A power distribution cable anomaly detection and management method, system, device, and medium

Abstract

The application discloses a power distribution optical cable anomaly detection and management method, system, device and medium, and belongs to the field of power systems. The method is as follows: an initial three-dimensional point cloud model is acquired, a first anomaly area of the model is determined according to point cloud data, and a characteristic parameter of the first anomaly area is determined; the sensitivity threshold of the model is adjusted according to the characteristic parameter, then the characteristic threshold corresponding to a second characteristic is adjusted, a second anomaly area and a damage degree are determined; the position of a target anomaly area is determined through positioning marks, feature analysis is performed on the target anomaly area to determine an influence range; model parameters are adjusted according to the influence range, and each point cloud data is refitted to obtain a target three-dimensional point cloud model; an anomaly detection result is determined according to the target three-dimensional point cloud model, and power distribution optical cable management is performed according to the anomaly detection result. Therefore, by implementing the application, the precision and accuracy of power distribution optical cable anomaly detection can be improved, and the management efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of power systems, and in particular to a method, system, equipment, and medium for detecting and managing anomalies in power distribution optical cables. Background Technology

[0002] In modern power distribution optical cable inventory management, machine vision-based intelligent warehousing technology improves inventory management efficiency and resource utilization through efficient and precise automation, thereby achieving stable operation and cost control of the power system.

[0003] In power systems, with the increasing demand for distribution optical cables, traditional inventory management methods rely heavily on manual inspections and static records. This is not only inefficient but also prone to errors in inventory status assessment due to human negligence, making it difficult to meet the large-scale and complex inventory management needs of the current environment. Furthermore, when optical cable reels are stored for extended periods, existing solutions using fixed feature extraction models for inventory management are ill-suited to the diverse anomalies caused by deformation or damage to the reels. They also lack robustness to environmental noise and changes in lighting, resulting in low accuracy in anomaly identification. Especially under complex and variable storage conditions, frequent misjudgments and missed anomalies further reduce inventory management efficiency. Summary of the Invention

[0004] This invention provides a method, system, equipment, and medium for detecting and managing anomalies in power distribution optical cables, which can solve the problem of low accuracy and precision in anomaly detection during power distribution optical cable inventory management.

[0005] This invention provides a method for detecting and managing anomalies in power distribution optical cables, comprising:

[0006] Acquire point cloud data when detecting each power distribution optical cable, and construct the corresponding initial three-dimensional point cloud model based on the point cloud data;

[0007] In each of the initial three-dimensional point cloud models, point cloud density data corresponding to the first feature is calculated based on the point cloud data, and a first abnormal region is determined based on the point cloud density data; the feature parameters of the first abnormal region are determined, and the sensitivity threshold of the initial three-dimensional point cloud model in the anomaly detection process is adjusted according to the feature parameters, thereby adjusting the feature threshold corresponding to the second feature, and determining the second abnormal region and the degree of damage;

[0008] The damage levels of the first and second abnormal regions are located and marked to determine the location of the target abnormal region. Feature analysis is performed on the target abnormal region to determine the range of influence. The model parameters of the initial three-dimensional point cloud model are adjusted according to the range of influence, and the point cloud data are refitted according to the adjusted model parameters to obtain the target three-dimensional point cloud model.

[0009] The anomaly detection results are determined based on the target 3D point cloud model, and the power distribution optical cable is managed based on the anomaly detection results.

[0010] This embodiment constructs an initial 3D point cloud model by acquiring point cloud data. Based on point cloud density data, it identifies the first anomalous region. Then, it adjusts the sensitivity threshold based on feature parameters, thereby adjusting the feature threshold of the second feature to determine the second anomalous region and its degree of damage. The anomalous region is then located, marked, and its features analyzed to determine the scope of influence. Finally, the model parameters are adjusted based on the scope of influence, and the model is refitted to obtain the target 3D point cloud model. Through multi-dimensional detection and model adjustment, anomalous regions are accurately located, improving anomaly detection accuracy and inventory management efficiency.

[0011] Furthermore, the step of determining the anomaly detection result based on the target three-dimensional point cloud model and managing the power distribution optical cable based on the anomaly detection result also includes: determining the target multidimensional visual feature vector of the target three-dimensional point cloud model, analyzing the changing trend between the multidimensional visual feature vector and the target multidimensional visual feature vector, and obtaining index data;

[0012] Based on the index data and the environmental data of the power distribution optical cable, the cumulative deformation value is calculated; if the cumulative deformation value is not within the preset range, the anomaly detection parameters of the target three-dimensional point cloud model are adjusted by the random forest algorithm to obtain the anomaly detection result and the inventory status data corresponding to the environmental data.

[0013] By combining the inventory status data with the target 3D point cloud model, a support vector machine algorithm is used to determine the real-time turnover efficiency, and the efficiency evaluation result is determined based on the real-time turnover efficiency.

[0014] Based on the efficiency evaluation results and the indicator data, a power distribution optical cable management scheme is determined. By extracting features from the operational data, information from different representational subspaces at different locations can be focused on, combining data from distant locations to achieve comprehensive capture of multi-scale features.

[0015] This allows for the combination of multi-dimensional visual features and environmental data to optimize anomaly detection parameters and improve inventory management efficiency.

[0016] Furthermore, the step of calculating the point cloud density data corresponding to the first feature based on the point cloud data, and determining the first abnormal region based on the point cloud density data, specifically involves:

[0017] Statistical analysis of the initial three-dimensional point cloud model is performed to obtain the point cloud density data, and the areas where the point cloud density data does not meet the preset range conditions are identified as the first abnormal areas.

[0018] The sensitivity threshold is adjusted according to the feature parameters, and an adjustment coefficient is calculated based on the adjusted sensitivity threshold. The initial three-dimensional point cloud model is then updated using the adjustment coefficient to obtain the updated point cloud density data.

[0019] If the updated point cloud density data still does not meet the preset range conditions, then iterative updates are performed until the preset range conditions are met, thus obtaining the first abnormal region.

[0020] By using a data-driven approach to gradually optimize the point cloud density distribution, not only can the consistency between the model and the actual object be improved, but the localization of abnormal areas can also be made more accurate, while sensitivity adjustment provides flexibility for optimization.

[0021] Further, the step of adjusting the sensitivity threshold of the initial 3D point cloud model in the anomaly detection process based on the feature parameters, and then adjusting the feature threshold corresponding to the second feature to determine the second anomaly region and the degree of damage, specifically involves:

[0022] The threshold corresponding to the second feature is updated based on the adjustment coefficient to obtain the feature threshold;

[0023] Obtain the reflection intensity data corresponding to the second feature, and perform time series analysis on the reflection intensity data to obtain the feature sequence;

[0024] Multiple second abnormal regions are determined based on the feature threshold and the feature sequence, and the degree of damage is obtained by statistical analysis of each second abnormal region.

[0025] By dynamically adjusting the feature matching strategy, the matching results between the point cloud model and the actual object are optimized, thereby improving the accuracy of anomaly detection.

[0026] Furthermore, the step of acquiring point cloud data of power distribution optical cable resources in the resource library and constructing corresponding initial three-dimensional point cloud models based on each point cloud data specifically involves:

[0027] The point cloud data is preprocessed, and a statistical filtering algorithm is used to process the preprocessed point cloud data to generate a three-dimensional point cloud model.

[0028] Extract the edge contour features of the three-dimensional point cloud model, determine the first feature and the second feature based on the edge contour features and the three-dimensional point cloud data, and fuse the first feature and the second feature to generate a multi-dimensional visual feature vector.

[0029] Based on the geometric deviation between the current iteration of the 3D point cloud model and the standard point cloud model, and combined with the multidimensional visual feature vector, the matching parameters between the 3D point cloud model and the standard point cloud model are updated until the geometric deviation is greater than or equal to a first preset threshold, at which point the iteration stops and the initial 3D point cloud model is output.

[0030] By filtering the data, the initial 3D point cloud model becomes smoother, clearly displaying the cylindrical structure of the optical cable reel and effectively improving the accuracy of subsequent feature extraction. By comparing the features with those of a standard optical cable reel, it is possible to quickly determine whether the quality meets the standards.

[0031] Further, the step of determining the first feature and the second feature based on the edge contour features and the 3D point cloud data, and fusing the first feature and the second feature to generate a multi-dimensional visual feature vector, specifically involves:

[0032] Calculate the point spacing distribution value from the edge contour features, and determine the tightness feature based on the point spacing distribution value;

[0033] Extract the surface protective layer of the power distribution optical cable resource. If the point cloud density value of the surface protective layer is lower than the second preset threshold, it is determined that there is an anomaly in the surface protective layer, and the protective integrity feature is obtained.

[0034] The multidimensional visual feature vector is generated by fusing the tightness feature and the protective integrity feature.

[0035] By updating the sensitivity threshold, damage to the protective layer can be accurately identified and classified, thus improving the accuracy of anomaly detection.

[0036] Furthermore, the step of performing feature analysis on the target anomaly region to determine the scope of influence specifically involves:

[0037] Extract the shape and distribution features of the target abnormal region, determine the influence range based on the shape and distribution features, and adjust the model parameters if the influence range is greater than or equal to a third preset threshold.

[0038] By using location markers and adjusting model parameters, the damaged and abnormal areas can be accurately identified, thus improving the accuracy of anomaly detection.

[0039] Another embodiment of the present invention provides a power distribution optical cable anomaly detection and management system, including: an acquisition module, an anomaly area determination module, a model adjustment module, and a management module;

[0040] The acquisition module is used to acquire point cloud data when detecting each power distribution optical cable, and to construct a corresponding initial three-dimensional point cloud model based on each point cloud data.

[0041] The abnormal region determination module is used to calculate the point cloud density data corresponding to the first feature based on the point cloud data in each of the initial three-dimensional point cloud models, determine the first abnormal region based on the point cloud density data, determine the feature parameters of the first abnormal region, and adjust the sensitivity threshold of the initial three-dimensional point cloud model in the abnormal detection process according to the feature parameters, thereby adjusting the feature threshold corresponding to the second feature, and determining the second abnormal region and the degree of damage.

[0042] The model adjustment module is used to locate and mark the damage degree of the first abnormal region and the second abnormal region to determine the location of the target abnormal region, perform feature analysis on the target abnormal region to determine the influence range, adjust the model parameters of the initial three-dimensional point cloud model according to the influence range, and refit each point cloud data according to the adjusted model parameters to obtain the target three-dimensional point cloud model.

[0043] The management module is used to determine the anomaly detection result based on the target 3D point cloud model, and to manage the power distribution optical cable based on the anomaly detection result.

[0044] This embodiment constructs an initial 3D point cloud model by acquiring point cloud data. Based on point cloud density data, it identifies the first anomalous region. Then, it adjusts the sensitivity threshold based on feature parameters, thereby adjusting the feature threshold of the second feature to determine the second anomalous region and its degree of damage. The anomalous region is then located, marked, and its features analyzed to determine the scope of influence. Finally, the model parameters are adjusted based on the scope of influence, and the model is refitted to obtain the target 3D point cloud model. Through multi-dimensional detection and model adjustment, anomalous regions are accurately located, improving anomaly detection accuracy and inventory management efficiency.

[0045] Another embodiment of the present invention provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the steps of the power distribution optical cable anomaly detection and management method of the present invention.

[0046] Another embodiment of the present invention 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 the steps of the power distribution optical cable anomaly detection and management method of the present invention. Attached Figure Description

[0047] 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.

[0048] Figure 1 This is a flowchart illustrating one embodiment of a method for detecting and managing abnormalities in power distribution optical cables;

[0049] Figure 2 This is a schematic diagram of an embodiment of a power distribution optical cable anomaly detection and management system. Detailed Implementation

[0050] 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.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] 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).

[0056] 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.

[0057] See Figure 1 To address the low accuracy and precision of anomaly detection in existing power distribution optical cables, this invention provides an embodiment of a method for anomaly detection and management in power distribution optical cables, such as... Figure 1 As shown, the method includes steps S101-S103, including:

[0058] Step 101: Obtain point cloud data when detecting each power distribution optical cable, and construct the corresponding initial three-dimensional point cloud model based on the point cloud data.

[0059] In this embodiment, a laser scanning device is used to scan the optical cable reels in the warehouse, collecting three-dimensional point cloud data of the reels, including their geometry, winding tightness, and surface protection information. For example, a high-precision laser scanner can be used to scan the optical cable reels, generating a point cloud dataset containing millions of points. These points not only reflect the outer contour of the optical cable reels but also include the winding layer spacing and surface details. It should be noted that the advantage of laser scanning lies in its non-contact measurement, enabling the acquisition of high-resolution data without disturbing the state of the optical cable reels, laying the foundation for subsequent analysis. Based on the point cloud data, a three-dimensional point cloud model is obtained. This three-dimensional point cloud model can then be matched with a standard model to obtain an aligned initial three-dimensional point cloud model.

[0060] As an example of an embodiment of the present invention, the step of acquiring point cloud data of power distribution optical cable resources in the resource library and constructing a corresponding initial three-dimensional point cloud model based on each point cloud data specifically involves: preprocessing the point cloud data and using a statistical filtering algorithm to process the preprocessed point cloud data to generate a three-dimensional point cloud model; extracting the edge contour features of the three-dimensional point cloud model, determining a first feature and a second feature based on the edge contour features and the three-dimensional point cloud data, and fusing the first feature and the second feature to generate a multi-dimensional visual feature vector; updating the matching parameters between the three-dimensional point cloud model and the standard point cloud model based on the geometric deviation between the currently iterated three-dimensional point cloud model and the standard point cloud model, combined with the multi-dimensional visual feature vector, until the geometric deviation is greater than or equal to a first preset threshold, stopping the iteration, and outputting the initial three-dimensional point cloud model.

[0061] In this embodiment, a statistical filtering algorithm is used to filter the point cloud data to remove noise. For example, assuming that the collected point cloud data contains outliers caused by ambient light interference, the statistical filter calculates the distance distribution between each point and its neighbors. If a point deviates too far from the average distance, such as exceeding two standard deviations, it is considered noise and removed. After filtering, the initial 3D point cloud model is smoother and can clearly show the cylindrical structure of the optical cable reel, effectively improving the accuracy of subsequent feature extraction. The statistical filtering algorithm is used to process the noise-removed 3D point cloud model to generate a 3D point cloud model. For the 3D point cloud model, the edge contour features corresponding to the geometric shape are extracted, and the contour boundary is determined by the Euclidean clustering algorithm. The Euclidean clustering algorithm clusters based on the spatial distance between points. For example, setting a distance threshold of 5 mm, the point cloud at the edge of the optical cable reel is clustered into one class, separating the contour from the background. The multidimensional visual feature vector can be generated by fusing the tightness feature and the protective integrity feature. This multidimensional visual feature vector is then used to calculate the initial 3D point cloud model data. The calculation process relies on the multidimensional information of the point cloud data. For example, in the detection scenario of an optical cable reel, the collected point cloud data may contain spatial coordinates and reflection intensity information. The feature vector can be generated by combining these data. For instance, assuming the diameter of the optical cable reel is 1 meter and the collected point cloud data contains 100,000 points, edge features can be extracted using clustering methods to generate a feature vector containing position and density. The geometric deviation value is obtained from comparing the 3D point cloud with the standard model. A point-to-point distance calculation method can be used. Specifically, the standard model may be a preset ideal geometric shape of the optical cable reel, such as a cylinder. Assuming the standard model has a diameter of 1 meter, while the initial 3D point cloud model has a measured diameter of 1.02 meters, the deviation is 0.02 meters. If the preset threshold is 0.01 meters, the deviation exceeds the standard. This comparison can intuitively reflect the deformation of the model, providing a basis for subsequent adjustments. If the geometric deviation exceeds the preset threshold, a dynamic adjustment method is used to update the feature matching strategy. For example, by adjusting the weight parameters of point cloud registration, priority can be given to matching key regions such as edges. Initial matching might only focus on the global point cloud distribution, but after adjustment, the weight of edge points can be increased from 30% to 50%, thereby improving matching accuracy. This strategy optimization effectively reduces bias. New matching parameters are obtained based on the adjusted matching strategy, generating optimized feature matching data. This process can introduce local feature descriptors; for example, for the winding area of ​​an optical cable reel, the curvature features of the point cloud can be extracted to generate new matching parameters. Assuming the curvature value is adjusted from 0.1 to 0.05, the matching data will more closely resemble the actual shape. This method improves the specificity of the data. The updated geometric deviation is calculated using the optimized feature matching data to determine if it meets the requirements. For example, if the updated deviation decreases from 0.02 meters to 0.008 meters, which is less than the threshold of 0.01 meters, then the requirements are met. This verification method ensures the reliability of the results.If the updated geometric deviation still exceeds the preset threshold, the matching parameters are adjusted iteratively to obtain an optimized result. For example, if the initial parameters are iterated only 5 times and the deviation is still 0.015 meters, the iterations can be increased to 10 times, with each iteration fine-tuning the registration angle to reduce the deviation to 0.009 meters. The matching accuracy between the 3D point cloud model and the standard model is determined based on the optimization results. Specifically, this can be evaluated by statistically analyzing the overlap rate of matching points. For example, an increase in the overlap rate from 85% to 95% indicates a significant improvement in accuracy. This high-precision matching helps with subsequent quality inspection of optical cable reels, ensuring that the product meets standards. In practical applications, this method can also reduce misjudgments caused by deviations and improve inspection efficiency. For example, through dynamic adjustment and iterative optimization of multi-dimensional features, the entire process can adapt to the inspection needs of different optical cable reels, demonstrating strong practicality.

[0062] As an example of an embodiment of the present invention, the step of determining a first feature and a second feature based on the edge contour features and the three-dimensional point cloud data, and fusing the first feature and the second feature to generate a multidimensional visual feature vector, specifically involves: calculating the point spacing distribution value from the edge contour features, determining the tightness feature based on the point spacing distribution value; extracting the surface protective layer of the power distribution optical cable resource, and if the point cloud density value of the surface protective layer is lower than a second preset threshold, determining that the surface protective layer has an anomaly, and obtaining the protective integrity feature; and fusing the tightness feature and the protective integrity feature to generate the multidimensional visual feature vector.

[0063] In this embodiment, the first feature is the tightness characteristic determined when analyzing the tightness of the optical cable reel winding, and the second feature is the protective integrity characteristic determined when analyzing the integrity of the protective layer on the surface of the optical cable reel. Specifically, when analyzing the tightness of the winding, the point spacing distribution is calculated from the edge contour features. For example, in the point cloud on the side of the optical cable reel, if the average point spacing of a certain winding area is 3 mm and the standard deviation is less than 0.5 mm, it can be judged that the winding is uniform; if the standard deviation rises to 1.2 mm, it indicates uneven tightness. This analysis can intuitively reflect the quality stability of the optical cable reel and help optimize the production process. When obtaining the surface protective layer integrity information, the point cloud density is a key indicator. For example, if the density threshold is set to 100 points per square centimeter, if the density of a certain area drops to 70 points, it may be due to the protective layer peeling off, resulting in a sparse point cloud and indicating a defect. This method can quickly locate the problem area and improve detection efficiency. After fusing the tightness analysis results and the protective integrity characteristics to generate multi-dimensional visual features, principal component analysis algorithm can be used for dimensionality reduction. For example, the feature set containing uniformity of tightness and density distribution can be compressed to three main dimensions, retaining 95% of the information variance. This dimensionality reduction reduces computational complexity while maintaining the effectiveness of the features, facilitating subsequent vectorization. When vectorizing the optimized visual feature set, the final feature representation can be generated through matrix operations. Specifically, the dimensionality-reduced feature set is mapped to a 1x3 vector, such as [0.85, 0.92, 0.78], representing the comprehensive scores of geometry, winding tightness, and surface protection, respectively. This representation is easy to store and compare, for example, by comparing with the features of a standard optical cable reel to quickly determine whether the quality meets the standards. In one embodiment, this feature vector can also be input into a machine learning model to further predict the service life of the optical cable reel, significantly improving the intelligence level of quality inspection.

[0064] Step 102: In each of the initial three-dimensional point cloud models, calculate the point cloud density data corresponding to the first feature based on the point cloud data, determine the first abnormal region based on the point cloud density data; determine the feature parameters of the first abnormal region, and adjust the sensitivity threshold of the initial three-dimensional point cloud model in the anomaly detection process according to the feature parameters, thereby adjusting the feature threshold corresponding to the second feature, and determining the second abnormal region and the degree of damage.

[0065] In this embodiment, the matched point cloud data is processed through statistical analysis to calculate the point cloud density distribution corresponding to the tightness, thus obtaining point cloud density data. This process aims to extract regularity information from massive point cloud data. For example, assuming the point cloud data originates from a surface scan of a mechanical part, the statistical analysis may calculate the density value based on the spacing between each point in the point cloud, such as the number of points per cubic millimeter, resulting in a density distribution curve. Based on this density distribution curve, a preset density range of 50-70 points / cubic millimeter is determined. The point cloud density data is compared with this preset density range; if there is a deviation, the deviation state is determined. Specifically, if a density of only 30 points / cubic millimeter is detected in a certain area, significantly lower than the normal range, it can be determined as a "loose" state. It should be noted that this deviation may be caused by insufficient accuracy of the scanning equipment or irregularities in the surface of the part. Preferably, the deviation area is marked in red using a visualization tool for easier subsequent processing. To address deviations, cluster analysis is used to identify multiple tightness / susceptibility anomaly regions. For example, K-means clustering can be used to group points with a density below 40 points / millimeter cubic meter into anomaly clusters, ultimately resulting in multiple tightness / susceptibility anomaly regions. For instance, the edge region of a part may have sparse point clouds due to wear, forming an independent anomaly region. This method helps to quickly locate problem areas and improve analysis efficiency. The sensitivity threshold is adjusted based on the characteristic parameters of the tightness / susceptibility anomaly region, and an adjustment coefficient is calculated based on the adjusted sensitivity threshold. The initial 3D point cloud model is updated using the adjustment coefficient to obtain updated point cloud density data. If the updated point cloud density data still does not meet the preset range condition, iterative updates are performed until the preset range condition is met, resulting in the first anomaly region. The characteristic parameters of the first anomaly region are determined, and the sensitivity threshold of the initial 3D point cloud model during anomaly detection is adjusted based on these characteristic parameters. This, in turn, adjusts the characteristic threshold corresponding to the second feature, determining the second anomaly region and the degree of damage.

[0066] As an example of an embodiment of the present invention, the step of calculating the point cloud density data corresponding to the first feature based on the point cloud data and determining the first abnormal region based on the point cloud density data specifically involves: statistically analyzing the initial three-dimensional point cloud model to obtain the point cloud density data, identifying regions where the point cloud density data does not meet a preset range condition as the first abnormal region; adjusting the sensitivity threshold according to the feature parameters, calculating an adjustment coefficient based on the adjusted sensitivity threshold, updating the initial three-dimensional point cloud model through the adjustment coefficient to obtain updated point cloud density data; if the updated point cloud density data still does not meet the preset range condition, iterative updates are performed until the preset range condition is met, thereby obtaining the first abnormal region.

[0067] In this embodiment, features are extracted from the first abnormal region to determine the feature parameters of the abnormal region. These feature parameters include the region's average density, boundary length, or shape complexity. For example, an abnormal region might have an average density of 35 points / m³, a boundary length of 10 mm, and an irregular polygonal shape. These parameters provide data support for subsequent adjustments. Specifically, if low density indicates that anomaly detection is too strict and the conditions need to be relaxed, the sensitivity is adjusted based on the feature parameters, and an adjustment coefficient is calculated. For instance, if the density of the abnormal region is too low, the sensitivity can be reduced by 20%, generating an adjustment coefficient such as 0.8. After adjustment, the density distribution is recalculated, and it is observed whether it tends towards normal. This adjustment can effectively reduce false positives and improve the robustness of matching. By adjusting the coefficient, the feature matching results in anomaly detection are optimized, resulting in an optimized point cloud density distribution. For example, if the density distribution value of a certain region is 30 points / m³, by adjusting the coefficient, the density distribution value of that region is recalculated to 45 points / m³, which is closer to the normal range. Preferably, this optimization allows the point cloud model to more realistically reflect the surface characteristics of the part. If the optimized distribution still deviates from the normal range, cluster analysis and feature extraction are repeated to obtain new adjustment coefficients. For example, the sensitivity might be further reduced to 0.6 in the second iteration until the requirement is met. This iterative approach ensures that the results gradually approach the target, improving matching accuracy. It should be noted that the above process, through a data-driven approach, progressively optimizes the point cloud density distribution, which not only improves the consistency between the model and the actual object but also provides a reliable basis for subsequent quality inspection. For example, in parts manufacturing, this method can be used to identify processing defects and ensure product pass rates. Understandably, the combination of clustering and feature extraction makes the location of abnormal regions more accurate, while sensitivity adjustment provides flexibility for optimization.

[0068] As an example of an embodiment of the present invention, the step of adjusting the sensitivity threshold of the initial three-dimensional point cloud model in the anomaly detection process according to the feature parameters, and then adjusting the feature threshold corresponding to the second feature to determine the second anomaly region and the degree of damage, specifically involves: updating the threshold corresponding to the second feature based on the adjustment coefficient to obtain the feature threshold; acquiring the reflection intensity data corresponding to the second feature, performing time series analysis on the reflection intensity data to obtain a feature sequence; determining multiple second anomaly regions according to the feature threshold and the feature sequence, and performing statistical analysis on each second anomaly region to obtain the degree of damage.

[0069] In this embodiment, the initial intensity threshold is updated using a preset sensitivity threshold adjustment formula and adjustment coefficient to obtain the target intensity threshold. The sensitivity threshold adjustment formula is as follows:

[0070] S = S0(1 + kC);

[0071] Where S is the target intensity threshold, S0 is the initial intensity threshold, k is the adjustment coefficient, and C is the sensitivity threshold.

[0072] For example, in surface protective layer testing, the initial intensity threshold S0 is set to 50, representing the baseline value of normal reflectivity. The adjustment factor k is typically set to 0.2 to indicate the adjustment range, while the sensitivity threshold C is set to 0.5 based on actual needs, resulting in a target intensity threshold S of 55. The core of this approach lies in its flexible adjustment based on environmental or material characteristics, avoiding misjudgments caused by fixed thresholds. Understandably, this adjustment can more accurately adapt to different degrees of aging or external interference in protective layers.

[0073] For example, the reflectance intensity data of the surface protective layer is collected every hour using an optical sensor for 24 hours, resulting in an intensity change sequence. For instance, the initial intensity is 48, rising to 56 after 10 hours, and then dropping to 52 after another 5 hours. Combined with a target intensity threshold of 55, any point in the intensity sequence exceeding 55 is marked as an anomaly. The advantage of this method is that it allows for real-time monitoring of the protective layer's condition and timely detection of potential problems. Specifically, the distribution characteristics of anomalies are statistically analyzed, and their concentration over time is examined. For example, if there are 5 anomalies within 24 hours, all concentrated between hours 8 and 12, it may indicate that the protective layer was subjected to an external impact during this period. Based on this, the damage level can be classified into three levels: minor, moderate, and severe, corresponding to 1-3, 4-6, and 7 or more anomalies, respectively. This classification helps to quickly determine whether the protective layer requires maintenance. Preferably, when grouping the damage category set using a clustering algorithm, the K-means method can be used to cluster the anomalies into 3 groups based on intensity value and time interval. For example, the first group of intensities is concentrated between 55 and 60, with a uniform time distribution; the second group has intensities exceeding 65, concentrated within a certain 2-hour period. Such grouping clearly reflects the regularity of damage, facilitating subsequent analysis. It should be noted that clustering results can also reveal whether anomalies are caused by a single factor. In one embodiment, when extracting key parameters from the protective layer features, the peak intensity and decay rate can be considered. For example, if a group of anomalies has a peak intensity of 68 and a decay rate of 2 units per hour, it indicates a high probability of localized peeling of the protective layer. Another group has a peak intensity of 60 and a decay rate of 0.5, which may indicate slight wear. The advantage of this parameter extraction is that it allows for a direct assessment of the overall stability of the protective layer. For instance, when assessing the overall state of the surface protective layer, if key parameters show that the peak intensity of multiple anomalies exceeds 60 and the decay rate is rapid, it may indicate that the protective layer is nearing failure and needs replacement. If only one anomaly exists and the decay rate is slow, it may be a localized problem that can be repaired.

[0074] Step 103: Locate and mark the damage degree of the first and second abnormal regions to determine the location of the target abnormal region; perform feature analysis on the target abnormal region to determine the influence range; adjust the model parameters of the initial three-dimensional point cloud model according to the influence range; and refit each point cloud data according to the adjusted model parameters to obtain the target three-dimensional point cloud model.

[0075] In this embodiment, identifying the target abnormal area by the degree of damage and the abnormal tightness relies on the accurate judgment of the surface protective layer's condition. For example, when inspecting a metal protective coating, assuming the abnormal tightness manifests as localized expansion or contraction, stress distribution data can be collected using sensors to identify the abnormal area. For instance, if the stress value in a certain area exceeds the normal range by 20%, combined with the damage category such as "minor peeling" or "deep crack," an anomaly can be initially determined. Feature analysis of the target abnormal area can extract the feature analysis results corresponding to shape and distribution features. Based on the feature analysis results, the influence range of the abnormal area is determined. If the influence range threshold is set to a radius of 10 cm, when the influence range of an abnormal area reaches 12 cm, the model parameters are dynamically adjusted. For example, the weight of the fitting algorithm is adjusted from 0.5 to 0.7 to enhance the focus on the abnormal area. This adjustment optimizes the fitting effect of the subsequent geometry. In one embodiment, after refitting the geometry using the adjusted model parameters, the initially updated 3D point cloud model shows that the edges of the abnormal area are smoother. For example, the jagged point cloud of the original crack edge is corrected to a continuous curve. This fitting process reduces data noise and improves model reliability. Analysis of the characteristic changes in the abnormal region using the initially updated 3D point cloud model reveals that the crack width decreased from 2 mm to 1.5 mm, indicating improved fitting accuracy. If the accuracy is not up to standard, for example, if the error still exceeds 0.5 mm, the geometry is adjusted using an iterative optimization algorithm. After three iterations, the error decreased to 0.2 mm, resulting in a more realistic 3D point cloud model of the target.

[0076] As an example of an embodiment of the present invention, the step of performing feature analysis on the target abnormal region to determine the influence range specifically involves: using positioning and marking technology to determine the regional location data of the target abnormal region, extracting the shape features and distribution features of the target abnormal region; determining the influence range based on the shape features and the distribution features; and adjusting the model parameters if the influence range is greater than or equal to a third preset threshold.

[0077] In this embodiment, a positioning marker technique is used to determine the location of the abnormal region in a 3D point cloud, and then a laser scanner is used to generate 3D point cloud data. Specifically, the coordinates of the abnormal region are marked as x=50, y=30, and z=10. By analyzing the changes in point cloud density and height, it is confirmed that the region deviates from the normal plane by approximately 5 mm. This positioning method can intuitively reflect the spatial distribution of the abnormal region, which is helpful for subsequent analysis. Image processing techniques can be combined to extract the shape and distribution features of the abnormal region and analyze the connectivity of abnormal points in the point cloud, thereby improving the accuracy of the judgment. For example, the abnormal region may present as a long strip crack, approximately 15 cm long and 2 mm wide, concentrated at the edge of the protective layer. This shape feature indicates that the damage may be caused by external stress concentration. The influence range of the abnormal region is determined based on the feature analysis results. If the influence range is greater than or equal to a third preset threshold, the model parameters are adjusted. Furthermore, the positioning markers of the abnormal region can be verified against the target 3D point cloud model. For example, it can be confirmed that the deviation of the marker points x=50, y=30, and z=10 is only 0.1 mm. Simultaneously, the damage category was reclassified from "deep crack" to "shallow scratch," and the abnormal tightness was also alleviated. This verification method can effectively assess the degree of repair and provide a basis for the maintenance of the protective layer.

[0078] Step 104: Determine the anomaly detection result based on the target 3D point cloud model, and manage the power distribution optical cable based on the anomaly detection result.

[0079] In this embodiment, based on the target 3D point cloud model, the multi-dimensional visual feature change trend and the impact of the storage environment are analyzed to obtain a quantitative index of deformation accumulation. If the quantitative index exceeds the preset range, the anomaly detection parameters are adjusted to obtain inventory status data adapted to the current environment. By combining this data with the 3D point cloud model and the anomaly detection results, the real-time inventory turnover efficiency of the optical cable reel is determined, and optimized management parameters are output. The optical cable reel is then managed according to the optimized management parameters.

[0080] As an example of an embodiment of the present invention, the step of determining the anomaly detection result based on the target 3D point cloud model and managing the power distribution optical cable based on the anomaly detection result specifically involves: determining the target multidimensional visual feature vector of the target 3D point cloud model, analyzing the changing trend between the multidimensional visual feature vector and the target multidimensional visual feature vector to obtain indicator data; calculating the cumulative deformation value based on the indicator data and the environmental data of the power distribution optical cable; if the cumulative deformation value is not within a preset range, adjusting the anomaly detection parameters of the target 3D point cloud model using a random forest algorithm to obtain the anomaly detection result and the inventory status data corresponding to the environmental data; combining the inventory status data and the target 3D point cloud model, using a support vector machine algorithm to determine the real-time turnover efficiency, and determining the efficiency evaluation result based on the real-time turnover efficiency; and determining the power distribution optical cable management scheme based on the efficiency evaluation result and the indicator data.

[0081] In this embodiment, extracting multi-dimensional visual features of the target through a 3D point cloud model can be understood as obtaining information such as shape, texture, and distribution from point cloud data. For example, in the inventory management of optical cable reels, the edge curvature and surface flatness of the reel can be captured through point cloud data, and the changing trends of these features over time can be analyzed. For instance, assuming the edge curvature of an optical cable reel increases from 0.5 to 0.8 within 30 days, it indicates potential deformation. The quantification index can be defined as the rate of change of curvature, with a threshold of 0.2. In one possible implementation, the cumulative deformation value is calculated by combining storage environment data such as temperature and humidity. Specifically, if the ambient temperature rises from 20°C to 35°C and the humidity increases from 50% to 70%, the cumulative deformation value can be inferred from historical data to reach 5mm, exceeding the preset range of 3mm. It should be noted that the calculation of this cumulative value relies on the correlation analysis between the environment and point cloud features, which helps in determining the reel's condition. If the cumulative deformation value exceeds the limit, the anomaly detection parameters are adjusted using a random forest algorithm. For example, the initial detection sensitivity is set to 80%, but adjusted to 90% after environmental changes, thus generating inventory status data adapted to high temperature and humidity. This adjustment can more accurately reflect tray anomalies and improve detection reliability. When judging real-time turnover efficiency by combining inventory status data with the target 3D point cloud model and using the support vector machine algorithm, it can be analyzed from two aspects: tray availability and handling difficulty. In one embodiment, if the point cloud shows that tray deformation leads to a reduction in stacking gaps, the turnover efficiency may drop from 95% to 85%, and the efficiency assessment result directly reflects management problems. Based on the efficiency assessment results and quantitative indicators, the optimization parameters can be adjusted, changing the handling priority from "high" to "medium" and optimizing the stacking height from 2 meters to 1.5 meters to determine the optical cable tray management scheme. This adjustment can reduce secondary damage to deformed trays and improve inventory turnover efficiency. Based on the optimization parameters, the features of the target 3D point cloud model are updated. For example, the edge curvature feature can be adjusted from 0.8 back to 0.6 to generate dynamic inventory data adapted to the current environment. This update can more realistically reflect the tray status and facilitate subsequent management decisions. By calculating the long-term trend of turnover efficiency using dynamic inventory data and anomaly detection results, for example, if the efficiency remains stable above 90% for three consecutive months, it can be inferred that the optimized values ​​of management parameters are approaching a reasonable level. For instance, maintaining a stacking height of 1.5 meters and a detection sensitivity of 90% in the long term indicates more efficient inventory management and a reduced anomaly rate. Specifically, this method can dynamically optimize the optical cable reel management process through multi-dimensional feature analysis and environmental adaptability adjustments.

[0082] like Figure 2 As shown, based on the above method embodiments, corresponding system embodiments are provided;

[0083] One embodiment of the present invention provides a power distribution optical cable anomaly detection and management system 200, including: an acquisition module 201, an anomaly area determination module 202, a model adjustment module 203, and a management module 204;

[0084] The acquisition module 201 is used to acquire point cloud data when detecting each power distribution optical cable, and to construct a corresponding initial three-dimensional point cloud model based on each point cloud data.

[0085] The abnormal region determination module 202 is used to calculate the point cloud density data corresponding to the first feature based on the point cloud data in each of the initial three-dimensional point cloud models, determine the first abnormal region based on the point cloud density data, determine the feature parameters of the first abnormal region, and adjust the sensitivity threshold of the initial three-dimensional point cloud model in the abnormal detection process according to the feature parameters, thereby adjusting the feature threshold corresponding to the second feature, and determining the second abnormal region and the degree of damage.

[0086] The model adjustment module 203 is used to locate the damage degree of the first abnormal region and the second abnormal region to determine the location of the target abnormal region, perform feature analysis on the target abnormal region to determine the influence range, adjust the model parameters of the initial three-dimensional point cloud model according to the influence range, and refit each point cloud data according to the adjusted model parameters to obtain the target three-dimensional point cloud model.

[0087] The management module 204 is used to determine the anomaly detection result based on the target three-dimensional point cloud model, and to manage the power distribution optical cable based on the anomaly detection result.

[0088] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can realize the power distribution optical cable anomaly detection and management method provided by any of the above-described method embodiments of the present invention.

[0089] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0090] Based on the above embodiments of the power distribution optical cable anomaly detection and management method, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the power distribution optical cable anomaly detection and management method of any embodiment of the present invention.

[0091] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0092] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0093] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0094] 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 execute the power distribution optical cable anomaly detection and management method described in any of the above-described method embodiments of the present invention.

[0095] 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, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0096] 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 power distribution cable anomaly detection and management method, characterized by, The method comprises the following steps: acquiring point cloud data when each power distribution optical cable is detected, and constructing a corresponding initial three-dimensional point cloud model based on each point cloud data; in each initial three-dimensional point cloud model, calculating point cloud density data corresponding to a first feature based on the point cloud data, determining a first abnormal area based on the point cloud density data, determining a feature parameter of the first abnormal area, and adjusting a sensitivity threshold of the initial three-dimensional point cloud model in the abnormal detection process according to the feature parameter, thereby adjusting a feature threshold corresponding to a second feature, determining a second abnormal area and a damage degree; locating and marking the first abnormal area and the damage degree of the second abnormal area to determine the position of a target abnormal area, performing feature analysis on the target abnormal area to determine an influence range, adjusting model parameters of the initial three-dimensional point cloud model according to the influence range, and refitting each point cloud data according to the adjusted model parameters to obtain a target three-dimensional point cloud model; determining an abnormal detection result according to the target three-dimensional point cloud model, and managing the power distribution optical cable according to the abnormal detection result.

2. The power distribution cable anomaly detection and management method of claim 1, wherein, The method of determining an abnormal detection result according to the target three-dimensional point cloud model and managing the power distribution optical cable according to the abnormal detection result comprises the following steps: determining a target multi-dimensional visual feature vector of the target three-dimensional point cloud model, analyzing the change trend between the multi-dimensional visual feature vector and the target multi-dimensional visual feature vector to obtain index data; calculating a deformation cumulative value based on the index data and environmental data of the power distribution optical cable; if the deformation cumulative value is not in a preset range, adjusting the abnormal detection parameters of the target three-dimensional point cloud model through a random forest algorithm to obtain the abnormal detection result and inventory state data corresponding to the environmental data; combining the inventory state data and the target three-dimensional point cloud model, determining a real-time turnover efficiency by using a support vector machine algorithm, and determining an efficiency evaluation result according to the real-time turnover efficiency; determining a power distribution optical cable management scheme according to the efficiency evaluation result and the index data.

3. The power distribution cable anomaly detection and management method of claim 1, wherein, The method of calculating point cloud density data corresponding to a first feature based on the point cloud data, and determining a first abnormal area based on the point cloud density data comprises the following steps: statistically analyzing the initial three-dimensional point cloud model to obtain the point cloud density data, and determining a region in which the point cloud density data does not satisfy a preset range condition as the first abnormal area; adjusting the sensitivity threshold according to the feature parameter, calculating an adjustment coefficient according to the adjusted sensitivity threshold, updating the initial three-dimensional point cloud model through the adjustment coefficient to obtain updated point cloud density data; if the updated point cloud density data still does not satisfy the preset range condition, iteratively updating until the preset range condition is satisfied to obtain the first abnormal area.

4. The method of power distribution cable anomaly detection and management of claim 3, wherein, The method of adjusting a sensitivity threshold of the initial three-dimensional point cloud model in the abnormal detection process according to the feature parameter, thereby adjusting a feature threshold corresponding to a second feature, and determining a second abnormal area and a damage degree comprises the following steps: updating a threshold corresponding to a second feature based on the adjustment coefficient to obtain the feature threshold; Obtain reflection intensity data corresponding to the second feature, perform time series analysis on the reflection intensity data to obtain a feature sequence; Determine a plurality of second abnormal regions according to the feature threshold and the feature sequence, and perform statistical analysis on each of the second abnormal regions to obtain a damage degree.

5. The method of power distribution cable anomaly detection and management of claim 1, wherein, The point cloud data when detecting each power distribution optical cable is obtained, and an initial three-dimensional point cloud model corresponding to each of the point cloud data is constructed based on the point cloud data, specifically as follows: The point cloud data is preprocessed, and a three-dimensional point cloud model is generated by processing the preprocessed point cloud data using a statistical filtering algorithm; Edge contour features of the three-dimensional point cloud model are extracted, a first feature and a second feature are determined based on the edge contour features and the point cloud data, and a multi-dimensional visual feature vector is generated by fusing the first feature and the second feature; The matching parameters between the three-dimensional point cloud model and the standard point cloud model are updated according to the geometric deviation between the three-dimensional point cloud model of the current iteration and the standard point cloud model, in combination with the multi-dimensional visual feature vector, until the geometric deviation is greater than or equal to a first preset threshold, the iteration is stopped, and the initial three-dimensional point cloud model is output.

6. The method of power distribution cable anomaly detection and management of claim 5, wherein, The first feature and the second feature are determined based on the edge contour features and the point cloud data, and the multi-dimensional visual feature vector is generated by fusing the first feature and the second feature, specifically as follows: A point distance distribution value is calculated from the edge contour features, and a tightness feature is determined according to the point distance distribution value; The surface protective layer of the power distribution optical cable is extracted, and if the point cloud density value of the surface protective layer is lower than a second preset threshold, it is determined that the surface protective layer is abnormal, and a protection integrity feature is obtained; The multi-dimensional visual feature vector is generated by fusing the tightness feature and the protection integrity feature.

7. The method of power distribution cable anomaly detection and management of claim 1, wherein, The feature analysis is performed on the target abnormal region to determine an influence range, specifically as follows: The region position data of the target abnormal region is determined using a positioning marker technology, and the shape feature and the distribution feature of the target abnormal region are extracted; The influence range is determined based on the shape feature and the distribution feature, and if the influence range is greater than or equal to a third preset threshold, the model parameters are adjusted.

8. A power distribution cable anomaly detection and management system, characterized by, It includes: An acquisition module, an abnormal region determination module, a model adjustment module, and a management module; The acquisition module is configured to obtain point cloud data when detecting each power distribution optical cable, and construct an initial three-dimensional point cloud model corresponding to each of the point cloud data based on the point cloud data; The abnormal region determination module is configured to calculate point cloud density data corresponding to a first feature based on the point cloud data in each of the initial three-dimensional point cloud models, determine a first abnormal region based on the point cloud density data, determine a feature parameter of the first abnormal region, adjust a sensitivity threshold of the initial three-dimensional point cloud model in an abnormal detection process according to the feature parameter, and further adjust a feature threshold corresponding to a second feature, determine a second abnormal region and a damage degree. The model adjustment module is configured to locate and mark the first abnormal area and the second abnormal area, determine the position of a target abnormal area, perform feature analysis on the target abnormal area to determine an influence range, adjust model parameters of the initial three-dimensional point cloud model according to the influence range, and refit each of the point cloud data according to the adjusted model parameters to obtain a target three-dimensional point cloud model. The management module is configured to determine an abnormality detection result according to the target three-dimensional point cloud model, and perform power distribution optical cable management according to the abnormality detection result.

9. A terminal device, comprising: A computer program product includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the power distribution optical cable abnormality detection and management method according to any one of claims 1-7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer program product includes: A stored computer program, wherein the computer program controls a device in which the computer readable storage medium is located to perform the power distribution optical cable abnormality detection and management method according to any one of claims 1-7 when the computer program is running.

Images