A method of welding a cable metal sheath, a cable, an apparatus, a device and a storage medium

Abstract

The application relates to a cable metal sheath welding method, a cable, a device, equipment and a storage medium. The method comprises the following steps: obtaining welding process parameters in the case that metal strip material wrapped outside a cable core is conveyed to a preset welding area, performing welding treatment on the metal strip material according to the welding process parameters, and forming a metal sheath welding seam; collecting welding electrical parameters in the welding process and a welding seam image of the metal sheath welding seam; detecting whether the metal sheath welding seam has welding defects according to the welding seam image and the welding electrical parameters, and obtaining welding defect detection result data; in the case that the welding defect detection result data represents that the metal sheath welding seam has welding defects, finding out welding compensation process parameters corresponding to the welding defects from preset welding process parameters, and performing welding compensation on the metal sheath welding seam according to the welding compensation process parameters. The method is beneficial to improving the manufacturing quality of the cable metal sheath.

Description

Technical Field

[0001] This application relates to the field of cable technology, and in particular to a method for welding the metal sheath of a cable, a cable, an apparatus, equipment, and a storage medium. Background Technology

[0002] High-voltage cables, especially those with smooth aluminum sheaths, are widely used due to their advantages in transmission capacity, weight, and corrosion resistance. Corrugated aluminum sheathed cables are prone to failure due to the erosion of their buffer layer. While using smooth aluminum sheaths can improve the electric field distribution, it places higher demands on the thermal conductivity, water resistance, and interface bonding of the buffer layer material.

[0003] However, the accuracy of welding defect detection in aluminum sheaths is low in related technologies, leading to an increased rate of missed defects, which affects the quality of aluminum sheaths and consequently their mechanical strength, sealing performance, and operational safety. Summary of the Invention

[0004] Therefore, it is necessary to provide a cable metal sheath welding method, cable, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the manufacturing quality of cable metal sheaths, addressing the aforementioned technical problems.

[0005] In a first aspect, this application provides a method for welding the metal sheath of a cable, comprising:

[0006] When the metal strip covering the cable core is conveyed to the preset welding area, the welding process parameters are obtained, and the metal strip is welded according to the welding process parameters to form the metal sheath weld.

[0007] Acquire welding electrical parameters and weld images of the metal sheath weld during the welding process;

[0008] Based on weld images and welding electrical parameters, the presence of welding defects in the metal sheath weld is detected, and welding defect detection result data is obtained.

[0009] When the welding defect detection results indicate that there are welding defects in the metal sheath weld, the welding compensation process parameters corresponding to the welding defects are found from the preset welding process parameters, and the metal sheath weld is compensated according to the welding compensation process parameters.

[0010] Secondly, this application also provides a cable metal sheath welding apparatus, comprising:

[0011] The welding module is used to obtain welding process parameters when the metal strip covering the cable core is conveyed to the preset welding area, and to perform welding on the metal strip according to the welding process parameters to form a metal sheath weld.

[0012] The parameter acquisition module is used to collect welding electrical parameters and weld images of the metal sheath weld during the welding process.

[0013] The defect detection module is used to detect whether there are welding defects in the metal sheath weld based on the weld image and welding electrical parameters, and to obtain welding defect detection result data;

[0014] The welding compensation module is used to find the welding compensation process parameters corresponding to the welding defects from the preset welding process parameters when the welding defect detection results indicate that there are welding defects in the weld of the metal sheath, and to perform welding compensation on the weld of the metal sheath according to the welding compensation process parameters.

[0015] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in any of the above embodiments of the cable metal sheath welding method.

[0016] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in any of the above embodiments of the cable metal sheath welding method.

[0017] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps in any of the above embodiments of the cable metal sheath welding method.

[0018] The aforementioned cable metal sheath welding method, apparatus, computer equipment, computer-readable storage medium, and computer program product firstly acquire welding process parameters when the metal strip covering the cable core is conveyed to a preset welding area, and then weld the metal strip according to the welding process parameters to form a metal sheath weld. Secondly, welding electrical parameters and weld images of the metal sheath weld are collected during the welding process. Thirdly, unlike related technologies that involve manual inspection and stop-to-weld repair after the aluminum sheath is formed, this method detects whether there are welding defects in the metal sheath weld based on the weld image and welding electrical parameters, and obtains welding defect detection result data. Thus, surface morphology detection is performed through images, auxiliary detection is performed through electrical parameters, and real-time defect detection is performed through multi-dimensional parameter integration, improving the accuracy and timeliness of defect detection. Finally, if the welding defect detection result data indicates the presence of welding defects in the metal sheath weld, the welding compensation process parameters corresponding to the welding defects are found from the preset welding process parameters, and welding compensation is performed on the metal sheath weld according to the welding compensation process parameters. In this way, defect detection of the metal sheath is integrated into the manufacturing process of the metal sheath, and the quality control point is moved from "outcome inspection" to "process control". This enables real-time defect detection and timely defect repair welding, forming a closed-loop manufacturing process for welding, inspection and repair welding of cable aluminum sheaths. This significantly reduces the rate of missed detection and rework, thereby improving the manufacturing quality of the metal sheath. Furthermore, while ensuring high quality, it is conducive to improving production continuity to meet the stable production needs of long-length and high-requirement cables. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is an application environment diagram of the cable metal sheath welding method in one embodiment;

[0021] Figure 2 This is a flowchart illustrating a cable metal sheath welding method in one embodiment;

[0022] Figure 3 This is a flowchart illustrating the cable metal sheath welding method in another embodiment;

[0023] Figure 4 This is a flowchart illustrating the cable metal sheath welding method in yet another embodiment;

[0024] Figure 5 This is a flowchart illustrating the cable metal sheath welding method in another embodiment;

[0025] Figure 6 This is a cable structure diagram from one embodiment;

[0026] Figure 7 This is a cable structure diagram from another embodiment;

[0027] Figure 8 This is a structural block diagram of a cable metal sheath welding device in one embodiment;

[0028] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0030] In the welding process of aluminum sheaths for cables, on the one hand, traditionally rolled and welded aluminum sheaths are prone to uneven thickness and weld defects (such as incomplete welds and missed welds), directly affecting the mechanical strength, sealing performance, and long-term operational safety of the aluminum sheath. On the other hand, controlling the stability of large-section cable production is difficult. As a core process, aluminum sheath welding relies on manual sampling in traditional production methods, making it difficult to detect and address latent defects in real time. Existing online monitoring systems mostly "only alarm, do not take action," requiring shutdown for maintenance or switching to backup equipment after a defect is detected, severely impacting production continuity and efficiency. Therefore, there is a lack of a closed-loop intelligent process for dual-welding gun welding that can identify, accurately locate, and automatically repair defects in real time on the production line.

[0031] The cable metal sheath welding method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, the first welding system 102 and the second welding system 104 are respectively connected to the control terminal 106. Specifically, when the metal strip covering the cable core is conveyed to the preset welding area, the control terminal 106 acquires welding process parameters, controls the first welding system 102 to weld the metal strip according to the welding process parameters to form a metal sheath weld, then acquires the welding electrical parameters and the weld image of the metal sheath weld during the welding process, then detects whether there are welding defects in the metal sheath weld based on the weld image and welding electrical parameters, and obtains welding defect detection result data. Finally, if the welding defect detection result data indicates that there are welding defects in the metal sheath weld, the welding compensation process parameters corresponding to the welding defects are found from the preset welding process parameters, and the second welding system 104 is controlled to perform welding compensation on the metal sheath weld according to the welding compensation process parameters.

[0032] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle systems, and projection devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. The server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0033] In one exemplary embodiment, such as Figure 2 As shown, a method for welding the metal sheath of a cable is provided, which can be applied to... Figure 1 Taking control terminal 106 as an example, the explanation includes the following steps (hereinafter referred to as S): S100 to S400. Wherein:

[0034] S100: When the metal strip covering the cable core is conveyed to the preset welding area, the welding process parameters are obtained, and the metal strip is welded according to the welding process parameters to form a metal sheath weld.

[0035] In practical applications, to improve welding and inspection efficiency, defect detection functions can be integrated into the metal sheath manufacturing production line. A traction machine continuously conveys the metal strip covering the cable core, and online defect detection is performed during the automated conveying of the metal strip. Therefore, a specific space can be pre-defined as the welding area on the manufacturing production line.

[0036] In this embodiment, high-frequency induction welding is used for the welding process. The welding process parameters may include the control parameters of the high-frequency welding host, such as the welding head power and frequency. The welding process parameters may also include the traction speed of the traction machine and the flow rate of the shielding gas. The metal strip used includes, but is not limited to, aluminum alloy strip or copper alloy strip.

[0037] For example, the control terminal may respond to the input data and obtain the set welding head power of 60kW, frequency of 220kHz, traction speed of 3.0m / min, and argon flow rate of 20L / min.

[0038] In practice, the precision-cut aluminum alloy strip is wrapped around the cable core (i.e., the core with the water-blocking buffer layer already wrapped around it) and pulled to the preset welding area by a traction machine. According to the welding process parameters, the first welding system (such as a high-frequency induction welding device) is controlled to weld the longitudinal joint, so that the butt joint edges are rapidly heated to a molten state under the skin effect and proximity effect of the high-frequency current, and a strong molecular bond is achieved under pressure to form a continuous weld. It is understood that the number of the first welding system can be one or more, determined according to the actual production needs, and is not limited here.

[0039] S200 collects welding electrical parameters and weld images of the metal sheath weld during the welding process.

[0040] Among them, welding electrical parameters may include, but are not limited to, welding current, voltage and wire feed speed during the welding process.

[0041] In this embodiment, defect detection is integrated into the manufacturing process, and the metal sheath manufacturing operation area is divided into multiple areas, such as welding area, monitoring area, laser marking area and welding compensation area. Thus, the operation is carried out in sequence through online welding, real-time monitoring, defect detection and adaptive repair welding.

[0042] For the monitoring area, laser cameras and electrical sensors can be pre-deployed to acquire weld images and welding electrical parameters, respectively. Specifically, the first welding system can send a synchronous trigger signal to the control terminal after completing a preset length (e.g., 10 cm) of weld. The control terminal controls the linear array camera to acquire weld images at a preset line frequency. Simultaneously, a high-precision encoder records the cable travel length, and all acquired data is aligned to the same physical position. For example, the encoder records the cable travel length in real time, and based on the cable travel length, each sampling point in the weld image and each sampling point in the welding electrical parameters is labeled with a corresponding position, so that the image position, welding electrical parameter time, and travel speed correspond.

[0043] The S300 detects welding defects in the metal sheath weld based on weld images and welding electrical parameters, and obtains welding defect detection result data.

[0044] The welding defect detection results data may include whether there are defects in the metal sheath weld, the detection timestamp, and the cable travel length. Welding defects include, but are not limited to, incomplete welds, porosity, cracks, and oxidation.

[0045] In this embodiment, welding defect detection is performed using multi-dimensional data. Specifically, weld images and welding electrical parameters can be used as inputs to call a trained welding defect detection model to automatically determine whether welding defects exist in the metal sheath weld. The trained welding defect detection model can be obtained by iteratively training a pre-trained initial defect detection model based on historical weld images and historical welding electrical parameters. Specifically, historical weld images and historical welding electrical parameters are collected, and the historical weld images are labeled, including whether they are defect-free, have incomplete welds, porosity, cracks, or oxidation.

[0046] The initial pre-trained defect detection model is built upon a combination of two pre-trained models: a model for defect detection in weld images, based on EfficientNet-B3, outputs the probability of each labeled defect type; and a model for detecting mechanical defects related to welding electrical parameters, based on a Long Short-Term Memory (LSTM) network and a Recurrent Neural Network (RNN), extracts statistical features (mean, variance, trend) of the welding electrical parameters. The probability of a welding defect is analyzed based on these statistical features. The outputs of the two models are then fused through a fusion channel to obtain the defect detection result data. For example, if the confidence level of the defect type corresponding to the weld image is high, the defect detection result data is output based on the defect detection result corresponding to the weld image; otherwise, the defect detection result data is output based on the probability corresponding to the welding parameters.

[0047] In other embodiments, during model training, the annotations may further include defect level (characterizing the degree of defect) and defect size (length and width), so that the output of the model for defect detection of weld images also includes defect level and defect size. The defect detection result data also includes defect level and defect size.

[0048] In other embodiments, edge detection can be performed on the weld image, and the weld region in the weld image can be located based on the edge detection results. Subsequently, weld morphology features of the weld region can be extracted, such as weld width and weld grayscale. Welding electrical features can be extracted from welding electrical parameters, such as average current, average voltage, and traction speed.

[0049] Furthermore, based on the weld morphology, welding electrical characteristics, and preset defect judgment rules, the presence of welding defects in the metal sheath weld is detected. Specifically, if there is a sudden change in weld grayscale, it indicates the presence of a crack in the weld; if the average grayscale value of the weld is lower than a preset average threshold, it indicates the presence of oxidation in the weld; and if the proportion of weld grayscale values ​​lower than the preset average threshold is greater than a preset proportion threshold, it indicates the presence of porosity in the weld.

[0050] Furthermore, if no welding defects are detected through weld morphology characteristics, further inspection based on welding electrical characteristics is required. Specifically, if the average current is lower than a preset average current threshold and the welding current does not change abruptly, it indicates that the weld may have a cold weld; if the current fluctuation amplitude is greater than a preset current fluctuation amplitude threshold, it indicates that there is porosity in the weld. Understandably, when the corresponding defect type is detected, it is determined that a welding defect exists.

[0051] While detecting welding defects in the metal sheath weld, a high-precision encoder records the cable travel length, and a laser marking unit is used to enable non-contact, precise positioning and marking of the identified defect locations.

[0052] S400: When the welding defect detection results indicate that there is a welding defect in the metal sheath weld, the welding compensation process parameters corresponding to the welding defect are found from the preset welding process parameters, and welding compensation is performed on the metal sheath weld according to the welding compensation process parameters.

[0053] Among them, the welding compensation process parameters characterize the welding process parameters used for secondary welding.

[0054] In practical applications, a welding process parameter knowledge base for welding compensation can be constructed by pre-associating known welding defects with corresponding welding process parameters for subsequent retrieval. Specifically, a defect sample matrix can be built, with defect type, defect level, and defect size as a combination. At least 10 samples can be built for each defect type (considering material batch differences). Subsequently, for each type of defect, different combinations of welding process parameters are tested and constructed, including the value ranges corresponding to different types of welding process parameters. For example, the welding current range is 80–150 A; the welding speed (traction speed) range is 2–8 mm / s; the argon flow rate range is 10–20 L / min; the pulse frequency range is 1–10 Hz; and the welding torch defocusing amount range is ±0.5 mm.

[0055] Next, a mapping table is established to obtain the preset welding machine process parameters corresponding to different defect types, defect levels, and defect sizes.

[0056] In specific implementation, when the welding defect detection results indicate the presence of welding defects in the metal sheath, the system first searches a preset mapping table by defect type to find a matching defect type, thereby locating the corresponding range of welding process parameters. Further, based on the defect size and defect level, it searches the range for matching welding process parameters. Finally, the welding compensation process parameters corresponding to the welding defect are obtained. The defect location is determined based on the recorded cable travel length, and the second welding system is controlled to perform secondary welding on the defect according to the defect location and the welding compensation process parameters. For example, the second welding system may include a multi-axis movable compensation welding head. In response to a repair welding command, the second welding system moves to the defect location to perform secondary welding. It is understood that the second welding system may include one or more compensation welding heads. When the second welding system includes multiple compensation welding heads, each compensation welding head may be assigned its own compensation welding area. The compensation welding area may be obtained by dividing the conveying device into regions, thereby controlling the corresponding compensation welding head to perform compensation welding based on the compensation welding area where the defect location is located. In other embodiments, the first welding system may also be controlled to perform compensation welding.

[0057] In the aforementioned cable metal sheath welding method, firstly, when the metal strip covering the cable core is conveyed to the preset welding area, welding process parameters are acquired, and the metal strip is welded according to the welding process parameters to form a metal sheath weld. Secondly, welding electrical parameters and weld images of the metal sheath weld are collected during the welding process. Thirdly, unlike the methods in related technologies that involve manual inspection and shutdown for repair welding after the aluminum sheath is formed, the presence of welding defects in the metal sheath weld is detected based on the weld images and welding electrical parameters, and welding defect detection result data is obtained. Thus, surface morphology detection is performed through images, auxiliary detection is performed through electrical parameters, and real-time defect detection is performed through the integration of multiple parameters, improving the accuracy and timeliness of defect detection. Finally, if the welding defect detection result data indicates the presence of welding defects in the metal sheath weld, the welding compensation process parameters corresponding to the welding defects are found from the preset welding process parameters, and welding compensation is performed on the metal sheath weld according to the welding compensation process parameters. In this way, defect detection of the metal sheath is integrated into the manufacturing process of the metal sheath, and the quality control point is moved from "outcome inspection" to "process control". This enables real-time defect detection and timely defect repair welding, forming a closed-loop manufacturing process for welding, inspection and repair welding of cable aluminum sheaths. This significantly reduces the rate of missed detection and rework, thereby improving the manufacturing quality of the metal sheath. Furthermore, while ensuring high quality, it is conducive to improving production continuity to meet the stable production needs of long-length and high-requirement cables.

[0058] In an exemplary embodiment, the method further includes S510 to S520, wherein:

[0059] S510, when the welding defect detection results indicate that there is a welding defect in the weld of the metal sheath, the defect type of the welding defect is identified based on the weld image.

[0060] In practice, edge detection can be performed on the weld image, and the weld region in the weld image can be located based on the edge detection results. Subsequently, the weld morphology features of the weld region can be extracted, such as weld width and weld grayscale.

[0061] Furthermore, based on the weld morphology, welding electrical characteristics, and preset defect judgment rules, the presence of welding defects in the metal sheath weld is detected. Specifically, if there is a sudden change in weld grayscale, it indicates the presence of a crack in the weld; if the average grayscale value of the weld is lower than a preset average threshold, it indicates the presence of oxidation in the weld; and if the proportion of weld grayscale values ​​lower than the preset average threshold is greater than a preset proportion threshold, it indicates the presence of porosity in the weld.

[0062] S520 assesses the defect level of a welding defect based on its dimensional parameters.

[0063] In practice, the defect levels are divided into three levels: Level 1, Level 2, and Level 3, representing different degrees of defect severity, increasing sequentially. A range of dimensional parameters corresponding to different defect levels can be pre-defined for each defect type. During evaluation, the dimensional parameters of the welding defect can be identified based on the grayscale values ​​of the weld area in the weld image, and the defect level can be determined based on these dimensional parameters and the pre-defined range.

[0064] For example, for cracks, the defect length corresponding to a level 1 defect is < 0.5 mm; the defect length corresponding to a level 2 defect is 0.5–2.0 mm; and the defect length corresponding to a level 3 defect is ≥ 2.0 mm.

[0065] For porosity, the defect levels are as follows: Level 1: single porosity diameter < 0.1 mm; Level 2: single porosity diameter 0.1–0.3 mm, or 2–3 porosities appearing in the same area (within 10 mm); Level 3: single porosity diameter ≥ 0.3 mm, or porosity in chains / clusters (≥ 4 / 10 mm), or located on the weld centerline.

[0066] For incomplete welds, the defect levels are as follows: Level 1: local defect width is less than the average defect width, but continuous without breaks; Level 2: defect width < 1.7 mm, continuous length 1–5 mm; Level 3: weld completely broken (length ≥ 1 mm), or width < 1.5 mm and length > 5 mm.

[0067] For oxidation, the defect levels are as follows: Level 1: area < 2 mm²; Level 2: defect area between 2 and 10 mm²; Level 3: defect area > 10 mm².

[0068] In this embodiment, identifying the defect type and assessing the severity of the defect through images is beneficial for guiding the generation of subsequent repair welding process parameters.

[0069] In one exemplary embodiment, such as Figure 3 As shown, the welding compensation process parameters corresponding to the welding defects are found from the preset welding process parameters, including S610, where:

[0070] S610, based on the defect type and defect level, retrieves the corresponding welding power, shielding gas flow rate and operation time from the preset welding process parameters, and compensates for welding parameters including welding power, operation time and shielding gas flow rate.

[0071] In practical applications, preset welding process parameters include welding power ranges, shielding gas flow rate ranges, and operation time ranges corresponding to different defect types. For example, the welding power for porosity defects can be in the medium power range to avoid creating new porosity due to excessive power; the welding power for incomplete fusion defects can be in the high power range to ensure complete penetration; the welding power for crack defects can be in the medium-high power range to ensure penetration depth but avoid thermal stress; and the welding power for slag inclusion defects can be in the high power range to penetrate the slag inclusion layer.

[0072] In specific implementation, firstly, for each identified defect type, the welding power range, shielding gas flow rate range, and operation time range corresponding to the identified defect type can be obtained from historical welding process parameters. Secondly, based on the defect level, the specific welding power, operation time, and shielding gas flow rate can be extracted from the identified welding power range, shielding gas flow rate range, and operation time range. In other embodiments, the specific welding power, operation time, and shielding gas flow rate can be extracted from the identified welding power range, shielding gas flow rate range, and operation time range based on the defect level and defect size parameters. For example, for welding power, weighting coefficients can be pre-assigned to different defect levels and weld size parameters. For instance, the weighting coefficients corresponding to the defect level can include: Level 1 (minor): 0.9-1.0; Level 2 (moderate): 1.0-1.1; Level 3 (severe): 1.1-1.2. The weighting coefficients corresponding to the weld size parameters can include: area < 10mm²: 0.9; 10-50mm²: 1.0; >50mm²: 1.1. Therefore, the welding power corresponding to a welding defect = the median of the welding power range × the weighting coefficient of the defect level × the weighting coefficient of the weld size parameter.

[0073] Regarding gas flow rate, the preset welding process parameters include gas flow rate ranges corresponding to different metal strip material types. For example, the reference gas flow rate range for aluminum alloy is 15-20 L / min. The gas flow rate can be obtained by referring to the method for obtaining welding power. In other embodiments, the adjustment range can be determined first based on the difference between the welding power determined above and the preset reference welding power. Further, the shielding gas flow rate corresponding to the welding defect can be determined based on the adjustment range and the preset reference gas flow rate range.

[0074] Regarding the operation time, the preset welding process parameters include a baseline operation time range corresponding to different defect types. For example, the baseline operation time range for porosity defects is 2-4 seconds to facilitate rapid repair and avoid prolonged heating; the baseline operation time range for non-fusion defects is 3-5 seconds; and the baseline operation time range for crack defects is 4-6 seconds. In practice, the baseline operation time range corresponding to the defect type is first found from the preset welding process parameters. Then, based on the defect level and the baseline operation time range, the operation time corresponding to the welding defect is determined. This can be done by referring to the above-mentioned method for obtaining welding defects. Furthermore, based on the obtained operation time, the operation time is linearly increased according to the defect area, for example, by 0.5 seconds for every 10 mm². This yields the operation time corresponding to the welding defect.

[0075] In this embodiment, the corresponding welding power, operation time and shielding gas flow rate are determined based on the defect type, defect level and welding size parameters, which improves the accuracy of the generation of welding compensation process parameters.

[0076] In an exemplary embodiment, based on the weld image, the defect type of the welding defect is identified, including: S511 to S512. Wherein:

[0077] S511, extract the weld morphology features of the weld area from the weld image.

[0078] Among them, the weld morphology features may include, but are not limited to, gray-scale statistical features, weld centerline, weld width, and weld area.

[0079] In practice, the weld seam image can be processed into a grayscale image. Then, image enhancement such as contrast enhancement and filtering can be performed on the grayscale image. After that, the weld seam region can be located from the grayscale image. This can be done by locating the weld seam region based on a pre-defined ROI (Region of Interest), by using a binarization segmentation method (such as the Otsu adaptive thresholding method), or by extracting the weld seam edge using an edge detection algorithm (such as the Canny operator) and locating the weld seam region based on the weld seam edge.

[0080] After locating the weld seam region, the weld seam width can be determined based on the pixel width within the weld seam region; the weld seam area can be determined based on the pixel area within the weld seam region. Gray-level statistical features, such as gray-level mean, standard deviation, skewness, and kurtosis, can be determined based on the gray-level values ​​of the pixels in the weld seam region. The weld centerline is then obtained by morphologically extracting the pixels in the weld seam region.

[0081] S512 identifies the type of welding defect based on the weld morphology characteristics and the preset threshold range of morphology characteristics.

[0082] In practical applications, a corresponding threshold range for morphological feature indicators is pre-defined for each type of weld morphology to identify the type of welding defect. If all weld morphological features fall within the threshold range corresponding to a certain defect type, then that defect type is determined to be the type of welding defect.

[0083] For example, if the width is within a preset width range (usually 1–3 pixels), the length is greater than a preset multiple of the width (e.g., the length is > 10 times the width), the grayscale value is lower than the grayscale value of the surrounding area, and the edge gradient shows a symmetrical high gradient change on both sides of the crack, then the welding defect type is determined to be a crack.

[0084] For example, if an isolated dark spot with a diameter within a preset range that meets the requirements of roundness (e.g., roundness > 0.7) is detected in the weld area, it is determined to be a porosity.

[0085] For example, if the weld width is consistently below the lower threshold (e.g., <1.8 mm), it is determined to be incomplete fusion or a poor weld.

[0086] In this embodiment, the defect type is identified by the weld morphology characteristics, which improves the efficiency of defect type identification.

[0087] In one exemplary embodiment, such as Figure 4 As shown, based on the weld image and the welding electrical parameters, the presence of welding defects in the metal sheath weld is detected, and welding defect detection result data is obtained, including S301 to S303, wherein:

[0088] S301, determine the difference between the welding electrical parameters and the preset standard welding electrical parameters, which are obtained based on the welding process of the standard weld.

[0089] In practical applications, welding electrical parameters corresponding to the welding process of standard welds can be pre-selected from historical welding electrical parameters and used as standard welding electrical parameters for defect judgment. During normal welding, electrical parameters such as current, voltage, and speed exhibit stable periodic fluctuations. However, when defects occur, the arc stability is disrupted, and abnormal signals appear. Therefore, welding current, welding voltage, and traction speed can be pre-collected and averaged from the welding processes of multiple standard welds to serve as preset standard welding electrical parameters.

[0090] In practice, the differences are calculated separately for welding current, welding voltage, and traction speed. First, the first difference between the welding current and the welding current in the preset standard welding electrical parameters is determined; second, the second difference between the welding voltage and the welding voltage in the preset standard welding electrical parameters is determined; finally, the third difference between the traction speed and the traction speed in the preset standard welding electrical parameters is determined. The differences include the first, second, and third differences.

[0091] S302, the weld region is segmented from the weld image, and the weld image features of the weld region are extracted.

[0092] The features of the weld image may include, but are not limited to, weld width, average grayscale value, and weld continuity.

[0093] In specific implementation, this may include, but is not limited to, identifying weld regions in weld images based on threshold or edge detection methods; then, determining the weld width based on the pixel width in the weld region; obtaining the gray-scale mean of the pixels in the weld region; and performing connected component detection on the weld region to determine the weld continuity.

[0094] S303, based on the difference and the weld image features, detect whether there are welding defects in the metal sheath weld, and obtain welding defect detection result data.

[0095] In specific implementation, following the steps above, the weld width, average grayscale value, and weld continuity are compared with their corresponding threshold ranges. Specifically, if the weld width is not within the preset weld width threshold range, it indicates an abnormal weld width; if the average grayscale value is not within the preset average grayscale threshold range, it indicates an abnormal weld surface condition; and if the weld continuity is not within the preset weld continuity threshold range, weld fracture is guaranteed. Furthermore, if at least one of the following is detected: abnormal weld width, abnormal weld surface condition, or weld fracture, it indicates an abnormal weld morphology.

[0096] Following the steps above, if at least one of the first, second, and third differences exceeds a preset difference threshold, it indicates an abnormality in the welding process. Further, if the weld morphology is abnormal and / or the welding process is abnormal, it is determined that there is a welding defect in the metal sheath weld. This determination result, the detection timestamp, and the cable travel length are integrated to obtain welding defect detection result data.

[0097] In this embodiment, welding defects in the metal sheath are detected from two dimensions, which improves the detection accuracy.

[0098] In an exemplary embodiment, after cable laying, the process further includes welding the metal sheaths of the cables on both sides. Exemplarily, the specific welding process includes: 1. Preparation and Alignment: Stripping the outer sheath from the cable ends, exposing approximately 200mm of the smooth aluminum sheath, and performing surface grinding and chemical cleaning. Using a dedicated automatic alignment clamp, fix the cables on both sides, ensuring the aluminum sheath ends are concentric, and adjust the gap to 2.0mm. 2. Automated Welding: Using a portable automated TIG welding system. Set the welding current to 180A, the welding speed to 120mm / min, and the argon gas protection flow rate to 15L / min. After startup, the welding torch automatically rotates one revolution around the weld to complete the welding. 3. Post-Weld Inspection: First, use a portable X-ray machine to take a 360° circumferential X-ray of the circumferential weld. The film shows that there is no incomplete fusion, incomplete penetration, or excessive porosity inside the weld, and the quality level is rated as ISO5817B, meeting the requirements. Secondly, based on the "false weld" defect and the sheath thickness, the repair welding parameters are called: 25kW power for the compensation welding head, and an action time of 1.5s. The movable compensation welding head accurately positions itself to the defect point within 2 seconds, performing local repair welding, with infrared temperature feedback controlling the temperature between 750-800℃. 4. Quality review and full-process data binding: After the repair welding is completed, it is reviewed again through the monitoring area. If it passes, it proceeds to the outer sheath extrusion process; if it fails, an alarm is triggered and the machine is stopped. All process data from aluminum strip unwinding to finished product output (including all process parameters, monitoring results, defect records, and compensation actions) is bound to a unique production order code and stored, realizing full lifecycle quality traceability and process big data analysis and optimization.

[0099] To provide a clearer explanation of the cable metal sheath welding method provided in this application, a specific embodiment is described below, which includes the following steps:

[0100] S1, when the metal strip covering the cable core is conveyed to the preset welding area, the welding process parameters are obtained, and the metal strip is welded according to the welding process parameters to form a metal sheath weld.

[0101] S2, collects welding electrical parameters and weld images of the metal sheath weld during the welding process.

[0102] S3, determine the difference between the welding electrical parameters and the preset standard welding electrical parameters, which are obtained based on the welding process of the standard weld.

[0103] S4. Extract weld image features from the weld area in the weld image. Based on the difference and weld image features, detect whether there are welding defects in the metal sheath weld and obtain welding defect detection result data.

[0104] S5. When the welding defect detection results indicate that there is a welding defect in the metal sheath weld, the weld morphology features of the weld area are extracted from the weld image. Based on the weld morphology features and the preset morphology feature index threshold, the defect type of the welding defect is identified.

[0105] S6. Evaluate the defect level of the welding defect based on its dimensional parameters.

[0106] S7, based on the defect type and defect level, finds the corresponding welding power, shielding gas flow rate and operation time from the preset welding process parameters, and compensates for the welding parameters including welding power, operation time and shielding gas flow rate.

[0107] After the repair welding, the weld seam is reviewed. The system performs quality monitoring on the repaired weld point again (using the same method as the initial monitoring) to obtain the review result. If the review result indicates that there are no welding defects, the correction is successful, and the process continues to the next step, with the repair data recorded. If the review result indicates that there are welding defects, the repair fails, an alarm message is sent, the system is shut down, and manual intervention is requested. Finally, the successfully corrected welding process parameters, weld seam images, weld defect detection results data, and compensation logs are all linked to the order number and stored in the database to achieve full-process data traceability.

[0108] In one example, such as Figure 5 As shown, the welding process for the metal sheath of the cable includes:

[0109] S1: Precision forming and initial welding of the aluminum sheath. The precision-cut aluminum strip is wrapped around the cable core (i.e., the core with the water-blocking buffer layer already wrapped), and the longitudinal joints are initially welded using high-frequency induction welding technology. A synchronous control system ensures precise matching of traction speed, welding power, and frequency, achieving stable forming.

[0110] S2: Multi-dimensional fusion real-time monitoring. Three-dimensional laser scanning, high-definition machine vision, and welding electrical parameter sensors are immediately deployed behind the welding point to synchronously acquire the macroscopic contour dimensions (width, height), microscopic appearance images (porosity, cracks, oxidation), and process parameters such as welding current, voltage, and speed of the weld in real time.

[0111] S3: Intelligent Defect Identification and Precise Location. The multi-source data collected by S2 is input into a defect identification model trained based on deep learning algorithms, automatically and in real-time identifying defect types and levels such as incomplete welds, cold welds, porosity, and weld misalignment. Simultaneously, a high-precision encoder records the cable travel length, and combined with a laser marking unit, the identified defect locations are precisely located and marked non-contactly.

[0112] S3 includes a logical judgment step that determines the subsequent path based on the judgment result:

[0113] Path 1 (No Defects): If the product is deemed qualified, it will flow directly to the subsequent sheath extrusion process, and the quality data of this batch ("No Defects" record) will be bound and stored.

[0114] Path 2 (Defect Detection): If a defect is identified, the closed-loop quality feedback process is initiated.

[0115] S4: Adaptive Secondary Compensation Welding. Based on the defect type, level, and cable specifications identified by S3, the intelligent control unit retrieves the optimal compensation welding parameters (such as power, time, and gas flow rate) from a pre-stored process parameter library. This drives a dedicated compensation welding head capable of multi-axis movement, quickly and accurately moving to the defect location to perform localized secondary welding. During the welding process, dynamic feedback via infrared temperature measurement allows for real-time parameter fine-tuning to prevent overheating or under-welding, ensuring a smooth transition between the repaired area and the original sheath.

[0116] S5: Quality review and full-process data binding. After the repair welding is completed, it is reviewed again through the monitoring area. If it passes, it proceeds to the outer sheath extrusion process; if it fails, an alarm is triggered and the machine is stopped. All process data from aluminum strip unwinding to finished product exit (including all process parameters, monitoring results, defect records, and compensation actions) is bound to a unique production order code and stored, realizing full lifecycle quality traceability and process big data analysis and optimization.

[0117] The forming process for the smooth aluminum sheath of the cable includes:

[0118] 1. Material feeding and forming: After being precision-cut, the aluminum alloy strip with a purity of 99.7% is wrapped onto the cable core that has completed the extrusion of the buffer layer by the forming mold.

[0119] 2. Initial High-Frequency Induction Welding: The high-frequency welding host is started, with the following parameters set: power 60kW, frequency 220kHz. The traction speed is set to 3.0m / min. Argon gas is used for protection in the welding area (flow rate 20L / min).

[0120] 3. Real-time monitoring: 60cm behind the weld point, a 3D laser scanner scans the weld contour at a frequency of 1000Hz, a 20-megapixel industrial camera captures images of the weld surface, and sensors simultaneously collect welding current and voltage.

[0121] 4. Intelligent Identification and Positioning: Monitoring data is transmitted to an industrial computer in real time. The built-in deep learning model (trained on tens of thousands of defect samples) identifies a "cold solder joint" defect within 100ms. At the same time, the encoder records that the defect is located at the 152.7-meter mark of the current production section, and the laser marker makes an invisible mark on the aluminum sheath surface at this location.

[0122] 5. Adaptive Secondary Welding Repair: The control unit calls up the welding repair parameters based on the "cold weld" defect and the sheath thickness: compensation welding head power 25kW, action time 1.5s. The movable compensation welding head accurately positions itself to the defect point within 2 seconds and performs local welding repair, with infrared temperature feedback controlling the temperature between 750-800℃.

[0123] 6. Verification and Data Binding: The repaired weld points were verified in the monitoring area, and their outline dimensions and appearance met the standards. All process parameters, monitoring images, defect records, and compensation logs for this cable reel are bound to the order number "Cable-2023-08-001" and stored in the database to achieve full-process data traceability.

[0124] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0125] Based on the same inventive concept, such as Figure 6 As shown, this application also provides a cable, which includes a conductor 1, an insulation layer 2, a water-blocking buffer layer 3, a metal sheath 4, and an outer sheath 5;

[0126] The metal sheath 4 is manufactured according to any of the above-mentioned cable metal sheath welding methods.

[0127] Preferably, the conductor 1 in this embodiment is made of high heat-resistant aluminum alloy and is designed as a segmented conductor structure, which is especially suitable for large cross-sections of 800mm² and above, in order to reduce skin effect and AC resistance.

[0128] Preferably, the insulating layer in this embodiment includes a wrapping tape 21, an inner shielding layer 22, a cross-linked polyethylene insulating layer 23, and an insulating shielding layer 24. The inner shielding layer 22, the cross-linked polyethylene insulating layer 23, and the insulating shielding layer 24 are formed in one step using a three-part co-extrusion process.

[0129] Preferably, the water-blocking buffer layer 3 in this embodiment is made of a composite water-blocking material. This composite water-blocking material uses high-efficiency water-blocking cotton as the matrix and uniformly disperses cross-linked polyolefin and nano-scale thermally conductive and insulating fillers (such as boron nitride). This design ensures excellent water-blocking and electrical insulation performance while significantly improving the thermal conductivity of the layer through nanofillers. It can promptly dissipate the Joule heat generated by the induced current of the aluminum sheath, thus suppressing the risk of ablation caused by heat accumulation in the buffer layer from a mechanistic perspective. Its elastic modulus matches that of the subsequently formed smooth aluminum sheath, ensuring that the two remain tightly bonded under thermal cycling. For example, the wrapping thickness of the water-blocking buffer layer is 4 mm, and the matrix of the composite water-blocking material used is high-efficiency water-blocking cotton, containing 5 wt% (mass percentage) cross-linked polyolefin and 3 wt% nano-boron nitride.

[0130] Preferably, the metal sheath thickness in this embodiment is 3 mm, and it is manufactured by the steps in any of the above-described cable metal sheath welding method embodiments.

[0131] Preferably, the outer sheath of this embodiment has an extrusion thickness of 8 mm and is made of weather-resistant halogen-free low-smoke flame-retardant polyolefin.

[0132] In other embodiments, the cable further includes a hot melt adhesive layer 6 and an external electrode layer 7, such as Figure 7 As shown.

[0133] In one exemplary embodiment, such as Figure 8 As shown, a cable metal sheath welding device 600 is provided, including: a welding processing module 610, a parameter acquisition module 620, a defect detection module 630, and a welding compensation module 640, wherein:

[0134] The welding processing module 610 is used to obtain welding process parameters when the metal strip covering the cable core is conveyed to the preset welding area, and to perform welding processing on the metal strip according to the welding process parameters to form a metal sheath weld.

[0135] The parameter acquisition module 620 is used to acquire welding electrical parameters and weld images of the metal sheath weld during the welding process;

[0136] The defect detection module 630 is used to detect whether there are welding defects in the metal sheath weld based on the weld image and welding electrical parameters, and to obtain welding defect detection result data;

[0137] The welding compensation module 640 is used to find the welding compensation process parameters corresponding to the welding defects from the preset welding process parameters when the welding defect detection result data indicates that there are welding defects in the weld of the metal sheath, and to perform welding compensation on the weld of the metal sheath according to the welding compensation process parameters.

[0138] In an exemplary embodiment, the defect detection module 630 is further configured to, when the welding defect detection result data characterizes the presence of welding defects in the metal sheath weld, identify the defect type of the welding defect based on the weld image; and evaluate the defect level of the welding defect based on the size parameters of the welding defect.

[0139] In an exemplary embodiment, the welding compensation module 640 is further configured to find the corresponding welding power, shielding gas flow rate and operation time from preset welding process parameters according to the defect type and defect level. The compensated welding parameters include welding power, operation time and shielding gas flow rate.

[0140] In an exemplary embodiment, the defect detection module 630 is further configured to extract weld morphology features of the weld area from the weld image; and identify the defect type of the welding defect based on the weld morphology features and a preset morphology feature index threshold.

[0141] In an exemplary embodiment, the defect detection module 630 is further configured to determine the difference between the welding electrical parameters and the preset standard welding electrical parameters, which are obtained based on the welding process of the standard weld; extract the weld image features of the weld area in the weld image; and detect whether there are welding defects in the metal sheath weld based on the difference and the weld image features, thereby obtaining welding defect detection result data.

[0142] Each module in the aforementioned cable metal sheath welding device 600 can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0143] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When executed by the processor, the computer program implements a method for welding the metal sheath of a cable.

[0144] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0145] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in any of the above embodiments of the cable metal sheath welding method.

[0146] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in any of the above embodiments of the cable metal sheath welding method.

[0147] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in any of the above embodiments of the cable metal sheath welding method.

[0148] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0149] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0150] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0151] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for welding the metal sheath of a cable, characterized in that, The method includes: When the metal strip covering the cable core is conveyed to the preset welding area, welding process parameters are obtained, and the metal strip is welded according to the welding process parameters to form a metal sheath weld. Acquire welding electrical parameters and weld images of the metal sheath weld during the welding process; Based on the weld image and the welding electrical parameters, the presence of welding defects in the metal sheath weld is detected, and welding defect detection result data is obtained. When the welding defect detection result data indicates that there is a welding defect in the weld of the metal sheath, the welding compensation process parameters corresponding to the welding defect are found from the preset welding process parameters, and the welding compensation process parameters are used to compensate the weld of the metal sheath.

2. The method according to claim 1, characterized in that, The method further includes: If the welding defect detection result data indicates that there is a welding defect in the weld of the metal sheath, the defect type of the welding defect is identified based on the weld image; The defect level of the welding defect is evaluated based on its dimensional parameters.

3. The method according to claim 2, characterized in that, The step of finding the welding compensation process parameters corresponding to the welding defect from the preset welding process parameters includes: Based on the defect type and defect level, the corresponding welding power, shielding gas flow rate and operation time are found from the preset welding process parameters; The compensated welding parameters include welding power, operation time, and shielding gas flow rate.

4. The method according to claim 2, characterized in that, The step of identifying the type of welding defect based on the weld image includes: Extract the weld morphology features of the weld area from the weld image; Based on the weld morphology characteristics and preset morphology characteristic index thresholds, the defect type of the welding defect is identified.

5. The method according to claim 1, characterized in that, The step of detecting whether there are welding defects in the metal sheath weld based on the weld image and the welding electrical parameters, and obtaining welding defect detection result data, includes: The difference between the welding electrical parameters and the preset standard welding electrical parameters is determined, which are obtained based on the welding process of a standard weld. Extract weld image features from the weld area in the weld image; Based on the difference and the weld image features, the presence of welding defects in the metal sheath weld is detected, and welding defect detection result data is obtained.

6. A cable, characterized in that, The cable includes a conductor, an insulation layer, a water-blocking buffer layer, a metal sheath, and an outer sheath; The metal sheath is manufactured according to the cable metal sheath welding method according to any one of claims 1 to 5.

7. A welding device for metal sheaths of cables, characterized in that, The device includes: The welding processing module is used to obtain welding process parameters when the metal strip covering the cable core is conveyed to a preset welding area, and to perform welding processing on the metal strip according to the welding process parameters to form a metal sheath weld. The parameter acquisition module is used to collect welding electrical parameters and weld images of the metal sheath weld during the welding process. The defect detection module is used to detect whether there are welding defects in the metal sheath weld based on the weld image and the welding electrical parameters, and to obtain welding defect detection result data; The welding compensation module is used to find the welding compensation process parameters corresponding to the welding defects from the preset welding process parameters when the welding defect detection result data indicates that there are welding defects in the weld of the metal sheath, and to perform welding compensation on the weld of the metal sheath according to the welding compensation process parameters.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images