Nondestructive testing methods, systems, media and products for cable semi-conductive buffer water-blocking layers

Abstract

The present application provides a method, system, medium and product for non-destructive detection of the semi-conductive buffer water-blocking layer of a cable, which relates to the field of non-destructive testing technology. The method includes first clarifying the part to be detected based on a preset strategy library, locking the buffer water-blocking layer of the high-risk target cable; then using an electronic nose to collect its odor information to find the initial position of the ablation; then using X-ray multi-angle shooting to obtain X-ray data; then combining the ablation detection model constructed based on deep learning of a large number of annotated X-ray data sets to determine the position, degree and other information of the ablation area, and confirming the position of the ablation area as the final position; finally, using a three-dimensional reconstruction algorithm, sending a three-dimensional image containing the final position to the visual end and marking the degree of ablation. The implementation of this method can effectively improve the accuracy and efficiency of ablation detection, timely discover and deal with cable hidden dangers, and ensure the safe and stable operation of high-voltage cables.

Description

Technical Field

[0001] The present application relates to the field of nondestructive testing technology, and in particular to a method, system, medium and product for nondestructive testing of a semi-conductive buffer water-blocking layer of a cable. Background Art

[0002] As power grids continue to expand and transmission voltage levels continue to rise, high-voltage cables, as critical equipment in power systems, face a significant operational safety challenge. The semi-conductive buffer layer of high-voltage cables, a crucial component of the cable, is susceptible to corrosion over long periods of operation, impacting the cable's insulation performance.

[0003] In the prior art, when detecting power cable faults, destructive testing is usually adopted after shutdown, that is, it is necessary to cut open a part of the cable for visual inspection or use traditional electromagnetic induction testing to try to detect internal changes.

[0004] However, existing technologies increase maintenance costs and power outage time. Traditional methods have limited detection sensitivity and are difficult to accurately locate the ablation area, especially for mild ablation, which is often difficult to capture effectively. This leads to the failure to eliminate hidden dangers in a timely manner and reduces the stability and safety of the power grid. Summary of the Invention

[0005] The present application provides a method, system, medium and product for non-destructive testing of a semi-conductive buffer water-blocking layer of a cable, which is used to efficiently and accurately capture the ablation of the semi-conductive buffer water-blocking layer of a high-voltage cable.

[0006] In the first aspect, the present application provides a nondestructive detection method for a semi-conductive buffer water-blocking layer of a cable, which is applied to a nondestructive testing system. The method comprises: determining the detection position information of the semi-conductive high-voltage cable to be detected through a preset strategy library; determining the semi-conductive buffer water-blocking layer of a high-risk target high-voltage cable in combination with the detection position information; obtaining the odor information of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable through an electronic nose device; determining the initial position information of the ablation of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable based on the odor information; and using X-rays to shoot the initial position information at multiple angles to obtain X-ray film data. ; Combined with the X-ray data, the ablation situation information of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable is determined through the ablation detection model. The ablation situation information includes at least the ablation area position information and the ablation degree information. The ablation detection model is constructed in advance based on multiple X-ray film data sets annotated with ablation situation information through deep learning; the ablation area position information is determined as the final position information of the ablation of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable; combined with the three-dimensional reconstruction algorithm, the three-dimensional image data containing the final position information is sent to the visual end, and the ablation degree information is annotated.

[0007] By adopting the above technical solutions, the preset strategy library can accurately locate the areas of the cable where ablation problems may occur and determine the inspection location information. Based on this information, the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable is found to achieve initial focus on the inspection object. The electronic nose device obtains odor information. Because ablation will cause the cable to produce a special odor, it can be used to determine the initial position information and indicate the direction for subsequent precise inspection. Multi-angle X-ray photography obtains X-ray data, and combined with the ablation detection model constructed by deep learning, it can accurately determine the location and extent of the ablation area. Finally, the three-dimensional reconstruction and annotation of the ablation degree information are displayed on the visual end, allowing inspectors to intuitively understand the ablation situation, effectively improving the accuracy and efficiency of ablation detection, and promptly discovering and handling cable hazards to ensure the safe and stable operation of high-voltage cables.

[0008] In combination with some embodiments of the first aspect, in some embodiments, before the step of determining the semi-conductive detection location information of the high-voltage cable to be detected through a preset strategy library, it also includes: determining a preset strategy library, which at least includes accessible places in the tunnel, places with pits on the aluminum sheath, and cable bends.

[0009] By implementing this technical solution, accessible areas within the tunnel are easily accessible for inspection. Pits in the aluminum sheath, where water accumulates and causes electric field distortion, are high-risk areas for ablation. Cable bends, where the electric field is unevenly distributed, are also prone to ablation. Incorporating these areas into the strategy library allows for early detection of these high-risk areas, avoiding blind testing and improving efficiency. This ensures that, within limited time and resources, inspections prioritize areas most likely to experience ablation, promptly identifying potential hazards, reducing the likelihood of cable failures, and ensuring stable power transmission.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the step of determining the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable in combination with the detection location information specifically includes: obtaining the pH value of the buffer water-blocking layer within the detection location information through a micro pH sensor array, and the micro pH sensor array is pre-set inside the semi-conductive buffer water-blocking layer of the high-voltage cable; if the pH value is greater than the set pH threshold, it is determined that the detection location information is the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable.

[0011] By employing this technical solution, a micro pH sensor array pre-installed within the semi-conductive buffer layer of a high-voltage cable acquires pH values. When the cable's semi-conductive buffer layer erodes, its internal chemical environment changes, causing a shift in pH. A pH threshold is set as a criterion. If the detected pH value exceeds this threshold, the area is identified as a high-risk target. This method, based on the changes in the cable's internal chemical properties, quickly and accurately identifies areas at risk of ablation, providing precise targets for subsequent testing and avoiding ineffective testing of numerous healthy areas.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the step of determining the initial position information of the ablation of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable based on the odor information specifically includes: combining the odor information, determining the odor anomaly value through a cable odor identification model, and the cable odor identification model is constructed in advance through deep learning using multiple odor information sets labeled with odor anomaly values; if the odor anomaly value is greater than the set odor anomaly threshold, determining a strategy library according to a preset range, and determining that the position information corresponding to the odor information is the initial position information of the ablation of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable.

[0013] By implementing the above technical solution, a cable odor recognition model built with deep learning can accurately analyze odor information acquired by the electronic nose and identify odor anomalies. Ablation can cause the cable to emit a distinctive odor, resulting in a change in the odor anomaly value. A threshold for odor anomaly is set. When the anomaly value exceeds this threshold, a strategy library is used within a preset range to lock the initial location. This process leverages the characteristic of odor to quickly locate areas of possible ablation within a complex cable environment, providing key clues for subsequent inspections, narrowing the inspection range, reducing the inspection workload, and improving inspection efficiency. Furthermore, odor information is used to assist in positioning, improving the accuracy of ablation location determination.

[0014] In combination with some embodiments of the first aspect, in some embodiments, the step of using X-rays to perform multi-angle shooting of the initial position information to obtain X-ray film data specifically includes: controlling the X-ray emitting device to shoot at multiple angles, and the multi-angle shooting includes at least vertical direction, horizontal direction and 45° direction.

[0015] By employing this technical solution, X-rays from different angles can penetrate different parts of the cable, obtaining more comprehensive information about its internal structure. Vertical imaging clearly reveals the cable's axial structure; horizontal imaging reveals radial conditions; and the 45° angle provides information not covered by the other two directions. X-ray data obtained from multiple angles complement each other, providing richer and more accurate input data for the ablation detection model. This allows the model to more accurately determine the location and extent of ablation, improving the accuracy of ablation detection, avoiding missed ablation areas due to a single detection angle, and ensuring the reliability of the test results.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the ablation area position information as the final position information where the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable is ablated, it also includes: determining the spatial overlap data of the initial position information and the ablation area position information; if the overlap data is lower than the set overlap threshold, the range determination strategy library is adjusted according to the set adjustment range.

[0017] By adopting the above technical solution, the overlap data between the initial position information and the ablation area position information is calculated and compared with the set overlap threshold. If the overlap is low, it means that the initial positioning and the final ablation area are significantly different. At this time, the range determination strategy library is adjusted. This feedback mechanism can optimize the detection strategy based on the actual detection situation, so that the subsequent detection process can more accurately locate the ablation area. By continuously adjusting the strategy library, it can adapt to the complex situations of different cables, improve the adaptability and accuracy of the detection method, ensure that each test is closer to the actual ablation location, avoid missed detection or misjudgment due to positioning deviation, and ensure the quality of high-voltage cable ablation detection.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the ablation area position information as the final position information where the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable is ablated, it also includes: using ultrasonic detection equipment to scan and detect the cable area corresponding to the final position information to obtain ultrasonic reflection echo data; comparing the ultrasonic reflection echo data with a pre-established ultrasonic feature library corresponding to different degrees of ablation to determine the characteristic deviation data; if the characteristic deviation is less than the set characteristic deviation threshold, the final position information is determined to be valid.

[0019] By adopting the above technical solution, ultrasonic detection equipment is used to scan the cable area corresponding to the final position, obtain reflected echo data, and then compare it with the pre-established ultrasonic feature library to determine the characteristic deviation data. Different degrees of ablation and different changes in the internal structure of the cable will result in different ultrasonic reflected echo characteristics. When the characteristic deviation is less than the set threshold, it means that the currently determined final position information is consistent with the characteristics of the known ablation degree, thereby verifying the validity of the final position information. This process uses ultrasonic detection to further confirm the ablation location, increase the reliability of the detection results, avoid misjudgment of the ablation location, and provide a more accurate basis for subsequent treatment of the ablation area, ensuring the credibility of the high-voltage cable detection results and maintaining the safe and stable operation of the power system.

[0020] In a second aspect, the present application provides a nondestructive testing system, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code comprising computer instructions, the one or more processors calling the computer instructions to cause the nondestructive testing system to perform the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a third aspect, the present application provides a computer-readable storage medium comprising instructions, which, when executed on a nondestructive testing system, causes the nondestructive testing system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, the present application provides a computer program product, which, when executed on a nondestructive testing system, enables the nondestructive testing system to execute the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0024] 1. Due to the use of a preset strategy library to locate the detection area, an electronic nose to sniff odors, multi-angle X-ray shooting combined with deep learning model analysis, and three-dimensional reconstruction to display the results, the technical problems of low accuracy, poor efficiency, and difficulty in intuitively presenting the ablation situation in the existing technology of ablation detection of the semi-conductive buffer water-blocking layer of high-voltage cables have been effectively solved. This has achieved the technical effects of accurately determining the location and extent of the ablation area, efficient detection, and intuitive display of detection results, timely discovering and handling cable hidden dangers, and ensuring the safe and stable operation of high-voltage cables.

[0025] 2. Due to the technical means of setting up a micro pH sensor array inside the semi-conductive buffer water-blocking layer of the high-voltage cable and determining the high-risk area based on the comparison of the detected pH value with the set threshold, the technical problem of the existing technology that it is difficult to accurately screen out the potential risk areas of ablation of the semi-conductive buffer water-blocking layer of the high-voltage cable is effectively solved, thereby achieving the technical effect of quickly locating high-risk targets, reducing invalid detections, improving detection efficiency and accuracy, and ensuring the safe operation of the cable.

[0026] 3. Due to the technical means of analyzing odor information by building a cable odor identification model through deep learning and locating the initial position of ablation by combining the preset threshold and range determination strategy library, it effectively solves the technical problem in the existing technology that it is impossible to use odor information to quickly and accurately locate the ablation position of the semi-conductive buffer water-blocking layer of the high-voltage cable, thereby achieving the technical effect of narrowing the detection range, improving detection efficiency, and enhancing the accuracy of ablation position judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is the first flow chart of the nondestructive testing method for the semi-conductive buffer water-blocking layer of a cable according to an embodiment of the present application;

[0028] Figure 2 This is a second flow chart of the nondestructive testing method for the semi-conductive buffer water-blocking layer of a cable in an embodiment of the present application;

[0029] Figure 3 It is a schematic diagram of the structure of a physical device of the nondestructive testing system in an embodiment of the present application.

[0030] Description of reference numerals:

[0031] 301. Central processing unit; 302. Read-only memory; 303. Random access memory; 304. Bus; 305. Input / output interface; 306. Input part; 307. Output part; 308. Storage part; 309. Communication part; 310. Drive; 311. Removable media. DETAILED DESCRIPTION

[0032] The terms used in the following examples of the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. As used in the specification and appended claims of the present application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to and encompasses any or all possible combinations of one or more of the listed items.

[0033] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0034] For ease of understanding, the following describes the process of the method provided by this implementation. Figure 1 , which is a first flow chart of the nondestructive testing method for the semi-conductive buffer water-blocking layer of a cable in an embodiment of the present application.

[0035] S101, determining the semi-conductive detection position information of the high-voltage cable to be detected through a preset strategy library;

[0036] The nondestructive testing system first establishes a preset strategy library based on extensive high-voltage cable operation data, failure case analysis, and industry experience. For example, during actual power grid operation, high-voltage cables in a certain region frequently experienced failures. An investigation revealed that some accessible areas within the cable tunnels had experienced severe erosion of the cables' semi-conductive buffering layer due to long-term moisture and poor ventilation. Some cables also had pits in their aluminum sheaths. Water accumulation in these pits caused electric field distortion, leading to erosion of the buffering layer. Furthermore, cable bends are also prone to erosion due to uneven electric field distribution. Based on these real-world conditions, the strategy library at least includes accessible areas within tunnels, areas with pits in the aluminum sheath, and cable bends.

[0037] After establishing the strategy library, the nondestructive testing system uses it to determine the inspection locations. For example, consider a city's power grid. High-voltage cables are distributed across multiple areas, some of which are laid in underground tunnels. When initiating an inspection task, the nondestructive testing system first analyzes the cables within the tunnel. The system identifies accessible locations within the tunnel, which serve as preliminary inspection locations. For cases where the aluminum sheath contains pits, the system draws on previous cable inspection data to obtain relevant information. If a pit is found in the aluminum sheath of a particular cable section, the area of ​​the cable where the pit is located is designated as the inspection location. For cable bends, the system uses cable design drawings and actual installation data to identify locations where the bend exceeds a certain standard and designates these locations as inspection locations. This method allows the nondestructive testing system to accurately determine the semi-conductive locations of the high-voltage cable under inspection, avoiding blind testing and significantly improving inspection efficiency.

[0038] S102, determining the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable based on the detection location information;

[0039] After determining the inspection site information, the nondestructive testing system needs to further clarify which areas are high-risk targets with real ablation risks. The micro pH sensor array plays a core role in this link. The array is carefully designed and pre-installed inside the semi-conductive buffer water barrier layer of the high-voltage cable, constantly monitoring the chemical environment changes of the buffer water barrier layer.

[0040] The micro pH sensor array consists of multiple microsensors that can highly sensitively detect pH changes within the buffer layer. Under normal circumstances, the chemical environment of the semiconductive buffer layer of a high-voltage cable is relatively stable, with the pH value remaining within a specific normal range. However, when the buffer layer erodes, its internal chemical balance is disrupted. For example, ablation can trigger a series of complex chemical reactions, leading to the production of acidic or alkaline substances, which in turn cause a pH change. This pH change becomes an important indicator for determining whether the buffer layer is at risk of ablation.

[0041] The nondestructive testing system connects to a micro pH sensor array to acquire real-time pH data for the buffer water barrier within the test location. For example, at a specific test location on a live high-voltage cable, the micro pH sensor array continuously collects data and transmits it to the nondestructive testing system. Assuming the pH threshold is set at 7.5, if the system receives a pH value of 8.0 at the test location, since 8.0 exceeds the threshold, the system, based on pre-set logic, determines that the area corresponding to the test location is the high-risk, semi-conductive buffer water barrier of the target high-voltage cable.

[0042] Changes in pH not only indicate the presence of ablation risk, but also reveal important information about its trend. If the pH value at a particular test location shows a sustained upward or downward trend over a period of time, even if it hasn't yet exceeded the established threshold, it should be a cause for concern. For example, if the pH value at a particular test location gradually rises from an initial value of 7.0 to 7.4, with a significant upward trend, this may indicate subtle chemical changes within the buffer layer. While not yet at a high-risk level, it is already in a risk warning state. Nondestructive testing systems can highlight and continuously monitor such areas, promptly identifying potential ablation risks. Traditional testing methods often rely on manual inspections or simple physical testing methods, making it difficult to penetrate deep into the cable to obtain accurate chemical information. However, using a micro pH sensor array, based on chemical changes within the cable, can quickly and accurately identify areas at risk of ablation. This not only avoids ineffective testing of numerous healthy areas, significantly improving testing efficiency, but also allows for early detection of ablation issues, saving valuable time for effective repair measures.

[0043] S103, obtaining odor information of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable through an electronic nose device;

[0044] After identifying the semi-conductive buffer layer of a high-risk high-voltage cable, the nondestructive testing system uses an electronic nose device to obtain odor information. The electronic nose device consists of a gas sensor array, a signal preprocessing unit, and a pattern recognition unit. Gas sensors detect volatile gas components in the air and convert them into electrical signals. Different types of sensors have different sensitivities to different gases.

[0045] In practice, nondestructive testing systems precisely deploy electronic nose devices near high-risk target areas. For example, in a city's underground high-voltage cable tunnel, if the buffer layer of a cable section is identified as a high-risk target, personnel will use a robotic arm or remote control to install the electronic nose device near that area in a well-ventilated location to ensure it can effectively collect odors emitted by the cable. Once the electronic nose device begins operating, it continuously samples the surrounding air. When the cable's semi-conductive buffer layer erodes, it releases volatile gases with distinctive odors, such as sulfur dioxide and ozone. When the gas sensor comes into contact with these gases, its physical properties, such as conductivity and capacitance, change, generating corresponding electrical signals. These signals are first transmitted to the signal preprocessing unit, which amplifies and filters the signals to remove interference such as environmental noise and improve signal quality. The processed signals are then transmitted to the pattern recognition unit, which has pre-stored signal patterns corresponding to both normal and abnormal odors. For example, under normal circumstances, the odor signal in the air surrounding the cable fluctuates within a specific range. If the detected signal exceeds this range, it may indicate the presence of an abnormal odor caused by ablation. By comparing these patterns, the pattern recognition unit accurately determines whether the current odor is abnormal and transmits the processed odor information in real time to the nondestructive testing system's central processor. The CPU stores this information and performs preliminary analysis, providing key information for subsequently determining the initial location of ablation.

[0046] S104, determining the initial position information of the ablation of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable based on the odor information;

[0047] After receiving odor information from the electronic nose device, the nondestructive testing system uses a cable odor discrimination model built using deep learning to identify odor anomalies. This model is trained using a large dataset of odor information labeled with odor anomalies. Researchers can pre-collect odor information from cables with different types of ablation, including varying degrees of ablation and locations, and annotate this information to identify corresponding odor anomalies. This data is then fed into the deep learning model for training, enabling the model to learn the complex relationship between odor information and anomalies.

[0048] During actual testing, the nondestructive testing system inputs the odor information collected by the electronic nose into the cable odor discrimination model. The model analyzes and processes the odor information and outputs an odor anomaly value. Assuming the odor anomaly threshold is set at 50, when the model outputs an odor anomaly value of 60, since 60 is greater than the set threshold, the nondestructive testing system activates the preset range determination strategy library. For example, the strategy library stipulates that when the odor anomaly value is greater than the threshold, the area within a radius of 5 meters centered on the odor collection point is considered a suspicious area. The system then conducts further investigations within this area, combining factors such as the cable's structural layout and geographic information to determine the location information corresponding to the odor information as the initial location information of the ablation.

[0049] If an abnormal odor is detected at a cable branch, the system prioritizes the branch with the highest odor concentration as the initial location based on the cable's route and layout. After determining the initial location, the system highlights that area and records the relevant data. If higher abnormal odor values ​​are subsequently detected in other areas, the system reassesses and updates the initial location to ensure accurate positioning and provide a precise target for subsequent X-ray imaging and ablation analysis.

[0050] S105, using X-rays to shoot the initial position information at multiple angles to obtain X-ray data;

[0051] After determining the initial ablation location, the nondestructive testing system controls the X-ray transmitter to capture that location from multiple angles. The X-ray transmitter is equipped with a high-precision control module that precisely adjusts the emission angle and intensity. Multi-angle imaging encompasses at least vertical, horizontal, and 45° directions to obtain comprehensive information about the cable's internal structure.

[0052] In actual operation, taking an overhead high-voltage cable as an example, after determining a certain position as the initial position of ablation, the staff will use a movable X-ray transmitter to take pictures. First, adjust the transmitter to a position perpendicular to the cable to emit X-rays. Vertical shooting can clearly show the axial structure of the cable and the distribution of the layers inside the cable, which helps to find signs of ablation in the axial direction, such as damage to the insulation layer, deformation of the conductor, etc. Next, move the transmitter to a horizontal position and shoot at a horizontal angle to the cable. Horizontal shooting can show the radial situation of the cable, observe the changes in the gaps between different layers inside the cable, and whether there are foreign objects. For example, if the semi-conductive buffer water-blocking layer of the cable is ablated, the horizontal X-ray film may show blurred boundaries or abnormal shadows between this layer and other layers.

[0053] Finally, the transmitting device is adjusted to a 45-degree angle with the cable for shooting. Shooting at 45 degrees can supplement the information not covered by the other two directions, observe the internal structure of the cable from a unique angle, and discover some subtle changes that are not easy to detect in the vertical and horizontal directions. After the shooting is completed, the X-ray receiving device will collect the X-rays passing through the cable and convert them into digital signals to generate X-ray data. This data is transmitted back to the non-destructive testing system and stored in a dedicated database. The system will perform preliminary processing on these X-ray data taken from multiple angles, such as grayscale adjustment and image enhancement, to provide a high-quality data foundation for subsequent analysis using the ablation detection model.

[0054] S106. Determine, using an ablation detection model, information about the ablation of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable, based on the X-ray data. The ablation detection model includes at least information about the location of the ablated region and information about the extent of the ablation. The ablation detection model is constructed using deep learning techniques based on multiple X-ray datasets annotated with ablation information.

[0055] After acquiring X-ray data from multiple angles, the nondestructive testing system feeds this data into an ablation detection model. This model is based on deep learning technology and is trained using a large dataset of X-rays annotated with ablation information. During the training phase, researchers collected numerous X-rays of high-voltage cables with varying degrees, locations, and types of ablation. Each X-ray was precisely annotated with information such as the location and degree of ablation. This data was then fed into the deep learning model for repeated training, enabling the model to learn the complex relationship between X-ray image features and ablation conditions.

[0056] In practical applications, for example, a nondestructive testing system preprocesses the acquired X-ray data to enhance image contrast and clarity, highlighting the internal structural features of the cable, and then feeds it into an ablation detection model. After receiving the data, the model uses its internal convolutional neural network (CNN) to analyze the X-ray image layer by layer. The convolutional layers in the CNN automatically extract various image features, such as edges and textures, while the pooling layers filter and reduce the dimensionality of these extracted features, reducing the data volume while retaining key information. Through multiple layers of convolution and pooling, the model can accurately identify ablated areas in X-rays. For example, for mild ablation, the model may identify subtle grayscale changes in the buffer layer, corresponding to the early stages of ablation. For severe ablation, the model can clearly distinguish large areas of abnormal shadows and accurately define the boundaries of the ablated area. The model also determines the severity of ablation based on image features. For example, by analyzing the grayscale value, size, and contrast with surrounding normal areas, the ablated area can be determined to determine whether the ablation is mild, moderate, or severe. The model outputs information about the ablation situation, including the location and extent of the ablation area. The nondestructive testing system stores and processes this information, providing key insights for determining the final ablation location and formulating a repair strategy. If the model detects moderate ablation of the semi-conductive buffer layer in a cable section, with the ablation area located at a specific axial position and radial range, the system records these details and marks the area as a priority.

[0057] S107, determining the ablation area position information as the final position information where the ablation of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable occurs;

[0058] After obtaining the ablation area location information output by the ablation detection model, the non-destructive testing system determines it as the final location information of the ablation. The system will combine the previously determined initial location information to calculate the spatial overlap data of the two. For example, by comparing the coordinate information of the initial position and the ablation area position, their overlap ratio in three-dimensional space is calculated. Assuming that the set overlap threshold is 70%, if the actual calculated overlap data is lower than the threshold, it means that the initial positioning and the final determined ablation area are quite different. At this point, the system will adjust the range determination strategy library according to the set adjustment range. For example, narrow or expand the scope of the suspicious area centered on the odor collection point, or change the weight of the cable structure layout and geographic information factors considered when determining the initial position, and then re-determine the initial position and the subsequent detection process to improve the accuracy of positioning.

[0059] S108 , combining a three-dimensional reconstruction algorithm, sending the three-dimensional image data including the final position information to a visual end, and marking the ablation degree information.

[0060] After determining the final location and extent of the ablation, the nondestructive testing system uses a 3D reconstruction algorithm to convert this information into intuitive 3D image data, which is then sent to the visual terminal for inspection. The 3D reconstruction algorithm works based on previously acquired multi-angle X-ray data and the final location information.

[0061] In actual implementation, the system first processes multi-angle X-ray data to extract the contour information of the cable's internal structure at different angles. For example, the axial profile of the cable is extracted from vertical X-rays, while radial and oblique profile information is extracted from horizontal and 45° X-rays. Then, using triangulation or other 3D reconstruction techniques, these contour information from different angles is fused and matched to construct a 3D model of the cable's internal structure.

[0062] During the 3D model construction process, the system accurately annotates the ablation areas corresponding to the final position information within the 3D model. The system also uses different colors or markings to indicate the degree of ablation. For example, areas of mild ablation are marked in green, areas of moderate ablation are marked in yellow, and areas of severe ablation are marked in red. The image is also accompanied by text describing the specific degree of ablation.

[0063] After completing the construction and annotation of the 3D image, the system transmits the 3D image data, including the final position information, via a network or other data transmission method to a visual terminal, such as a computer display or mobile terminal. This terminal allows inspectors to visually observe the ablation of the high-voltage cable's semi-conductive buffer and water-blocking layer, clearly showing the specific location, shape, and size of the ablated area within the cable, as well as the severity of the ablation. This helps inspectors make quick decisions and develop targeted repair plans.

[0064] In the above embodiment, a series of technical means are used to accurately detect the ablation of the semi-conductive buffer and water-blocking layer of the high-voltage cable through a series of technical means, such as determining the detection location information through a preset strategy library, screening high-risk targets with a micro pH sensor array, locating the initial position with an electronic nose combined with an odor recognition model, acquiring data through multi-angle X-ray photography, and analyzing the ablation detection model and displaying the results with three-dimensional reconstruction. This not only effectively solves the problems of low detection accuracy, poor efficiency, and difficulty in visually presenting the ablation situation in the existing technology, but also can quickly locate the ablation area, accurately determine the degree of ablation, promptly discover and address cable hazards, ensure the safe and stable operation of the high-voltage cable, and reduce invalid detection.

[0065] After combining the above content, the following is a more detailed description of the process of the method provided by this implementation. Figure 2, which is a second flow chart of the nondestructive testing method of the semi-conductive buffer water-blocking layer of the cable in an embodiment of the present application.

[0066] S201, using ultrasonic detection equipment to scan and detect the cable area corresponding to the final position information to obtain ultrasonic reflection echo data;

[0067] After determining the final location information of the ablation of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable, the non-destructive testing system uses ultrasonic testing equipment to scan the cable area corresponding to the location to further verify the accuracy of the ablation location.

[0068] Ultrasonic testing equipment used in nondestructive testing systems is typically equipped with a high-performance ultrasonic transducer. This transducer converts electrical signals into ultrasonic signals and transmits them toward the cable. In practice, for example, in a city's underground high-voltage cable inspection scenario, after determining the final ablation location in a specific area of ​​a cable segment, workers use a movable inspection bracket to precisely position the ultrasonic testing equipment near that area. To ensure accurate testing, the equipment's position and angle are adjusted so that the ultrasonic transducer is as perpendicular to the cable surface as possible, ensuring that the ultrasonic waves effectively penetrate the cable's internal structure.

[0069] When the device is activated, the ultrasonic transducer emits high-frequency ultrasonic waves. As these waves propagate through the cable, they are reflected, refracted, and scattered at the interfaces between different media. Due to differences in the acoustic properties of the cable's semi-conductive buffer layer, insulation layer, and conductor, the propagation characteristics of the ultrasonic waves are altered when they encounter the ablated area. For example, the structure of the ablated area may become loose or voids may form, causing parameters such as the ultrasonic propagation speed and reflection coefficient to differ from those in normal areas.

[0070] While transmitting ultrasonic waves, the ultrasonic transducer also receives reflected echoes. These echoes carry information about the cable's internal structure, including the location, size, and shape of the ablated area. The received reflected echo signals are very weak and often mixed with various noises. Therefore, nondestructive testing systems perform a series of signal processing steps. First, the signal is amplified by a preamplifier to enhance its strength for subsequent processing. Next, a filter removes noise and interference, improving signal quality.

[0071] S202, comparing the ultrasonic reflection echo data with a pre-established ultrasonic feature library corresponding to different ablation degrees to determine feature deviation data;

[0072] After the nondestructive testing system acquires the ultrasonic reflection echo data, it compares and analyzes it with a pre-established ultrasonic feature library to determine the characteristic deviation data, and then evaluate the degree of match between the ablation situation and the known standard. The ultrasonic feature library is established based on a large amount of experimental data and actual testing experience. Researchers conducted ultrasonic testing on high-voltage cables with different degrees of ablation, collecting and analyzing the characteristics of the reflected echo, including parameters such as the echo amplitude, frequency, phase, and waveform. For example, experiments have found that when there is mild ablation, the amplitude of the ultrasonic reflection echo increases slightly, the frequency changes slightly, and the waveform is relatively regular; while when there is severe ablation, the echo amplitude increases significantly, the frequency shifts significantly, and the waveform becomes complex and distorted. The ultrasonic feature data under different degrees of ablation are sorted and summarized to construct an ultrasonic feature library.

[0073] During the actual comparison process, the signal processing unit of the nondestructive testing system extracts key features from the current reflected echo data. For example, for a section of cable suspected of ablation, the system extracts the maximum echo amplitude, primary frequency components, and waveform profile from the reflected echo. These features are then compared one by one with the characteristic data for different ablation degrees stored in the ultrasonic signature library. When comparing amplitude features, the difference between the current echo amplitude and the corresponding amplitude for each ablation degree in the signature library is calculated and converted into an amplitude deviation using a specific algorithm. For frequency features, the relative frequency deviation is calculated. Combining the deviations of these different features, a specific algorithm is used to derive an overall characteristic deviation. The system continuously searches for the known ablation degree signature that most closely resembles the current reflected echo signature. If the current reflected echo signature deviates slightly from the signature library for mild ablation but significantly from the signatures for moderate and severe ablation, the ablation condition is preliminarily determined to be close to mild. Through this comparison, the nondestructive testing system can quantify the difference between the current ablation condition and the standard ablation degree, providing objective data support for subsequent determination of the validity of the final location information.

[0074] S203: If the feature deviation is less than the set feature deviation threshold, determine that the final position information is valid.

[0075] After calculating the characteristic deviation, the nondestructive testing system compares it with a set characteristic deviation threshold to determine the validity of the final position information. This threshold is determined based on extensive experimentation and actual testing. For example, ultrasonic testing and characteristic analysis of multiple cable sections with varying degrees of ablation revealed that when the characteristic deviation is less than 10%, the detected ablation condition closely matches the pre-set ablation characteristic, and the test result is considered reliable. Therefore, 10% is set as the characteristic deviation threshold (this threshold will be adjusted based on specific circumstances in actual applications).

[0076] When the characteristic deviation calculated by the system is less than the set threshold, it indicates that the currently detected ultrasonic reflection echo feature has a high degree of similarity with the features corresponding to the ablation degree in the pre-established ultrasonic feature library. Taking the detection of a high-voltage cable as an example, if the calculated characteristic deviation is 8%, which is less than the set 10% threshold, this indicates that within the cable area corresponding to the final position information, the ablation situation matches the characteristics of a certain ablation degree in the feature library, which means that the previously determined final position information is valid. This further verifies the accuracy of the ablation location determined through a series of processes including the pre-set strategy library, electronic nose detection, X-ray photography, and ablation detection model analysis.

[0077] On the contrary, if the feature deviation is greater than the set threshold, the system will consider the current test result uncertain. This may be due to the special ablation situation that exceeds the coverage of the feature library, or the presence of interference factors during the test process that affect the accuracy of the result. At this time, the non-destructive testing system may initiate a re-test process and adjust the test parameters, such as changing the frequency of the ultrasonic testing equipment, recalibrating the equipment, or re-performing multi-angle X-ray shooting and ablation detection model analysis to re-determine the location and extent of the ablation, ensure the reliability of the test results, provide an accurate basis for the subsequent formulation of maintenance strategies, and ensure the safe and stable operation of high-voltage cables.

[0078] In the embodiment of the present application, an ultrasonic detection device is used to obtain the reflected echo data of the cable ablation area, and the data is compared with a pre-established ultrasonic feature library. The final position information is then verified based on the comparison result of the feature deviation and the set threshold value, thereby effectively verifying the accuracy of the final position information of the ablation of the semi-conductive buffer water-blocking layer of the high-voltage cable, further improving the reliability of the detection results and avoiding misjudgment of the ablation position.

[0079] The following describes the nondestructive testing system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of the physical device structure of the nondestructive testing system in an embodiment of the present application.

[0080] It should be noted that Figure 3 The structure of the nondestructive testing system shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0081] like Figure 3As shown, the nondestructive testing system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage unit 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for system operation. CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0082] The following components are connected to the input / output interface 305: an input section 306 including an audio input device, push button switches, and the like; an output section 307 including a liquid crystal display (LCD), an audio output device, indicator lights, and the like; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the input / output interface 305 as needed. Removable media 311, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the media can be installed in the storage section 308 as needed.

[0083] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from removable media 311. When executed by the central processing unit (CPU) 301, the computer program performs the various functions defined in the present invention.

[0084] It should be noted that specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0085] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings.

[0086] Specifically, the nondestructive testing system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the nondestructive testing method for the semiconductive buffer water-blocking layer of the cable provided in the above embodiment is implemented.

[0087] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the nondestructive testing system described in the above embodiments, or may exist independently and not be incorporated into the nondestructive testing system. The storage medium carries one or more computer programs, which, when executed by a processor of the nondestructive testing system, enable the nondestructive testing system to implement the nondestructive testing method for a semiconductive buffer water-blocking layer of a cable as provided in the above embodiments.

[0088] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0089] As used in the above embodiments, the term “when” may be interpreted to mean “if” or “after” or “in response to determining that” or “in response to detecting that”, depending on the context. Similarly, the phrases “upon determining that” or “if (stated condition or event) is detected” may be interpreted to mean “if determining that” or “in response to determining that” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0090] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A nondestructive testing method for ablation of a semi-conductive buffer water-blocking layer of a high-voltage cable, applied to a nondestructive testing system, characterized in that: The method comprises: Determine the semi-conductive detection position information of the high-voltage cable to be detected through a preset strategy library; Determine the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable in combination with the detection location information; Acquiring odor information of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable through an electronic nose device; Determining, based on the odor information, initial location information of the ablation of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable; Using X-rays to shoot the initial position information at multiple angles to obtain X-ray data; In combination with the X-ray data, ablation information of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable is determined using an ablation detection model, wherein the ablation information includes at least ablation area location information and ablation extent information. The ablation detection model is constructed in advance using a plurality of X-ray data sets annotated with ablation information through deep learning. Determining the ablation area position information as the final position information where ablation occurs to the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable; In combination with a three-dimensional reconstruction algorithm, the three-dimensional image data including the final position information is sent to a visual end and the ablation degree information is annotated; Before the step of determining the semi-conductive detection position information of the high-voltage cable to be detected by using a preset strategy library, the method further includes: Determining a preset strategy library, wherein the strategy library at least includes accessible locations in the tunnel, locations where the aluminum sheath has pits, and cable bends; The step of determining the initial position information of the ablation of the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable according to the odor information specifically includes: In combination with the odor information, an odor anomaly value is determined using a cable odor discrimination model, wherein the cable odor discrimination model is constructed by deep learning using a plurality of odor information sets labeled with odor anomaly values ​​in advance; If the odor abnormality value is greater than the set odor abnormality threshold, the strategy library is determined according to the preset range to determine that the position information corresponding to the odor information is the initial position information where the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable is ablated.

2. The method according to claim 1, characterized in that The step of determining the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable in combination with the detection location information specifically includes: Acquiring the pH value of the buffer water-blocking layer in the detection site information through a micro pH sensor array, wherein the micro pH sensor array is pre-arranged inside the semi-conductive buffer water-blocking layer of the high-voltage cable; If the pH value is greater than a set pH threshold, it is determined that the detection location information is a semi-conductive buffer water-blocking layer of a high-risk target high-voltage cable.

3. The method according to claim 1, characterized in that The step of photographing the initial position information at multiple angles using X-rays to obtain X-ray film data specifically includes: The X-ray emission device is controlled to shoot at multiple angles, wherein the multiple angles at least include a vertical direction, a horizontal direction, and a 45° direction.

4. The method according to claim 1, wherein After the step of determining the ablation area position information as the final position information where the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable is ablated, the method further includes: Determining spatial overlap data between the initial position information and the ablation area position information; If the overlap data is lower than a set overlap threshold, the range determination strategy library is adjusted according to a set adjustment range.

5. The method according to claim 1, characterized in that After the step of determining the ablation area position information as the final position information where the semi-conductive buffer water-blocking layer of the high-risk target high-voltage cable is ablated, the method further includes: Scan and detect the cable area corresponding to the final position information using ultrasonic detection equipment to obtain ultrasonic reflection echo data; Comparing the ultrasonic reflection echo data with a pre-established ultrasonic feature library corresponding to different ablation degrees to determine feature deviation data; If the characteristic deviation is less than the set characteristic deviation threshold, it is determined that the final position information is valid.

6. A non-destructive testing system, characterized in that: The nondestructive testing system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the nondestructive testing system to perform the method according to any one of claims 1 to 5.

7. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a non-destructive testing system, the non-destructive testing system is caused to perform the method according to any one of claims 1 to 5.

8. A computer program product, characterized in that When the computer program product is run on a non-destructive testing system, the non-destructive testing system is caused to perform the method according to any one of claims 1 to 5.

Images