Method and device for measuring size of high-voltage cable accessory and electronic equipment

Abstract

The invention discloses a high-voltage cable accessory size measurement method and device and electronic equipment. The method comprises the following steps: acquiring point cloud data of a high-voltage cable accessory; processing the point cloud data through reverse three-dimensional reconstruction to obtain a reconstructed cable point cloud; performing end plane stripping and cutting on the reconstructed cable point cloud to obtain a plurality of end plane point clouds; sorting the plurality of end plane point clouds to obtain cable end plane point clouds; performing size segmentation inner diameter statistics on preset key features in the cable end surface point cloud to obtain an inner diameter statistics result; and performing size measurement on the key features based on the inner diameter statistical result to obtain a size measurement result of the key features in the high-voltage cable accessory. According to the invention, the technical problems of complex measurement process and low accuracy of the key feature size of the high-voltage cable accessory in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the field of high-voltage cable detection, and in particular to a method, a device and an electronic device for measuring the dimensions of high-voltage cable accessories. Background Art

[0002] In the related art, when measuring the characteristic dimensions of key process nodes in the installation of high-voltage cable accessories, special measuring tools are mainly used to accurately measure the key dimensions of cable accessories, such as outer diameter, inner diameter, length, angle, etc. However, the specific details and tool selection of these measurement methods may vary depending on the cable type and accessory structure. This results in low complexity and accuracy in the measurement of key characteristic dimensions of high-voltage cable accessories.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present invention provide a method, device and electronic device for measuring the dimensions of a high-voltage cable accessory, so as to at least solve the technical problem in the related art that the measurement process of key characteristic dimensions of high-voltage cable accessories is complicated and has low accuracy.

[0005] According to one aspect of an embodiment of the present invention, a method for measuring the dimensions of a high-voltage cable accessory is provided, comprising: acquiring point cloud data of a high-voltage cable accessory; processing the point cloud data through reverse 3D reconstruction to obtain a reconstructed cable point cloud; performing end plane peeling and segmentation on the reconstructed cable point cloud to obtain a plurality of end plane point clouds; sorting the plurality of end plane point clouds to obtain a cable end face point cloud; performing size segmentation inner diameter statistics on preset key features in the cable end face point cloud to obtain inner diameter statistics results; and based on the inner diameter statistics results, performing size measurement on the key features to obtain size measurement results of the key features in the high-voltage cable accessory.

[0006] According to another aspect of an embodiment of the present invention, a high-voltage cable accessory dimension measuring device is also provided, including: a data acquisition module, used to acquire point cloud data of a high-voltage cable accessory; a data processing module, used to process the point cloud data through reverse three-dimensional reconstruction to obtain a reconstructed cable point cloud; an end plane segmentation module, used to perform end plane peeling and segmentation on the reconstructed cable point cloud to obtain a plurality of end plane point clouds; a sorting module, used to sort the plurality of end plane point clouds to obtain a cable end face point cloud; a statistical module, used to perform size segmentation inner diameter statistics on preset key features in the cable end face point cloud to obtain inner diameter statistical results; a measurement module, used to perform size measurement on the key features based on the inner diameter statistical results to obtain size measurement results of the key features in the high-voltage cable accessory.

[0007] 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 measuring the dimensions of high-voltage cable accessories.

[0008] In an embodiment of the present invention, point cloud data of a high-voltage cable accessory is acquired; the point cloud data is processed through reverse three-dimensional reconstruction to obtain a reconstructed cable point cloud; the reconstructed cable point cloud is subjected to end plane stripping and segmentation to obtain a plurality of end plane point clouds; the plurality of end plane point clouds are sorted to obtain a cable end face point cloud; size segmented inner diameter statistics are performed on preset key features in the cable end face point cloud to obtain inner diameter statistical results; based on the inner diameter statistical results, the key features are sized to obtain the size measurement results of the key features in the high-voltage cable accessory, thereby achieving the purpose of automatically and accurately acquiring the key feature sizes of the high-voltage cable accessories by acquiring point cloud data, performing three-dimensional reconstruction, end plane segmentation, sorting, and inner diameter statistics and measurement of key feature sizes, thereby achieving the technical effect of improving the measurement efficiency and accuracy of the key feature sizes of the high-voltage cable accessories, and further solving the technical problem of complex and low accuracy in the measurement process of the key feature sizes of the high-voltage cable accessories in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] 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:

[0010] Figure 1 is a flow chart of a method for measuring dimensions of a high-voltage cable accessory according to an embodiment of the present invention;

[0011] Figure 2 is a flow chart of an optional method for measuring dimensions of high-voltage cable accessories according to an embodiment of the present invention;

[0012] Figure 3 is an optional inner diameter statistical schematic diagram according to an embodiment of the present invention;

[0013] Figure 4 Schematic diagram of a device for measuring the dimensions of high-voltage cable accessories according to an embodiment of the present invention. DETAILED DESCRIPTION

[0014] 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.

[0015] 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.

[0016] First, to facilitate understanding of the embodiments of the present invention, some terms or nouns involved in the present invention are explained below:

[0017] An Oriented Bounding Box (OBB) is a bounding box in three-dimensional space. It is different from the traditional axis-aligned bounding box (AABB) and can enclose the target object in any direction. It is usually used for object collision detection or to simplify complex geometric models. The generation of OBB depends on the coordinate data of the vertices on the surface of the target object.

[0018] High-voltage cable accessories can effectively improve the safety of the power system. They provide insulation protection, waterproof and moisture-proof, anti-corrosion and other functions, thereby avoiding the occurrence of safety problems such as voltage leakage. In the design and manufacturing process of cable accessories, safety factors such as electrical insulation, voltage resistance and arc resistance are taken into account to ensure that the personal safety of power equipment and users can be effectively protected in high-voltage electrical environments. High-voltage cable accessories can protect cables from the influence of the external environment. For example, protective tubes and explosion-proof tubes can prevent cables from being damaged or destroyed, thereby improving the stability and reliability of the power system. They can seal cables to prevent damage to cables by moisture, dust, oxygen, chemicals, etc., reduce the number of cable repairs and replacements, and extend the service life of cables. High-voltage cable accessories not only have the function of connecting cables, but also can achieve multiple functions such as insulation, shielding, and protection. These functions together ensure the reliable and stable operation of the power system. High-voltage cable accessories play an important role in improving the safety, reliability, stability of power systems and promoting the development of cable technology.

[0019] In the related art, when measuring the characteristic dimensions of key process nodes in the installation of high-voltage cable accessories, special measuring tools are mainly used to accurately measure the key dimensions of cable accessories, such as outer diameter, inner diameter, length, angle, etc. However, the specific details and tool selection of these measurement methods may vary depending on the cable type and accessory structure. The following problems are common:

[0020] High requirements for measuring tools: High-voltage cable accessories have complex structures and high dimensional accuracy requirements, so high-precision and high-quality measuring tools are required, which may increase the measurement cost.

[0021] Affected by the installation environment: The installation quality of cables and accessories is greatly affected by the temperature, humidity and cleanliness of the on-site installation environment. If the installation environment is not ideal, it may affect the accuracy of the measurement results.

[0022] Complex operation: Some measurement methods require complex operation steps and techniques, and require high skills of the operator. If the operation is not done properly, it may lead to inaccurate measurement results or damage the cable accessories.

[0023] Limited measurement range: Some measurement methods may only be applicable to certain types of cable accessories or measurements of certain sizes. Different methods or tools may be required for other types of cable accessories or measurements of different sizes.

[0024] Interpretation of measurement results: The measurement results need to be correctly interpreted and analyzed to draw accurate conclusions. Improper interpretation or lack of experience may lead to misjudgment of the quality of cable accessories installation.

[0025] In summary, the key feature dimension measurement method of high-voltage cable accessories in the related art has problems such as complex process and low measurement accuracy.

[0026] In response to the above problems, an embodiment of the present invention provides an embodiment of a method for measuring the dimensions of high-voltage cable accessories. 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.

[0027] Figure 1 is a flow chart of a method for measuring dimensions of high voltage cable accessories according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0028] Step S102, obtaining point cloud data of high-voltage cable accessories;

[0029] In the above step S102, point cloud data of the surface of the high-voltage cable accessories can be obtained through a three-dimensional scanning device or other sensors to provide basic information for subsequent three-dimensional reconstruction. The above method can comprehensively capture the three-dimensional geometric information of the cable accessories, including but not limited to surface shape and size, etc., laying a data foundation for subsequent accurate measurement.

[0030] Step S104, processing the point cloud data through reverse 3D reconstruction to obtain a reconstructed cable point cloud;

[0031] In the above step S104, the point cloud data of the high-voltage cable accessories is converted into a three-dimensional model, and the reverse engineering process allows the geometric shape of the cable accessories to be recovered from the point cloud data. In this way, the readability and comprehension of the point cloud data can be improved, making it easier to subsequently process and measure. In addition, the three-dimensional reconstruction helps to identify and correct noise and missing points in the point cloud data.

[0032] Step S106, performing end plane peeling and segmentation on the reconstructed cable point cloud to obtain a plurality of end plane point clouds;

[0033] In the above step S106, by performing end plane stripping and segmentation on the reconstructed cable point cloud, the plane areas at both ends of the cable accessories can be identified, and these plane areas are key reference points for the size measurement of the cable accessories. The above method helps to accurately locate the two ends of the cable accessories and provide an accurate reference plane for size measurement. At the same time, by segmenting the end plane, the amount of data for subsequent processing can be reduced, thereby improving efficiency.

[0034] Optionally, in order to avoid inaccurate segmentation results due to coordinate deviation, the reconstructed cable point cloud can be subjected to coordinate uniform processing to obtain a cable point cloud in a unified coordinate system, and the cable point cloud in the unified coordinate system can be subjected to end plane peeling and segmentation to obtain multiple end plane point clouds.

[0035] In an optional embodiment, the reconstructed cable point cloud is subjected to end plane peeling and segmentation to obtain multiple end plane point clouds, including: determining a directed bounding box feature of the reconstructed cable point cloud; based on the directed bounding box feature, performing coordinate system one on the reconstructed cable point cloud to obtain a cable point cloud in a unified coordinate system; determining a measurement direction of a peeling algorithm; based on the measurement direction of the peeling algorithm, performing end plane peeling and segmentation on the cable point cloud in the unified coordinate system to obtain multiple end plane point clouds.

[0036] Optionally, by calculating the Oriented Bounding Box (OBB) feature of the reconstructed cable point cloud and performing coordinate system unification on the reconstructed cable point cloud, it can ensure that all point cloud data are subsequently processed in a unified coordinate system, eliminate the coordinate system deviation caused by different data acquisition angles and positions, and provide a consistent reference frame for stripping, segmentation and size measurement. The measurement direction of the stripping algorithm can be calculated based on the main axis direction. By analyzing the main axis of the OBB, the direction that best reflects the cable characteristics can be determined, so that when stripping and segmenting along this direction, the end face information of the cable can be more accurately captured. Based on the determined measurement direction, the end plane stripping and segmentation of the cable point cloud in the unified coordinate system can be performed to accurately identify the end face point cloud of the cable, which is the basis for size measurement and can ensure that the measured point cloud data is valid and represents specific features.

[0037] In the above method, by determining the coordinate system and the measurement direction, the error in the measurement process can be reduced and the accuracy of the measurement results can be improved. Coordinate transformation through OBB features can simplify the subsequent data processing process, making the implementation of the stripping algorithm more efficient and easy to implement. The end plane stripping segmentation based on the measurement direction can accurately identify the end face of the cable, provide accurate point cloud data for the measurement of key feature dimensions, and help improve the reliability of the entire measurement method. The above method has good adaptability to high-voltage cable accessories with complex structures and irregular geometric shapes, and can handle the measurement challenges caused by the complex structure of cable accessories.

[0038] In an optional embodiment, determining the directed bounding box features of the reconstructed cable point cloud includes: obtaining surface vertices of the reconstructed cable point cloud; performing principal component analysis on the surface vertices to obtain a covariance matrix corresponding to the surface vertices; determining the principal axis of the reconstructed cable point cloud based on the eigenvectors of the covariance matrix; and obtaining the directed bounding box features based on the principal axis of the reconstructed cable point cloud and the eigenvalues ​​of the covariance matrix.

[0039] It can be understood that by obtaining the surface vertices of the reconstructed cable point cloud and performing principal component analysis on it, the main distribution direction of the point cloud data in space can be found, which is the key to determining the OBB features. Based on the eigenvectors of the covariance matrix of the surface vertices, the principal axis of the reconstructed cable point cloud, that is, the longest axis of the OBB, can be determined, which provides a basis for subsequent operations in the direction of the principal axis. According to the eigenvalues ​​of the principal axis and covariance matrix of the reconstructed cable point cloud, the size and direction of the OBB can be accurately calculated, so that the point cloud data can be analyzed and processed in a more reasonable coordinate system. In the above manner, by accurately calculating the OBB features, complex cable point cloud data can be analyzed more accurately, reducing the impact of the random distribution of point cloud data on the measurement results. The determination of the OBB features helps to unify the coordinate system of the reconstructed cable point cloud into a standard coordinate system, which is conducive to the stripping, segmentation and measurement of the point cloud in the subsequent processing steps, ensuring the consistency and comparability of the measurement.

[0040] Optionally, the OBB feature obtains the OBB principal axis by introducing a principal component analysis of the covariance matrix based on the surface vertices, wherein the OBB bounding box is generated along the direction of the eigenvector of the maximum eigenvalue, and the eigenvector of the covariance matrix represents the direction of the OBB bounding box. Specifically, all surface vertices of the reconstructed cable point cloud can be obtained. Principal component analysis (PCA) is performed on these vertices, and the main direction of the cable point cloud is identified by constructing the covariance matrix of the vertices. The eigenvectors and eigenvalues ​​of the covariance matrix are calculated. The eigenvector corresponding to the maximum eigenvalue is selected as the principal axis direction of the cable point cloud, i.e., the OBB principal axis. Further, based on the aforementioned determined principal axis direction, an OBB bounding box is generated. The direction of the OBB bounding box is determined by the eigenvector corresponding to the maximum eigenvalue of the covariance matrix, ensuring that the bounding box extends along the longest direction of the cable point cloud.

[0041] In an optional embodiment, based on the directed bounding box feature, the reconstructed cable point cloud is subjected to coordinate system one to obtain a cable point cloud in a unified coordinate system, including: based on the directed bounding box feature of the reconstructed cable point cloud, the principal axis of the reconstructed cable point cloud is transformed to the longitudinal axis of a predetermined two-dimensional coordinate system, and the center of mass of the reconstructed cable point cloud is transformed to the coordinate origin to obtain a center of mass vector and a principal axis vector; based on the center of mass vector and the principal axis vector, the reconstructed cable point cloud is subjected to coordinate system one to obtain a cable point cloud in a unified coordinate system.

[0042] It can be understood that by calculating the directed bounding box OBB features of the reconstructed cable point cloud, determining the main axis and center of mass of the point cloud, aligning its main axis with the longitudinal axis (i.e., the Y axis), and placing the center of mass at the coordinate origin, it can ensure that all point cloud data are subsequently processed in a unified coordinate system, eliminating the coordinate system deviation caused by different data acquisition angles and positions, and providing a consistent reference frame for stripping, segmentation, and size measurement.

[0043] Optionally, the vertical axis of the predetermined two-dimensional coordinate system is the Y axis, and the principal axis of the reconstructed cable point cloud is transformed to the Y axis, and the center of mass of the reconstructed cable point cloud is transformed to the coordinate origin. When there is no interface interaction, the rotation vector is used to complete the transformation, and when there is interface interaction, the interaction point is used to complete the transformation. The center of mass vector and the principal axis vector generate a transformation matrix to complete the unified coordinate system. Among them, interface interaction refers to the way users interact with software or systems. Specifically, "no interface interaction" means that the system automatically performs coordinate transformation without direct input or operation by the user. "Interface interaction" means that a user interface is provided in the system, allowing operators to manually select or adjust through the interface to complete the coordinate transformation.

[0044] In an optional embodiment, determining the measurement direction of the stripping algorithm includes: calculating the transverse inner diameter of the reconstructed cable point cloud at the boundaries on both sides of the main axis of the directed bounding box feature; and determining the measurement direction of the stripping algorithm based on the transverse inner diameter.

[0045] It can be understood that the measurement direction of the stripping algorithm can be further obtained by calculating the transverse inner diameter at the two side boundaries along the main axis direction. By calculating the transverse inner diameter of the reconstructed cable point cloud at the two side boundaries of the main axis of the oriented bounding box (OBB) feature, a more accurate measurement direction can be determined. This is because the OBB feature can reflect the actual shape and direction of the cable point cloud, and the transverse inner diameter at the two side boundaries provides clues to the change of the cable diameter, which helps the stripping algorithm to locate the end face of the cable more accurately. Since the transverse inner diameter at the two side boundaries will be affected by the actual structure of the cable, for example, the diameter of the cable may change at different positions, by analyzing the change of the transverse inner diameter, the stripping algorithm can more intelligently adapt to the change of the cable shape, so that it has stronger robustness when dealing with different types of cable accessories. Once the measurement direction is determined, the stripping algorithm can effectively segment and process the cable point cloud data along this direction, avoiding unnecessary calculations and data processing, thereby improving the efficiency of the entire measurement process. In addition, by determining the measurement direction based on the OBB feature and the transverse inner diameter, the measurement error caused by the irregularity and noise of the cable point cloud data can be reduced, and the accuracy of the dimensional measurement can be ensured. The optimization of the stripping direction also helps to segment the cable point cloud more accurately, thereby obtaining more accurate statistics and measurement results in the subsequent key feature size measurement.

[0046] In an optional embodiment, the reconstructed cable point cloud is subjected to end plane peeling and segmentation to obtain multiple end plane point clouds, including: for each point cloud in the reconstructed cable point cloud, the neighborhood point set of each point cloud is subjected to plane fitting using the least squares method to obtain a plane fitting result; based on the plane fitting result, the normal vector of each point cloud is determined; based on the normal vector of each point cloud, the reconstructed cable point cloud is subjected to end plane peeling and segmentation to obtain multiple end plane point clouds.

[0047] It can be understood that accurate normal vector calculation helps to more accurately identify the end plane of the cable, thereby improving the accuracy of key feature size measurement and ensuring the installation quality of cable accessories. Based on the optimization of the normal vector, the stripping algorithm can more intelligently segment the point cloud and obtain a more regular cable end face point cloud, which is conducive to the subsequent dimensional measurement. Through the least squares method and normal vector calculation, it can better adapt to cable accessories of different shapes and sizes, and improve the versatility and flexibility of measurement. The automated processing can reduce the errors introduced by human factors and ensure the consistency and reliability of the measurement results.

[0048] Optionally, the least squares method can be used to perform plane fitting on the domain of points and the fitting plane to solve the minimum problem to obtain a linear equation group, and the normalized eigenvector corresponding to the minimum eigenvalue of the linear equation group is calculated to obtain the point cloud normal vector. Identify the spindle end face point cloud, use the Y value of the point cloud normal vector as a basis to segment the point cloud, and identify and segment all end plane point clouds by region growing, that is, obtain multiple end plane point clouds. Specifically, for each point cloud of the reconstructed cable point cloud data of the high-voltage cable accessories, determine its neighborhood point set. Use the least squares method to perform plane fitting on the neighborhood point set of each point, and obtain the normal vector of the point by solving the normalized eigenvector corresponding to the minimum eigenvalue of the linear equation group. Obtain the normal vector of each point cloud. Based on the Y value of the point cloud normal vector as the identification basis, screen out points whose normal vector Y value is close to or equal to 0, and these points may belong to the end plane. By analyzing the geometric distribution of the point cloud, identify the end plane point cloud that is roughly perpendicular to the spindle direction, and obtain the identified spindle end face point cloud set. A seed point is further selected from the spindle end face point cloud set, and region growth is performed based on the similarity of the point cloud normal vector and the distance between points. The point set is expanded until the normal vector and the distance between points in the region meet the preset threshold, or the point cloud boundary is reached. The above steps are repeated until all end plane point clouds are segmented, and a set of all segmented end plane point clouds (i.e., multiple end plane point clouds) is obtained.

[0049] Step S108, sorting multiple end plane point clouds to obtain a cable end surface point cloud;

[0050] In the above step S108, by sorting the multiple end plane point clouds, it can be ensured that the measurement of the cable accessories is performed in the correct order. The sorted end face point clouds facilitate the management of the automated measurement process and ensure the continuity and logic of the measurement results.

[0051] In an optional embodiment, multiple end plane point clouds are sorted to obtain a cable end face point cloud, including: determining the centroid positions corresponding to the multiple end plane point clouds; sorting the multiple end plane point clouds according to the coordinate values ​​of the centroid positions corresponding to the multiple end plane point clouds along a predetermined measurement direction to obtain the cable end face point cloud.

[0052] It can be understood that by calculating the centroid position of each end plane point cloud, the center point of each end plane point cloud in space can be determined, which is the basis for subsequent sorting and measurement. Sorting is performed according to the coordinate value of the centroid of each end plane point cloud along the predetermined measurement direction (usually the main axis direction of the cable, that is, the Y-axis direction). This sorting method based on the geometric center can ensure that the point cloud is correctly arranged according to the extension direction of the cable, providing an accurate reference for subsequent dimensional measurement. In the above method, through centroid sorting, the various end planes of the cable can be more accurately located, thereby improving the accuracy of measuring key feature dimensions such as inner diameter and length. The sorted point cloud is arranged in order to facilitate automatic measurement program recognition and processing, thereby reducing the need for manual or complex algorithm processing of the point cloud and improving the degree of automation of the measurement process.

[0053] It should be noted that even if there are slight irregularities or noises in the original point cloud data, the centroid-based sorting method can provide relatively stable reference points and reduce measurement errors. The sorted cable end face point cloud can be directly used for the measurement of key feature dimensions without the need for additional preprocessing steps, thereby speeding up the entire measurement process.

[0054] Optionally, for the segmented end plane point cloud set (i.e., multiple end plane point clouds), the centroid position of each end plane point cloud set is calculated for subsequent sorting and measurement. The coordinate values ​​of the centroid of the end plane point cloud along the measurement direction (usually the Y-axis direction) are sorted to determine the relative position of the end plane, and the cable end face point cloud set sorted along the measurement direction is obtained as the cable end face point cloud.

[0055] Step S110, performing size segmented inner diameter statistics on preset key features in the cable end face point cloud to obtain inner diameter statistics results;

[0056] In the above step S110, the dimensional changes of key features of cable accessories, especially the inner diameter, are counted and analyzed to evaluate their geometric consistency. Through the inner diameter statistics, the dimensional changes and potential manufacturing defects of key features such as conductors, insulation layers, and sheaths in cable accessories can be identified, providing data support for subsequent dimensional measurements.

[0057] Optionally, the key features may include but are not limited to stripping off the outer sheath, enamelling the base lead, stripping off the metal sheath, heating and straightening, stripping off the conductor, stripping off the semi-conductive layer, grinding the main insulation, insulating shielding layer treatment, conductor crimping, installing the stress cone and lead enameling; the key feature dimensions include the dimensions of the stripped outer sheath, the length and thickness of the base lead enameling, the dimensions of the stripped metal sheath, the time, temperature and curvature of heating and straightening, the dimensions of the stripped conductor, the dimensions of the stripped semi-conductive layer, the orthogonal diameter difference of the polished main insulation and the insulation diameter being greater than the inner diameter of the stress cone, the dimensions of the slope end of the insulating shielding layer treatment and the maximum difference in the waves at the slope end port, the distance between the two insulations after the conductor is crimped, the length and positioning mark of the stress cone, the ignition time, length and sealing thickness of the lead enameling.

[0058] In an optional embodiment, the preset key features in the cable end face point cloud are dimensionally segmented to obtain inner diameter statistics, including: according to a predetermined time interval, the cable end face point cloud is segmented and detected along a predetermined measurement direction by a straight-through filtering method to obtain multiple cylinders and end face information corresponding to the multiple cylinders, wherein the end face information includes a first end face and a second end face, and the multiple cylinders are obtained by segmenting the cable end face point cloud, and the multiple cylinders have the same length; based on the end face information corresponding to the multiple cylinders, the inner diameters corresponding to the multiple cylinders are determined; according to the sampling time sequence, the first gradient change point and the second gradient change point in the inner diameters corresponding to the multiple cylinders are searched, wherein the first gradient change point and the second gradient change point are cylinder positions where the inner diameter change between two adjacent cylinders in the multiple cylinders is greater than a predetermined change threshold, and the sampling time of the first gradient change point is earlier than the sampling time of the second gradient change point; the first gradient change point is marked as the bottom of the slope, and the second gradient change point is marked as the top of the slope to obtain a marking result; based on the marking result, the inner diameter statistics result is obtained.

[0059] Optionally, the first gradient change is used to indicate the position where the inner diameter value begins to change significantly when the inner diameter is counted along the measurement direction of the cable end face point cloud, marking the starting point of the cable structural feature, such as the transition from the cable conductor to the semi-conductive layer. The second gradient change point is used to indicate the position where the inner diameter value changes significantly again during the inner diameter statistics process, marking the end point of another structural feature, such as the end point of the transition from the semi-conductive layer to the insulating layer, and it defines the length of the slope area together with the first gradient change point.

[0060] It can be understood that by setting a predetermined time interval and adopting a straight-through filtering method, the standardization and automation of the measurement process can be ensured, and the measurement error caused by human factors can be reduced. At the same time, the point cloud is segmented into multiple cylinders of the same length, so that the inner diameter measurement of each cylinder is more accurate, providing a stable basis for the subsequent gradient change point search. The first gradient change point and the second gradient change point are the key to identifying the slope position. By searching for the gradient change point in the inner diameter change, the starting and ending positions of the slope can be accurately determined, which is crucial for detecting the slope features in the cable accessories because it directly affects the installation accuracy and performance of the cable accessories. The first gradient change point is marked as the bottom of the slope, and the second gradient change point is marked as the top of the slope. This automated marking method greatly simplifies manual operation and improves the efficiency of feature recognition. At the same time, it can also reduce the measurement error caused by inaccurate manual marking. The inner diameter statistical results obtained based on the marking results not only include the basic measurement value of the inner diameter, but also cover the positioning information of key features, such as the bottom and top positions of the slope. This detailed data analysis is of great significance for evaluating the manufacturing quality, installation process and performance of cable accessories, helping to detect and solve problems in a timely manner and ensure the safe operation of the power system.

[0061] Optionally, the predetermined measurement direction can be determined based on the main axis direction obtained by OBB feature calculation, which is usually the axial direction of the cable. Along the predetermined measurement direction, the point cloud data is intercepted at intervals of 5mm, and the cylindrical area point cloud with a thickness of 1mm is intercepted each time, and the two end faces of the cylinder are defined as the first end face and the second end face. For each intercepted 1mm cylindrical area, its inner diameter is measured as the basic data for measuring the key characteristic dimensions of the cable. During the measurement process, the shape of the cylindrical area is continuously checked to see if it remains standardized. Once the cylindricality is found to be non-standard, that is, the cylindrical shape has changed significantly, the position is recorded as the non-standard cylindricality stop point (P3). The spatial Y value of the center point of the cable end face point cloud is calculated, and the spatial Y value of the non-standard cylindricality stop point identified previously is combined to determine the effective area of ​​the straight-through filter to ensure the accuracy of the subsequent measurement range. Based on the preliminary detection, the position where the inner diameter size changes significantly for the first time, that is, the first gradient change point (P1), is searched, which usually marks the starting point where the cable characteristic dimension begins to change. From the first gradient change point, the point cloud is re-intercepted with a finer 1mm interval to measure the inner diameter of the cylinder to more accurately capture the details of the size change. Based on the measurement near the first gradient change point (P1), the measurement continues along the predetermined measurement direction until the second significant change in the inner diameter size is detected, that is, the second gradient change point (P2), which marks the end point of the cable characteristic size change. The first gradient change point (P1) is marked as the bottom of the slope, and the second gradient change point (P2) is marked as the top of the slope. These two points are key reference points for subsequent size analysis.

[0062] Step S112, based on the inner diameter statistical results, the key features are measured to obtain the size measurement results of the key features in the high-voltage cable accessories.

[0063] In the above step S112, the inner diameter statistical result is used for actual size measurement to ensure the accuracy and reliability of the measurement. The above method can provide detailed key characteristic size data of cable accessories, including but not limited to conductor length, semi-conductive layer thickness, insulation outer diameter, etc., for verifying the manufacturing quality and installation accuracy of cable accessories. At the same time, the above method can realize non-contact measurement, avoiding the damage that traditional contact measurement may cause to cable accessories.

[0064] Optionally, the measurement items of the dimension measurement may include but are not limited to the length of the conductor removed, the length of the semi-conductive layer removed, the slope length, the length of the metal sheath removed and the outer diameter of the insulation, wherein the length of the conductor removed can be measured according to the distance between the first end face and the second end face; the length of the semi-conductive layer removed can be measured according to the distance between the second end face and the second gradient change point; the slope length can be measured according to the distance between the first gradient change point and the second gradient change point; the length of the metal sheath removed can be measured according to the distance between the second end face and the stopping point of the cylindrical irregularity; the outer diameter of the insulation can be measured according to the second end face and the measurement direction.

[0065] Through the above steps S102 to S112, the purpose of automatically and accurately obtaining the key characteristic dimensions of high-voltage cable accessories can be achieved by acquiring point cloud data, performing three-dimensional reconstruction, end plane segmentation, sorting, and inner diameter statistics and measurement of key characteristic dimensions, thereby achieving the technical effect of improving the measurement efficiency and measurement accuracy of key characteristic dimensions of high-voltage cable accessories, and further solving the technical problem of complex key characteristic dimension measurement process and low accuracy of high-voltage cable accessories in related technologies.

[0066] 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 measuring the dimensions of high-voltage cable accessories according to an embodiment of the present invention, such as Figure 2 As shown, the method includes:

[0067] S1, obtaining point cloud data of high-voltage cable accessories, and performing reverse 3D reconstruction on the point cloud data of high-voltage cable accessories to obtain a reconstructed cable point cloud;

[0068] S2, calculating and reconstructing the OBB features of the cable point cloud and performing coordinate system one processing to obtain the cable point cloud of the unified coordinate system;

[0069] S3, determining the measurement direction of the stripping algorithm for the cable point cloud in the unified coordinate system, performing end plane stripping segmentation and sorting to obtain the cable end surface point cloud;

[0070] S4, after counting the key feature size of the cable end face point cloud and the inner diameter of the segment, the size is measured to complete the key feature size measurement of the high-voltage cable accessories.

[0071] This embodiment can be understood as a method for measuring the key feature dimensions of high-voltage cable accessories based on three-dimensional reconstruction. This method uses an algorithm to automatically measure the key feature dimensions of high-voltage cable accessories, improve measurement accuracy, achieve non-contact measurement, improve work efficiency, and reduce measurement costs. It has the characteristics of high efficiency and can quickly and conveniently complete the measurement of key feature dimensions of high-voltage cable accessories, greatly reducing the workload and time of staff, and can significantly reduce labor intensity and improve work efficiency. Through automated and intelligent technical means, the degree of manual intervention in the measurement process is reduced, and the impact of human factors on the measurement results is reduced, thereby reducing the measurement cost. It can also achieve fast and accurate data acquisition and processing, improve the effective utilization of data, and further reduce the measurement cost.

[0072] Furthermore, high-quality camera lenses and advanced digital image processing technology can be used to obtain high-quality digital images, thereby ensuring the accuracy of measurement data, improving the positioning accuracy of digital image edges, and making the measurement of geometric and mechanical performance parameters such as cable insulation layer, sheath thickness, and cable dimensions more accurate. Furthermore, optical detection technology and image processing methods can be used to achieve non-contact measurement of high-voltage cable accessories, avoiding the artificial force interference of traditional contact measurement on flexible objects, and ensuring the accuracy and reliability of measurement.

[0073] Based on the above embodiment and optional embodiment, the present invention proposes another optional implementation method of measuring the size of high-voltage cable accessories, and the specific process is as follows:

[0074] Calculate the OBB features of the cable point cloud, correspond the point cloud principal axis and center of mass to the Y axis and the coordinate origin, use the rotation vector to complete the transformation when there is no interface interaction, and use the interaction point, center of mass and principal axis vector to generate the transformation matrix to complete the unified coordinate system when there is interface interaction.

[0075] OBB obtains the eigenvector, i.e., the principal axis of OBB, through the PCA method based on the vertices of the object surface; principal component analysis is a method of transforming a set of possibly related variables into a set of linearly unrelated variables, i.e., the principal components, through orthogonal transformation.

[0076] The concept of covariance matrix is ​​introduced. Covariance represents the degree of linear correlation between two variables. The smaller the covariance, the more independent the two variables are, that is, the smaller the linear correlation is. The formula for calculating covariance is as follows:

[0077] cov(X i ,Xj )=E[(X i -μ i )(X j -μ j )]

[0078] Through the calculation formula of covariance, the covariance matrix can be obtained:

[0079]

[0080] In the above formula, cov represents covariance, E represents expected value, μ i Represents X i The average value over the dimension, μ j Represents X j The average value over the dimension.

[0081] The elements on the main diagonal represent the variance of the variables. Larger elements on the main diagonal represent strong signals. The elements off the main diagonal represent the covariance between the variables. Larger off-diagonal elements represent data distortion. To reduce distortion, we can redefine the linear combinations between the variables and diagonalize the covariance matrix. The elements of the covariance matrix are real and symmetric.

[0082] The eigenvector of the covariance matrix represents the direction of the OBB bounding box. Large eigenvalues ​​correspond to large variances, so the OBB bounding box should be along the direction of the eigenvector corresponding to the maximum eigenvalue.

[0083] The calculated main axis itself is affected by the actual collected point cloud. It is necessary to calculate the transverse inner diameter at the boundaries on both sides along the main axis direction to determine the measurement direction of the peeling algorithm. The measurement direction can start from the small end.

[0084] After the point cloud has unified its coordinate system, due to the principal axis relationship, the direction of the point cloud no longer changes due to the acquisition method. The point cloud whose normal is basically parallel to the principal axis can be used as a segmentation method for key points in the cable. At this time, the principal axis end face point cloud is first identified. This solution is suitable for cable measurement with cross sections. The point cloud is segmented mainly based on the Y value of the point cloud normal vector, and then all end plane point clouds are identified and segmented through regional growing. The plane is sorted along the measurement direction according to the centroid of the end face point cloud.

[0085] The point cloud normal vector is the most basic point cloud feature and plays a vital role in the point cloud processing algorithm; this algorithm uses the neighborhood point fitting method to obtain the point normal vector.

[0086] The general idea of ​​the point cloud normal vector is to fit a plane based on the points in the neighborhood, and the normal direction of the plane is the normal vector of the point. The neighborhood of the point is:

[0087] N={p i (x i ,yi ,z i )|i=1,2,3,……n}

[0088] The general form of the plane that needs to be fitted is:

[0089] Ax+By+Cz+D=0

[0090] A 2 +B 2 +C 2 =1

[0091] The least squares method is used for plane fitting to solve the following minimum problem:

[0092]

[0093] By taking the derivative and setting the derivative to 0 and eliminating D from the system of equations, we can obtain the following linear equations:

[0094]

[0095] Among them, M is the covariance matrix, and the normalized eigenvector corresponding to the minimum eigenvalue of the covariance matrix M is calculated to obtain the point cloud normal vector:

[0096]

[0097] In the above formula, the set of N domain points p i (x i ,y i ,z i ) The three-dimensional coordinate point (A, B, C) is the plane normal vector, D is the vertical distance from the origin to the plane, x 2 represents the sum of squares of x, represents the mean of the sum of squares of x, represents the square of the mean value of x, represents the summed average of x and y. Point normal vector, n x , n y , n z Represents the directional components of the normal vector, and T represents transpose.

[0098] End face recognition can be used to locate cylindrical point clouds. The end face point cloud identified by peeling can be used for segmented detection along the measurement direction. For the initial detection, 1mm cylinders are intercepted at 5mm intervals to measure the inner diameter of the cylinder. When the cylindricality is poor, stop P3. Figure 3 is an optional inner diameter statistical schematic diagram according to an embodiment of the present invention, such as Figure 3As shown, search for the gradient change point of the measured inner diameter, measure the inner diameter of the cylinder at 1 mm intervals near the gradient change point, accurately search for the gradient change point, and mark two positions as the slope bottom P1 and slope top P2.

[0099] Note that the coordinates of the center point of the red end face are not P, and the spatial Y values ​​of P and P3 are obtained as the effective area of ​​the through-filter. The through-filter method is used to complete the segmented point cloud interception. The segmentation starting point calculation method is:

[0100] Y min =Y P +5*nn=0,1,2……(Y p3 -Y P ) / 5

[0101] Y max =Y min +1

[0102] Calculate the Y value of each point in the point cloud, according to Y min and Y max Complete the grouping of point clouds for subsequent calculation of the inner diameter of the cylinder:

[0103]

[0104] In the above formula, Y min Indicates the lower limit of the Y value of the direct filter, Y max Indicates the upper limit of the Y value of the direct filter, Y P Indicates the Y value of point P, Y P3 Indicates the Y value of point P3, x 0 ,y 0 , z 0 represents a point on the cylinder axis, (l,m,n) represents the direction vector of the cylinder axis, and r represents the radius of the cylinder.

[0105] The insulation outer diameter measurement is divided into two directions. The measurement can be completed by intercepting a point cloud of about 3mm every 50mm, and obtaining the AABB bounding box of the intercepted point cloud. Since the point cloud preprocessing has defined the Y direction of the coordinate system as the axis direction, the difference in the X and Z directions can be used as the outer diameter measurement result.

[0106] The AABB bounding box is represented as a hexahedron in three-dimensional space, each side of which is parallel to a coordinate plane; the AABB bounding box is defined by the maximum and minimum values ​​of the X, Y, and Z directions of the input three-dimensional object.

[0107] The key features, end face 1, end face 2, slope end points P1 and P2 have been identified, and the lengths are measured according to the measurement items in Table 1:

[0108] Table 1 Analysis of measurement items

[0109] Measurement items Feature 1 Feature 2 Measurement Conductor length cut out End face 1 End 2 Distance between faces Eliminate the length of the semi-conductive layer End 2 P1 Point to surface distance Slope length P1 P2 Distance between points (with direction) Length of metal sheath removed End 2 P3 Point to surface distance Insulation outer diameter End 2 Measuring direction Cylinder inner diameter

[0110] The measurement of straightening can be simplified to the measurement of geometric tolerance straightness, fitting the straight line point cloud, obtaining the straight line fitting parameters, using the straight line fitting parameters as the projection plane, and projecting the straight line point cloud onto the projection plane. Calculate the minimum circumscribed circle diameter of the projected point cloud as the 600mm straightness measurement result.

[0111] Measuring the straightness of a cylinder requires obtaining the center axis point of the cylinder. The straight-through filtering method in the measurement calculation section is used to obtain the segmented cylinder point cloud. The point cloud is intercepted with a length of l, and the entire point cloud is segmented. min and Y max The calculation is as follows:

[0112] Y min =Y P +l*nn=0,1,2……(Y p3 -Y P ) / l

[0113] Y max =Y min +l

[0114] The standard equation of a straight line in space is:

[0115]

[0116] Perform an equivalent transformation on this equation:

[0117]

[0118] The spatial straight line can be regarded as the intersection of the two planes in the above formula. The least squares fitting principle is as follows, using the residual sum of squares:

[0119] Q 1 =∑(x i -k 1 z i +b 1 ) 2

[0120] Q 2 =∑(y i -k 2 z i +b 2 ) 2

[0121] Get the minimum model parameters:

[0122]

[0123] but:

[0124]

[0125] In the above formula, Y min Indicates the lower limit of the Y value of the direct filter, Y max Indicates the upper limit of the Y value of the direct filter, Y P Indicates the Y value of point P, Y P3 Indicates the Y value of point P3, x 0 ,y 0 , z 0 represents a point on a line, (m,n,p) represents the direction vector of the line, k 1 , b 1 , k 2 , b 2 is the equivalent conversion symbol for the equation of a line.

[0126] Complete the straight line fitting of the cable centerline and calculate whether the cable straightness meets the process requirements.

[0127] The key characteristic dimension requirements of different high-voltage cable accessories are shown in Table 2.

[0128] Table 2 Key characteristic dimension requirements for different high voltage cable accessories

[0129]

[0130]

[0131]

[0132] In this embodiment, a high-voltage cable accessory size measuring 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 implement a combination of software and / or hardware for 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.

[0133] According to an embodiment of the present invention, there is also provided an embodiment of a device for implementing the above-mentioned method for measuring the dimensions of high-voltage cable accessories. Figure 4 is a schematic structural diagram of a high-voltage cable accessory dimension measuring device according to an embodiment of the present invention. Figure 4 As shown, the above-mentioned high-voltage cable accessory size measuring device includes: a data acquisition module 800, a data processing module 802, an end plane segmentation module 804, a sorting module 806, a statistics module 808, and a measurement module 810, wherein:

[0134] The data acquisition module 800 is used to acquire point cloud data of high voltage cable accessories;

[0135] The data processing module 802 is used to process the point cloud data through reverse 3D reconstruction to obtain a reconstructed cable point cloud;

[0136] The end plane segmentation module 804 is used to perform end plane stripping and segmentation on the reconstructed cable point cloud to obtain multiple end plane point clouds;

[0137] A sorting module 806 is used to sort the multiple end plane point clouds to obtain the cable end surface point cloud;

[0138] The statistics module 808 is used to perform size segment inner diameter statistics on preset key features in the cable end face point cloud to obtain inner diameter statistics results;

[0139] The measurement module 810 is used to measure the dimensions of key features based on the inner diameter statistical results to obtain the dimension measurement results of the key features in the high-voltage cable accessories.

[0140] 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.

[0141] It should be noted that the above data acquisition module 800, data processing module 802, end plane segmentation module 804, sorting module 806, statistics module 808, and measurement module 810 correspond to steps S102 to S112 in the embodiment, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules can be run in a computer terminal as part of the device.

[0142] 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.

[0143] The above-mentioned high-voltage cable accessory size measuring device may also include a processor and a memory. The above-mentioned data acquisition module 800, data processing module 802, end plane segmentation module 804, sorting module 806, statistics module 808, measurement module 810, 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.

[0144] 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.

[0145] 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 one of the above-mentioned high-voltage cable accessory size measurement methods.

[0146] 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.

[0147] Optionally, when the program is running, the device where the non-volatile storage medium is located is controlled to perform the following functions: obtain point cloud data of high-voltage cable accessories; process the point cloud data through reverse three-dimensional reconstruction to obtain a reconstructed cable point cloud; perform end plane peeling and segmentation on the reconstructed cable point cloud to obtain multiple end plane point clouds; sort the multiple end plane point clouds to obtain a cable end face point cloud; perform size segmentation inner diameter statistics on preset key features in the cable end face point cloud to obtain inner diameter statistical results; based on the inner diameter statistical results, perform size measurement on the key features to obtain size measurement results of the key features in the high-voltage cable accessories.

[0148] 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 high-voltage cable accessory size measurement methods is executed.

[0149] According to an embodiment of the present application, an embodiment of a computer program product is also provided. When executed on a data processing device, it is suitable for executing a program that initializes any one of the steps of the above-mentioned high-voltage cable accessory size measurement method.

[0150] 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 point cloud data of high-voltage cable accessories; processing the point cloud data through reverse three-dimensional reconstruction to obtain a reconstructed cable point cloud; performing end plane peeling and segmentation on the reconstructed cable point cloud to obtain multiple end plane point clouds; sorting the multiple end plane point clouds to obtain a cable end face point cloud; performing size segmentation inner diameter statistics on preset key features in the cable end face point cloud to obtain inner diameter statistical results; based on the inner diameter statistical results, performing size measurement on the key features to obtain size measurement results of the key features in the high-voltage cable accessories.

[0151] 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 point cloud data of high-voltage cable accessories; processing the point cloud data through reverse three-dimensional reconstruction to obtain a reconstructed cable point cloud; performing end plane peeling and segmentation on the reconstructed cable point cloud to obtain a plurality of end plane point clouds; sorting the plurality of end plane point clouds to obtain a cable end face point cloud; performing size segmentation inner diameter statistics on preset key features in the cable end face point cloud to obtain inner diameter statistics results; and based on the inner diameter statistics results, performing size measurement on the key features to obtain size measurement results of the key features in the high-voltage cable accessories.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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 measuring the dimensions of high-voltage cable accessories, characterized in that: include: Obtain point cloud data of high-voltage cable accessories; Processing the point cloud data through reverse three-dimensional reconstruction to obtain a reconstructed cable point cloud; Performing end plane peeling and segmentation on the reconstructed cable point cloud to obtain a plurality of end plane point clouds; Sorting the plurality of end plane point clouds to obtain a cable end surface point cloud; Performing size segmented inner diameter statistics on preset key features in the cable end face point cloud to obtain inner diameter statistics results; Based on the inner diameter statistical results, the key features are measured to obtain the size measurement results of the key features in the high-voltage cable accessories.

2. The method according to claim 1, characterized in that The step of performing end plane peeling and segmentation on the reconstructed cable point cloud to obtain a plurality of end plane point clouds includes: Determining directed bounding box features of the reconstructed cable point cloud; Based on the directed bounding box feature, coordinate system 1 is performed on the reconstructed cable point cloud to obtain a cable point cloud in a unified coordinate system; Determine the measurement direction of the stripping algorithm; Based on the measurement direction of the stripping algorithm, the cable point cloud in the unified coordinate system is segmented by end plane stripping to obtain the multiple end plane point clouds.

3. The method according to claim 2, characterized in that Determining the directed bounding box features of the reconstructed cable point cloud includes: Obtaining surface vertices of the reconstructed cable point cloud; Performing principal component analysis on the surface vertices to obtain a covariance matrix corresponding to the surface vertices; Determining the principal axis of the reconstructed cable point cloud based on the eigenvectors of the covariance matrix; The directed bounding box feature is obtained based on the principal axis of the reconstructed cable point cloud and the eigenvalues ​​of the covariance matrix.

4. The method according to claim 2, characterized in that: The step of performing coordinate system 1 on the reconstructed cable point cloud based on the directed bounding box feature to obtain a cable point cloud in a unified coordinate system includes: Based on the directed bounding box feature of the reconstructed cable point cloud, transform the principal axis of the reconstructed cable point cloud to the longitudinal axis of a predetermined two-dimensional coordinate system, and transform the centroid of the reconstructed cable point cloud to the origin of the coordinate system to obtain a centroid vector and a principal axis vector; Based on the centroid vector and the principal axis vector, the reconstructed cable point cloud is subjected to coordinate system one to obtain the cable point cloud in the unified coordinate system.

5. The method according to claim 3, characterized in that: Determining the measurement direction of the stripping algorithm includes: Calculate the lateral inner diameter of the reconstructed cable point cloud at the boundaries on both sides of the main axis of the directed bounding box feature; Based on the transverse inner diameter, a measurement direction of the spalling algorithm is determined.

6. The method according to claim 1, characterized in that The step of performing end plane peeling and segmentation on the reconstructed cable point cloud to obtain a plurality of end plane point clouds includes: For each point cloud in the reconstructed cable point cloud, a least square method is used to perform plane fitting on a neighborhood point set of each point cloud to obtain a plane fitting result; Based on the plane fitting result, determining the normal vector of each point cloud; Based on the normal vector of each point cloud, the reconstructed cable point cloud is subjected to end plane peeling and segmentation to obtain the multiple end plane point clouds.

7. The method according to claim 6, characterized in that The step of sorting the plurality of end plane point clouds to obtain the cable end surface point cloud comprises: Determine the centroid positions corresponding to the plurality of end plane point clouds respectively; The plurality of end plane point clouds are sorted according to the coordinate values ​​of the centroid positions respectively corresponding to the plurality of end plane point clouds along a predetermined measurement direction to obtain the cable end face point cloud.

8. The method according to claim 1, characterized in that The step of performing size segmented inner diameter statistics on the preset key features in the cable end face point cloud to obtain inner diameter statistics results includes: According to a predetermined time interval, the cable end face point cloud is segmented and detected along a predetermined measurement direction by using a straight-through filtering method to obtain a plurality of cylinders and end face information corresponding to the plurality of cylinders, wherein the end face information includes a first end face and a second end face, the plurality of cylinders are obtained by segmenting the cable end face point cloud, and the plurality of cylinders have the same length; Determine the inner diameters corresponding to the plurality of cylinders based on the end surface information corresponding to the plurality of cylinders; Searching for a first gradient change point and a second gradient change point in the inner diameters respectively corresponding to the plurality of cylinders in a sampling time sequence, wherein the first gradient change point and the second gradient change point are cylinder positions where the change amount of the inner diameter between two adjacent cylinders among the plurality of cylinders is greater than a predetermined change amount threshold, and the sampling time of the first gradient change point is earlier than the sampling time of the second gradient change point; Marking the first gradient change point as the bottom of the slope, and marking the second gradient change point as the top of the slope, to obtain a marking result; Based on the marking result, the inner diameter statistical result is obtained.

9. A device for measuring the dimensions of high-voltage cable accessories, characterized in that: include: A data acquisition module, used to acquire point cloud data of high-voltage cable accessories; A data processing module, used to process the point cloud data through reverse three-dimensional reconstruction to obtain a reconstructed cable point cloud; An end plane segmentation module is used to perform end plane peeling and segmentation on the reconstructed cable point cloud to obtain multiple end plane point clouds; A sorting module, used for sorting the plurality of end plane point clouds to obtain a cable end surface point cloud; A statistical module, used for performing size segment inner diameter statistics on preset key features in the cable end face point cloud to obtain inner diameter statistical results; The measuring module is used to measure the size of the key feature based on the inner diameter statistical result to obtain the size measurement result of the key feature in the high-voltage cable accessory.

10. An electronic device, characterized in that: It comprises 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 size measuring method as described in any one of claims 1 to 8.

Images