A lightweight RKM-YOLO algorithm for transmission line fault inspection

IF 5.1 3区工程技术 Q2 ENERGY & FUELS

Energy Reports Pub Date : 2025-07-30 DOI:10.1016/j.egyr.2025.06.052

Haofei Li , Zhenjie Wu , Yuyang Sun , Xiaowei Wu , Kai Luo , Quanfu Zhu , Gang Wang

{"title":"A lightweight RKM-YOLO algorithm for transmission line fault inspection","authors":"Haofei Li , Zhenjie Wu , Yuyang Sun , Xiaowei Wu , Kai Luo , Quanfu Zhu , Gang Wang","doi":"10.1016/j.egyr.2025.06.052","DOIUrl":null,"url":null,"abstract":"<div><div>The inspection of transmission lines using Unmanned Aerial Vehicles (UAVs) is crucial for ensuring reliable power supply systems. However, environmental complexity often leads to difficulties in locating equipment faults and maintenance delays, compromising power supply security. Given these challenges, this research presents a lightweight algorithm utilizing an enhanced version of YOLOv8n. First, the Receptive Field and Channel Attention Convolution (RFCAConv) module is introduced, capturing global and local features through a receptive field optimization mechanism, suppressing noise interference and mitigating image degradation caused by light refraction and reflection. We designed the K3_RFCA structure, which effectively integrates shallow and deep feature information to enhance the network’s feature extraction capability. Second, an improved KBiFPN structure is employed during feature fusion stage to enhance multi-scale adaptability while reducing computational costs. Finally, to tackle small target detection in transmission line inspection, an innovative Multi-scale and Multi-dimensional Cooperative Attention (MMCA) is proposed, adaptively weighting regional contextual information through multi-scale convolution and spatial-channel fusion, improving critical region representation. Experimental results demonstrate that RKM-YOLO achieves an average detection accuracy (mAP) of 90.7%, with an 18.27% reduction in parameters and a 3.1% improvement in recall and mAP50, while its detection speed meets the requirements for UAV inspections.</div></div>","PeriodicalId":11798,"journal":{"name":"Energy Reports","volume":"14 ","pages":"Pages 1509-1522"},"PeriodicalIF":5.1000,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy Reports","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2352484725004494","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}

引用次数: 0

Abstract

The inspection of transmission lines using Unmanned Aerial Vehicles (UAVs) is crucial for ensuring reliable power supply systems. However, environmental complexity often leads to difficulties in locating equipment faults and maintenance delays, compromising power supply security. Given these challenges, this research presents a lightweight algorithm utilizing an enhanced version of YOLOv8n. First, the Receptive Field and Channel Attention Convolution (RFCAConv) module is introduced, capturing global and local features through a receptive field optimization mechanism, suppressing noise interference and mitigating image degradation caused by light refraction and reflection. We designed the K3_RFCA structure, which effectively integrates shallow and deep feature information to enhance the network’s feature extraction capability. Second, an improved KBiFPN structure is employed during feature fusion stage to enhance multi-scale adaptability while reducing computational costs. Finally, to tackle small target detection in transmission line inspection, an innovative Multi-scale and Multi-dimensional Cooperative Attention (MMCA) is proposed, adaptively weighting regional contextual information through multi-scale convolution and spatial-channel fusion, improving critical region representation. Experimental results demonstrate that RKM-YOLO achieves an average detection accuracy (mAP) of 90.7%, with an 18.27% reduction in parameters and a 3.1% improvement in recall and mAP50, while its detection speed meets the requirements for UAV inspections.

查看原文本刊更多论文

输电线路故障检测的轻量级RKM-YOLO算法

使用无人机（uav）对输电线路进行检查对于确保可靠的供电系统至关重要。然而，环境的复杂性往往导致设备故障定位困难和维护延误，影响了供电的安全性。鉴于这些挑战，本研究提出了一种轻量级算法，利用增强版的YOLOv8n。首先，介绍了RFCAConv （Receptive Field and Channel Attention Convolution）模块，通过感受野优化机制捕获全局和局部特征，抑制噪声干扰，减轻光折射和反射引起的图像退化。我们设计了K3_RFCA结构，有效地整合了浅层和深层特征信息，增强了网络的特征提取能力。其次，在特征融合阶段采用改进的KBiFPN结构，增强多尺度适应性，同时降低计算成本；最后，针对输电线路检测中的小目标检测问题，提出了一种创新的多尺度多维协同关注（MMCA）方法，通过多尺度卷积和空间信道融合自适应加权区域上下文信息，提高了关键区域的表征能力。实验结果表明，RKM-YOLO的平均检测精度（mAP）为90.7%，参数减少18.27%，召回率和mAP50提高3.1%，检测速度满足无人机检测要求。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Energy Reports Energy-General Energy

CiteScore

8.20

自引率

13.50%

发文量

2608

审稿时长

38 days

期刊介绍： Energy Reports is a new online multidisciplinary open access journal which focuses on publishing new research in the area of Energy with a rapid review and publication time. Energy Reports will be open to direct submissions and also to submissions from other Elsevier Energy journals, whose Editors have determined that Energy Reports would be a better fit.