Cable defect detection method and device, nonvolatile storage medium and electronic equipment

Abstract

The invention discloses a cable defect detection method and device, a nonvolatile storage medium and electronic equipment. The method comprises the following steps: acquiring a target point cloud data set of a to-be-detected cable; the target point cloud data set is fitted to obtain a target cylinder model, and the target cylinder model is used for describing the distribution condition of the point cloud data set corresponding to the cable without the defect; screening out an abnormal point set in the target point cloud data set according to the target cylinder model and a preset abnormal condition; and determining the defect position of the to-be-detected cable according to the abnormal point set. The technical problem that the defects of the cable cannot be accurately detected due to the bending form of the cable is solved.

Description

Technical Field

[0001] The present invention relates to the field of high-voltage cable defect detection, and in particular to a cable defect detection method, device, non-volatile storage medium and electronic equipment. Background Art

[0002] The detection of the main insulation surface of high-voltage cables is of vital importance to ensure the safe and stable operation of the power system. The main insulation layer is the core component of the cable, which is responsible for isolating the current under high voltage and preventing current leakage and damage caused by external factors. Once defects such as cracks, bubbles, impurities, etc. appear on the main insulation surface, it may not only cause partial discharge and damage the cable, but also cause serious safety hazards to the entire power system. The existing detection methods for surface defects of the main insulation of high-voltage cables mainly include visual inspection, ultrasonic detection, laser ray detection, etc., but the above methods have certain problems in practical applications, especially when the cable is bent. For example, in visual inspection, the bent cable may lead to limited vision, making it difficult to directly observe some defects; although ultrasonic detection is more sensitive to internal defects of the material, when the cable is bent, the propagation path and reflection characteristics of the ultrasonic wave will change, which may cause the defect signal to be covered or misjudged; although laser ray detection can penetrate the cable surface and directly observe internal defects, it will also be affected by the bending and stress distribution of the cable, resulting in image quality degradation and difficulty in defect identification. Due to the bending shape of the cable, the main insulation layer may be deformed and the stress distribution is uneven, which affects the accuracy of the detection results.

[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 cable defect detection method, device, non-volatile storage medium and electronic device to at least solve the technical problem that defects existing in the cable cannot be accurately detected due to the bending shape of the cable.

[0005] According to one aspect of an embodiment of the present invention, a cable defect detection method is provided, comprising: obtaining a target point cloud data set of a cable to be tested; fitting the target point cloud data set to obtain a target cylindrical model, wherein the target cylindrical model is used to describe the distribution of a point cloud data set corresponding to a cable without defects; screening out an abnormal point set in the target point cloud data set based on the target cylindrical model and pre-set abnormal conditions; and determining the defect position of the cable to be tested based on the abnormal point set.

[0006] Optionally, obtaining a target point cloud data set of the cable to be tested includes: obtaining an original point cloud data set of the cable to be tested; and filtering the original point cloud data set to obtain a target point cloud data set.

[0007] Optionally, the original point cloud data set is filtered to obtain a target point cloud data set, including: determining a neighborhood point set of the target data point in the original point cloud data set according to a preset number of adjacent data points, wherein the neighborhood point set refers to a collection of multiple data points that are closest to the target data point; calculating the mean and standard deviation of the neighborhood point set; determining a first range according to the mean and standard deviation of the neighborhood point set; if the average distance between the target data point and multiple data points in the neighborhood point set is within the first range, the target data point does not need to be filtered out; if the average distance between the target data point and multiple data points in the neighborhood point set exceeds the first range, the target data point needs to be filtered out; and filtering the data points in the original point cloud data set in accordance with the above-mentioned method of filtering the target data points to obtain the target point cloud data set.

[0008] Optionally, the target point cloud data set is fitted to obtain a target cylindrical model, including: randomly selecting some data points in the point cloud data set as an initial credible point set; generating an initial cylindrical model based on the initial credible point set; respectively calculating the distances between a plurality of remaining data points in the target point cloud data set and the initial cylindrical model, wherein the plurality of remaining data points are other data points in the target point cloud data set except the initial credible point set; adding the remaining data points whose distances to the initial cylindrical model are less than a predetermined error to the initial credible point set to obtain a target credible point set; and updating the initial cylindrical model based on the target credible point set to obtain a target cylindrical model.

[0009] Optionally, based on the target cylindrical model and pre-set abnormal conditions, an abnormal point set in the target point cloud data set is screened out, including: respectively calculating the degree of deviation of all data points in the target point cloud data set from the target cylindrical model; taking multiple data points in the target point cloud data set whose degree of deviation is greater than a predetermined deviation threshold as abnormal data points, to obtain an abnormal point set.

[0010] Optionally, the defect position of the cable to be tested is determined based on the abnormal point set, including: taking the abnormal point set as the center, determining the data points within a preset radius as a defect structure point cloud set; using a three-dimensional rectangular structure that is adapted to the shape of the defect structure point cloud set to surround the defect point cloud, calculating the defect structure point cloud set, and obtaining the defect position of the cable to be tested.

[0011] According to another aspect of an embodiment of the present invention, a cable defect detection device is provided, including: an acquisition module, which acquires a target point cloud data set of a cable to be tested; a fitting module, which is used to fit the target point cloud data set to obtain a target cylindrical model, wherein the target cylindrical model is used to describe the distribution of a point cloud data set corresponding to a cable without defects; a screening module, which is used to screen out an abnormal point set in the target point cloud data set according to the target cylindrical model and pre-set abnormal conditions; and a determination module, which is used to determine the defect position of the cable to be tested according to the abnormal point set.

[0012] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided. The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing any one of the cable defect detection methods.

[0013] According to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors and a memory, the memory being 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 cable defect detection methods.

[0014] According to another aspect of the embodiments of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, any one of the above-mentioned cable defect detection methods is implemented.

[0015] In an embodiment of the present invention, a target point cloud data set of a cable to be tested is obtained; the target point cloud data set is fitted to obtain a target cylindrical model, wherein the target cylindrical model is used to describe the distribution of a point cloud data set corresponding to a cable without defects; an abnormal point set in the target point cloud data set is screened out according to the target cylindrical model and pre-set abnormal conditions; and the defect position of the cable to be tested is determined according to the abnormal point set, thereby solving the technical problem of being unable to accurately detect defects in the cable due to the bending shape of the cable, and achieving the technical effect of improving the accuracy of cable defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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:

[0017] Figure 1 is a flow chart of a cable defect detection method provided according to an embodiment of the present invention;

[0018] Figure 2 is a schematic diagram of the structure of a point cloud KD tree provided according to an embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of a neighborhood radius provided according to an embodiment of the present invention;

[0020] Figure 4 is a schematic diagram of a cable defect detection device provided according to an embodiment of the present invention;

[0021] Figure 5 is a schematic diagram of an electronic device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] 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.

[0023] 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.

[0024] According to an embodiment of the present invention, a method embodiment of cable defect detection 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 the 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 cable defect detection method according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0026] Step S102, obtaining a target point cloud data set of the cable to be tested;

[0027] In this step, a laser scanner, a 3D camera or similar 3D data acquisition equipment is used to collect high-density, high-resolution 3D data of the cable surface to obtain a data set that can accurately reflect the geometric characteristics of the cable surface, namely the "target point cloud data set".

[0028] In an optional embodiment, obtaining a target point cloud data set of the cable to be tested includes: obtaining an original point cloud data set of the cable to be tested; and filtering the original point cloud data set to obtain a target point cloud data set.

[0029] Optionally, after obtaining the original point cloud data set, the data points in the original point cloud data set are filtered, that is, statistical filtering or other filtering methods are applied to remove noise and outliers in the original point cloud data set, and retain high-quality data points closely related to the cable surface features, thereby obtaining a target point cloud data set. The target point cloud data set more accurately reflects the true geometric features of the cable surface, laying the foundation for subsequent fitting algorithms and defect detection.

[0030] In an optional embodiment, the original point cloud data set is filtered to obtain a target point cloud data set, including: determining a neighborhood point set of the target data point in the original point cloud data set according to a preset number of adjacent data points, wherein the neighborhood point set refers to a collection of multiple data points that are closest to the target data point; calculating a mean and a standard deviation of the neighborhood point set; determining a first range according to the mean and the standard deviation of the neighborhood point set; if the average distance between the target data point and multiple data points in the neighborhood point set is within the first range, the target data point does not need to be filtered out; if the average distance between the target data point and multiple data points in the neighborhood point set exceeds the first range, the target data point needs to be filtered out; and filtering the data points in the original point cloud data set in accordance with the above-mentioned method of filtering the target data points to obtain the target point cloud data set.

[0031] Optionally, based on a preset number of adjacent data points (k value), the neighborhood point set of the target data point is determined, and the neighborhood point set refers to a set of k data points that are closest to the current target data point. Calculate the average distance and standard deviation between all neighborhood points and the target data point, and set a first range based on the calculated mean and standard deviation. For each target data point in the original point cloud data set, if the average distance between the point and multiple data points in the neighborhood point set is within the first range, the target data point is considered a normal point and does not need to be filtered out; if the average distance between the target data and the neighborhood point set exceeds the first range, the point is considered an outlier or noise point and needs to be filtered out from the data set. All data points in the original point cloud data set are filtered in the above manner to obtain a new point cloud data set, namely the target point cloud data set.

[0032] As a specific embodiment, for the original point cloud data set P = {p i ,p2,…,p n} performs statistical analysis on the neighborhood of each point in the graph and calculates the target data point p i The distance S to the nearest k points i ;

[0033] According to the target data point p i The distance S to the nearest k points i , calculate the target data point p iThe average distance μ to the nearest k points is as follows:

[0034]

[0035] According to the target data point p i The distance S to the nearest k points i and the target data point p i The average distance μ to the nearest k points is used to calculate the target data point p i The standard deviation σ to the nearest k points is as follows:

[0036]

[0037] Judgment point p i Whether the average distance to its neighborhood is within the first range, i.e., (μ-std*σ, μ+std*σ), where std represents the standard deviation multiple. If the average distance between the target data point and its k neighboring points is within the first range, the target data point is retained, otherwise it is removed as an outlier, and all data points are filtered in the same way as the steps for filtering the target data point to obtain the filtered target point cloud data set.

[0038] Step S104, fitting the target point cloud data set to obtain a target cylindrical model, wherein the target cylindrical model is used to describe the distribution of the point cloud data set corresponding to the cable without defects;

[0039] In this step, fitting refers to matching the points in the cable point cloud data set with a mathematical model using mathematical methods (such as the least squares method and the random sample consensus algorithm) to find the optimal parameters of the model. In this solution, the goal of fitting is to establish a cylindrical model. The parameters of this model (such as the central axis, radius, length, etc. of the cylinder) will be determined by an optimization algorithm so that the model can match the distribution of the point cloud data as much as possible. Establishing the target cylindrical model can quantify and describe the geometric features of the normal surface of the cable, providing a benchmark for the subsequent detection of defect points.

[0040] In an optional embodiment, a target point cloud data set is fitted to obtain a target cylindrical model, including: randomly selecting some data points in the point cloud data set as an initial credible point set; generating an initial cylindrical model based on the initial credible point set; respectively calculating the distances between a plurality of remaining data points in the target point cloud data set and the initial cylindrical model, wherein the plurality of remaining data points are other data points in the target point cloud data set except the initial credible point set; adding the remaining data points whose distances to the initial cylindrical model are less than a predetermined error to the initial credible point set to obtain a target credible point set; and updating the initial cylindrical model based on the target credible point set to obtain a target cylindrical model.

[0041] Optionally, a small number of data points are randomly selected in the target point cloud data set as the initial credible point set. Based on the selected initial credible point set, an initial cylindrical model is generated through geometric calculation, and the Euclidean distance between each remaining data point (point not in the initial credible point set) and the initial cylindrical model is calculated, that is, the vertical distance from the point to the surface of the cylindrical model, and a predetermined error range is set. The data points whose Euclidean distance to the initial cylindrical model is less than the predetermined error range among the remaining data points are regarded as "inside points", that is, they are consistent with the expected shape of the model. These inside points are added to the initial credible point set to form the target credible point set. Based on the expanded target credible point set, the initial cylindrical model is updated, and the parameters such as the central axis and radius of the cylindrical model are recalculated to more accurately fit the point cloud data of the cable surface, thereby reducing the average error between all points and the cylindrical model. The above steps are an iterative process of the cylindrical model. In order to improve the robustness and accuracy of the model, the algorithm will repeat the above process many times, and each iteration will randomly select a different initial credible point set to generate a different initial cylindrical model, and then screen and update the model. Finally, the model parameters that can maximize the number of local points (i.e., the coverage of normal points in the point cloud data) are selected to obtain the optimized target cylindrical model.

[0042] As a specific embodiment, the point cloud data set is fitted based on the Random Sample Consensus Algorithm, and three points (p1, p2, p3) are randomly selected from the target point cloud data set as the credible point set to generate the initial cylindrical model; after the initial cylindrical model is generated, the remaining points in the target point cloud data set except (p1, p2, p3) are evaluated to see whether they match this model. The evaluation method is: calculate the points p in the data except (p1, p2, p3) one by one. a The Euclidean distance dis(p a ). If dis(p a )≤dis error , then p aIncorporate a trusted point set to build a more accurate cylindrical model, where dis error is the predetermined error range. a After being added to the trusted point set, the algorithm recalculates the new cylindrical model based on the current trusted point set and calculates the average error between all points in the trusted point set and the new cylindrical model. If the average error of the new cylindrical model If the error is smaller than the current optimal error, the new model will be retained and become the basis for the next round of updating of the cylindrical model.

[0043] If dis(p a )>dis error , the algorithm will not try to include it in the trusted point set, but will skip it directly, and finally obtain a cylindrical model that can maximize the coverage of normal points in the point cloud dataset.

[0044] Step S106, filtering out abnormal point sets in the target point cloud data set according to the target cylindrical model and the pre-set abnormal conditions;

[0045] In this step, after obtaining the target cylindrical model and setting the abnormal conditions, each point in the target point cloud data set is checked to determine whether it deviates from the surface of the target cylindrical model by more than the preset abnormal conditions. If the deviation of a point exceeds the set conditions, then the point is marked as an abnormal point, and all abnormal points will be collected to form an abnormal point set. By identifying and analyzing the abnormal point set, the defect position on the cable surface can be further located, the size and severity of the defect can be evaluated, and a basis can be provided for subsequent defect repair or cable maintenance.

[0046] In an optional embodiment, an abnormal point set in the target point cloud data set is screened out according to the target cylindrical model and pre-set abnormal conditions, including: respectively calculating the degree of deviation of all data points in the target point cloud data set from the target cylindrical model; taking multiple data points in the target point cloud data set whose deviation degree is greater than a predetermined deviation threshold as abnormal data points, to obtain an abnormal point set.

[0047] Optionally, after obtaining the target cylindrical model, the vertical distance from each point to the surface of the cylindrical model is calculated. This distance reflects the deviation between the point and the model, that is, the degree of deviation of the point. If the degree of deviation (i.e., the vertical distance) of a data point from the target cylindrical model is greater than or equal to a predetermined deviation threshold, then this point is regarded as an abnormal data point, and all abnormal data points are collected to form an abnormal point set. For example, the preset deviation threshold can be set to 0.05 mm, and points with a degree of deviation greater than 0.05 mm are identified as abnormal data points, thereby obtaining an abnormal point set.

[0048] Step S108, determining the defect location of the cable to be tested according to the abnormal point set.

[0049] In this step, after the abnormal point set is obtained, the abnormal point set is further analyzed and processed to identify the boundary of the defect, locate the center position of the defect, or determine the range of the defect.

[0050] In an optional embodiment, the defect position of the cable to be tested is determined based on the abnormal point set, including: taking the abnormal point set as the center, determining the data points within a preset radius as a defect structure point cloud set; using a three-dimensional rectangular structure that is adapted to the shape of the defect structure point cloud set to surround the defect point cloud, calculating the defect structure point cloud set, and obtaining the defect position of the cable to be tested.

[0051] Optionally, after the abnormal point set is screened, these points represent defects on the cable surface. In order to more accurately determine the scope of the defects, the abnormal point set needs to be further expanded. The specific steps of the expansion are as follows: Figure 2 As shown, a point cloud KD tree is constructed. KD tree is a data organization form in three-dimensional space. It uses dimensions to divide data and is mostly used to establish relationships in high-dimensional data, which can achieve fast retrieval of data. KD tree is a binary tree in which each node is a k-dimensional point. Taking two-dimensional data points as an example, after A(2,3), B(5,4), C(9,6), D(4,7), E(8,1), and F(7,2) are organized by KD tree, about 1 / 2 of the data points are located on the left side of the tree and 1 / 2 of the data points are located on the right side of the tree. When the space contains only one node, the construction process of KD tree ends.

[0052] like Figure 3 As shown in the figure, a neighbor search method based on a KD tree is used, that is, each point in the abnormal point set is taken as the center, a preset radius is set, and the point cloud data within the preset radius around it is searched. These nearby point clouds searched, if associated with the abnormal point, will be included in the defective structure point cloud set. After the defective structure point cloud set is determined, a three-dimensional rectangular structure, i.e., a bounding box, is used to enclose the defective structure point cloud set. The length, width, height and other features of the bounding box are calculated, which can intuitively represent the size information of the defect. At the same time, the position information of the bounding box also reflects the specific location of the defect on the cable.

[0053] The target point cloud data set of the cable to be tested is obtained through the above-mentioned method; the target point cloud data set is fitted to obtain a target cylindrical model, wherein the target cylindrical model is used to describe the distribution of the point cloud data set corresponding to the cable without defects; according to the target cylindrical model and pre-set abnormal conditions, the abnormal point set in the target point cloud data set is screened out; according to the abnormal point set, the defect position of the cable to be tested is determined, which solves the technical problem of being unable to accurately detect defects in the cable due to the bending shape of the cable, and achieves the technical effect of improving the accuracy of cable defect detection.

[0054] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation manner.

[0055] Step S1, obtaining a target point cloud data set of the cable to be tested, including: obtaining an original point cloud data set of the cable to be tested; filtering the original point cloud data set to obtain a target point cloud data set.

[0056] Optionally, after obtaining the original point cloud data set, the data points in the original point cloud data set are filtered, that is, statistical filtering or other filtering methods are applied to remove noise and outliers in the original point cloud data set, and retain high-quality data points closely related to the cable surface features, thereby obtaining a target point cloud data set. The target point cloud data set more accurately reflects the true geometric features of the cable surface, laying the foundation for subsequent fitting algorithms and defect detection.

[0057] Step S11, filtering the original point cloud data set to obtain a target point cloud data set, including: determining a neighborhood point set of the target data point in the original point cloud data set according to a preset number of adjacent data points, wherein the neighborhood point set refers to a collection of multiple data points that are closest to the target data point; calculating the mean and standard deviation of the neighborhood point set; determining a first range according to the mean and standard deviation of the neighborhood point set; if the average distance between the target data point and multiple data points in the neighborhood point set is within the first range, the target data point does not need to be filtered out; if the average distance between the target data point and multiple data points in the neighborhood point set exceeds the first range, the target data point needs to be filtered out; according to the above-mentioned method of filtering the target data point, the data points in the original point cloud data set are filtered to obtain the target point cloud data set.

[0058] Optionally, based on a preset number of adjacent data points (k value), the neighborhood point set of the target data point is determined, and the neighborhood point set refers to a set of k data points that are closest to the current target data point. The average distance and standard deviation between all neighborhood points and the target data point are calculated, and a first range is set based on the calculated mean and standard deviation. For each target data point in the original point cloud data set, if the average distance between the point and multiple data points in the neighborhood point set is within the first range, the target data point is considered a normal point and does not need to be filtered out; if the average distance between the target data and the neighborhood point set exceeds the first range, the point is considered an outlier or noise point and needs to be filtered out from the data set. Following the steps of filtering the target data point, all data points in the original point cloud data set are filtered to obtain a new point cloud data set, namely the target point cloud data set.

[0059] Step S2, fitting the target point cloud data set to obtain a target cylindrical model, including: randomly selecting some data points in the point cloud data set as an initial credible point set; generating an initial cylindrical model based on the initial credible point set; respectively calculating the distances between a plurality of remaining data points in the target point cloud data set and the initial cylindrical model, wherein the plurality of remaining data points are other data points in the target point cloud data set except the initial credible point set; adding the remaining data points whose distances to the initial cylindrical model are less than a predetermined error to the initial credible point set to obtain a target credible point set; and updating the initial cylindrical model based on the target credible point set to obtain a target cylindrical model.

[0060] Optionally, a small number of data points are randomly selected in the target point cloud data set as the initial credible point set. Based on the selected initial credible point set, an initial cylindrical model is generated through geometric calculation, and the Euclidean distance between each remaining data point (point not in the initial credible point set) and the initial cylindrical model is calculated, that is, the vertical distance from the point to the surface of the cylindrical model, and a predetermined error range is set. The data points whose Euclidean distance to the initial cylindrical model is less than the predetermined error range among the remaining data points are regarded as "inside points", that is, they are consistent with the expected shape of the model. These inside points are added to the initial credible point set to form the target credible point set. Based on the expanded target credible point set, the initial cylindrical model is updated, and the parameters such as the central axis and radius of the cylindrical model are recalculated to more accurately fit the point cloud data of the cable surface, thereby reducing the average error between all points and the cylindrical model. The above steps are an iterative process of the cylindrical model. In order to improve the robustness and accuracy of the model, the algorithm will repeat the above process many times, and each iteration will randomly select a different initial credible point set to generate a different initial cylindrical model, and then screen and update the model. Finally, the model parameters that can maximize the number of local points (i.e., the coverage of normal points in the point cloud data) are selected to obtain the optimized target cylindrical model.

[0061] Step S3, based on the target cylindrical model and the pre-set abnormal conditions, screen out the abnormal point set in the target point cloud data set, including: respectively calculating the degree of deviation of all data points in the target point cloud data set from the target cylindrical model; taking multiple data points in the target point cloud data set whose degree of deviation is greater than a predetermined deviation threshold as abnormal data points, to obtain an abnormal point set.

[0062] Optionally, after obtaining the target cylindrical model, the vertical distance from each point to the surface of the cylindrical model is calculated. This distance reflects the deviation between the point and the model, that is, the degree of deviation of the point. If the degree of deviation (i.e., the vertical distance) of a data point from the target cylindrical model is greater than or equal to a predetermined deviation threshold, then this point is regarded as an abnormal data point, and all abnormal data points are collected to form an abnormal point set. For example, the preset deviation threshold can be set to 0.05 mm, and points with a degree of deviation greater than 0.05 mm are identified as abnormal data points, thereby obtaining an abnormal point set.

[0063] Step S4, determining the defect position of the cable to be tested based on the abnormal point set, including: taking the abnormal point set as the center, determining the data points within a preset radius as a defect structure point cloud set; using a three-dimensional rectangular structure that is adapted to the shape of the defect structure point cloud set to surround the defect point cloud, calculating the defect structure point cloud set, and obtaining the defect position of the cable to be tested.

[0064] Optionally, after the abnormal point set is screened, these points represent defects on the cable surface. In order to more accurately determine the scope of the defects, the abnormal point set needs to be further expanded. The specific steps of the expansion are as follows: Figure 2 As shown, a point cloud KD tree is constructed. KD tree is a data organization form in three-dimensional space. It uses dimensions to divide data and is mostly used to establish relationships in high-dimensional data, which can achieve fast retrieval of data. KD tree is a binary tree in which each node is a k-dimensional point. Taking two-dimensional data points as an example, after A(2,3), B(5,4), C(9,6), D(4,7), E(8,1), and F(7,2) are organized by KD tree, about 1 / 2 of the data points are located on the left side of the tree and 1 / 2 of the data points are located on the right side of the tree. When the space contains only one node, the construction process of KD tree ends.

[0065] like Figure 3 As shown in the figure, a neighbor search method based on a KD tree is used, that is, each point in the abnormal point set is taken as the center, a preset radius is set, and the point cloud data within the preset radius around it is searched. These nearby point clouds searched, if associated with the abnormal point, will be included in the defective structure point cloud set. After the defective structure point cloud set is determined, a three-dimensional rectangular structure, i.e., a bounding box, is used to enclose the defective structure point cloud set. The length, width, height and other features of the bounding box are calculated, which can intuitively represent the size information of the defect. At the same time, the position information of the bounding box also reflects the specific location of the defect on the cable.

[0066] The above optional implementation achieves at least the following effects: solving the technical problem of being unable to accurately detect defects in the cable due to the bending shape of the cable, and achieving the technical effect of improving the accuracy of cable defect detection.

[0067] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0068] In this embodiment, a cable defect detection device is also provided, which is used to implement the above embodiments and preferred implementations, 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.

[0069] According to an embodiment of the present invention, there is also provided an embodiment of a device for implementing a cable defect detection method. Figure 4 A schematic diagram of a cable defect detection device according to an embodiment of the present invention is shown as follows Figure 4 As shown, the above-mentioned cable defect detection device includes an acquisition module 41, a fitting module 42, a screening module 43, and a determination module 44. The device is described below.

[0070] An acquisition module 41 is used to acquire a target point cloud data set of the cable to be tested;

[0071] The fitting module 42 is connected to the acquisition module 41 and is used to fit the target point cloud data set to obtain a target cylindrical model, wherein the target cylindrical model is used to describe the distribution of the point cloud data set corresponding to the cable without defects;

[0072] The screening module 43 is connected to the fitting module 42 and is used to screen out abnormal point sets in the target point cloud data set according to the target cylindrical model and the preset abnormal conditions;

[0073] The determination module 44 is connected to the screening module 43 and is used to determine the defect position of the cable to be tested according to the abnormal point set.

[0074] In a cable defect detection device provided by an embodiment of the present invention, an acquisition module is set to obtain a target point cloud data set of a cable to be tested; a fitting module is used to fit the target point cloud data set to obtain a target cylindrical model, wherein the target cylindrical model is used to describe the distribution of the point cloud data set corresponding to a cable without defects; a screening module is used to screen out abnormal point sets in the target point cloud data set according to the target cylindrical model and pre-set abnormal conditions; and a determination module is used to determine the defect position of the cable to be tested according to the abnormal point set, thereby solving the technical problem of being unable to accurately detect defects in the cable due to the bending shape of the cable, and achieving the technical effect of improving the accuracy of cable defect detection.

[0075] 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.

[0076] It should be noted that the acquisition module 41, the fitting module 42, the screening module 43, and the determination module 44 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.

[0077] 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.

[0078] The above-mentioned cable defect detection device may also include a processor and a memory. The acquisition module 41, the fitting module 42, the screening module 43, the determination module 44, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0079] The processor includes a kernel, which retrieves the corresponding program unit from the memory. There can be one or more kernels. 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, and the memory includes at least one storage chip.

[0080] An embodiment of the present invention provides a non-volatile storage medium on which a program is stored. When the program is executed by a processor, a cable defect detection method is implemented.

[0081] like Figure 5 It is shown that an embodiment of the present invention provides an electronic device, the electronic device 10 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: the memory is used to store a computer program, wherein, when the computer program is executed by the processor, the processor implements the above-mentioned cable defect detection method. The device in this article can be a server, a PC, etc.

[0082] The present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: computer instructions are executed by a processor to perform the above-mentioned cable defect detection method.

[0083] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0084] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0085] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0087] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0088] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0089] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0090] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0091] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0092] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A cable defect detection method, characterized in that: include: Obtain a target point cloud data set of the cable to be tested; Fitting the target point cloud data set to obtain a target cylindrical model, wherein the target cylindrical model is used to describe the distribution of the point cloud data set corresponding to the cable without defects; According to the target cylindrical model and the pre-set abnormal conditions, filtering out the abnormal point set in the target point cloud data set; The defect position of the cable to be tested is determined according to the abnormal point set.

2. The method according to claim 1, characterized in that The step of obtaining a target point cloud data set of the cable to be tested comprises: Obtain the original point cloud data set of the cable to be tested; The original point cloud data set is filtered to obtain the target point cloud data set.

3. The method according to claim 2, characterized in that The filtering of the original point cloud data set to obtain the target point cloud data set includes: Determine a neighborhood point set of a target data point in the original point cloud data set according to a preset number of adjacent data points, wherein the neighborhood point set refers to a set of multiple data points that are closest to the target data point; Calculate the mean and standard deviation of the neighborhood point set; Determining a first range according to the mean and standard deviation of the neighborhood point set; If the average distance between the target data point and a plurality of data points in the neighborhood point set is within the first range, the target data point does not need to be filtered out; If the average distance between the target data point and a plurality of data points in the neighborhood point set exceeds the first range, the target data point needs to be filtered out; According to the above-mentioned method of filtering the target data points, the data points in the original point cloud data set are filtered to obtain the target point cloud data set.

4. The method according to claim 1, characterized in that: The step of fitting the target point cloud data set to obtain a target cylindrical model includes: Randomly selecting some data points in the point cloud data set as an initial credible point set; Generate an initial cylindrical model according to the initial credible point set; Respectively calculating the distances between a plurality of remaining data points in the target point cloud data set and the initial cylindrical model, wherein the plurality of remaining data points are other data points in the target point cloud data set except the initial credible point set; Add the remaining data points whose distances from the initial cylindrical model are less than a predetermined error to the initial credible point set to obtain a target credible point set; The initial cylindrical model is updated according to the target credible point set to obtain the target cylindrical model.

5. The method according to claim 1, characterized in that The step of screening out an abnormal point set in the target point cloud data set according to the target cylindrical model and a preset abnormal condition includes: Calculating the degree of deviation between all data points in the target point cloud data set and the target cylindrical model respectively; A plurality of data points in the target point cloud data set whose deviation degree is greater than a predetermined deviation threshold are taken as abnormal data points to obtain the abnormal point set.

6. The method according to claim 1, characterized in that The step of determining the defect position of the cable to be tested according to the abnormal point set includes: Taking the abnormal point set as the center, determining the data points within a preset radius as the defective structure point cloud set; A three-dimensional rectangular structure adapted to the shape of the defective structure point cloud set is used to surround the defective point cloud set, and the defective structure point cloud set is calculated to obtain the defect position of the cable to be tested.

7. A cable defect detection device, characterized in that: include: An acquisition module is used to acquire a target point cloud data set of the cable to be tested; A fitting module, used for fitting the target point cloud data set to obtain a target cylindrical model, wherein the target cylindrical model is used to describe the distribution of the point cloud data set corresponding to the cable without defects; A screening module, used for screening out abnormal point sets in the target point cloud data set according to the target cylindrical model and pre-set abnormal conditions; The determination module is used to determine the defect position of the cable to be tested according to the abnormal point set.

8. 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 cable defect detection method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: 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 cable defect detection method described in any one of claims 1 to 6.

10. A computer program product comprising computer instructions, characterized in that: The computer instructions are executed by the processor to implement the cable defect detection method according to any one of claims 1 to 6.

Images