High-voltage cable accessory installation defect identification method, device and system and electronic equipment

Abstract

The invention discloses a high-voltage cable accessory installation defect identification method, device and system and electronic equipment. The method comprises the following steps: acquiring all point cloud data of the surface of a to-be-measured high-voltage cable accessory; preprocessing all the point cloud data to obtain original point cloud data; performing three-dimensional model reconstruction based on the original point cloud data to obtain reconstructed point cloud data; key part size features in the reconstructed point cloud data are extracted; and carrying out defect identification on the size characteristics of the key part to obtain a defect identification result of the to-be-detected high-voltage cable accessory. According to the invention, the technical problem that the high-voltage cable accessory installation defect identification efficiency and the identification accuracy are low when the high-voltage cable accessory installation defect identification is carried out through human experience in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of smart grids, and in particular to a method, device, system and electronic equipment for identifying installation defects of high-voltage cable accessories. Background Art

[0002] In the power system, cables are key facilities for transmitting electric energy, and their safety and stability are of vital importance. However, due to the complexity and diversity of cable laying environments, including underground, underwater, high altitude and other scenarios, as well as the constant changes in external environmental factors such as temperature, humidity, stress, etc., cable insulation failure has become a problem that cannot be ignored in the power system. These failures often lead to serious accidents such as power outages and fires, which not only directly cause power supply interruptions and bring great inconvenience to production and life, but also cause equipment damage and repair costs caused by accidents, which also constitute economic losses that cannot be ignored.

[0003] Among the many causes of cable failure, cable accessory failure is particularly prominent. According to statistics, cable accessory failure accounts for the vast majority of cable line failures, while the probability of cable body failure is relatively low. This is because cable accessories are the weak link of the cable line, and their production quality and installation process directly affect the overall performance of the cable line. When a cable accessory fails, it will not only cause huge economic losses due to equipment damage and repair costs, but more importantly, such failures often lead to large-scale power outages, bringing about a wide range of adverse effects, including traffic interruptions, poor communications, and business shutdowns. However, the current status of cable accessory production quality control is not optimistic. To a large extent, the quality control of cable accessories still depends on the skill level of the installation and production personnel and the experience judgment of the technical supervisors. This quality control method that relies on human factors makes it difficult to ensure that every detail in the production and installation of cable accessories can be accurately monitored and managed, and the efficiency and accuracy of high-voltage cable accessory installation defect recognition are low.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, system and electronic device for identifying installation defects of high-voltage cable accessories, so as to at least solve the technical problem in the related art that the efficiency and accuracy of identifying installation defects of high-voltage cable accessories are low when identifying installation defects of high-voltage cable accessories through manual experience.

[0006] According to one aspect of an embodiment of the present invention, a method for identifying installation defects of a high-voltage cable accessory is provided, comprising: acquiring all point cloud data of the surface of a high-voltage cable accessory to be tested; preprocessing all the point cloud data to obtain original point cloud data; reconstructing a three-dimensional model based on the original point cloud data to obtain reconstructed point cloud data; extracting dimensional features of key parts in the reconstructed point cloud data; and identifying defects on the dimensional features of the key parts to obtain defect identification results of the high-voltage cable accessory to be tested.

[0007] According to another aspect of an embodiment of the present invention, a high-voltage cable accessory installation defect identification device is also provided, including: a data acquisition module, used to acquire all point cloud data on the surface of the high-voltage cable accessory to be tested; a preprocessing module, used to preprocess all the point cloud data to obtain original point cloud data; a three-dimensional reconstruction module, used to reconstruct a three-dimensional model based on the original point cloud data to obtain reconstructed point cloud data; a key feature extraction module, used to extract key part size features in the reconstructed point cloud data; a defect identification module, used to identify defects on the key part size features to obtain defect identification results of the high-voltage cable accessory to be tested.

[0008] According to another aspect of an embodiment of the present invention, a high-voltage cable accessory installation defect identification system is also provided, including: a data acquisition component, a main control device, and a mobile detection platform, wherein the mobile detection platform is used to carry the data acquisition component to move within the scanning range of the high-voltage cable accessory to be tested; the data acquisition component is used to collect all point cloud data on the surface of the high-voltage cable accessory to be tested, and send all the point cloud data to a data processing device; the main control device is connected to the data acquisition component, and is used to execute any one of the high-voltage cable accessory installation defect identification methods described.

[0009] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, wherein the non-volatile storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing any one of the methods for identifying installation defects of high-voltage cable accessories.

[0010] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the methods for identifying installation defects of high-voltage cable accessories.

[0011] In an embodiment of the present invention, all point cloud data of the surface of a high-voltage cable accessory to be tested are acquired; the original point cloud data are preprocessed; a three-dimensional model is reconstructed based on the original point cloud data to obtain reconstructed point cloud data; key part size features in the reconstructed point cloud data are extracted; defects are identified on the key part size features to obtain a defect identification result of the high-voltage cable accessory to be tested, thereby achieving the purpose of three-dimensional reconstruction and feature extraction of all point cloud data on the surface of the high-voltage cable accessory to be tested, and accurately identifying defects on the key part size features, thereby achieving the technical effect of improving the efficiency and accuracy of high-voltage cable accessory installation defect identification, and further solving the technical problem of low efficiency and accuracy of high-voltage cable accessory installation defect identification in the related art through artificial experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0013] Figure 1 is a flow chart of a method for identifying installation defects of high-voltage cable accessories according to an embodiment of the present invention;

[0014] Figure 2 is a flow chart of an optional method for identifying installation defects of high-voltage cable accessories according to an embodiment of the present invention;

[0015] Figure 3 is a structural schematic diagram of a high-voltage cable accessory installation defect identification system according to an embodiment of the present invention;

[0016] Figure 4 is a schematic structural diagram of an optional high-voltage cable accessory installation defect identification system according to an embodiment of the present invention;

[0017] Figure 5 is a workflow diagram of an optional high-voltage cable accessory installation defect identification system according to an embodiment of the present invention;

[0018] Figure 6 is a schematic diagram of a high-voltage cable accessory installation defect identification device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] First, to facilitate understanding of the embodiments of the present invention, some terms or nouns involved in the present invention are explained below:

[0022] The normal orientation algorithm is used to estimate the normal vector of each point, that is, the vector perpendicular to the surface of the point. The normal orientation algorithm based on priority queue optimization usually refers to the use of priority queue to optimize the calculation process when estimating the normal of the point cloud, thereby improving the efficiency and accuracy of the algorithm.

[0023] Poisson reconstruction algorithm is a popular and efficient 3D surface reconstruction technology, which generates a continuous 3D surface model by solving Poisson's equation from point cloud data. Poisson's equation mathematically describes the relationship between the density distribution of point cloud and surface normal, so that the complete surface of the object can be inferred from point cloud data.

[0024] According to an embodiment of the present invention, a method embodiment for identifying installation defects of high-voltage cable accessories is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 is a flow chart of a method for identifying installation defects of high-voltage cable accessories according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0026] Step S102, obtaining all point cloud data of the surface of the high-voltage cable accessory to be tested;

[0027] In the above step S102, a three-dimensional scanning device, such as a data acquisition component composed of one or more trinocular cameras and related components, is used to capture the three-dimensional coordinate information of the surface of the high-voltage cable accessory to obtain all point cloud data of the surface of the high-voltage cable accessory to be tested. The all point cloud data is a collection of a large number of discrete three-dimensional points obtained by scanning the surface of the high-voltage cable accessory to be tested, and can describe the surface features of the high-voltage cable accessory in detail.

[0028] Step S104, pre-processing all point cloud data to obtain original point cloud data;

[0029] In the above step S104, all point cloud data of the surface of the high-voltage cable accessory to be tested are preprocessed, which may include but is not limited to splicing, filtering and noise reduction to eliminate noise and redundant points in the scanning process and improve the quality of point cloud data. Splicing is to merge point cloud data from multiple perspectives into a whole, and filtering and noise reduction are to remove abnormal points and random fluctuations in the data to ensure the accuracy of subsequent processing.

[0030] In an optional embodiment, when all point cloud data include point cloud data corresponding to multiple parts of the surface of the high-voltage cable accessory to be tested, all point cloud data are pre-processed to obtain original point cloud data, including: splicing the point cloud data corresponding to the multiple parts to obtain spliced ​​point cloud data; filtering the spliced ​​point cloud data to obtain filtered point cloud data; denoising the filtered point cloud data to obtain denoised point cloud data; and cropping the denoised point cloud data to obtain original point cloud data.

[0031] It should be noted that in the process of acquiring the three-dimensional surface features of high-voltage cable accessories, due to the complex shape and large size of cable accessories, point cloud data may need to be collected from multiple angles or multiple parts, which results in the point cloud data finally collected being scattered, that is, including point cloud data corresponding to multiple parts of the surface of the high-voltage cable accessories to be tested. In order to be able to build a complete and accurate three-dimensional model of cable accessories, these scattered point cloud data can be further preprocessed. Specifically, first, these scattered point cloud data need to be spliced, that is, the point cloud data collected from different angles or parts are merged into a complete point cloud data set. The spliced ​​point cloud data may contain some irrelevant or erroneous information, such as interfering objects in the environment, noise during the measurement process, etc. The point cloud data of these non-cable accessory surfaces can be removed by filtering, so that the data for subsequent processing is purer and the error in the reconstruction process is reduced. Even after filtering, there may still be some random noise points in the point cloud data. Noise reduction processing can further improve the quality of point cloud data, reduce the influence of noise on three-dimensional reconstruction and dimensional measurement, and ensure the accuracy of dimensional measurement. The point cloud data after noise reduction may still contain some unnecessary areas that are not important for a specific measurement task. Through cropping, the data of these non-critical parts can be removed and the point cloud data of the critical parts can be retained, thereby reducing the amount of calculation and improving processing speed and efficiency.

[0032] Through the above preprocessing steps, more accurate and optimized original point cloud data can be obtained, which provides a high-quality data foundation for the subsequent triangulated mesh reconstruction algorithm based on the Poisson equation, ensuring the accuracy and reliability of three-dimensional reconstruction. At the same time, the optimization processing of the original point cloud data is also conducive to the rapid identification of the dimensional features of key parts and the accurate judgment of defect information, thereby realizing real-time and effective monitoring of defects in the installation process of high-voltage cable accessories, and improving the installation quality and process level of cable accessories.

[0033] Step S106, reconstructing a three-dimensional model based on the original point cloud data to obtain reconstructed point cloud data;

[0034] In the above step S106, the original point cloud data obtained after preprocessing can be subjected to reverse 3D reconstruction using a triangulated mesh reconstruction algorithm based on the Poisson equation, but is not limited thereto. The Poisson reconstruction algorithm can infer the surface of the object from the point cloud, and by constructing an optimal surface to interpret the point cloud data, the surface takes into account both the density and the normal direction of the points, thereby generating an accurate 3D model with complete surface features, i.e., reconstructing the point cloud data.

[0035] In an optional embodiment, a three-dimensional model is reconstructed based on the original point cloud data to obtain reconstructed point cloud data, including: grid sampling and spatial sampling of the original point cloud data to obtain first point cloud data; uniformly sampling the first point cloud data to obtain second point cloud data; using a normal orientation algorithm based on priority queue optimization to estimate and redirect the normal of the second point cloud data to obtain third point cloud data with normal information; using a Poisson reconstruction algorithm to triangulate the third point cloud data to obtain a reconstructed mesh with density information; and cropping the reconstructed mesh with density information to obtain reconstructed point cloud data.

[0036] It can be understood that by performing grid sampling on the original point cloud data, the density of the point cloud data in different areas can be ensured to be uniform, while spatial sampling is to sample the point cloud in three-dimensional space to obtain a point cloud with variable density (i.e., the first point cloud data) to adapt to the complex geometric shapes of different parts of the high-voltage cable accessories. This can effectively reduce the amount of data while maintaining the details of key parts. After completing the grid and spatial sampling, further uniform sampling is performed to obtain sampling-optimized point cloud data (i.e., the second point cloud data). The purpose of uniform sampling is to ensure that the distribution of the point cloud is as uniform as possible during the reconstruction process to avoid model distortion caused by oversampling or undersampling. Normal estimation and redirection are key steps in the reconstruction process, which can improve the accuracy and smoothness of the triangulated mesh. The normal orientation algorithm optimized by the priority queue is used to estimate and redirect the normal of the second point cloud data to obtain a point cloud with normal information (i.e., the third point cloud data), which can efficiently process a large amount of point cloud data and ensure that the normal direction of each point is correct, thereby obtaining a higher quality reconstructed model. The Poisson reconstruction algorithm can reconstruct a three-dimensional mesh model with density information based on the normal information of the point cloud data. Triangulation is the process of converting point cloud data into triangular meshes, which can generate a more stable and easy-to-analyze model. After the model is reconstructed, the mesh needs to be cropped to remove unnecessary or low-quality parts to obtain the final reconstructed point cloud data. Adaptive cropping density can automatically adjust the cropping strategy according to different areas of the model to ensure that the details of key parts are retained while reducing the complexity of non-key parts.

[0037] Step S108, extracting key part size features in the reconstructed point cloud data;

[0038] In the above step S108, through the reconstructed three-dimensional model, key dimensional features related to the installation quality of cable accessories can be identified and extracted, such as outer sheath stripping size, main insulation stripping size, conductor crimping size and insulation surface polishing finish, etc. Accurate measurement of these features is crucial for evaluating the installation quality of cable accessories and checking potential defects.

[0039] In an optional embodiment, extracting dimensional features of key parts in the reconstructed point cloud data includes: determining a preset detection task, wherein the detection task is used to indicate the key parts of the high-voltage cable accessories to be extracted; based on the detection task, extracting dimensional features of key parts from the reconstructed point cloud data, wherein the dimensional features of key parts include at least one of the following: outer sheath stripping size, main insulation stripping size, conductor crimping size, and insulation surface polishing finish.

[0040] Optionally, before defect identification, it is necessary to first clarify the inspection task, that is, determine the key parts you want to inspect. These key parts are the parts most prone to defects during the installation of high-voltage cable accessories, including but not limited to the outer sheath stripping size, main insulation stripping size, conductor crimping size, and the finish of insulation surface grinding. Once the inspection task is determined, we will focus on extracting the key part size features related to the task from the reconstructed point cloud data. For example, if the task is to check the outer sheath stripping size, the algorithm will identify and extract the relevant point cloud data, calculate the actual stripping size of the outer sheath, and compare it with the standard size.

[0041] In the above methods, by clarifying the inspection tasks and extracting the key parts features in a targeted manner, the accuracy and efficiency of defect identification can be significantly improved. This method avoids blind analysis of the entire point cloud data set and reduces the possibility of misjudgment and missed judgment. Through the preset of the inspection tasks and the automatic extraction of the key parts features, the entire inspection process can be automated. This not only saves labor costs, but also improves the continuity and consistency of inspection and reduces errors caused by human factors. The extraction of key parts dimensional features, especially for outer sheath stripping, main insulation stripping, conductor crimping and insulation surface grinding, can more carefully check the installation quality of cable accessories. This helps to promptly discover minor defects that may affect cable performance and safety, such as inaccurate stripping dimensions, insufficient crimping force, and uneven grinding. Through accurate identification and analysis of key parts dimensional features, specific problem points can be fed back to installers or engineers to help them improve the process and improve the installation quality and reliability of high-voltage cable accessories.

[0042] Step S110, performing defect identification on the dimensional features of the key parts to obtain a defect identification result of the high-voltage cable accessory to be tested.

[0043] In the above step S110, the extracted key part dimensional features are compared with the standard cable connector drawings or specifications to identify whether there are dimensional deviations, structural incompleteness or other types of defects. If defects are found, the system will generate defect identification results and may further trigger an alarm to prompt the operator to further inspect or correct the defects.

[0044] In an optional embodiment, defect identification is performed on the dimensional features of key parts to obtain defect identification results of the high-voltage cable accessories to be tested, including: obtaining current dimensional information of the dimensional features of key parts; comparing the current dimensional information with the corresponding preset dimensional information to obtain a comparison result; based on the comparison result, determining the defect identification results of the high-voltage cable accessories to be tested.

[0045] Optionally, before defect identification, the current size information of key parts is first extracted from the reconstructed point cloud data obtained by reverse three-dimensional reconstruction, including but not limited to: outer sheath stripping size, main insulation stripping size, conductor crimping size, and insulation surface polishing finish. Through the analysis of three-dimensional point cloud data, the actual size of these key parts can be obtained, providing a data basis for subsequent defect identification. Next, the extracted current size information is compared with the preset standard size information. The preset size information can be derived from the manufacturing standards and installation specifications of high-voltage cable accessories, such as the size range specified in the standard cable connector drawing. By comparison, it can be determined whether the size of each key part meets the standard. If it exceeds the standard range, it is considered that there is a size defect. The comparison result is an important basis for defect information identification. According to the comparison result, the defect information of the high-voltage cable accessories to be tested can be automatically identified, such as outer sheath stripping size error, main insulation stripping size error, conductor crimping size error, etc. If the size information of any key part does not match the preset size information, the system will generate an alarm to indicate that there is an installation defect in the part. This process can achieve fast and accurate defect detection, thereby improving the full-process digital management and control capabilities of cable accessories construction technology.

[0046] Optionally, the defects can be graded based on the size deviation between the current size information and the corresponding preset size information in the comparison result, and the defect identification results can be divided into three levels: minor, medium and severe, to guide subsequent processing and maintenance work.

[0047] In an optional embodiment, the defect identification result includes at least one of the following: incorrect outer sheath stripping size, incorrect main insulation stripping size, heating straightening offset exceeding a preset maximum limit, incorrect conductor crimping size, burrs on the conductor connecting tube, main insulation anomalies, and stress cone installation errors, anomalies including pits and / or scratches.

[0048] Optionally, outer sheath stripping size error is used to indicate whether the outer sheath stripping meets the design requirements, avoid the degradation of insulation performance or insufficient physical protection caused by insufficient or excessive stripping, and ensure that the cable accessories can provide sufficient insulation and protection after installation. Main insulation stripping size error is used to ensure the accuracy of main insulation stripping, avoid poor electrical performance caused by stripping errors, such as partial discharge, breakdown and other problems, and ensure the electrical safety and stability of cable accessories. Heating straightening offset exceeds the preset maximum limit to monitor the offset during heating straightening, prevent deformation or damage of cable accessories due to excessive offset during heating straightening, and ensure the geometry and electrical performance of cable accessories. Conductor crimping size error is used to check the dimensional consistency of the conductor crimping process, avoid electrical faults such as increased contact resistance, heating, and breakage caused by insufficient or excessive crimping, and ensure the reliability and safety of conductor connections. Conductor connection tube burr is used to identify burrs on the surface of the conductor connection tube, prevent burrs from causing electrical short circuits or partial discharges, and ensure the electrical performance and safety of cable accessories. Main insulation anomalies include pits and / or scratches. Detect whether the main insulation surface is damaged to avoid the degradation of electrical performance caused by these damages, such as increased partial discharge, to ensure the electrical safety and stability of cable accessories. Stress cone installation errors are used to check whether the installation position and angle of the stress cone are accurate to avoid uneven electric field distribution caused by installation errors, which may cause partial discharge or insulation breakdown, and ensure the electrical performance and reliability of cable accessories. Based on the above forms of defect identification results, the installation process of high-voltage cable accessories can be monitored more accurately and comprehensively, and potential installation defects can be discovered and corrected in a timely manner, thereby improving the installation quality and electrical performance of cable accessories, reducing cable failures caused by installation defects, and ensuring the safe and stable operation of the power system.

[0049] In the above steps S102 to S110, the accuracy of defect identification can be ensured through three-dimensional reconstruction and accurate extraction of dimensional features of key parts, avoiding subjective errors and visual limitations that may exist in traditional manual inspections, and improving the accuracy of inspections. The entire identification process is automated and can be carried out in real time, greatly shortening the detection time and improving work efficiency. Especially at the cable accessory installation site, potential problems can be quickly discovered and solved, reducing subsequent failures and maintenance costs caused by installation defects. It can comprehensively evaluate the installation quality of high-voltage cable accessories, conduct comprehensive dimensional inspections and defect identification on key parts, thereby improving the reliability of cable accessories, reducing cable failures caused by improper installation, and ensuring the safe and stable operation of the power system. The identification process is based on data, and the generated defect identification results provide an objective basis for subsequent quality control and improvement, which helps to establish a data-driven decision-making mechanism and improve the quality control level of cable accessory installation. The three-dimensional reconstruction technology can adapt to the complex environment of cable accessory installation, such as narrow spaces and hard-to-reach parts, to achieve accurate inspection of these parts, making up for the shortcomings of traditional methods in complex environments. Through the above steps, the inspection efficiency and accuracy of the installation quality of high-voltage cable accessories can be effectively improved, which is of great significance for improving the reliability and safety of cable lines.

[0050] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation mode: Figure 2 is a flow chart of an optional method for identifying installation defects of high-voltage cable accessories according to an embodiment of the present invention, such as Figure 2 As shown, the method includes:

[0051] S21. Use a trinocular camera to collect surface features of the high-voltage cable accessories to be tested and obtain all point cloud data;

[0052] S22, based on all the point cloud data obtained in step S21, stitching, filtering and noise reduction are performed to obtain original point cloud data, and reverse three-dimensional reconstruction is performed on the original point cloud data to obtain reconstructed point cloud data, wherein the reverse three-dimensional reconstruction of the original point cloud data includes:

[0053] S221, performing grid sampling and spatial sampling on the original point cloud data input, and uniformly sampling the point cloud with variable density;

[0054] S222, performing normal estimation and redirection on the point cloud after sampling optimization, and optimizing the normal orientation algorithm by using a priority queue;

[0055] S223, inputting the point cloud with normal information into a reconstruction module, and triangulating the input point cloud using a Poisson reconstruction algorithm;

[0056] S224, cropping the reconstructed grid with density information, and cropping the reconstructed grid using adaptive cropping density.

[0057] S23, intelligently identifying and extracting key part features in the reconstructed point cloud data according to the measurement task, measuring the size of the key parts, and obtaining the key part size features in the reconstructed point cloud data, wherein the key part size features include at least one of the following: outer sheath stripping size, main insulation stripping size, conductor crimping size, and insulation surface polishing finish;

[0058] S24. Perform defect identification on the dimensional features of key parts, intelligently and quickly identify defect information, obtain defect identification results of the high-voltage cable accessories to be tested, and perform alarm processing, wherein the defect identification results include at least one of the following: outer sheath stripping size error, main insulation stripping size error, heating straightening offset exceeding the preset maximum limit, conductor crimping size error, conductor connecting tube burrs, main insulation abnormalities, stress cone installation errors, and abnormalities include pits and / or scratches.

[0059] This embodiment can achieve at least one of the following effects: 1) The high-voltage cable accessory installation defect identification method proposed in this embodiment can solve the technical problem of frequent line failures caused by cable accessory installation defects, can quickly and accurately identify various process size defects, improve the digital control capability of the entire cable accessory construction process, and improve the reliability and stability of cable joints. 2) Through three-dimensional reconstruction and real-time monitoring of the cable accessory installation process, defects and problems in the installation process are discovered in time, and corresponding measures are taken to correct and improve them. Not only can the installation quality of cable accessories be improved and the probability of failures be reduced, but also power outages and economic losses caused by failures can be reduced, which is of great significance for ensuring the safety and stable operation of the power system. 3) By three-dimensionally reconstructing the installation process of high-voltage cable accessories, collecting the size information of key feature parts, comparing the collected size information with the standard cable joint drawing, and quickly identifying the defect information, each link of the high-voltage cable accessory installation is effectively monitored in real time, avoiding the occurrence of various defects in the installation process of high-voltage cable accessories.

[0060] According to an embodiment of the present invention, a system embodiment for implementing the above-mentioned method for identifying installation defects of high-voltage cable accessories is also provided. Figure 3 is a structural schematic diagram of a high-voltage cable accessory installation defect identification system according to an embodiment of the present invention. Figure 3 As shown, the above-mentioned high-voltage cable accessory installation defect identification system includes: a data acquisition component 20, a main control device 40, and a mobile detection platform 60, wherein:

[0061] A mobile detection platform 60, used to carry the data acquisition component 20 and move within the scanning range of the high-voltage cable accessories to be tested;

[0062] The data acquisition component 20 is used to collect all point cloud data on the surface of the high-voltage cable accessory to be tested, and send all point cloud data to the data processing device 40;

[0063] The main control device 40 is connected to the data acquisition component 20 and is used to execute any one of the above-mentioned high-voltage cable accessory installation defect identification methods.

[0064] Optionally, the mobile detection platform 60 is used to carry the data acquisition component 20 and move within the scanning range of the high-voltage cable accessory to be tested. Specifically, the mobile detection platform 60 can be composed of a linear motor module and a rocker device, and its function is to accurately control the position of the data acquisition component to ensure that the surface feature information of the high-voltage cable accessory to be tested can be obtained from various angles and positions. This precise mobile control is essential for the comprehensive and accurate acquisition of point cloud data, thereby ensuring the accuracy of subsequent three-dimensional reconstruction and defect identification. The data acquisition component 20 can be mainly composed of a stereo camera and a camera bracket, which is used to collect all point cloud data on the surface of the high-voltage cable accessory to be tested. The stereo camera can be set to 3 groups, and each group of stereo cameras is arranged at an interval of 120° in the circumferential direction of the cable accessory to ensure all-round data collection without dead angles. At the same time, the stereo camera is equipped with a protective cover, which is in a non-closed loop form and has an opening on one side. Such a design can protect the camera from interference from the external environment and ensure that the camera can shoot the cable accessory without obstacles. The collected point cloud data will be sent to the main control device 40 for further processing and analysis. The main control device 40 is connected to the data acquisition component 20, and its core task is to execute the above-described method for identifying defects in the installation of high-voltage cable accessories based on three-dimensional reconstruction. This means that the main control device can be responsible for data preprocessing, three-dimensional reconstruction, identification of key part dimensional features, and identification and alarm of defect information. The main control device can process the point cloud data from the data acquisition component by running the computer program stored in it, perform efficient three-dimensional reconstruction, identify defects in the installation process of high-voltage cable accessories, and thus issue timely warnings to avoid line failures caused by these defects.

[0065] Based on the high-voltage cable accessories installation defect recognition system, through automated data collection and intelligent analysis, the efficiency of detection is greatly improved, the workload and time of manual detection are reduced, and defect recognition is made faster and more real-time. The precise movement of the mobile detection platform and the all-round data collection of the stereo camera can be further combined with the triangulated mesh reconstruction algorithm based on the Poisson equation to ensure the accuracy of three-dimensional reconstruction, thereby improving the accuracy of defect information recognition. During the installation process, the dimensional characteristics of key parts of high-voltage cable accessories are monitored in real time. Once dimensional errors, pits, scratches and other defects are found, an alarm can be immediately issued, so that errors can be corrected in time during the construction process to avoid subsequent line failures. The application of the high-voltage cable accessories installation defect recognition system helps to realize the digital control of the entire process of cable accessories construction technology, improve the intelligent level of construction management and monitoring, and reduce errors caused by human factors.

[0066] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation mode: Figure 4 is a schematic diagram of the structure of an optional high-voltage cable accessory installation defect identification system according to an embodiment of the present invention, such as Figure 4 As shown, the system includes:

[0067] Data collection component 20, main control device 40 and mobile detection platform 60, wherein:

[0068] The data acquisition component 20 includes a stereo camera 1 and a camera bracket 4; three groups of stereo cameras 1 are provided, and the three groups of stereo cameras 1 are arranged at intervals of 120° in the circumferential direction of the high-voltage cable accessory 2 to be tested;

[0069] The stereo camera 1 is provided with a camera bracket 4 and a protective cover, the protective cover is in a non-closed loop form, and an opening is provided on one side of the protective cover;

[0070] The high-voltage cable accessory 4 to be tested is placed on the fixed bracket;

[0071] The mobile detection platform 60 is composed of a linear motor module 5 and a rocker device 3. The mobile detection platform 60 is connected to the stereo camera 1 and is used to carry the stereo camera 1 to move within the scanning range of the high-voltage cable accessory 2 to be tested;

[0072] The main control device 40 may be an intelligent computing component, on which three-dimensional visual intelligent detection software is installed.

[0073] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation mode: Figure 5 : is a workflow diagram of an optional high-voltage cable accessory installation defect identification system according to an embodiment of the present invention, such as Figure 5 As shown, the system includes:

[0074] S501, material preparation: the high-voltage cable accessory 2 to be tested is placed on a fixed bracket;

[0075] S502, equipment in place: put the mobile detection platform 60 in place, drag the rocker device 3, and ensure that the stereo camera 1 can capture the high-voltage cable accessories 2 to be tested;

[0076] S503, opening the 3D visual intelligent detection software;

[0077] S504, select / input workpiece number / model: the operator selects / inputs the workpiece number / model to be tested on the software interface;

[0078] S505, selecting a measurement task: the operator selects a measurement task, and the measurement task is created in advance according to the measurement requirements;

[0079] S506, start: the operator clicks the "start button" on the software interface, and the system starts the detection operation;

[0080] S507, point cloud data acquisition: the software automatically controls the motion mechanism to carry the stereo camera to collect the surface features of the product to be tested according to the preset points to obtain all the surface point cloud data;

[0081] S508, 3D reconstruction and measurement calculation: The measurement software performs reverse reconstruction by stitching, filtering and noise reduction on the surface point cloud data collected by the three cameras. At the same time, the software intelligently identifies and extracts key part features according to the measurement task, and measures and gives key dimension information, etc.

[0082] S509, data saving: automatically saving the reconstructed model, key dimension measurement results and process data.

[0083] S560, detection shutdown: automatically shut down after the detection is completed.

[0084] It should be noted that in this application Figure 3 to Figure 4 The specific structure of the high-voltage cable accessory installation defect recognition system shown in the figure is only for reference. In specific applications, the high-voltage cable accessory installation defect recognition system in this application can be compared to Figure 3 to Figure 4 The high voltage cable accessories installation defect identification system shown has more or less structure.

[0085] It should be noted that any optional or preferred high-voltage cable accessory installation defect identification method in the above method embodiments can be executed or implemented in the high-voltage cable accessory installation defect identification system provided in this embodiment.

[0086] In addition, it is still necessary to explain that the optional or preferred implementation modes of this embodiment can refer to the relevant descriptions in the method embodiments, which will not be repeated here.

[0087] In this embodiment, a high-voltage cable accessory installation defect identification device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the terms "module" and "device" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0088] According to an embodiment of the present invention, there is also provided an embodiment of a device for implementing the above-mentioned method for identifying installation defects of high-voltage cable accessories. Figure 6 is a schematic diagram of the structure of a high-voltage cable accessory installation defect identification device according to an embodiment of the present invention. Figure 6 As shown, the above-mentioned high-voltage cable accessory installation defect recognition device includes: a data acquisition module 600, a preprocessing module 602, a three-dimensional reconstruction module 604, a key feature extraction module 606, and a defect recognition module 608, wherein:

[0089] The data acquisition module 600 is used to acquire all point cloud data of the surface of the high-voltage cable accessory to be tested;

[0090] The preprocessing module 602 is connected to the data acquisition module 600 and is used to preprocess all point cloud data to obtain original point cloud data;

[0091] The three-dimensional reconstruction module 604 is connected to the pre-processing module 602 and is used to reconstruct the three-dimensional model based on the original point cloud data to obtain reconstructed point cloud data;

[0092] The key feature extraction module 606 is connected to the 3D reconstruction module 604 and is used to extract the key part size features in the reconstructed point cloud data;

[0093] The defect identification module 608 is connected to the key feature extraction module 606 and is used to identify defects in the dimensional features of key parts to obtain defect identification results of the high-voltage cable accessories to be tested.

[0094] In the embodiment of the present invention, a data acquisition module 600 is set to acquire all point cloud data of the surface of the high-voltage cable accessory to be tested; a preprocessing module 602 is connected to the data acquisition module 600 to preprocess all point cloud data to obtain original point cloud data; a three-dimensional reconstruction module 604 is connected to the preprocessing module 602 to reconstruct a three-dimensional model based on the original point cloud data to obtain reconstructed point cloud data; a key feature extraction module 606 is connected to the three-dimensional reconstruction module 604 to extract key part size features in the reconstructed point cloud data; a defect recognition module 608 is connected to the key feature extraction module 606 to identify defects in key part size features to obtain a defect recognition result of the high-voltage cable accessory to be tested, thereby achieving the purpose of three-dimensional reconstruction and feature extraction of all point cloud data on the surface of the high-voltage cable accessory to be tested, and accurately identifying defects for key part size features, thereby achieving the technical effect of improving the efficiency and accuracy of high-voltage cable accessory installation defect recognition, and thus solving the technical problem of low efficiency and accuracy of high-voltage cable accessory installation defect recognition in the related art through artificial experience.

[0095] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0096] It should be noted that the data acquisition module 600, preprocessing module 602, 3D reconstruction module 604, key feature extraction module 606, and defect recognition module 608 correspond to steps S102 to S110 in the embodiment, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment. It should be noted that the modules as part of the device can be run in a computer terminal.

[0097] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in the embodiment, which will not be repeated here.

[0098] The above-mentioned high-voltage cable accessory installation defect identification device may also include a processor and a memory. The above-mentioned data acquisition module 600, preprocessing module 602, three-dimensional reconstruction module 604, key feature extraction module 606, defect identification module 608, etc. are all stored in the memory as program modules, and the processor executes the above-mentioned program modules stored in the memory to realize the corresponding functions.

[0099] The processor includes a kernel, which retrieves the corresponding program module from the memory. The kernel may be one or more. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory includes at least one memory chip.

[0100] According to an embodiment of the present application, an embodiment of a non-volatile storage medium is also provided. Optionally, in this embodiment, the non-volatile storage medium includes a stored program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute any of the above-mentioned methods for identifying installation defects of high-voltage cable accessories.

[0101] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group, and the non-volatile storage medium includes a stored program.

[0102] Optionally, when the program is running, the device where the non-volatile storage medium is located is controlled to perform the following functions: obtain all point cloud data on the surface of the high-voltage cable accessory to be tested; pre-process all point cloud data to obtain original point cloud data; reconstruct a three-dimensional model based on the original point cloud data to obtain reconstructed point cloud data; extract dimensional features of key parts in the reconstructed point cloud data; perform defect identification on the dimensional features of key parts to obtain defect identification results of the high-voltage cable accessory to be tested.

[0103] According to an embodiment of the present application, an embodiment of a processor is also provided. Optionally, in this embodiment, the processor is used to run a program, wherein when the program is run, any one of the above-mentioned methods for identifying installation defects of high-voltage cable accessories is executed.

[0104] According to an embodiment of the present application, an embodiment of a computer program product is also provided, which, when executed on a data processing device, is suitable for executing a program that initializes any of the steps of the above-mentioned high-voltage cable accessory installation defect identification method.

[0105] Optionally, the above-mentioned computer program product, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: obtaining all point cloud data of the surface of the high-voltage cable accessory to be tested; preprocessing all point cloud data to obtain original point cloud data; reconstructing a three-dimensional model based on the original point cloud data to obtain reconstructed point cloud data; extracting dimensional features of key parts in the reconstructed point cloud data; performing defect identification on the dimensional features of key parts to obtain defect identification results of the high-voltage cable accessory to be tested.

[0106] An embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: acquiring all point cloud data on the surface of a high-voltage cable accessory to be tested; preprocessing all point cloud data to obtain original point cloud data; reconstructing a three-dimensional model based on the original point cloud data to obtain reconstructed point cloud data; extracting dimensional features of key parts in the reconstructed point cloud data; and performing defect identification on the dimensional features of key parts to obtain defect identification results of the high-voltage cable accessory to be tested.

[0107] The above sequence of the embodiments of the present invention is for description only and does not represent the superiority or inferiority of the embodiments.

[0108] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0109] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the above modules can be a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, modules or indirect coupling or communication connection of modules, which can be electrical or other forms.

[0110] The modules described above as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0111] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0112] If the above-mentioned integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a non-volatile storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present invention. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0113] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for identifying installation defects of high-voltage cable accessories, characterized in that: include: Obtain all point cloud data on the surface of the high-voltage cable accessories to be tested; Preprocessing all the point cloud data to obtain original point cloud data; Reconstructing a three-dimensional model based on the original point cloud data to obtain reconstructed point cloud data; Extracting key part size features from the reconstructed point cloud data; Defect identification is performed on the dimensional features of the key parts to obtain defect identification results of the high-voltage cable accessory to be tested.

2. The method according to claim 1, characterized in that: The three-dimensional model is reconstructed based on the original point cloud data to obtain reconstructed point cloud data, including: Performing grid sampling and spatial sampling on the original point cloud data to obtain first point cloud data; Uniformly sampling the first point cloud data to obtain second point cloud data; Using a normal orientation algorithm based on priority queue optimization to perform normal estimation and redirection on the second point cloud data to obtain third point cloud data with normal information; Using a Poisson reconstruction algorithm to triangulate the third point cloud data to obtain a reconstructed mesh with density information; The reconstructed grid with density information is cropped to obtain the reconstructed point cloud data.

3. The method according to claim 1, characterized in that: In the case where the entire point cloud data includes point cloud data corresponding to a plurality of parts of the surface of the high-voltage cable accessory to be tested, the preprocessing of the entire point cloud data to obtain the original point cloud data includes: Performing splicing processing on the point cloud data corresponding to the multiple parts to obtain spliced ​​point cloud data; Performing filtering processing on the spliced ​​point cloud data to obtain filtered point cloud data; Performing noise reduction processing on the filtered point cloud data to obtain noise-reduced point cloud data; The denoised point cloud data is cropped to obtain the original point cloud data.

4. The method according to claim 1, characterized in that: The extracting of key part size features in the reconstructed point cloud data includes: Determining a preset detection task, wherein the detection task is used to indicate a key part of the high-voltage cable accessory to be detected to be extracted; Based on the detection task, the key part dimensional features are extracted from the reconstructed point cloud data, wherein the key part dimensional features include at least one of the following: outer sheath stripping size, main insulation stripping size, conductor crimping size, and insulation surface polishing finish.

5. The method according to claim 1, characterized in that The defect identification of the key part dimension feature is performed to obtain the defect identification result of the high-voltage cable accessory to be tested, including: Obtaining current size information of the size features of the key parts; Comparing the current size information with the corresponding preset size information to obtain a comparison result; Based on the comparison result, the defect identification result of the high-voltage cable accessory to be tested is determined.

6. The method according to any one of claims 1 to 5, characterized in that The defect identification result includes at least one of the following: outer sheath stripping size error, main insulation stripping size error, heating straightening offset exceeding a preset maximum limit, conductor crimping size error, conductor connecting tube burrs, main insulation anomaly, stress cone installation error, and the anomaly includes pits and / or scratches.

7. A high-voltage cable accessory installation defect identification system, characterized in that: include: Data acquisition components, main control equipment, mobile detection platform, including: The mobile detection platform is used to carry the data acquisition component and move within the scanning range of the high-voltage cable accessories to be tested; The data acquisition component is used to collect all point cloud data on the surface of the high-voltage cable accessory to be tested, and send all the point cloud data to a data processing device; The main control device is connected to the data acquisition component and is used to execute the high-voltage cable accessory installation defect identification method as described in any one of claims 1 to 6.

8. A device for identifying installation defects of high-voltage cable accessories, characterized in that: include: A data acquisition module is used to acquire all point cloud data on the surface of the high-voltage cable accessories to be tested; A preprocessing module, used for preprocessing all the point cloud data to obtain original point cloud data; A three-dimensional reconstruction module, used to reconstruct a three-dimensional model based on the original point cloud data to obtain reconstructed point cloud data; A key feature extraction module, used to extract key part size features in the reconstructed point cloud data; The defect recognition module is used to perform defect recognition on the dimension features of the key parts to obtain defect recognition results of the high-voltage cable accessories to be tested.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method for identifying installation defects of high-voltage cable accessories as described in any one of claims 1 to 6.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the high-voltage cable accessory installation defect identification method as described in any one of claims 1 to 6.

Images