A power transmission line defect detection and analysis method based on unmanned aerial vehicle inspection

By constructing a drone inspection trajectory model and optimization algorithm, and combining convolutional neural networks and clustering algorithms, the problems of trajectory planning and defect identification in drone inspection were solved, achieving efficient and accurate transmission line defect detection and ensuring the safety of the power system.

CN122116199APending Publication Date: 2026-05-29SHANGQIU POWER SUPPLY CO OF STATE GRID HANAN ELECTRIC POWER CO
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHANGQIU POWER SUPPLY CO OF STATE GRID HANAN ELECTRIC POWER CO
Filing Date
2026-01-27
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing drone inspection technologies struggle to plan flight paths effectively, improve inspection efficiency and quality, and accurately identify subtle defects in power transmission lines from massive amounts of image data.

Method used

A drone inspection trajectory model was constructed, the inspection path was optimized using the Grey Wolf Optimization Algorithm, and defect features were identified and classified using convolutional neural networks and K-means clustering algorithms. Defect regions were then selected by combining image feature entropy values.

Benefits of technology

This enables efficient planning of drone inspection routes, improves the reliability of data collection and the accuracy of defect detection, and ensures the safe and reliable operation of the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122116199A_ABST
    Figure CN122116199A_ABST
Patent Text Reader

Abstract

The application discloses a kind of power transmission line defect detection analysis methods based on unmanned aerial vehicle inspection, including the following detection analysis steps: S1, construct unmanned aerial vehicle inspection track model;S2, optimization solution is carried out using grey wolf optimization algorithm, and the optimal inspection path is obtained;S3, data acquisition is carried out through the image acquisition equipment carried by unmanned aerial vehicle body;S4, the power transmission line image data collected is handled;S5, image features are extracted by convolutional neural network;S6, defect features are identified by the characteristic entropy value of extracted image;S7, the defect features obtained after identification are classified, and the power transmission line defect feature category is output after classification;The present application can reasonably plan the track of unmanned aerial vehicle inspection, improve the inspection efficiency, ensure the reliability of data acquisition, accurately identify the defect features, improve the accuracy and efficiency of defect detection, and ensure the safe, reliable and stable operation of power system.
Need to check novelty before this filing date? Find Prior Art