch A, LW represents the temperature fluctuation data set between segments, LR represents the resistance change data set between segments, represents the Pearson correlation coefficient between the data sets LW and LR, Indicates the overall resistance change index of production batch A; Wherein, in determining the interference rate of each production batch to other production batches according to the resistance data, temperature data and resistance change index of each production batch, the interference rate of each production batch to any other production batch is determined by the following steps: Perform linear fitting based on the resistance data and temperature data of all production batches to obtain the slope parameter; Obtaining a theoretical resistance difference between the two production batches based on the slope parameter and the temperature data of the two production batches; Obtaining a resistance change impact index based on the resistance change index and resistance data of two production batches and the theoretical resistance difference; Obtaining the interference rate according to the resistance change impact index and the batch difference between two production batches; The linear fitting is to perform optimal linear fitting using the least square method according to the function model, wherein the function model is: in, Indicates the size of the resistor, represents the intercept parameter, represents the slope parameter, Indicates the temperature; The calculation formula of the theoretical resistance difference is: in, Indicates the theoretical resistance difference between production batch A and production batch B, represents the slope parameter, It represents the average temperature of all segments collected in production batch A. It represents the average value of all segment temperatures collected in production batch B; The calculation formula of the resistance change impact index is: in, It indicates the impact index of the resistance change of production batch B on production batch A. Indicates the resistance change index of production batch A, Indicates the resistance change index of production batch B, It represents the average value of all segment resistances collected from production batch A. It represents the average value of all segment resistances collected from production batch B. Indicates the theoretical resistance difference between production batch A and production batch B, Indicates preset parameters; The calculation formula of the interference rate is: in, It represents the interference rate of production batch B to production batch A, represents the maximum and minimum normalized function, It indicates the impact index of production batch B on the resistance change of production batch A. Indicates the batch difference between production batch A and production batch B; The method of obtaining the abnormality detection result by using the LOF algorithm is to obtain the local abnormality factor of each production batch by using the LOF algorithm, and determine whether each production batch is abnormal based on the local abnormality factor; The correcting the abnormality detection result based on the interference rate is to reconstruct the calculation formula of the local abnormality factor based on the interference rate.

2. A cable conductor resistance detection system applied to a cable production line, characterized in that: The system is used to implement a cable conductor resistance detection method applied to a cable production line as described in claim 1, comprising: A data acquisition module, used to collect resistance data of each production batch and its corresponding temperature data, wherein the resistance data includes the resistance of multiple sections of cable conductors, and the temperature data includes multiple temperatures when the resistance is collected; A data processing module, used to determine the resistance change index of different production batches based on the resistance data of the same production batch and its corresponding temperature data, and to determine the interference rate of each production batch on other production batches based on the resistance data, temperature data and resistance change index of each production batch; The correction module corrects the abnormality detection result based on the interference rate to obtain a corrected abnormality detection result.