Climbing robot for cable defect detection and detection method

Abstract

The invention relates to the technical field of cable defect detection, and provides a climbing robot for cable defect detection and a detection method. The climbing robot is used for carrying out surface defect detection and internal defect detection on a cable simultaneously, and comprises a main body rack of a frame structure, and a clamping walking unit mounted in the frame structure of the main body rack, a cable penetrating through the two ends of a frame structure of a main body rack is clamped through at least one main driving wheel and at least two clamping wheels in a clamping walking unit, and surface defect detection and internal defect detection are conducted on the cable through a visual detection module and a magnetic flux leakage detection module which are installed at the two ends of the rack; the driving unit installed on the frame structure of the main body rack drives the main driving wheel to rotate, so that the main body frame automatically walks on the cable along the length direction. Therefore, while real-time and synchronous detection of internal defects and external defects of the cable is realized, comprehensive detection of the total length of the cable is realized through autonomous movement.

Description

Technical Field

[0001] The present application relates to the technical field of cable defect detection, and in particular to a climbing robot and a detection method for cable defect detection. Background Art

[0002] Cables are important load-bearing or supporting structures and are widely used in various projects such as bridges, towers, power transmission, oil pipelines, and cableways. Their safety directly affects the operational reliability of facilities and public safety. Therefore, regular inspection and maintenance of cables are particularly important. Traditional cable inspections mainly rely on manual inspections or equipment based on a single inspection technology. These methods have many limitations in practical applications.

[0003] During manual inspection, inspectors conduct visual inspections or use simple tools. However, cables are usually deployed at high altitudes or in hard-to-reach areas. Manual inspection is not only time-consuming and labor-intensive, but also highly dangerous, especially in high-risk working environments such as high towers and bridges. In addition, the experience and skill level of inspectors also directly affect the accuracy of inspections. Manual inspections are difficult to effectively detect hidden defects inside cables.

[0004] At present, the equipment that uses non-destructive testing technologies such as magnetic flux leakage, ultrasonic waves, and eddy currents to automatically test cables often has a single function and poor mobility, and cannot efficiently cope with the complex and changing cable environment. These fixed testing methods can often only be installed in a fixed position to perform local testing on the cable, and it is difficult to cover the testing needs of the entire cable. When these devices are manually moved to test the cable, the testing efficiency is greatly reduced. Summary of the invention

[0005] The purpose of the present application is to provide a climbing robot and a detection method for cable defect detection, so as to solve or alleviate the problems existing in the above-mentioned prior art.

[0006] In order to achieve the above objectives, this application provides the following technical solutions: The present application provides a climbing robot for cable defect detection, which is used to simultaneously perform surface defect detection and internal defect detection on the cable, and the climbing robot comprises: a main frame, which is a frame structure; A clamping walking unit is installed in the frame structure of the main frame, and includes: at least one main driving wheel and at least two clamping wheels, wherein the main driving wheel and the clamping wheels can clamp the cables passing through the two ends of the frame structure of the main frame; The cable detection unit includes a visual detection module and a magnetic flux leakage detection module, which are installed at both ends of the main frame and are used to perform surface defect detection and internal defect detection on the cable respectively; The driving unit is installed on the frame structure of the main body frame and is used to drive the main driving wheel to rotate, so as to drive the main body frame to move along the length direction on the cable.

[0007] Preferably, the main body frame includes an upper frame and a lower frame. At both ends of the upper frame, upper connecting frames with a U-shaped structure are respectively arranged. At both ends of the lower frame, lower connecting frames with a C-shaped structure adapted to the upper connecting frames are respectively arranged. The upper connecting frames and the lower connecting frames can be telescopically adjusted along a first direction; wherein, the first direction is the extending direction of the side plate of the upper connecting frame or the lower connecting frame; the main driving wheel is rotatably installed on the bottom surface of the upper frame, and the clamping wheel is installed on the top surface of the lower frame, and the relative distance between the clamping wheel and the main driving wheel can be adaptively adjusted according to the radial dimension of the cable.

[0008] Preferably, the clamping wheel is rotatably installed on the lower frame through a clamping wheel frame. The clamping wheel frame includes a rotating connecting rod and a tension spring. One end of the rotating connecting rod is rotatably installed on the lower frame, and the other end is rotatably installed with the clamping wheel; one end of the tension spring is connected to the middle part of the rotating connecting rod, and the other end is connected to the lower frame, and is used to drive the rotating connecting rod to have a relative movement trend towards the cable around its connection axis with the lower frame, so as to clamp the cable with the clamping wheel.

[0009] Preferably, there are two groups of the clamping wheel frames, and the two groups of clamping wheel frames are symmetrically arranged at both ends of the lower frame to drive the two clamping wheels to have a trend of moving towards each other.

[0010] Preferably, there are two main driving wheels, and the two main driving wheels are respectively arranged opposite to the two clamping wheels; and / or, the two main driving wheels are respectively connected to the output ends of the two driving units through synchronous belt drives.

[0011] Preferably, both the main driving wheel and the clamping wheel are in a spindle shape to clamp the cable.

[0012] Preferably, the vision detection module includes an image detection bracket and at least three vision detection cameras. The image detection bracket is installed at the head of the main body frame and is circumferentially provided with at least three claws. Three vision detection cameras are respectively arranged on the at least three claws in one-to-one correspondence, so that the imaging ranges of the three vision detection cameras cover the surface of the cable circumferentially.

[0013] Preferably, the magnetic flux leakage detection module includes: a magnetic detection bracket, an excitation device and a detection device; the magnetic detection bracket is installed at the tail of the main frame; the excitation device is an annular structure, installed on the magnetic detection bracket close to the main frame, and is used to magnetize the internal steel wire of the cable; wherein the cable passes through the center of the annular structure of the excitation device; the detection device is an annular structure, installed on the magnetic detection bracket parallel to the excitation device and away from the main frame, and is used to detect magnetic defects in the magnetized steel wire inside the cable.

[0014] Preferably, the detection device includes: a detection mounting plate and a plurality of Hall sensors, the detection mounting plate is mounted on the magnetic detection bracket parallel to the excitation device, and the plurality of Hall sensors are evenly distributed on the detection mounting plate to detect magnetic defects of the magnetized steel wire inside the cable.

[0015] The embodiment of the present application further provides a detection method for cable defect detection, using any of the above-mentioned climbing robots for cable defect detection to simultaneously perform surface defect detection and internal defect detection on the cable, the detection method comprising: Step S101, performing image enhancement processing on the acquired surface image of the cable, and extracting surface defect features of the cable based on the Canny edge detection algorithm and a pre-built composite deep learning model; as well as, De-noising the collected cable magnetic flux leakage signal, and obtaining the cable magnetic flux leakage defect characteristics based on the spectrum analysis method; Step S102, inputting the surface defect features and the magnetic flux leakage defect features of the cable into a generator of a generative adversarial network at the same time, fusing the surface defect features and the magnetic flux leakage defect features to obtain comprehensive defect data of the cable; Step S103: acquiring depth information of cable defects according to the comprehensive defect data, and generating a three-dimensional point cloud of the cable defects, so as to simultaneously acquire surface defects and internal defects of the cable.

[0016] Preferably, step S101 comprises: performing image enhancement processing on the surface image after Gaussian filtering and denoising based on a contrast-limited adaptive histogram equalization method to obtain a surface enhanced image of the cable; Performing gradient calculation on the surface enhancement image of the cable, removing edge redundant pixels from the obtained gradient image based on a non-maximum suppression method, and performing edge detection and connection on the image from which the edge redundant pixels have been removed based on a double threshold method, so as to obtain an edge image of the cable surface defects; The edge image is input into a composite deep learning model based on a convolutional neural network and a Transformer architecture to extract surface defect features of the cable.

[0017] Preferably, in step S101, the collected magnetic leakage signal of the cable is denoised by wavelet transform and low-pass filtering in sequence; based on the spectrum analysis method, the denoised signal obtained by the denoising process is subjected to fast Fourier transform to obtain the distribution characteristics of the denoised signal at different frequencies, so as to obtain the magnetic leakage defect characteristics of the cable.

[0018] Preferably, in step S102, the generator of the generative adversarial network performs feature splicing and weighted fusion on the surface defect features and the magnetic leakage defect features in sequence to obtain the comprehensive defect data.

[0019] Preferably, it also includes: based on the discriminator of the generative adversarial network, respectively calculating the loss function, mean square error and cross entropy loss between the generated comprehensive defect data and the pre-acquired cable defect sample data to evaluate the generated comprehensive defect data, and iteratively optimizing the generator of the generative adversarial network according to the evaluation results.

[0020] Beneficial effects: The climbing robot for cable defect detection provided by the embodiment of the present application is used to simultaneously perform surface defect detection and internal defect detection on the cable. The climbing robot includes a main frame of a frame structure, a clamping walking unit installed in the frame structure of the main frame, and the cables passing through the two ends of the frame structure of the main frame are clamped by at least one main driving wheel and at least two clamping wheels in the clamping walking unit, and the visual inspection module and the magnetic flux leakage inspection module installed at both ends of the frame are used to perform surface defect detection and internal defect detection on the cable. In the detection process, the main driving wheel is driven to rotate by the driving unit installed on the frame structure of the main frame, so that the main frame can self-walk along the length square on the cable. In this way, while realizing the real-time and synchronous detection of the internal and external defects of the cable, the full length of the cable can be fully inspected through autonomous movement.

[0021] At the same time, the cable surface image obtained by the climbing robot is enhanced, and the surface defect features of the cable are extracted based on the Canny edge detection algorithm and the pre-built composite deep learning model; the collected cable magnetic leakage signal is denoised, and the cable magnetic leakage defect features are obtained based on the spectrum analysis method; then, the cable surface defect features and magnetic leakage defect features are simultaneously input into the generator of the generative adversarial network, and the surface defect features and magnetic leakage defect features are fused to obtain the comprehensive defect data of the cable; finally, according to the comprehensive defect data, the depth information of the cable defect is obtained, and the three-dimensional point cloud of the cable defect is generated to simultaneously obtain the surface defects and internal defects of the cable. In this way, the synchronous analysis and detection of the internal and external defects of the cable are realized according to the cable surface image and magnetic leakage information obtained by the climbing robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. Among them: Figure 1 A schematic structural diagram of a climbing robot for cable defect detection provided according to some embodiments of the present application; Figure 2 A schematic diagram of the structure of a main frame provided according to some embodiments of the present application; Figure 3 A schematic diagram of installing a clamping walking unit on a main frame according to some embodiments of the present application; Figure 4 A schematic diagram of assembling a clamping wheel frame on a lower frame according to some embodiments of the present application; Figure 5 A schematic diagram of assembling a cable detection unit on a main frame according to some embodiments of the present application; Figure 6 A schematic diagram of the structure of a main driving wheel provided according to some embodiments of the present application; Figure 7 A schematic flow chart of a detection method for cable defect detection provided according to some embodiments of the present application.

[0023] Description of reference numerals: 100, main frame; 200, clamping and traveling unit; 300, cable detection unit; 400, driving unit; 101, upper frame; 102, lower frame; 111, top plate installation; 121, upper connecting frame; 112, bottom plate installation; 122, lower connecting frame; 201, main driving wheel; 202, clamping wheel; 203, clamping wheel frame; 213, rotating connecting rod; 223, tension spring; 301, visual inspection module; 302, magnetic flux leakage inspection module; 312, magnetic inspection bracket; 322, excitation device; 332, detection device. DETAILED DESCRIPTION

[0024] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. Each example is provided by way of explanation of the present application and does not limit the present application. In fact, it will be clear to those skilled in the art that modifications and variations may be made in the present application without departing from the scope or spirit of the present application. For example, a feature shown or described as a part of an embodiment may be used in another embodiment to produce yet another embodiment. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the embodiments of the present invention should belong to the scope of protection of the embodiments of the present invention.

[0025] At present, during the inspection of cables, manual inspections can only be carried out periodically, with poor real-time performance, and unable to detect sudden structural problems in a timely manner, and there are great safety hazards. Automated inspection equipment using non-destructive testing technology is difficult to move and has low inspection efficiency. On the other hand, it can only detect specific types of defects. For example, magnetic flux leakage detection can only identify broken wires or corrosion points in the cable, but cannot detect surface wear or mechanical damage.

[0026] However, the damage of cables can take many forms, including internal broken wires and corrosion due to material fatigue, and surface wear, cracks, corrosion and other damage due to long-term exposure to the external environment. This requires the detection equipment to be able to identify both internal and external defects, and the current single detection technology is difficult to meet this demand. Magnetic flux leakage technology can detect internal defects of cables, but it is powerless against surface defects; while visual inspection technology can identify external defects, but cannot penetrate into the interior of the cable.

[0027] Based on this, the present application proposes a climbing robot for cable defect detection, which can realize real-time and synchronous detection of internal and external defects of cables, and realize comprehensive detection of cables through autonomous movement. Figures 1 to 6 As shown, the climbing robot includes: a main frame 100, and a clamping and walking unit 200, a cable detection unit 300 and a driving unit 400 installed on the main frame 100. The clamping and walking unit 200 is used to clamp the cable to be detected and drive the main frame 100 to walk along the length direction of the cable under the premise of power provided by the driving unit 400; the cable detection unit 300 is used to simultaneously perform surface defect detection and internal defect detection on the cable to be detected, and during the detection process, it moves on the cable together with the main frame 100, realizing real-time and synchronous detection of internal and external defects of the cable, and performing comprehensive detection of the full length of the cable.

[0028] In this application, the main frame 100 has a frame structure with both ends and sides hollowed out to reduce the overall mass of the frame structure. The clamping and walking unit 200, the cable detection unit 300, and the driving unit 400 are respectively installed on the top plate and the bottom plate of the frame structure. Here, the main mechanism is assembled by buckling the upper and lower parts, so as to detect the installed cable or the non-installed cable, and improve the overall applicability of the climbing robot.

[0029] In a specific example, the main frame 100 includes an upper frame 101 and a lower frame 102. At both ends of the upper frame 101, upper connecting frames 121 with a U-shaped structure are respectively provided. At both ends of the lower frame 102, lower connecting frames 122 with a C-shaped structure adapted to the upper connecting frames 121 are respectively provided. A plurality of adapted adjustment through holes are respectively arranged along the length direction on the side plates of the upper connecting frame 121 and the lower connecting frame 122. When detecting cables with different diameters, through the cooperation of the adjustment through holes at different positions on the upper connecting frame 121 and the lower connecting frame 122, the upper connecting frame 121 and the lower connecting frame 122 are telescopically adjusted along the first direction (the extending direction of the side plate of the upper connecting frame 121 or the lower connecting frame 122), so as to adjust the relative distance between the upper frame 101 and the lower frame 102 to adapt to cables of different sizes.

[0030] Here, the upper connecting frame 121 is detachably installed on the installation top plate 111 of the upper frame 101 through a bolt fastening assembly. That is to say, the top plate of the U-shaped structure of the upper connecting frame 121 and the installation top plate 111 are fixedly connected through a bolt and nut assembly; the lower connecting frame 122 adopts the same installation and connection method as the upper connecting frame 121 and is detachably installed on the installation bottom plate 112 of the lower frame 102.

[0031] The main driving wheel 201 is rotatably installed on the bottom surface of the installation top plate 111 of the upper frame 101. Here, installation pads are symmetrically arranged along the second direction (the width direction of the climbing robot, perpendicular to the first direction and the cable axis) on the bottom surface of the installation top plate 111; both ends of the main driving wheel 201 are respectively rotatably installed on bearing seats, and then the bearing seats are detachably installed on the installation pads through a bolt fastening assembly. One end of the rotating shaft of the main driving wheel 201 extending out of the bearing seat is installed with a synchronous belt driven wheel, and a driving unit 400 (stepping motor) is detachably installed on the upper surface of the installation top plate 111. The output end of the driving unit 400 is installed with a synchronous belt driving wheel. The synchronous belt driving wheel and the synchronous belt driven wheel are driven by a synchronous belt to transmit the output power of the stepping motor to the main driving wheel 201. Thus, when clamping the cable, the climbing robot is driven to move on the cable through the frictional force between the main driving wheel 201 and the cable.

[0032] In this embodiment, a main drive wheel 201 is symmetrically installed at both ends (axial direction of the cable) of the mounting top plate 111 of the upper frame 101, that is, two main drive wheels 201 are installed at both ends of the mounting top plate 111, thereby effectively enhancing the contact force between the climbing robot and the cable, and the front and rear main drive wheels 201 are driven simultaneously, so that the movement of the climbing robot on the cable is smoother. Here, the two main drive wheels 201 can be synchronously driven by a set of drive units 400, or can be driven separately by two independent drive units 400. When two independent drive units 400 are used for separate driving, the two independent drive units 400 are respectively arranged at both ends of the mounting top plate 111, so that the center of gravity of the climbing robot is close to the middle, so that the climbing robot has a better force bearing condition with the cable in the working state.

[0033] In the embodiment of the present application, a clamping wheel 202 is installed on the top surface of the mounting base plate 112 of the lower frame 102. Specifically, the clamping wheel 202 is rotatably mounted on the lower frame 102 through a clamping wheel frame 203; one end of the clamping wheel frame 203 is rotatably mounted on the lower frame 102, and the other end of the clamping wheel 202 is rotatably mounted. Then, the rotation of the clamping wheel frame 203 around the axis of rotation connection with the lower frame 102 can drive the clamping wheel 202 to rotate, so that the relative distance of the clamping wheel 202 with respect to the main driving wheel 201 can be adaptively adjusted according to the radial size of the cable.

[0034] In this embodiment, the clamping wheel frame 203 includes two parallel rotating links 213 and a tension spring 223. Among them, one end of the two parallel rotating links 213 is respectively symmetrically rotated and installed on the upper surface of the mounting base plate 112 of the lower frame 102 along the second direction, and the other end of the two parallel rotating links 213 (between the two rotating links 213) is rotationally installed on the clamping wheel 202, and then, the clamping wheel 202 moves together with the rotation of the rotating links 213 about the rotation connection axis with the lower frame 102.

[0035] Here, the adaptive adjustment of the relative distance of the clamping wheel 202 relative to the main driving wheel 201 is achieved through a tension spring 223, one end of which is connected to the middle part of the rotating link 213 and the other end is connected to the mounting top plate 111 of the lower frame 102. The contraction of the tension spring 223 drives the rotating link 213 to have a relative movement tendency toward the cable about the connection axis between the rotating link 213 and the lower frame 102, so that the clamping wheel 202 clamps the cable.

[0036] In a specific example, two parallel rotating links 213 are connected through a wheel frame shaft, that is, both ends of the wheel frame shaft are detachably mounted on the middle of the two parallel rotating links 213; further, one end of the tension spring 223 is connected to the wheel frame shaft, and the other end is connected to the middle of the mounting base 112. Further, there are two tension springs 223, and the two tension springs 223 are arranged in parallel close to the two parallel rotating links 213, so that the clamping wheel frame 203 has a more uniform force condition.

[0037] Here, the rotating connecting rod 213 is connected to the mounting base 112 through a mounting base. The rotating connecting rod 213 is rotatably mounted on the mounting base, and the mounting base is detachably connected to the mounting base 112 through a bolt fastening assembly. At the same time, the tension spring 223 is also connected to the mounting base 112 through another mounting base, wherein the mounting base matched with the tension spring 223 is detachably mounted on the mounting pad located on the mounting base 112 through a bolt fastening assembly. When two tension springs 223 are used to act on the clamping wheel frame 203, a wheel seat shaft is arranged between two mounting bases (matched with the tension spring 223) symmetrically arranged along the second direction, and the two tension springs 223 are respectively connected to the wheel seat shaft. In this embodiment, the connection between the tension spring 223 and the wheel frame shaft and the wheel seat shaft respectively limits the displacement of the two ends of the tension spring 223 along the second direction through a retaining ring, so as to effectively avoid the deviation of the tension spring 223 and avoid the tension spring 223 from generating an eccentric load on the clamping wheel frame 203.

[0038] In the present application, the two clamping wheels 202 are respectively mounted on the mounting base plate 112 of the lower frame 102 through two sets of clamping wheel frames 203. The two sets of clamping wheel frames 203 are symmetrically arranged at both ends of the lower frame 102 to drive the two clamping wheels 202 to have a tendency to move toward each other, so that the cable is clamped under the cooperation of the two clamping wheels 202 and the main driving wheel 201. When two sets of independent driving units 400 are used to drive the two main driving wheels 201, the two main driving wheels 201 are respectively arranged opposite to the two clamping wheels 202, so that the cable has a better force-bearing condition.

[0039] After the main driving wheel 201 and the clamping wheel 202 clamp the cable, the main driving wheel 201 is driven to rotate by the driving unit 400 to realize the movement of the climbing robot on the cable. Among them, the main driving wheel 201 and the clamping wheel 202 are not conical structures, so that when the cable is clamped, automatic centering can be achieved during the walking process, so that the climbing robot always moves along the cable axis, effectively avoiding deviation.

[0040] In the embodiment of the present application, the visual inspection module 301 is used to detect the surface defects of the cable. The visual inspection module 301 includes: an image inspection bracket and at least three visual inspection cameras, the image inspection bracket is installed on the head of the main bracket, and at least three claws are evenly distributed along the circumference, and three visual inspection cameras are arranged one by one on at least three claws, so that the imaging range of the three visual inspection cameras covers the cable surface along the circumference, thereby, by at least three visual inspection cameras covering the cable surface along the circumference to image, the circumferential surface defects of the cable are detected without omission.

[0041] In the embodiment of the present application, the magnetic flux leakage detection module 302 is used to detect the internal defects of the cable. The magnetic flux leakage detection module 302 includes: a magnetic detection bracket 312, an excitation device 322 and a detection device 332; the magnetic detection bracket 312 is installed at the tail of the main frame 100, and the excitation device 322 is a ring structure, which is installed on the magnetic detection bracket 312 close to the main frame 100, and is used to magnetize the internal steel wire of the cable. Specifically, a permanent magnet is arranged in the excitation device 322. When the cable passes through the center of the ring structure of the excitation device 322, a uniform magnetic field is formed inside the cable under the action of the permanent magnet, so as to magnetize the steel wire inside the cable.

[0042] The ring-shaped detection device 332 is installed on the magnetic detection bracket 312 in parallel with the excitation device 322 and away from the main frame 100, and is used to detect magnetic defects of the magnetized steel wire inside the cable. The detection device 332 includes: a detection mounting plate and a plurality of Hall sensors. The detection mounting plate and the excitation device 322 are installed on the magnetic detection bracket 312; the plurality of Hall sensors are evenly distributed on the detection mounting plate along the circumference to realize the magnetic defect detection of the magnetized steel wire inside the cable. When the detection device passes through the damaged or defective parts inside the cable, due to the change in the magnetic permeability of the damaged or defective parts, part of the magnetic flux will leak into the air to form a leakage magnetic field. The Hall sensor captures this leakage magnetic change signal and converts it into an electrical signal to detect the magnetic defects inside the cable, such as broken wires, rust, etc.

[0043] The data acquired by the visual detection module 301 and the magnetic flux leakage detection module 302 are exchanged through the data communication unit installed on the main frame 100 and transmitted to the data processing unit, which judges the defects and damage of the cable according to the received cable surface data and internal data. Among them, the data communication unit is installed on the mounting top plate 111 of the upper frame 101 and is located between the two drive units 400; at the same time, a main control unit is also arranged between the two drive units 400, and the control program of the climbing robot is deployed in the main control unit to realize the self-movement and detection of the climbing robot. During the movement of the climbing robot, the real-time movement of the climbing robot is monitored by multiple position, posture, speed and other sensors installed on the main frame 100, and the monitoring data is transmitted to the main control module by the sensor, and the main control module autonomously adjusts the position, posture, speed and other aspects of the climbing robot in real time according to the control program.

[0044] Here, data storage, data processing and other unit modules can also be deployed on the main frame 100 of the climbing robot. The data storage unit can be used to store the data collected by the climbing robot, and the data processing unit can be used to perform noise filtering, signal enhancement, image recognition and other operations on the collected data, so as to realize the identification and judgment of cracks, corrosion, wear and tear on the cable surface and defects such as broken wires and rust inside the cable.

[0045] When the climbing robot of any of the above-mentioned embodiments is used to simultaneously detect surface defects and internal defects of the cable, first, before the detection operation begins, the climbing robot is assembled, including installing the clamping walking unit 200, the cable detection unit 300, the drive unit 400, the data communication unit, the data storage unit, the power supply, the sensor, etc. on the main frame 100, and each part is inspected to ensure that it can work normally; then, the upper and lower parts of the main frame 100 are disassembled, and symmetrically wrapped around the two sides of the cable, and the upper and lower parts of the main frame 100 are pushed toward the center of gravity of the cable until the main drive wheel 201 and the clamping wheel 202 clamp the cable, and the appropriate adjustment through hole is selected to fasten the upper and lower parts to complete the clamping of the climbing robot on the cable to be detected.

[0046] After the climbing robot is clamped on the cable to be detected, the detection unit and the sensor are initialized, and the moving path and detection parameters of the climbing robot are set in the main control unit according to the actual situation of the cable; then, the climbing robot is started, and the climbing robot walks autonomously on the cable, while obtaining the image of the cable surface through the visual detection module 301, and obtaining the magnetic field change inside the cable through the magnetic leakage detection module 302, and the obtained image and magnetic field change data are transmitted to the data storage and data processing unit in real time through the data communication unit; the data processing unit performs denoising and signal enhancement on the magnetic field change data of the cable, and performs edge detection, morphological processing, image recognition and other operations on the collected image, and then identifies and judges the type, location and severity of the surface defects and internal defects of the cable. Finally, after completing the full-length detection of the cable, the climbing robot automatically returns to the starting position; or, after completing the detection of the set area, other cable areas are detected. In addition, the detection data can also be transmitted to other terminals through the data communication module to realize parallel storage and processing of data, etc., for analysis, decision-making and maintenance of the cable.

[0047] The climbing robot for cable defect detection can simultaneously detect the surface defects and internal defects of the cable. After obtaining the surface image data and magnetic flux leakage signal data of the cable, the cable defect analysis program deployed in the data processing unit can be used to simultaneously analyze the surface defects and internal defects of the cable. Figure 7 As shown, the detection method for cable defect detection deployed in the data processing unit includes: Step 101: perform image enhancement processing on the acquired surface image of the cable, and extract the surface defect characteristics of the cable based on the Canny edge detection algorithm and the pre-built composite deep learning model; and perform denoising processing on the collected leakage magnetic signal of the cable, and obtain the leakage magnetic defect characteristics of the cable based on the spectrum analysis method.

[0048] In the present application, when processing the surface image acquired by the climbing robot and extracting the surface defect features of the cable, the edge information in the surface image of the cable acquired by the climbing robot is extracted by the Canny edge detection algorithm, and the image edge is found by calculating the image gradient, and the image is refined. Specifically, firstly, based on the contrast-limited adaptive histogram equalization method, the surface image after Gaussian filtering and denoising is enhanced to obtain a surface enhanced image of the cable.

[0049] Here, the surface image is denoised and smoothed by Gaussian filtering to make the details in the image clearer and improve the usability and visual quality of the image. After the smoothed image is obtained by Gaussian filtering, the image is further enhanced by the histogram equalization method to optimize the visual effect of the image, improve the image contrast, and generate a surface enhanced image. Specifically, the number of pixels at each gray level in the smoothed image is first counted to obtain the gray distribution histogram of the image, and the cumulative probability distribution of the image is calculated based on the gray distribution histogram to obtain the cumulative frequency of the corresponding gray value; then, the gray value of the smoothed image is mapped to a new gray value range by the CDF method, so that the pixel values ​​are evenly distributed in the entire gray range; finally, the gray value in the smoothed image is replaced by the mapped gray value to generate a surface enhanced image with higher contrast.

[0050] Then, the cable surface enhancement image is gradient calculated, and the edge redundant pixels are removed from the obtained gradient image based on the non-maximum suppression method. Specifically, the Sobel operator is used to convolve the surface enhancement image to obtain the horizontal gradient of the image. and the vertical gradient , and according to the formula: Determine the gradient strength of a pixel in a gradient image and the gradient direction .

[0051] Then, the edge of the gradient image is processed by performing non-maximum suppression on the gradient image. The gradient direction is used to determine the direction of each pixel when performing neighborhood comparison, that is, when performing non-maximum suppression, the neighboring pixels of the current pixel are reversely selected according to the gradient, and the gradient strength in this direction is compared. The gradient strength of each pixel is used to determine whether to retain the pixel. Only when the gradient strength of the pixel is greater than the gradient strength of the neighboring pixels along the gradient direction, the pixel is retained as the edge point of the image.

[0052] Among them, after determining the gradient direction of each pixel in the gradient image, the neighborhood of each pixel is divided into two parts along the gradient direction (i.e., the front and back two neighborhood pixels) according to the gradient direction of the pixel; then compare the gradient strength of the current pixel with the gradient strength of the neighborhood pixels. If the gradient strength of the current pixel is greater than the gradient strength of its two neighborhood pixels, the current pixel is retained; if the gradient strength of the current pixel is less than the gradient strength of its two neighborhood pixels, the current pixel is suppressed, that is, the pixel value of the current pixel is set to 0.

[0053] The gradient image is refined by non-maximum suppression, redundant edge pixels are removed, and the most significant edge pixels are retained to facilitate edge connection and defect location. In this application, the image with redundant edge pixels removed is edge detected and connected based on the double threshold method to obtain the edge image of the cable surface defect. Thus, the image with redundant edge pixels removed is edge detected by the double threshold method to determine the strength of the image edge and separate the strong edge, weak edge and non-edge area.

[0054] Specifically, the gradient intensities of pixels in the image with edge redundant pixels removed are compared by using two preset intensity thresholds (a first intensity threshold and a second intensity threshold, and the first intensity threshold is greater than the second intensity threshold), pixels with gradient intensities higher than the first intensity threshold are regarded as strong edge pixels and marked as edge points of the image; pixels with gradient intensities lower than the second intensity threshold are regarded as non-edge pixels, and the non-edge pixels are suppressed or removed.

[0055] Pixels whose gradient intensity is between the first intensity threshold and the second intensity threshold are regarded as weak edge pixels. The gradient intensity of weak edge pixels is low and insufficient to form a clear edge independently. In the present application, an edge tracking method is adopted to scan along the gradient direction of the edge pixel, and check whether the neighborhood pixels of the edge pixel contain strong edge pixels. If the weak edge pixel is directly adjacent to a strong edge pixel, the weak edge pixel is marked as an edge point of the image, that is, marked as a valid edge and added to the edge of the image; if the weak edge pixel is not adjacent to the strong edge pixel, the weak edge pixel is considered to be noise or an incomplete edge, and the weak edge pixel is marked as an isolated edge pixel, and the weak edge pixel is removed to ensure the edge continuity and accuracy of the image, thereby obtaining an edge image of the cable surface defect.

[0056] After obtaining the edge image of the cable surface defect, the edge image is input into the composite deep learning model based on the convolutional neural network and the Transformer architecture for feature extraction, and the surface defect features of the cable are extracted from the edge image containing clear edge information. Specifically, the cable surface edge image containing clear edge information is input into the composite deep learning model based on the convolutional neural network and the Transformer architecture, and the convolutional neural network part extracts the local features of the image through multi-layer convolution kernel operations, such as edge texture patterns, geometric structures, etc. At the same time, the pooling layer is used to reduce the data dimension and enhance the stability of the extracted local features; through the Transformer module, the self-attention mechanism is used to capture the correlation relationship and global characteristics between different regions in the image, ensuring that the features not only reflect local details, but also cover global context information; then, the local and global features extracted by the convolutional neural network and the Transformer are integrated through deep learning, and a high-dimensional feature vector is generated to fully describe the shape, size and distribution of the cable surface defects. Finally, the extracted high-dimensional features, namely the surface defect features, are output for defect detection and classification.

[0057] When processing the magnetic flux leakage signal acquired by the climbing robot and obtaining the magnetic flux leakage defect characteristics of the cable, the collected magnetic flux leakage signal of the cable is denoised by wavelet transform and low-pass filtering. Specifically, the collected magnetic flux leakage signal is first subjected to discrete wavelet transform to decompose the magnetic flux leakage signal into low-frequency components and high-frequency components. The low-frequency component retains the main characteristics and trends of the signal, while the high-frequency component contains more noise information. In this process, an appropriate wavelet basis and decomposition layer number are selected to ensure that the decomposition result accurately expresses the signal characteristics.

[0058] Then, the noise in the high-frequency components is suppressed by setting a threshold (based on statistical methods such as VisuShrink calculation or empirical value determination) and applying a soft threshold or hard threshold method. Among them, the soft threshold method can smoothly adjust the components exceeding the threshold, while the hard threshold method directly sets the noise part less than the threshold to zero, ensuring that the high-frequency components after denoising retain the necessary detail features.

[0059] Next, the low-frequency components are further processed using a low-pass filter. By designing the filter parameters (such as the filter cutoff frequency and order), possible high-frequency residual noise is filtered out, while the smoothness of the signal is enhanced and the main trend information of the cable magnetic leakage signal is retained. Finally, the processed high-frequency and low-frequency components are subjected to an inverse wavelet transform to reconstruct the denoised signal, ensuring the overall integrity of the signal and significantly improving the signal-to-noise ratio, providing high-quality input data for subsequent spectrum analysis and feature extraction.

[0060] After the collected leakage magnetic signal of the cable is denoised, the denoised signal obtained by the denoising process is subjected to a fast Fourier transform based on the spectrum analysis method to obtain the distribution characteristics of the denoised signal at different frequencies, so as to obtain the leakage magnetic defect characteristics of the cable. Specifically, the denoised signal is first divided into several segments for spectrum analysis through the selected signal window to avoid frequency leakage; then, each segment of the signal is converted from the time domain to the frequency domain by applying the fast Fourier transform. In the frequency domain, the frequency components of the signal are expressed in the form of amplitude and phase. The corresponding spectrum diagram is obtained by calculating the Fourier transform of each segment of the signal, and the amplitude (intensity) distribution of the signal at each frequency is displayed through the spectrum diagram. Here, in order to remove the influence of noise, the spectrum diagram is smoothed, such as using a sliding window to smooth the amplitude, and the main frequency components in the signal are identified by observing the amplitude changes in the spectrum diagram.

[0061] The surface defects of the cable will cause obvious changes in the spectrum, especially the significant increase or change of the frequency components in the spectrum. For example, defects such as cracks and corrosion usually show specific peaks or change patterns in the frequency domain, so the frequency distribution characteristics of the signal can be extracted through the spectrum diagram. By extracting key signal features in the spectrum, such as frequency peak, angle, waveform factor, etc., it is helpful to identify possible defects in the signal; for example, the change of frequency peak indicates the presence of a certain type of defect on the surface or inside the cable. Finally, according to the distribution characteristics of the spectrum and the frequency change of the signal, combined with the known defect mode, by analyzing the amplitude, phase, frequency band and other information of the signal, the leakage magnetic defects in the cable can be identified and located.

[0062] Step S102: Input the surface defect features and magnetic leakage defect features of the cable into the generator of the generative adversarial network at the same time, fuse the surface defect features and magnetic leakage defect features, and obtain comprehensive defect data of the cable.

[0063] In the present application, in the generative adversarial network, the fusion of surface defect features and magnetic leakage defect features is achieved through feature splicing and weighted fusion. Specifically, after the surface defect features and magnetic leakage defect features of the cable are input into the generative adversarial network, the generator of the generative adversarial network performs feature splicing on the input surface defect features and magnetic leakage defect features, and directly merges the surface defect features and magnetic leakage defect features, that is, the surface defect features and magnetic leakage defect features are spliced ​​in the feature vector dimension according to the columns or rows of the feature vector to form a new feature vector. For example, the vector dimension of the surface defect feature is , the vector dimension of the leakage defect feature is ; When the surface defect features and the magnetic flux leakage defect features are concatenated according to the rows of the feature vector, the dimension of the new feature matrix is ; When the surface defect features and the magnetic flux leakage defect features are concatenated according to the columns of the feature vector, the dimension of the new feature matrix is .

[0064] After the surface defect features and magnetic flux leakage defect features are spliced ​​in the feature vector dimension, different weights are assigned to different features according to their importance, and the contribution of different features to the fusion result (comprehensive defect data) is adjusted to achieve weighted fusion of surface defect features and magnetic flux leakage defect features. In the weighted fusion process, each part (surface features and magnetic flux leakage features) of the new feature vector (the spliced ​​feature vector) will be assigned corresponding weights according to its importance, so as to adjust its contribution to the final comprehensive defect data in the fusion. Weighted fusion reflects the importance of features in weights, optimizes feature expression, and improves the accuracy of defect detection.

[0065] In the weighted fusion process, the initial weights are randomly generated first, and the weight values ​​of surface features and magnetic flux leakage features are preliminarily set. Subsequently, the weights of surface features and magnetic flux leakage features are automatically adjusted according to the discriminator results through back propagation through the generative adversarial network, so that the contribution of the two types of features to the fusion results matches the actual detection requirements. Specifically, the concatenated feature vectors are first The surface features of And leakage magnetic characteristics Assign weights to each and ; Then, according to the formula: Surface feature parts And leakage magnetic characteristics Perform weighted calculation to obtain the fused comprehensive feature vector In this process, the expression ability of fusion features can be improved through nonlinear changes, and the fused feature vector That is, comprehensive defect data, which contains key information of the cable’s surface defects and magnetic leakage defects, and provides input for subsequent defect type identification or quantitative analysis.

[0066] In this application, cable defect sample data are collected through cable fault detection (reporting, maintenance, etc.) in historical periods, including various defects of cables during long-term use marked by surface detection, including cracks, corrosion, fractures and other defect types, defect sizes, defect locations, etc., as well as internal defects of cables obtained by traditional detection methods (visual inspection, ultrasonic detection, magnetic flux leakage detection, X-ray, etc.).

[0067] Then, based on the discriminator of the generative adversarial network, the loss function, mean square error and cross entropy loss between the generated comprehensive defect data and the pre-acquired cable defect sample data are calculated respectively, the generated comprehensive defect data are evaluated, and the generator of the generative adversarial network is iteratively optimized according to the evaluation results. Specifically, the discriminator calculates the loss function, mean square error and cross entropy loss, judges the difference (loss error) between the generated comprehensive defect data and the defect sample data, and feeds back the judgment result to the generator; the generator performs adaptive iterative optimization according to the feedback information; and then, through the iterative optimization of the generator, the quality and accuracy of the generated comprehensive defect data are further improved.

[0068] In this process, the discriminator learns the characteristics of the defect sample data to determine whether the generated comprehensive defect data conforms to the common defect pattern of the cable. Specifically, the discriminator extracts the defect features (defect shape, size, distribution, edge features and signal spectrum characteristics) from the comprehensive defect data and compares them with the defect sample data. If the defect features extracted from the generated comprehensive defect data match the defect features in the defect sample data, the discriminator automatically determines that the generated comprehensive defect data conforms to the common defect pattern of the cable; otherwise, the discriminator automatically determines that the generated comprehensive defect data does not conform to the common defect pattern of the cable, and gives feedback results to optimize the generator.

[0069] The loss function, mean square error and cross entropy loss calculated by the discriminator on the comprehensive defect data produced characterize the difference between the generated comprehensive defect data and the defect sample data; the generator is iteratively optimized according to the feedback results of the discriminator to reduce the difference between the generated comprehensive defect data and the defect sample data and improve the quality of the generated comprehensive defect data.

[0070] When the generator receives the feedback result (loss error) from the discriminator, the gradient of each parameter inside the generator is calculated through the back propagation algorithm. After the error of each neural network layer is calculated based on the loss error, the calculated error of each neural network layer is transferred layer by layer through the chain rule. The generator adjusts the parameter weights and biases based on this gradient information, thereby optimizing the generation process of comprehensive defect data.

[0071] In each training, the generator will adjust the generated comprehensive defect data according to the feedback from the discriminator, so that it is closer to the defect sample data in terms of shape, size, distribution, etc. As the training continues, the generator continuously adjusts its own generation measurement so that the generated comprehensive defect data can be closer to the common pattern of cable defects. At the same time, the discriminator will gradually improve the judgment accuracy according to the optimization of the generator. Ultimately, the comprehensive defect data generated by the generator will be able to pass the high standard detection of the discriminator and reach a level closest to the defect sample data.

[0072] Step S103: acquiring the depth information of the cable according to the comprehensive defect data, and generating a three-dimensional point cloud of the cable defects, so as to simultaneously acquire the surface defects and internal defects of the cable.

[0073] In this application, the edges of cable surface defects and internal defects are usually shown as high-contrast areas in the image, such as cracks and scratches. The depth information of the edge points can be obtained from the corresponding magnetic leakage signal. The change of the magnetic leakage signal of the cable can effectively reflect the depth and position of the defect. Then, through wavelet transform and spectrum analysis technology, the characteristics such as signal amplitude change and frequency response are extracted from the magnetic leakage signal of the cable. These characteristics reflect the different characteristics of defects inside and outside the cable and can provide depth information of the defects.

[0074] In the two-dimensional image coordinate system In the process of combining the depth information in the magnetic flux leakage signal , transform these defect points into coordinates in three-dimensional space The location of each defect point is a point cloud, and all defect points together constitute a three-dimensional point cloud. The density of the point cloud represents the severity of the defect or the density of the defect, and the distribution range of the point cloud can reflect the expansion form of the defect.

[0075] Then, the geometric fitting RANSAC algorithm is used to fit the extracted 3D point cloud data into a 3D geometric model (such as sphere, cylinder, crack and other 3D defect models) to describe the shape of the defect in the cable. Through the 3D defect model, key areas (such as deep cracks that may cause fatigue fracture, local fatigue damage, etc.) are identified, the impact of defects on the cable structure is evaluated, and support for subsequent maintenance decisions is provided.

[0076] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0077] In addition, 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. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0078] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection, an electrical connection, or communication with each other; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0079] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0080] In the present invention, the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" mean that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0081] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A climbing robot for cable defect detection, characterized in that: For simultaneously detecting surface defects and internal defects of a cable, the climbing robot includes: A main body frame, which is a frame structure; A clamping and walking unit installed within the frame structure of the main body frame, including: at least one main driving wheel and at least two clamping wheels, and the main driving wheel and the clamping wheels can clamp a cable passing through both ends of the frame structure of the main body frame; A cable detection unit, including a visual detection module and a magnetic flux leakage detection module, installed at both ends of the main body frame, respectively used for detecting surface defects and internal defects of the cable; A driving unit installed on the frame structure of the main body frame, used to drive the main driving wheel to rotate, so as to drive the main body frame to move along the length direction on the cable.

2. The climbing robot for cable defect detection according to claim 1, characterized in that: The main body frame includes: an upper frame and a lower frame, At both ends of the upper frame, there are respectively arranged upper connecting frames in a 冂-shaped structure, and at both ends of the lower frame, there are respectively arranged lower connecting frames in a 凵-shaped structure adapted to the upper connecting frames, and the upper connecting frames and the lower connecting frames can be telescopically adjusted along a first direction; wherein, the first direction is the extending direction of the side plates of the upper connecting frame or the lower connecting frame; The main driving wheel is rotatably installed on the bottom surface of the upper frame, and the clamping wheels are installed on the top surface of the lower frame, and the relative distance between the clamping wheels and the main driving wheel can be adaptively adjusted according to the radial dimension of the cable.

3. The climbing robot for cable defect detection according to claim 2, characterized in that: The clamping wheels are rotatably installed on the lower frame through clamping wheel brackets, and the clamping wheel brackets include: rotating connecting rods and tension springs, One end of the rotating connecting rod is rotatably installed on the lower frame, and the other end is rotatably installed with the clamping wheel; One end of the tension spring is connected to the middle part of the rotating connecting rod, and the other end is connected to the lower frame, and is used to drive the rotating connecting rod to have a relative movement trend towards the cable around its connection axis with the lower frame, so that the clamping wheels clamp the cable; There are two groups of the clamping wheel brackets, and the two groups of clamping wheel brackets are symmetrically arranged at both ends of the lower frame to drive the two clamping wheels to have a trend of moving towards each other.

4. The climbing robot for cable defect detection according to claim 1, characterized in that: There are two main driving wheels, and the two main driving wheels are respectively arranged opposite to the two clamping wheels; And / or, the two main driving wheels are respectively connected to the output ends of the two driving units through synchronous belt drives; And / or, both the main driving wheels and the clamping wheels are in a spindle-shaped structure to clamp the cable.

5. The climbing robot for cable defect detection according to claim 1, characterized in that: The visual detection module includes: an image detection bracket and at least three visual detection cameras, the image detection bracket is installed at the head of the main body frame, and there are at least three claws evenly distributed along the circumferential direction, and three visual detection cameras are respectively arranged on the at least three claws in one-to-one correspondence, so that the imaging ranges of the three visual detection cameras cover the surface of the cable along the circumferential direction; The magnetic flux leakage detection module includes: a magnetic detection bracket, an exciting device and a detecting device; The magnetic detection bracket is installed at the tail of the main body frame; The exciting device is in a ring structure, installed on the magnetic detection bracket close to the main body frame, and is used to magnetize the internal steel wires of the cable; wherein, the cable passes through the center of the ring structure of the exciting device; The detection device is an annular structure, installed on the magnetic detection bracket in parallel with the excitation device and away from the main frame, and is used for detecting magnetic defects of the magnetized steel wire inside the cable.

6. A detection method for cable defect detection, characterized in that: The climbing robot for cable defect detection according to any one of claims 1 to 5 is used to simultaneously perform surface defect detection and internal defect detection on the cable, and the detection method comprises: Step S101, performing image enhancement processing on the acquired surface image of the cable, and extracting surface defect features of the cable based on the Canny edge detection algorithm and a pre-built composite deep learning model; as well as, De-noising the collected cable magnetic flux leakage signal, and obtaining the cable magnetic flux leakage defect characteristics based on the spectrum analysis method; Step S102, inputting the surface defect features and the magnetic flux leakage defect features of the cable into a generator of a generative adversarial network at the same time, fusing the surface defect features and the magnetic flux leakage defect features to obtain comprehensive defect data of the cable; Step S103: acquiring depth information of cable defects according to the comprehensive defect data, and generating a three-dimensional point cloud of the cable defects, so as to simultaneously acquire surface defects and internal defects of the cable.

7. The detection method for cable defect detection according to claim 6, characterized in that: Step S101 includes: Based on the contrast-limited adaptive histogram equalization method, the surface image after Gaussian filtering and denoising is enhanced to obtain the surface enhanced image of the cable. Performing gradient calculation on the surface enhancement image of the cable, removing edge redundant pixels from the obtained gradient image based on a non-maximum suppression method, and performing edge detection and connection on the image from which the edge redundant pixels have been removed based on a double threshold method, so as to obtain an edge image of the cable surface defects; The edge image is input into a composite deep learning model based on a convolutional neural network and a Transformer architecture to extract surface defect features of the cable.

8. The detection method for cable defect detection according to claim 6, characterized in that: In step S101, The collected cable magnetic leakage signal is de-noised by wavelet transform and low-pass filtering in turn; Based on the spectrum analysis method, the denoised signal obtained by the denoising process is subjected to fast Fourier transform to obtain the distribution characteristics of the denoised signal at different frequencies, so as to obtain the leakage magnetic defect characteristics of the cable.

9. The detection method for cable defect detection according to claim 6, characterized in that: In step S102, The generator of the generative adversarial network sequentially performs feature splicing and weighted fusion on the surface defect features and the magnetic flux leakage defect features to obtain the comprehensive defect data.

10. The detection method for cable defect detection according to claim 6, characterized in that: Also includes: Based on the discriminator of the generative adversarial network, the loss function, mean square error and cross entropy loss between the generated comprehensive defect data and the pre-acquired cable defect sample data are calculated respectively to evaluate the generated comprehensive defect data, and the generator of the generative adversarial network is iteratively optimized according to the evaluation results.

Images