Multi-class target fault detection method, system and device in power transmission line and medium

Abstract

The invention belongs to the technical field of high-voltage power transmission line fault detection, and discloses a method, a system, equipment and a medium for detecting faults of multiple types of targets in a power transmission line. Secondly, on the basis of a YOLOv5 algorithm framework, space and channel convolution attention models are introduced to suppress interference of a complex background; an FPN + PAN structure at a check part in YOLOv5 is changed into a BiFPN structure, and a multi-scale and same-scale feature adaptive weighted fusion module is designed to enhance the detection capability of a detection network on a fault target under a shielding condition, and a detection model is constructed; outputting a detection result; in order to verify the detection precision and the real-time performance of the algorithm, the detection precision and the real-time performance of the algorithm are compared with YOLOv5s. Compared with a YOLOv5s algorithm, the method has the advantages that the detection accuracy and the recall rate of various target faults in the power transmission line are the highest, and meanwhile, the algorithm has relatively good real-time performance.

Description

technical field [0001] The invention belongs to the technical field of fault detection of high-voltage transmission lines, and in particular relates to a method, system, equipment and medium for detecting multi-type target faults in transmission lines. Background technique [0002] At present, with the continuous expansion of the scale of the State Grid and the continuous complexity and multi-function of transmission lines, the safe operation of various transmission lines is becoming more and more important. The traditional transmission line maintenance method of manual inspection of transmission lines and substations has been unable Meet the growing transmission lines. With the vigorous development of artificial intelligence, the State Grid Corporation of China has gradually introduced artificial intelligence into the intelligent inspection of transmission lines, such as using intelligent drones loaded with intelligent detection methods to take pictures of high-altitude tra...

AI Technical Summary

Problems solved by technology

[0003] By consulting relevant literature, based on the Faster R-CNN algorithm framework to detect multi-target faults on transmission lines, good detection accuracy can be achieved, but the detection speed is slower than the YOLOv4 and YOLOv5 algorithms, which cannot meet the real-time detection requirements; based on The detection algorithms of YOLOv4 and YOLOv5 have higher detection accuracy for fault detection in transmission lines, but the YOLOv5 detection algorithm has higher detection accuracy and better real-time performance than the YOLOv4 algorithm.

However, some existing intelligent detection methods always have more or less defects, which cannot meet the needs of high efficiency and high accuracy in the working conditions of power line detection.

[0004] Through the above analysis, the existing problems and defects of the existing technology are: the fault target is difficult to be accurately detected due to its low saliency in complex environments; the lack of expressive ability of the target to be detected results in missed detection and false detection

[0005] The difficulty in solving the above problems and defects is: most fault targets in power transmission lines include target faults such as falling off pins in bolts, missing screw gaskets, cracked insulator strings, excessive parallel gaps, etc., especially when faced with strong light, objects, etc. How to accurately detect these multi-type target faults under special circumstances such as occlusion and complex background is a huge problem

[0006] The significance of solving the above problems and defects is: because high-voltage transmission lines are exposed to harsh natural environments for a long time, affected by natural environmental factors including strong winds, thunderstorms, freezing damage, bird damage, etc., often cause transmission lines to occur such as insulators falling off, screw damage, etc. Fault conditions such as looseness and damage to the straight spacer rods cause huge potential safety hazards in the power transmission system

Images