Online quality detection method and system for stranded cable

Abstract

The invention discloses an online quality detection method and system for a stranded cable. The system comprises a data acquisition module, a data processing module and a quality detection module, relates to the technical field of cable quality detection, and solves the technical problem that the accuracy of cable quality detection in the wire drawing and stranding process is not high due to the fact that the acquisition frequency of a sensor is dynamically adjusted according to the movement speed of a stranded cable in the prior art. According to the invention, the movement speed of the wire rod is obtained in real time and the detection frequency is dynamically adjusted, so that the synchronous matching of the detection process and the production rhythm is ensured, and the problem of missing detection or repeated acquisition caused by traditional fixed frequency detection is avoided; the cable stranded wire is divided into a plurality of detection sections, and multi-dimensional data acquisition and analysis are performed in combination with an image recognition algorithm and a laser detection technology, so that the defect recognition precision and the detection efficiency are improved; and furthermore, the quality condition is comprehensively judged based on the defect area and the laser data, so that the accuracy of quality evaluation of the cable stranded wire is improved.

Description

Technical Field

[0001] This invention belongs to the field of cable quality testing technology, specifically an online quality testing method and system for cable strands. Background Technology

[0002] Cable stranding is a wire product used to transmit electrical or magnetic energy information and realize electromagnetic energy conversion. In a narrow sense, cable refers to insulated cable, which can be defined as an assembly composed of one or more insulated cores and their respective possible covering layers, overall protective layers, and outer sheaths. Various defects may occur in cable production, such as scratches, oxidation, wire diameter deviation, and back strands. Therefore, how to achieve timely and accurate detection and diagnosis of cable quality during the wire drawing and stranding process has become an urgent technical problem to be solved.

[0003] Existing technologies acquire image information of cable strands using sensors, and then use machine vision to extract features from the images to obtain defect information. Based on this defect information, they determine whether the cable strands have quality problems. However, existing solutions use a fixed detection frequency to inspect the cable strands, resulting in inconsistent sampling intervals in the spatial distribution of the sensor-acquired detection information. This leads to low accuracy in the quality inspection of cable strands.

[0004] This invention provides an online quality inspection method and system for cable strands to solve the above-mentioned technical problems. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an online quality inspection method and system for cable strands, which solves the technical problem that the existing solution dynamically adjusts the sensor acquisition frequency according to the movement speed of the cable strands, resulting in low accuracy in detecting cable quality during the wire drawing and stranding process.

[0006] To achieve the above objectives, a first aspect of the present invention provides an online quality inspection method for cable strands, comprising:

[0007] To obtain the speed of the cable strand movement;

[0008] The detection frequency of the cable strand is determined based on the linear mapping relationship between the cable movement speed and the preset spatial sampling interval.

[0009] The cable strands are divided into several inspection sections;

[0010] Based on the detection frequency, image acquisition and laser detection are performed on each detection segment to obtain the original image and laser detection data of each detection segment;

[0011] Defects are identified in the original image based on image recognition algorithms to obtain the defect area.

[0012] Quality inspection of cable strands is performed based on defect area and laser detection data to obtain inspection results;

[0013] The cable strands were processed based on the test results.

[0014] Preferably, dividing the cable strand into several detection sections includes:

[0015] The cable strand is divided into several detection sections based on a preset length;

[0016] In the various processes of cable stranding, each testing section is inspected; these processes include laying out, stranding, tightening, and winding.

[0017] Preferably, determining the detection frequency of the cable strand based on the linear mapping relationship between the cable movement speed and the preset spatial sampling interval includes:

[0018] Extract the wire speed using the formula. Calculate the detection frequency f of the cable strand; where v is the speed of the cable movement and s is the preset spatial sampling interval.

[0019] Preferably, the defect identification of the original image based on the image recognition algorithm includes:

[0020] Extract several sets of original images;

[0021] The original image is preprocessed to obtain the image to be detected; the image preprocessing includes image grayscale conversion, histogram equalization, and filtering and noise reduction.

[0022] The edge detection algorithm is used to perform contour recognition on the image to be detected, resulting in several defect contours; wherein, the defect contour refers to the boundary range of the defect.

[0023] Obtain the number of pixels occupied by each defect contour; using the formula The defect area QXMj corresponding to each defect contour is calculated; where the defect area refers to the actual area size of each defect on the cable strand; Pj is the number of pixels occupied by defect contour j, Q is the pixel length of the reference calibration object, L is the actual length of the reference calibration object; j = 1, 2, ..., m, m is the total number of defect contours.

[0024] Preferably, the quality inspection of the cable strand based on defect area and laser detection data includes:

[0025] Extract the defect area and laser detection data of the detection section;

[0026] Determine whether the defect area is greater than a preset area threshold; if yes, mark the first detection result as a surface defect; otherwise, mark the first detection result as a normal surface.

[0027] The diameter of the cable strand is detected based on laser detection data, and a second detection result is obtained; the second detection result includes normal diameter and abnormal diameter.

[0028] The first and second test results are combined into a single test result.

[0029] Preferably, the detection of the diameter of the cable strand based on laser detection data includes:

[0030] Extract several sets of laser detection data; generate the diameter fluctuation curve of the target cable based on the laser detection data; analyze the diameter fluctuation curve to obtain diameter characteristic data; among which, the diameter characteristic data includes the cumulative diameter tolerance, diameter uniformity coefficient, maximum diameter and minimum diameter;

[0031] Determine whether the cumulative diameter tolerance is greater than the preset cumulative tolerance threshold; if yes, mark the first diameter label as 1; if no, mark the first diameter label as 0.

[0032] Determine whether the diameter uniformity coefficient is greater than the preset uniformity coefficient threshold; if yes, mark the second diameter label as 1; if no, mark the second diameter label as 0.

[0033] Determine whether both the maximum and minimum diameters are within the preset standard diameter range; if yes, mark the third diameter label as 0; otherwise, mark the third diameter label as 1.

[0034] Determine whether the sum of the first diameter label, the second diameter label, and the third diameter label is equal to 0; if yes, mark the second detection result as normal diameter; otherwise, mark the second detection result as abnormal diameter.

[0035] Preferably, the analysis of the diameter fluctuation curve includes:

[0036] Extract the diameter fluctuation curve and standard diameter of the detection segment;

[0037] Through formula Calculate the cumulative diameter tolerance LGCi of inspection segment i; where x is the length, the value of x is 0≦x≦L, L is the length of the inspection segment, Fi(x) is the diameter fluctuation curve of inspection segment i, BZJ is the standard diameter; || is the absolute value operator; i=1,2,…,n, n is the total number of inspection segments;

[0038] Calculate the variance between the diameter fluctuation curve and the standard diameter and label it as the diameter uniformity coefficient;

[0039] Mark the maximum value in the diameter fluctuation curve as the maximum diameter, and mark the minimum value in the diameter fluctuation curve as the minimum diameter;

[0040] The cumulative diameter tolerance, diameter uniformity coefficient, maximum diameter, and minimum diameter are integrated into diameter characteristic data.

[0041] Preferably, the processing of the cable strands based on the detection results includes:

[0042] Extract the detection results of each detection segment;

[0043] The defect level of each test section in the cable strand is determined based on the test results; the defect level includes Level 1 defects and Level 2 defects.

[0044] Determine if the defect level is Level 1; if yes, obtain the corresponding detection segment number and location information, and generate a shutdown alarm command; otherwise, continue processing the detection results of the remaining detection segments.

[0045] Preferably, determining the defect level of each inspection segment in the cable strand based on the inspection results includes:

[0046] Extract the first and second detection results for each detection segment;

[0047] Determine whether the first detection result is a surface defect; if yes, set the first defect label of the corresponding detection segment to 1; otherwise, set the first defect label of the corresponding detection segment to 0.

[0048] Determine whether the second detection result is a diameter abnormality; if yes, set the second defect label of the corresponding detection segment to 1; if no, set the second defect label of the corresponding detection segment to 0.

[0049] Calculate the sum of the first defect label and the second defect label and mark it as the defect label value;

[0050] Determine if the defect label value is equal to 2; if yes, mark the corresponding inspection segment as a Level 1 defect; otherwise, mark the corresponding inspection segment as a Level 2 defect.

[0051] A second aspect of the present invention provides an online quality inspection system for cable strands, comprising: a data processing module, and a data acquisition module and a quality inspection module connected thereto;

[0052] The data acquisition module is used to acquire the wire movement speed of the cable strand; and to determine the detection frequency of the cable strand based on the linear mapping relationship between the wire movement speed and the preset spatial sampling interval.

[0053] The data processing module is used to divide the cable strand into several detection segments; to perform image acquisition and laser detection on each detection segment according to the detection frequency, and obtain the original image and laser detection data of each detection segment; to perform defect identification on the original image based on the image recognition algorithm, and obtain the defect area; and to perform quality inspection on the cable strand based on the defect area and the laser detection data, and obtain the inspection result.

[0054] The quality inspection module is used to process the cable strands based on the inspection results.

[0055] Compared with the prior art, the beneficial effects of the present invention are:

[0056] 1. This invention ensures the synchronization between the detection process and the production rhythm by acquiring the wire movement speed in real time and dynamically adjusting the detection frequency, avoiding the problems of missed detection or repeated collection caused by traditional fixed-frequency detection; by dividing the cable strand into multiple detection segments and combining image recognition algorithms with laser detection technology for multi-dimensional data collection and analysis, the accuracy of defect identification and detection efficiency are improved; furthermore, the quality status is judged comprehensively based on the defect area and laser data, which helps to improve the accuracy of quality assessment of cable strand.

[0057] 2. This invention obtains the movement speed of the cable strand and calculates the detection frequency based on the movement speed and a preset spatial sampling interval. This allows the detection frequency to be dynamically adjusted according to the change in the movement speed of the cable, ensuring the consistency of the spatial sampling interval between the subsequent original image and laser detection data during the acquisition process, thereby improving the accuracy of quality inspection of cable strands.

[0058] 3. This invention calculates and integrates the absolute value of the difference between the diameter fluctuation curve of each detection segment and the standard diameter to obtain the cumulative diameter tolerance. The calculated cumulative diameter tolerance can reflect the overall deviation between the cable strand and the standard diameter, and the diameter uniformity coefficient can accurately reflect the uniformity of the cable strand, making the analysis process of cable diameter detection data more comprehensive, thereby improving the accuracy of quality detection of cable strand. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 This is an overall flowchart of the online quality inspection method for cable strands according to the present invention;

[0061] Figure 2 This is a schematic diagram of the online quality inspection system for cable strands according to the present invention;

[0062] Figure 3 This is a flowchart illustrating how the defect level of each detection segment is determined based on the detection results in this invention. Detailed Implementation

[0063] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0064] Please see Figures 1-3 The first aspect of the present invention provides an online quality inspection method for cable strands, comprising:

[0065] S1: Obtain the speed of the cable strand movement;

[0066] S2: Determine the detection frequency of the cable strand based on the linear mapping relationship between the wire movement speed and the preset spatial sampling interval;

[0067] S3: Divide the cable strands into several inspection sections;

[0068] S4: Based on the detection frequency, perform image acquisition and laser detection on each detection segment to obtain the original image and laser detection data of each detection segment;

[0069] S5: Based on image recognition algorithms, defects are identified in the original image to obtain the defect area;

[0070] S6: Quality inspection of cable strands is performed based on defect area and laser detection data to obtain inspection results;

[0071] S7: Process the cable strands based on the test results.

[0072] In this embodiment, the cable strand is divided into several detection sections, including:

[0073] The cable strand is divided into several detection sections based on a preset length;

[0074] In several process steps of cable stranding, each inspection segment is inspected and the inspection segment is marked as i; the process steps include laying out, stranding, tightening and winding; i = 1, 2, ..., n, where n is the total number of inspection segments.

[0075] In this embodiment, the detection frequency of the cable strand is determined based on the linear mapping relationship between the cable movement speed and the preset spatial sampling interval, including:

[0076] Extract the speed of the wire movement; using the formula Calculate the detection frequency f of the cable strand; where v is the speed of the cable movement and s is the preset spatial sampling interval.

[0077] This invention acquires the movement speed of the cable strand and calculates the detection frequency based on the movement speed and a preset spatial sampling interval. This allows the detection frequency to be dynamically adjusted according to changes in the movement speed of the cable, ensuring the consistency of the spatial sampling interval between the subsequent original image and laser detection data during the acquisition process. This, in turn, helps to improve the accuracy of quality inspection of cable strands.

[0078] For example, the wire movement speed is set to v = 10m / s, and the preset spatial sampling interval is s = 2mm; the detection frequency of the cable strand is calculated to be f = 5000 through the formula.

[0079] In this embodiment, defect identification of the original image is performed based on an image recognition algorithm, including:

[0080] Extract several sets of original images;

[0081] The original image is preprocessed to obtain the image to be detected; the image preprocessing includes image grayscale conversion, histogram equalization, and filtering and noise reduction.

[0082] Based on the edge detection algorithm, contour recognition is performed on the image to be detected to obtain several defect contours; where the defect contour refers to the boundary range of the defect.

[0083] Obtain the number of pixels occupied by each defect contour; using the formula The defect area QXMj corresponding to each defect contour is calculated; where the defect area refers to the actual area size of each defect on the cable strand; Pj is the number of pixels occupied by defect contour j, Q is the pixel length of the reference calibration object, L is the actual length of the reference calibration object; j = 1, 2, ..., m, m is the total number of defect contours.

[0084] For example, the number of pixels occupied by defect contour 1 is set to P1 = 60000, the pixel length of the reference calibration object is Q = 400, and the actual length of the reference calibration object is L = 1cm; the defect area corresponding to defect contour 1 is calculated to be Q×M1 = 0.375cm² using the formula. 2 .

[0085] In this embodiment, the quality inspection of the cable strands is performed based on the defect area and laser detection data, including:

[0086] Extract the defect area and laser detection data of the detection section;

[0087] Determine whether the defect area is greater than a preset area threshold; if yes, mark the first detection result as a surface defect; otherwise, mark the first detection result as a normal surface.

[0088] The diameter of the cable strand is detected based on laser detection data, and a second detection result is obtained; the second detection result includes normal diameter and abnormal diameter.

[0089] The first and second test results are combined into a single test result.

[0090] For example, the defect area of ​​detection segment 1 is set to 5mm. 2 The area threshold is 2mm. 2 Since the defect area is greater than the preset area threshold, the first detection result is marked as a surface defect.

[0091] In this embodiment, the diameter of the cable strand is detected based on laser detection data, including:

[0092] Extract several sets of laser detection data; generate the diameter fluctuation curve of the target cable based on the laser detection data; analyze the diameter fluctuation curve to obtain diameter characteristic data; among which, the diameter characteristic data includes the cumulative diameter tolerance, diameter uniformity coefficient, maximum diameter and minimum diameter;

[0093] Determine whether the cumulative diameter tolerance is greater than the preset cumulative tolerance threshold; if yes, mark the first diameter label as 1; if no, mark the first diameter label as 0.

[0094] Determine whether the diameter uniformity coefficient is greater than the preset uniformity coefficient threshold; if yes, mark the second diameter label as 1; if no, mark the second diameter label as 0.

[0095] Determine whether both the maximum and minimum diameters are within the preset standard diameter range; if yes, mark the third diameter label as 0; otherwise, mark the third diameter label as 1.

[0096] Determine whether the sum of the first diameter label, the second diameter label, and the third diameter label is equal to 0; if yes, mark the second detection result as normal diameter; otherwise, mark the second detection result as abnormal diameter.

[0097] For example, the diameter feature data is set to include a cumulative diameter tolerance of 0.8 mm, a diameter uniformity coefficient of 0.2 mm, a maximum diameter of 10.3 mm, and a minimum diameter of 9.8 mm; the cumulative tolerance threshold is 0.5 mm, the uniformity coefficient threshold is 0.3 mm, and the standard diameter range is [9.9 mm, 10.1 mm].

[0098] Since the cumulative diameter tolerance is greater than the preset cumulative tolerance threshold, the first diameter label is marked as 1;

[0099] Since the diameter uniformity coefficient is less than the preset uniformity coefficient threshold, the second diameter label is marked as 0;

[0100] Since both the maximum and minimum diameters are outside the preset standard diameter range, the third diameter label is marked as 1;

[0101] Since the sum of the first diameter label, the second diameter label, and the third diameter label is not equal to 0, the second detection result is marked as a diameter anomaly.

[0102] In this embodiment, the diameter fluctuation curve is analyzed, including:

[0103] Extract the diameter fluctuation curve and standard diameter of the detection segment;

[0104] Through formula Calculate the cumulative diameter tolerance LGCi of inspection segment i; where x is the length, the value of x is 0≦x≦L, L is the length of the inspection segment, Fi(x) is the diameter fluctuation curve of inspection segment i, BZJ is the standard diameter; || is the absolute value operator; i=1,2,…,n, n is the total number of inspection segments;

[0105] Calculate the variance between the diameter fluctuation curve and the standard diameter and label it as the diameter uniformity coefficient;

[0106] Mark the maximum value in the diameter fluctuation curve as the maximum diameter, and mark the minimum value in the diameter fluctuation curve as the minimum diameter;

[0107] The cumulative diameter tolerance, diameter uniformity coefficient, maximum diameter, and minimum diameter are integrated into diameter characteristic data.

[0108] This invention calculates and integrates the absolute value of the difference between the diameter fluctuation curve of each detection segment and the standard diameter to obtain the cumulative diameter tolerance. The calculated cumulative diameter tolerance can reflect the overall deviation between the cable strand and the standard diameter, and the diameter uniformity coefficient can accurately reflect the uniformity of the cable strand, making the analysis process of cable diameter detection data more comprehensive, thereby improving the accuracy of quality inspection of cable strand.

[0109] In this embodiment, the cable strands are processed based on the detection results, including:

[0110] Extract the detection results of each detection segment;

[0111] The defect level of each test section in the cable strand is determined based on the test results; the defect level includes Level 1 defects and Level 2 defects.

[0112] Determine if the defect level is Level 1; if yes, obtain the corresponding detection segment number and location information, and generate a shutdown alarm command; otherwise, continue processing the detection results of the remaining detection segments.

[0113] For example, the defect level of detection segment 1 is set to level 1 defect, the corresponding detection segment number and location information are obtained, and a shutdown alarm command is generated.

[0114] In this embodiment, the defect level of each inspection segment in the cable strand is determined based on the inspection results, including:

[0115] Extract the first and second detection results for each detection segment;

[0116] Determine whether the first detection result is a surface defect; if yes, set the first defect label of the corresponding detection segment to 1; otherwise, set the first defect label of the corresponding detection segment to 0.

[0117] Determine whether the second detection result is a diameter abnormality; if yes, set the second defect label of the corresponding detection segment to 1; if no, set the second defect label of the corresponding detection segment to 0.

[0118] Calculate the sum of the first defect label and the second defect label and mark it as the defect label value;

[0119] Determine if the defect label value is equal to 2; if yes, mark the corresponding inspection segment as a Level 1 defect; otherwise, mark the corresponding inspection segment as a Level 2 defect.

[0120] For example, the first detection result of detection segment 1 is set as surface defect and the second detection result is diameter abnormality; since the first detection result is surface defect, the first defect label of detection segment 1 is set to 1; since the second detection result is diameter abnormality, the second defect label of detection segment 1 is set to 1; the sum of the first defect label and the second defect label is calculated to obtain a defect label value of 2; since the defect label value is equal to 2, the defect level of detection segment 1 is marked as a level 1 defect.

[0121] A second aspect of the present invention provides an online quality inspection system for cable strands, comprising: a data processing module, and a data acquisition module and a quality inspection module connected thereto;

[0122] Data acquisition module: used to acquire the movement speed of the cable strand; determine the detection frequency of the cable strand based on the linear mapping relationship between the movement speed of the strand and the preset spatial sampling interval;

[0123] Data processing module: used to divide the cable strand into several inspection segments; to perform image acquisition and laser inspection on each inspection segment according to the inspection frequency, and obtain the original image and laser inspection data of each inspection segment; to perform defect identification on the original image based on the image recognition algorithm, and obtain the defect area; to perform quality inspection on the cable strand based on the defect area and laser inspection data, and obtain the inspection result;

[0124] Quality inspection module: Used to process cable strands based on inspection results.

[0125] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0126] Working principle of the invention:

[0127] This invention obtains the wire movement speed of a cable strand; determines the detection frequency of the cable strand based on the linear mapping relationship between the wire movement speed and a preset spatial sampling interval; divides the cable strand into several detection segments; collects original images and laser detection data of each detection segment according to the detection frequency; identifies defects in the original images based on an image recognition algorithm to obtain the defect area; performs quality inspection on the cable strand based on the defect area and laser detection data to obtain the inspection result; and processes the cable strand based on the inspection result.

[0128] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. An online quality inspection method for cable strands, characterized in that, To obtain the speed of the cable stranded wire moving on the production line; The detection frequency of the cable strand is determined based on the linear mapping relationship between the cable movement speed and the preset spatial sampling interval. The cable strands are divided into several inspection sections; Based on the detection frequency, image acquisition and laser detection are performed on each detection segment to obtain the original image and laser detection data of each detection segment; Defects are identified in the original image based on image recognition algorithms to obtain the defect area. Quality inspection of cable strands is performed based on defect area and laser detection data to obtain inspection results; The cable strands were processed based on the test results.

2. The online quality inspection method for cable strands according to claim 1, characterized in that, The process of dividing the cable strand into several detection sections includes: The cable strand is divided into several detection sections based on a preset length; In the various processes of cable stranding, each testing section is inspected; these processes include laying out, stranding, tightening, and winding.

3. The online quality inspection method for cable strands according to claim 1, characterized in that, The determination of the detection frequency of the cable strand based on the linear mapping relationship between the cable movement speed and the preset spatial sampling interval includes: Extract the wire speed using the formula. Calculate the detection frequency f of the cable strand; where v is the speed of the cable movement and s is the preset spatial sampling interval.

4. The online quality inspection method for cable strands according to claim 1, characterized in that, The defect identification of the original image based on the image recognition algorithm includes: Extract several sets of original images; The original image is preprocessed to obtain the image to be detected; the image preprocessing includes image grayscale conversion, histogram equalization, and filtering and noise reduction. The edge detection algorithm is used to perform contour recognition on the image to be detected, resulting in several defect contours; wherein, the defect contour refers to the boundary range of the defect. Obtain the number of pixels occupied by each defect contour; using the formula The defect area QXMj corresponding to each defect contour is calculated; where the defect area refers to the actual area size of each defect on the cable strand; Pj is the number of pixels occupied by defect contour j, Q is the pixel length of the reference calibration object, L is the actual length of the reference calibration object; j = 1, 2, ..., m, m is the total number of defect contours.

5. The online quality inspection method for cable strands according to claim 1, characterized in that, The quality inspection of cable strands based on defect area and laser detection data includes: Extract the defect area and laser detection data of the detection section; Determine whether the defect area is greater than a preset area threshold; if yes, mark the first detection result as a surface defect; otherwise, mark the first detection result as a normal surface. The diameter of the cable strand is detected based on laser detection data, and a second detection result is obtained; the second detection result includes normal diameter and abnormal diameter. The first and second test results are combined into a single test result.

6. The online quality inspection method for cable strands according to claim 5, characterized in that, The process of detecting the diameter of the cable strand based on laser detection data includes: Extract several sets of laser detection data; generate the diameter fluctuation curve of the target cable based on the laser detection data; analyze the diameter fluctuation curve to obtain diameter characteristic data; among which, the diameter characteristic data includes the cumulative diameter tolerance, diameter uniformity coefficient, maximum diameter and minimum diameter; Determine whether the cumulative diameter tolerance is greater than the preset cumulative tolerance threshold; if yes, mark the first diameter label as 1; if no, mark the first diameter label as 0. Determine whether the diameter uniformity coefficient is greater than the preset uniformity coefficient threshold; if yes, mark the second diameter label as 1; if no, mark the second diameter label as 0. Determine whether both the maximum and minimum diameters are within the preset standard diameter range; if yes, mark the third diameter label as 0; otherwise, mark the third diameter label as 1. Determine whether the sum of the first diameter label, the second diameter label, and the third diameter label is equal to 0; if yes, mark the second detection result as normal diameter; otherwise, mark the second detection result as abnormal diameter.

7. The online quality inspection method for cable strands according to claim 6, characterized in that, The analysis of the diameter fluctuation curve includes: Extract the diameter fluctuation curve and standard diameter of the detection segment; Through formula Calculate the cumulative diameter tolerance LGCi of inspection segment i; where x is the length, the value of x is 0≦x≦L, L is the length of the inspection segment, Fi(x) is the diameter fluctuation curve of inspection segment i, BZJ is the standard diameter; || is the absolute value operator; where i=1,2,…,n, n is the total number of inspection segments; Calculate the variance between the diameter fluctuation curve and the standard diameter and label it as the diameter uniformity coefficient; Mark the maximum value in the diameter fluctuation curve as the maximum diameter, and mark the minimum value in the diameter fluctuation curve as the minimum diameter; The cumulative diameter tolerance, diameter uniformity coefficient, maximum diameter, and minimum diameter are integrated into diameter characteristic data.

8. The online quality inspection method for cable strands according to claim 5, characterized in that, The processing of the cable strands based on the detection results includes: Extract the detection results of the detection segment; The defect level of each test section in the cable strand is determined based on the test results; the defect level includes Level 1 defects and Level 2 defects. Determine if the defect level is Level 1; if yes, obtain the corresponding detection segment number and location information, and generate a shutdown alarm command; otherwise, continue processing the detection results of the remaining detection segments.

9. The online quality inspection method for cable strands according to claim 8, characterized in that, The determination of the defect level of each inspection segment in the cable strand based on the inspection results includes: Extract the first and second detection results for each detection segment; Determine whether the first detection result is a surface defect; if yes, set the first defect label of the corresponding detection segment to 1; otherwise, set the first defect label of the corresponding detection segment to 0. Determine whether the second detection result is a diameter abnormality; if yes, set the second defect label of the corresponding detection segment to 1; if no, set the second defect label of the corresponding detection segment to 0. Calculate the sum of the first defect label and the second defect label and mark it as the defect label value; Determine if the defect label value is equal to 2; if yes, mark the corresponding inspection segment as a Level 1 defect; otherwise, mark the corresponding inspection segment as a Level 2 defect.

10. An online quality inspection system for cable strands, used to implement the online quality inspection method for cable strands as described in any one of claims 1-9, characterized in that, include: The data processing module, and the connected data acquisition module and quality inspection module; The data acquisition module is used to acquire the speed of the cable strand movement. The detection frequency of the cable strand is determined based on the linear mapping relationship between the cable movement speed and the preset spatial sampling interval. The data processing module is used to divide the cable strand into several detection segments; to perform image acquisition and laser detection on each detection segment according to the detection frequency, so as to obtain the original image and laser detection data of each detection segment; and to perform defect identification on the original image based on the image recognition algorithm to obtain the defect area. Quality inspection of cable strands is performed based on defect area and laser detection data to obtain inspection results; The quality inspection module is used to process the cable strands based on the inspection results.

Images