A method, apparatus, device and medium for risk assessment of cable curvature

Abstract

The application discloses a kind of cable curvature risk assessment method, device, equipment and medium, belong to the risk assessment field of cable curvature.The method is: obtaining the visible image of the cable to be measured and extracting two-dimensional contour data;The cable to be measured is scanned non-contact, and three-dimensional point cloud data is obtained;Two-dimensional contour data is mapped to the three-dimensional coordinate system in which three-dimensional point cloud data is located, to obtain the three-dimensional point set after fusion, and least square method is used to fit spline curve;Finally, the risk assessment of the spline curve is carried out, and the risk assessment result of the cable to be measured is obtained.Therefore, by implementing the present application, the problem of low accuracy of cable curvature risk assessment in the prior art can be solved.

Description

Technical Field

[0001] This invention relates to the field of risk assessment of cable curvature, and more particularly to a method, apparatus, equipment and medium for risk assessment of cable curvature. Background Technology

[0002] During the laying of power cables, controlling the radius of curvature is one of the key factors in ensuring the long-term safe operation of the cables. If the radius of curvature is too small, the internal structure of the cable may be damaged due to excessive bending, thereby affecting its electrical performance and service life. Different voltage levels and different specifications of cables have their own strict standard requirements for the radius of curvature. Therefore, during the laying and acceptance phase, it is necessary to accurately measure and assess the bending state of the cable to determine whether it meets the design requirements and avoid safety hazards or equipment failures caused by improper curvature.

[0003] Accurate measurement of cable curvature is crucial for ensuring the quality of power cable laying. Insufficient bending radius can damage the internal structure, affecting service life and operational safety. Currently, cable curvature measurement primarily relies on binocular vision systems to acquire 3D point cloud data, calculating curvature by analyzing the cable's spatial morphology. However, relying solely on binocular cameras for point cloud data has significant limitations in practical applications: pure point cloud data lacks the ability to finely depict cable surface texture and local contours, making it difficult to accurately identify cable boundaries and axial direction, thus affecting the accuracy of curvature calculations. Because curvature measurement results themselves contain biases, subsequent laying quality assessments, safety analyses, and risk assessments based on these results will also lose reliability, potentially leading to incorrect judgments by acceptance personnel regarding the cable's actual condition and even creating safety hazards. Therefore, existing technologies often struggle to guarantee the accuracy of curvature measurements under complex operating conditions, failing to meet the high reliability requirements of power engineering acceptance results, and consequently affecting the accuracy of risk assessments. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for risk assessment of cable curvature, which can solve the problem of low accuracy in risk assessment of cable curvature in the prior art.

[0005] In a first aspect, embodiments of the present invention provide a method for risk assessment of cable curvature, comprising: A first visible image of the cable under test is acquired, and contour extraction is performed on the first visible image to obtain the two-dimensional contour data of the cable under test. The cable under test is scanned non-contactly according to a preset sampling frequency to obtain three-dimensional point cloud data of the cable under test in three-dimensional space. The two-dimensional contour data is mapped to the three-dimensional coordinate system where the three-dimensional point cloud data is located to obtain the first three-dimensional point set. Based on the first three-dimensional point set, the least squares method is used to fit the spline curve to obtain the first spline curve. Risk assessment is performed based on the first spline curve to obtain the risk assessment result of the cable under test.

[0006] This application embodiment acquires high-resolution visible images of the cable under test and extracts its contours, accurately capturing the cable's boundary and surface texture features. This compensates for the lack of detail in pure point cloud data, providing a reliable two-dimensional geometric basis for subsequent curvature calculation. Secondly, by acquiring three-dimensional point cloud data through non-contact scanning, the overall shape and orientation of the cable can be described in spatial dimension, providing necessary three-dimensional spatial information for curvature analysis. Based on this, the two-dimensional contour data is mapped to the three-dimensional point cloud coordinate system, achieving spatial registration and deep fusion of the two types of data. This utilizes point cloud data to locate the cable's spatial orientation and image contours to constrain the cable's precise shape, effectively suppressing errors caused by a single data source. Subsequently, by using the least squares method to fit spline curves, a continuous and smooth cable axis curve can be extracted from the fused discrete point set, further eliminating local fluctuations and outlier interference in the original data, making the fitted curve more realistically reflect the actual three-dimensional shape of the cable. Finally, risk assessment is performed based on this spline curve, which can more accurately calculate the curvature values ​​at various locations of the cable and compare them with preset thresholds, thereby generating reliable risk assessment results. In summary, this application can solve the problem of low accuracy in risk assessment of cable curvature in the prior art.

[0007] As a preferred example of the first aspect, the step of fitting a spline curve using the least squares method based on the first three-dimensional point set to obtain the first spline curve includes: Based on the distribution of 3D points in the first 3D point set, an objective function for spline curve fitting is constructed. Using the coordinates of the 3D point cloud as constraints, the control vertices and node vectors are determined by minimizing the objective function. The first spline curve is generated based on the control vertex and the node vector.

[0008] In this preferred example, by constructing an objective function based on the three-dimensional point distribution and minimizing it using point cloud coordinates as constraints, the spline curve control vertices and node vectors that best represent the actual shape of the cable can be adaptively determined. This has two advantages: firstly, the objective function constructed based on the point cloud distribution characteristics ensures that the fitting process fully considers the actual spatial shape of the cable; secondly, using point cloud coordinates as constraints ensures an accurate match between the fitted curve and the measured data. The resulting spline curve accurately approximates the cable's true three-dimensional axis, providing a precise mathematical model foundation for subsequent curvature calculations and significantly improving the accuracy of cable curvature measurement.

[0009] As a preferred example of the first aspect, generating the first spline curve based on the control vertex and the node vector includes: The first spline curve is obtained by using the control vertex as the control point of the first spline curve and the node vector as the node sequence of the first spline curve, and by calculating using a preset spline curve basis function.

[0010] In this preferred example, using the optimized control vertices and node vectors as core parameters, a smooth spline curve capable of accurately representing the actual shape of the cable is generated through mathematical reconstruction using spline curve basis functions. Its function is as follows: the control vertices determine the overall direction and local shape of the curve, while the node vectors control the continuity and smoothness of the curve in each interval. Together, they ensure that the generated spline curve faithfully fits the discrete point cloud data while possessing ideal geometric smoothness. This curve generation mechanism provides a continuous and differentiable mathematical model for subsequent curvature calculations, eliminating calculation errors caused by discrete point data, thereby guaranteeing the accuracy and reliability of curvature measurement.

[0011] As a preferred example of the first aspect, the step of mapping the two-dimensional contour data to the three-dimensional coordinate system where the three-dimensional point cloud data is located to obtain a first three-dimensional point set includes: By using a preset perspective transformation matrix, each feature point in the two-dimensional contour data is projected onto the three-dimensional coordinate system where the three-dimensional point cloud data is located, to obtain a second three-dimensional point set. The outliers in the second three-dimensional point set are removed using a random sampling consensus algorithm to obtain the first three-dimensional point set.

[0012] In this preferred example, the two-dimensional contour feature points are accurately projected onto the three-dimensional coordinate system using a perspective transformation matrix, achieving effective fusion of two-dimensional image information and three-dimensional spatial data, laying a spatial consistency foundation for subsequent calculations. Subsequently, a random sampling consensus algorithm is used to process the projected point set. Through iterative fitting and threshold judgment, outliers caused by equipment vibration, environmental interference, or scanning errors are effectively identified and eliminated. This denoising mechanism significantly improves the purity and reliability of the three-dimensional point cloud data, eliminates the interference of noise points on the description of the cable axis morphology, and ensures that the data used for subsequent curvature calculations accurately reflects the actual spatial orientation of the cable, thereby improving the accuracy of the measurement results.

[0013] As a preferred example of the first aspect, the step of extracting the contour from the first visible image to obtain the two-dimensional contour data of the cable under test includes: The first visible image is subjected to background noise filtering to obtain the second visible image; Based on a preset deep learning model, cable edge recognition is performed on the second visible image to obtain the two-dimensional contour data of the cable under test.

[0014] In this preferred example, background noise filtering effectively eliminates environmental interference in the image, improving the signal-to-noise ratio and image quality, and providing a clear and reliable image foundation for subsequent contour extraction. Subsequently, cable edge recognition is performed based on a pre-defined deep learning model. Leveraging the powerful feature extraction capabilities of neural networks, the edge features of the cable can be accurately identified from complex backgrounds, generating continuous two-dimensional contour data. This combined approach solves the problem of accurately locating cable boundaries in low-light and cluttered backgrounds using traditional image processing methods, ensuring the accuracy and continuity of two-dimensional contour extraction and providing high-quality data support for subsequent fusion with three-dimensional point cloud data.

[0015] As a preferred example of the first aspect, the step of performing a risk assessment based on the first spline curve to obtain the risk assessment result of the cable under test includes: The first spline curve is differentiated to obtain the first and second derivatives of each point in the first spline curve. Based on the first and second derivatives of each point, the curvature is calculated using the curvature formula to obtain the curvature of each position in the first spline curve. The curvature at each of the aforementioned locations is sequentially compared with a preset risk threshold to generate several comparison results, and a risk assessment result for the cable under test is generated based on each of the comparison results.

[0016] In this preferred example, by performing differentiation on the spline curve, the first and second derivatives at each point on the curve are obtained. Based on the curvature formula, the curvature value at each location is accurately calculated, thus transforming the cable's geometry into quantified bending data. On this basis, the curvature at each location is compared with a preset risk threshold, and a risk assessment result is automatically generated through point-by-point judgment. The advantages of this combined approach are: differentiation ensures the mathematical rigor and continuity of curvature calculation, solving the problem that discrete point data is difficult to accurately describe bending characteristics; risk threshold comparison directly links the measurement results to engineering acceptance standards, realizing an automated closed loop from data acquisition to risk assessment, providing an objective and quantitative decision-making basis for cable laying quality evaluation.

[0017] As a preferred example of the first aspect, the step of sequentially comparing the curvature at each of the aforementioned locations with a preset risk threshold to generate comparison results, and generating a risk assessment result for the cable under test based on each of the comparison results, includes: The curvature of each position is compared with the preset risk threshold in sequence. If the curvature of any position exceeds the preset risk threshold, the comparison result corresponding to the position is determined to be in an over-limit state; otherwise, it is in a normal state. If at least one comparison result indicates an out-of-limit condition, a risk assessment result is generated indicating that the cable under test has a risk; if all comparison results indicate a normal condition, a risk assessment result is generated indicating that the cable under test has no risk.

[0018] In this preferred example, the cable bending state is accurately determined by comparing the curvature values ​​at each location with a preset risk threshold point by point: if the curvature exceeds the threshold, it is marked as an over-limit state; otherwise, it is a normal state, thus transforming continuous curvature measurement results into discrete state determinations. Based on this, a logical synthesis is used to determine whether an over-limit state exists, automatically generating the final risk assessment result. The advantages of this combined approach are: the point-by-point comparison mechanism ensures that anomalies at each bending location are detected promptly, avoiding the problem of localized excessive bending being masked by overall averaging; the logical closed loop of state determination and result generation provides acceptance personnel with clear and objective decision-making basis, solving the problems of traditional methods relying on manual experience and inconsistent assessment standards, and significantly improving the accuracy and reliability of risk assessment.

[0019] Secondly, the present invention provides a risk assessment device for cable curvature, comprising: a first assessment module, a second assessment module, a third assessment module, and a fourth assessment module; The first evaluation module is used to acquire a first visible image of the cable under test and extract the contour of the first visible image to obtain two-dimensional contour data of the cable under test. The second evaluation module is used to perform a non-contact scanning operation on the cable under test according to a preset sampling frequency to obtain the three-dimensional point cloud data of the cable under test in three-dimensional space. The third evaluation module is used to map the two-dimensional contour data to the three-dimensional coordinate system where the three-dimensional point cloud data is located to obtain a first three-dimensional point set, and to fit a spline curve using the least squares method based on the first three-dimensional point set to obtain a first spline curve. The fourth assessment module is used to perform risk assessment based on the first spline curve to obtain the risk assessment result of the cable under test.

[0020] As a preferred example of the second aspect, the step of fitting a spline curve using the least squares method based on the first three-dimensional point set to obtain the first spline curve includes: Based on the distribution of 3D points in the first 3D point set, an objective function for spline curve fitting is constructed. Using the coordinates of the 3D point cloud as constraints, the control vertices and node vectors are determined by minimizing the objective function. The first spline curve is generated based on the control vertex and the node vector.

[0021] As a preferred example of the second aspect, generating the first spline curve based on the control vertex and the node vector includes: The first spline curve is obtained by using the control vertex as the control point of the first spline curve and the node vector as the node sequence of the first spline curve, and by calculating using a preset spline curve basis function.

[0022] As a preferred example of the second aspect, the step of mapping the two-dimensional contour data to the three-dimensional coordinate system where the three-dimensional point cloud data resides to obtain a first three-dimensional point set includes: By using a preset perspective transformation matrix, each feature point in the two-dimensional contour data is projected onto the three-dimensional coordinate system where the three-dimensional point cloud data is located, to obtain a second three-dimensional point set. The outliers in the second three-dimensional point set are removed using a random sampling consensus algorithm to obtain the first three-dimensional point set.

[0023] As a preferred example of the second aspect, the step of extracting the contour from the first visible image to obtain the two-dimensional contour data of the cable under test includes: The first visible image is subjected to background noise filtering to obtain the second visible image; Based on a preset deep learning model, cable edge recognition is performed on the second visible image to obtain the two-dimensional contour data of the cable under test.

[0024] As a preferred example of the second aspect, the step of performing a risk assessment based on the first spline curve to obtain the risk assessment result of the cable under test includes: The first spline curve is differentiated to obtain the first and second derivatives of each point in the first spline curve. Based on the first and second derivatives of each point, the curvature is calculated using the curvature formula to obtain the curvature of each position in the first spline curve. The curvature at each of the aforementioned locations is sequentially compared with a preset risk threshold to generate several comparison results, and a risk assessment result for the cable under test is generated based on each of the comparison results.

[0025] As a preferred example of the second aspect, the step of sequentially comparing the curvature at each of the aforementioned locations with a preset risk threshold to generate comparison results, and generating a risk assessment result for the cable under test based on each of the comparison results, includes: The curvature of each position is compared with the preset risk threshold in sequence. If the curvature of any position exceeds the preset risk threshold, the comparison result corresponding to the position is determined to be in an over-limit state; otherwise, it is in a normal state. If at least one comparison result indicates an out-of-limit condition, a risk assessment result is generated indicating that the cable under test has a risk; if all comparison results indicate a normal condition, a risk assessment result is generated indicating that the cable under test has no risk.

[0026] In summary, this application's embodiments, by acquiring high-resolution visible images of the cable under test and extracting its contours, can accurately capture the cable's boundary and surface texture features, compensating for the shortcomings of pure point cloud data in detail depiction and providing a reliable two-dimensional geometric basis for subsequent curvature calculation. Secondly, by acquiring three-dimensional point cloud data through non-contact scanning, the overall shape and orientation of the cable can be described in spatial dimension, providing necessary three-dimensional spatial information for curvature analysis. On this basis, the two-dimensional contour data is mapped to the three-dimensional point cloud coordinate system, realizing spatial registration and deep fusion of the two types of data. This utilizes point cloud data to locate the cable's spatial orientation and uses image contours to constrain the cable's precise shape, thereby effectively suppressing errors caused by a single data source. Subsequently, by using the least squares method to fit spline curves, a continuous and smooth cable axis curve can be extracted from the fused discrete point set, further eliminating local fluctuations and outlier interference in the original data, making the fitted curve more realistically reflect the actual three-dimensional shape of the cable. Finally, risk assessment based on this spline curve can more accurately calculate the curvature values ​​at various locations of the cable and compare them with preset thresholds, thereby generating reliable risk assessment results. In summary, this application can solve the problem of low accuracy in risk assessment of cable curvature in the prior art.

[0027] Another embodiment of the present invention provides a cable curvature risk assessment device, including an image acquisition device, a point cloud data acquisition device, a lighting device, a data processing device, a human-computer interaction device, and a lithium battery. The risk assessment device is used to perform the steps of the cable curvature risk assessment method of the present invention.

[0028] Another embodiment of the present invention also provides a computer-readable storage medium item, including: a stored computer program, which, when the computer program is running, controls the device where the computer-readable storage medium is located to perform steps such as the cable curvature risk assessment method of the present invention. Attached Figure Description

[0029] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0030] Figure 1 A flowchart illustrating an embodiment of a cable curvature risk assessment method provided by the present invention; Figure 2 A structural diagram of a cable curvature risk assessment device, which is an embodiment of a cable curvature risk assessment method provided by the present invention; Figure 3 A visible image of the cable under test, as an embodiment of a risk assessment method for cable curvature provided by the present invention; Figure 4 A two-dimensional profile of the cable under test, as an embodiment of a risk assessment method for cable curvature provided by the present invention; Figure 5 A three-dimensional point cloud data map of the cable under test, which is an embodiment of the cable curvature risk assessment method provided by the present invention; Figure 6 A fusion result diagram of two-dimensional contour data and three-dimensional point cloud data of an embodiment of a cable curvature risk assessment method provided by the present invention; Figure 7 This is a module structure diagram of one embodiment of a cable curvature risk assessment device provided by the present invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0033] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0034] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0035] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0036] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0037] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0038] Example 1 See Figure 1 To address the issue of low accuracy in risk assessment of cable curvature in existing technologies, an embodiment of the present invention provides a method for risk assessment of cable curvature, comprising: S1. Obtain a first visible image of the cable under test, and extract the contour of the first visible image to obtain the two-dimensional contour data of the cable under test. In a preferred embodiment, the step of extracting the contour from the first visible image to obtain the two-dimensional contour data of the cable under test includes: The first visible image is subjected to background noise filtering to obtain the second visible image; Based on a preset deep learning model, cable edge recognition is performed on the second visible image to obtain the two-dimensional contour data of the cable under test.

[0039] Specifically, acquiring the first visible image of the cable under test can be implemented through the following preferred method: The first visible image of the cable under test is acquired using a risk assessment device for cable curvature, such as... Figure 2 As shown, the risk assessment equipment for cable curvature is mainly composed of the cable under test (1), image acquisition device (2), point cloud data acquisition device (3), lighting device (4), data processing device (5), human-computer interaction device (6), and lithium battery (7).

[0040] First, fix the testing equipment at a distance of 1m from the laying path of the cable to be tested (1), turn on the lithium battery (7) to power it, select the automatic testing mode through the human-computer interaction device (6), and the system automatically initializes the image acquisition device (2) and the point cloud data acquisition device (3).

[0041] Next, the LED light source of the lighting device (4) is adjusted, and the dual industrial cameras of the image acquisition device (2) simultaneously acquire visible images of the cable surface as the first visible image.

[0042] For example, a field inspection of a 110kV cross-linked polyethylene cable (120mm in diameter) yielded the following visible images: Figure 3 As shown, the obtained two-dimensional contour data is as follows: Figure 4 As shown.

[0043] S2. Perform a non-contact scanning operation on the cable under test according to a preset sampling frequency to obtain the three-dimensional point cloud data of the cable under test in three-dimensional space. For example, on-site testing was performed on a 110kV cross-linked polyethylene cable (120mm in diameter), and the resulting three-dimensional point cloud data is as follows: Figure 5 As shown.

[0044] S3. Map the two-dimensional contour data to the three-dimensional coordinate system where the three-dimensional point cloud data is located to obtain the first three-dimensional point set, and use the least squares method to fit the spline curve based on the first three-dimensional point set to obtain the first spline curve. As a preferred embodiment, the step of fitting a spline curve using the least squares method based on the first three-dimensional point set to obtain the first spline curve includes: Based on the distribution of 3D points in the first 3D point set, an objective function for spline curve fitting is constructed. Using the coordinates of the 3D point cloud as constraints, the control vertices and node vectors are determined by minimizing the objective function. The first spline curve is generated based on the control vertex and the node vector.

[0045] In a preferred embodiment, generating the first spline curve based on the control vertex and the node vector includes: The first spline curve is obtained by using the control vertex as the control point of the first spline curve and the node vector as the node sequence of the first spline curve, and by calculating using a preset spline curve basis function.

[0046] As a preferred embodiment, mapping the two-dimensional contour data to the three-dimensional coordinate system where the three-dimensional point cloud data resides to obtain a first three-dimensional point set includes: By using a preset perspective transformation matrix, each feature point in the two-dimensional contour data is projected onto the three-dimensional coordinate system where the three-dimensional point cloud data is located, to obtain a second three-dimensional point set. The outliers in the second three-dimensional point set are removed using a random sampling consensus algorithm to obtain the first three-dimensional point set.

[0047] Specifically, mapping the two-dimensional contour data to the three-dimensional coordinate system where the three-dimensional point cloud data is located to obtain a first three-dimensional point set, and fitting a spline curve using the least squares method based on the first three-dimensional point set to obtain a first spline curve, can be implemented in the following preferred manner: A perspective transformation matrix is ​​constructed based on the camera's intrinsic and extrinsic parameters, as well as the transformation relationship from the image coordinate system to the world coordinate system. Using this matrix, each feature point on the 2D contour is projected into 3D space, resulting in a corresponding 3D point set. Next, the RANSAC algorithm is used to process the 3D point set. An appropriate distance threshold is set, and random sample points are iteratively selected to fit the initial model. The distance from other points to the model is calculated, and points with a distance less than the threshold are considered inliers, while those with a distance greater than the threshold are identified as outliers and removed, resulting in cleaner 3D point cloud data for the cable. Then, for the 3D point cloud data after outlier removal, a spline curve is fitted using the least squares method. Specifically, an appropriate spline curve type, such as a B-spline curve, is selected based on the distribution of the 3D points. Then, using the coordinates of the 3D points as constraints, an objective function is constructed. By minimizing this objective function, the control vertices and node vectors of the spline curve are determined, ensuring that the fitted spline curve best approximates the actual 3D shape of the cable. Finally, the curvature value is calculated based on the fitted spline curve. By differentiating the spline curve, the first and second derivatives at each point on the curve are obtained. Then, using the curvature calculation formula, the curvature value of the cable at different positions in three-dimensional space can be accurately calculated, providing key geometric parameters for subsequent cable condition analysis and fault diagnosis.

[0048] For example, on-site testing of a 110kV cross-linked polyethylene cable (120mm in diameter) yielded the fusion result of two-dimensional contour data and three-dimensional point cloud data, as shown below. Figure 6 As shown.

[0049] S4. Perform a risk assessment on the first spline curve to obtain the risk assessment result of the cable under test.

[0050] In a preferred embodiment, the step of performing a risk assessment based on the first spline curve to obtain the risk assessment result of the cable under test includes: The first spline curve is differentiated to obtain the first and second derivatives of each point in the first spline curve. Based on the first and second derivatives of each point, the curvature is calculated using the curvature formula to obtain the curvature of each position in the first spline curve. The curvature at each of the aforementioned locations is sequentially compared with a preset risk threshold to generate several comparison results, and a risk assessment result for the cable under test is generated based on each of the comparison results.

[0051] In a preferred embodiment, the step of sequentially comparing the curvature at each of the aforementioned locations with a preset risk threshold to generate comparison results, and generating a risk assessment result for the cable under test based on each comparison result, includes: The curvature of each position is compared with the preset risk threshold in sequence. If the curvature of any position exceeds the preset risk threshold, the comparison result corresponding to the position is determined to be in an over-limit state; otherwise, it is in a normal state. If at least one comparison result indicates an out-of-limit condition, a risk assessment result is generated indicating that the cable under test has a risk; if all comparison results indicate a normal condition, a risk assessment result is generated indicating that the cable under test has no risk.

[0052] Specifically, the risk assessment of the first spline curve to obtain the risk assessment result of the cable under test can be implemented in the following preferred manner: The human-machine interface device (6) has a built-in preset curvature threshold parameter, which is set comprehensively based on the material characteristics of the cable, the laying environment, the service life, and relevant industry standards. When the curvature value of any point in the curvature value transmitted by the data processing device (5) exceeds this preset threshold, the human-machine interface device (6) will immediately trigger the out-of-tolerance warning mechanism. The warning method includes, but is not limited to, displaying the coordinate information of the out-of-tolerance location and the specific curvature value in bright red font on the LCD screen, and simultaneously emitting a buzzer prompt sound so that the operator can quickly detect the abnormality. At the same time, the system will automatically store the detailed information of this out-of-tolerance event, including the occurrence time, location coordinates, curvature value, and the corresponding original three-dimensional point cloud data fragment, into the local database to provide complete data support for subsequent fault tracing, trend analysis, and maintenance decisions. The operator can view historical out-of-tolerance records, adjust the warning threshold parameter, and export relevant data reports through the operation buttons or touch interface on the human-machine interface device (6).

[0053] In summary, this application's embodiments, by acquiring high-resolution visible images of the cable under test and extracting its contours, can accurately capture the cable's boundary and surface texture features, compensating for the shortcomings of pure point cloud data in detail depiction and providing a reliable two-dimensional geometric basis for subsequent curvature calculation. Secondly, by acquiring three-dimensional point cloud data through non-contact scanning, the overall shape and orientation of the cable can be described in spatial dimension, providing necessary three-dimensional spatial information for curvature analysis. On this basis, the two-dimensional contour data is mapped to the three-dimensional point cloud coordinate system, realizing spatial registration and deep fusion of the two types of data. This utilizes point cloud data to locate the cable's spatial orientation and uses image contours to constrain the cable's precise shape, thereby effectively suppressing errors caused by a single data source. Subsequently, by using the least squares method to fit spline curves, a continuous and smooth cable axis curve can be extracted from the fused discrete point set, further eliminating local fluctuations and outlier interference in the original data, making the fitted curve more realistically reflect the actual three-dimensional shape of the cable. Finally, risk assessment based on this spline curve can more accurately calculate the curvature values ​​at various locations of the cable and compare them with preset thresholds, thereby generating reliable risk assessment results. In summary, this application can solve the problem of low accuracy in risk assessment of cable curvature in the prior art.

[0054] Example 2 like Figure 7 As shown, based on the above method embodiments, corresponding device embodiments are provided; An embodiment of the present invention provides a risk assessment device for cable curvature, comprising: a first assessment module 71, a second assessment module 72, a third assessment module 73, and a fourth assessment module 74; The first evaluation module 71 is used to acquire a first visible image of the cable under test and extract the contour of the first visible image to obtain two-dimensional contour data of the cable under test. The second evaluation module 72 is used to perform a non-contact scanning operation on the cable under test according to a preset sampling frequency to obtain the three-dimensional point cloud data of the cable under test in three-dimensional space. The third evaluation module 73 is used to map the two-dimensional contour data to the three-dimensional coordinate system where the three-dimensional point cloud data is located to obtain a first three-dimensional point set, and to fit a spline curve using the least squares method based on the first three-dimensional point set to obtain a first spline curve. The fourth assessment module 74 is used to perform risk assessment based on the first spline curve to obtain the risk assessment result of the cable under test.

[0055] As a preferred embodiment, the step of fitting a spline curve using the least squares method based on the first three-dimensional point set to obtain the first spline curve includes: Based on the distribution of 3D points in the first 3D point set, an objective function for spline curve fitting is constructed. Using the coordinates of the 3D point cloud as constraints, the control vertices and node vectors are determined by minimizing the objective function. The first spline curve is generated based on the control vertex and the node vector.

[0056] In a preferred embodiment, generating the first spline curve based on the control vertex and the node vector includes: The first spline curve is obtained by using the control vertex as the control point of the first spline curve and the node vector as the node sequence of the first spline curve, and by calculating using a preset spline curve basis function.

[0057] As a preferred embodiment, mapping the two-dimensional contour data to the three-dimensional coordinate system where the three-dimensional point cloud data resides to obtain a first three-dimensional point set includes: By using a preset perspective transformation matrix, each feature point in the two-dimensional contour data is projected onto the three-dimensional coordinate system where the three-dimensional point cloud data is located, to obtain a second three-dimensional point set. The outliers in the second three-dimensional point set are removed using a random sampling consensus algorithm to obtain the first three-dimensional point set.

[0058] In a preferred embodiment, the step of extracting the contour from the first visible image to obtain the two-dimensional contour data of the cable under test includes: The first visible image is subjected to background noise filtering to obtain the second visible image; Based on a preset deep learning model, cable edge recognition is performed on the second visible image to obtain the two-dimensional contour data of the cable under test.

[0059] In a preferred embodiment, the step of performing a risk assessment based on the first spline curve to obtain the risk assessment result of the cable under test includes: The first spline curve is differentiated to obtain the first and second derivatives of each point in the first spline curve. Based on the first and second derivatives of each point, the curvature is calculated using the curvature formula to obtain the curvature of each position in the first spline curve. The curvature at each of the aforementioned locations is sequentially compared with a preset risk threshold to generate several comparison results, and a risk assessment result for the cable under test is generated based on each of the comparison results.

[0060] In a preferred embodiment, the step of sequentially comparing the curvature at each of the aforementioned locations with a preset risk threshold to generate comparison results, and generating a risk assessment result for the cable under test based on each comparison result, includes: The curvature of each position is compared with the preset risk threshold in sequence. If the curvature of any position exceeds the preset risk threshold, the comparison result corresponding to the position is determined to be in an over-limit state; otherwise, it is in a normal state. If at least one comparison result indicates an out-of-limit condition, a risk assessment result is generated indicating that the cable under test has a risk; if all comparison results indicate a normal condition, a risk assessment result is generated indicating that the cable under test has no risk.

[0061] For more detailed steps and working principles of this embodiment, please refer to the relevant description in Embodiment 1, but not limited to these descriptions.

[0062] In summary, this application's embodiments, by acquiring high-resolution visible images of the cable under test and extracting its contours, can accurately capture the cable's boundary and surface texture features, compensating for the shortcomings of pure point cloud data in detail depiction and providing a reliable two-dimensional geometric basis for subsequent curvature calculation. Secondly, by acquiring three-dimensional point cloud data through non-contact scanning, the overall shape and orientation of the cable can be described in spatial dimension, providing necessary three-dimensional spatial information for curvature analysis. On this basis, the two-dimensional contour data is mapped to the three-dimensional point cloud coordinate system, realizing spatial registration and deep fusion of the two types of data. This utilizes point cloud data to locate the cable's spatial orientation and uses image contours to constrain the cable's precise shape, thereby effectively suppressing errors caused by a single data source. Subsequently, by using the least squares method to fit spline curves, a continuous and smooth cable axis curve can be extracted from the fused discrete point set, further eliminating local fluctuations and outlier interference in the original data, making the fitted curve more realistically reflect the actual three-dimensional shape of the cable. Finally, risk assessment based on this spline curve can more accurately calculate the curvature values ​​at various locations of the cable and compare them with preset thresholds, thereby generating reliable risk assessment results. In summary, this application can solve the problem of low accuracy in risk assessment of cable curvature in the prior art.

[0063] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can implement the cable curvature risk assessment method provided by any of the above-described method embodiments of the present invention.

[0064] Example 3 Based on the above method embodiments, corresponding physical device embodiments are provided; An embodiment of the present invention provides a risk assessment device for cable curvature, including an image acquisition device, a point cloud data acquisition device, a lighting device, a data processing device, a human-computer interaction device, and a lithium battery. The risk assessment device is used to perform the steps of the risk assessment method for cable curvature of the present invention.

[0065] Example 4 Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the cable curvature risk assessment method described in any of the above-described method embodiments of the present invention.

[0066] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0067] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for risk assessment of cable curvature, characterized in that, include: A first visible image of the cable under test is acquired, and contour extraction is performed on the first visible image to obtain the two-dimensional contour data of the cable under test. The cable under test is scanned non-contactly according to a preset sampling frequency to obtain three-dimensional point cloud data of the cable under test in three-dimensional space. The two-dimensional contour data is mapped to the three-dimensional coordinate system where the three-dimensional point cloud data is located to obtain the first three-dimensional point set. Based on the first three-dimensional point set, the least squares method is used to fit the spline curve to obtain the first spline curve. A risk assessment is performed on the first spline curve to obtain the risk assessment result of the cable under test.

2. The method for risk assessment of cable curvature as described in claim 1, characterized in that, The step of fitting a spline curve using the least squares method based on the first three-dimensional point set to obtain the first spline curve includes: Based on the distribution of 3D points in the first 3D point set, an objective function for spline curve fitting is constructed. Using the coordinates of the 3D point cloud as constraints, the control vertices and node vectors are determined by minimizing the objective function. The first spline curve is generated based on the control vertex and the node vector.

3. The method for risk assessment of cable curvature as described in claim 2, characterized in that, The step of generating the first spline curve based on the control vertex and the node vector includes: The first spline curve is obtained by using the control vertex as the control point of the first spline curve and the node vector as the node sequence of the first spline curve, and by calculating using a preset spline curve basis function.

4. The method for risk assessment of cable curvature as described in claim 1, characterized in that, The step of mapping the two-dimensional contour data to the three-dimensional coordinate system where the three-dimensional point cloud data is located to obtain the first three-dimensional point set includes: By using a preset perspective transformation matrix, each feature point in the two-dimensional contour data is projected onto the three-dimensional coordinate system where the three-dimensional point cloud data is located, to obtain a second three-dimensional point set. The outliers in the second three-dimensional point set are removed using a random sampling consensus algorithm to obtain the first three-dimensional point set.

5. The method for risk assessment of cable curvature as described in claim 1, characterized in that, The step of extracting the contour from the first visible image to obtain the two-dimensional contour data of the cable under test includes: The first visible image is subjected to background noise filtering to obtain the second visible image; Based on a preset deep learning model, cable edge recognition is performed on the second visible image to obtain the two-dimensional contour data of the cable under test.

6. The method for risk assessment of cable curvature as described in claim 1, characterized in that, The step of performing a risk assessment based on the first spline curve to obtain the risk assessment result of the cable under test includes: The first spline curve is differentiated to obtain the first and second derivatives of each point in the first spline curve. Based on the first and second derivatives of each point, the curvature is calculated using the curvature formula to obtain the curvature of each position in the first spline curve. The curvature at each of the aforementioned locations is sequentially compared with a preset risk threshold to generate several comparison results, and a risk assessment result for the cable under test is generated based on each of the comparison results.

7. The method for risk assessment of cable curvature as described in claim 6, characterized in that, The step of comparing the curvature at each of the aforementioned locations sequentially with a preset risk threshold to generate comparison results, and generating a risk assessment result for the cable under test based on each comparison result, includes: The curvature of each position is compared with the preset risk threshold in sequence. If the curvature of any position exceeds the preset risk threshold, the comparison result corresponding to the position is determined to be in an over-limit state; otherwise, it is in a normal state. If at least one comparison result indicates an out-of-limit condition, a risk assessment result is generated indicating that the cable under test has a risk; if all comparison results indicate a normal condition, a risk assessment result is generated indicating that the cable under test has no risk.

8. A risk assessment device for cable curvature, characterized in that, include: The first evaluation module, the second evaluation module, the third evaluation module, and the fourth evaluation module; The first evaluation module is used to acquire a first visible image of the cable under test and extract the contour of the first visible image to obtain two-dimensional contour data of the cable under test. The second evaluation module is used to perform a non-contact scanning operation on the cable under test according to a preset sampling frequency to obtain the three-dimensional point cloud data of the cable under test in three-dimensional space. The third evaluation module is used to map the two-dimensional contour data to the three-dimensional coordinate system where the three-dimensional point cloud data is located to obtain a first three-dimensional point set, and to fit a spline curve using the least squares method based on the first three-dimensional point set to obtain a first spline curve. The fourth assessment module is used to perform risk assessment based on the first spline curve to obtain the risk assessment result of the cable under test.

9. A risk assessment device for cable curvature, characterized in that, The device includes an image acquisition device, a point cloud data acquisition device, a lighting device, a data processing device, a human-computer interaction device, and a lithium battery. The risk assessment device is used to implement the risk assessment method for cable curvature as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, include: A stored computer program, wherein, when the computer program is executed, the device containing the computer-readable storage medium is controlled to perform the risk assessment method for cable curvature as described in any one of claims 1-7.

Images