Fault Detection in Power Distribution Networks Based on Comprehensive-YOLOv5

Abstract

Real-time fault detection in power distribution networks has become a popular issue in current power systems. However, the low power and computational capabilities of edge devices often fail to meet the requirements of real-time detection. To overcome these challenges, this paper proposes a lightweight algorithm, named Comprehensive-YOLOv5, for identifying defects in distribution networks. The proposed method focuses on achieving rapid localization and accurate identification of three common defects: insulator without loop, cable detachment from the insulator, and cable detachment from the spacer. Based on the You Only Look Once version 5 (YOLOv5) algorithm, this paper adopts GhostNet to reconstruct the original backbone of YOLOv5; introduces Bidirectional Feature Pyramid Network (BiFPN) structure to replace Path Aggregation Network (PANet) for feature fusion, which enhances the feature fusion ability; and replaces Generalized Intersection over Union GIOU with Focal Extended Intersection over Union (Focal-EIOU) to optimize the loss function, which improves the mean average precision and speed of the algorithm. The effectiveness of the improved Comprehensive-YOLOv5 algorithm is verified through a “morphological experiment”, while an “algorithm comparison experiment” confirms its superiority over other algorithms. Compared with the original YOLOv5, the Comprehensive-YOLOv5 algorithm improves mean average precision (mAP) from 88.3% to 90.1% and increases Frames per second (FPS) from 20 to 52 frames. This improvement significantly reduces false positives and false negatives in defect detection. Consequently, the proposed algorithm enhances detection speed and improves inspection efficiency, providing a viable solution for real-time detection and deployment at the edge of power distribution networks.

Surround Sensing Technique for Trucks Based on Multi-Features and Improved Yolov5 Algorithm

“…At the same time, an adaptive scaling strategy is adopted. The input images of different sizes are scaled into a standard size and sent into the detection network [25]. The commonly used sizes of YOLOv5 are 416 × 416 and 608 × 608.…”

A Lightweight Detection Method for Blueberry Fruit Maturity Based on an Improved YOLOv5 Algorithm

“…The loss functions of the output layers of the YOLOv5 model consist of three components. The Generalized Intersection over Union (GIoU) loss function is used to calculate the loss for boundary regression [24]. The YOLOv5 model performs weighted Non-Maximum Suppression (NMS) on GIOU_Loss to achieve the efficient selection of the optimal bounding box.…”

ID-YOLOv7: an efficient method for insulator defect detection in power distribution network

“…Currently, deep learning has demonstrated remarkable achievements across various domains, such as autonomous driving (Nguyen et al, 2018 ), medical diagnostics (Bakator and Radosav, 2018 ), and computer vision (Voulodimos et al, 2018 ). At the same time, experts have gradually shifted their focus to the field of electrical equipment inspection, especially in the insulator defect detection (Prates et al, 2019 ; Niu et al, 2023 ). Deep learning, with its remarkable generalization and cross-scenario adaptability, is ushering in a revolutionary transformation in insulator defect detection.…”