亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

A Real-Time Edge Inference Method for Insulator Contamination Detection With YOLOv11-ssL

污染 计算机科学 GSM演进的增强数据速率 推论 人工智能 生态学 生物
作者
Lijun Jin,Wendi Ding,Shijia Han,Jinyu Wang
出处
期刊:IEEE Transactions on Instrumentation and Measurement [Institute of Electrical and Electronics Engineers]
卷期号:74: 1-15 被引量:5
标识
DOI:10.1109/tim.2025.3565254
摘要

Insulators are a critical component of power transmission and distribution lines, requiring extensive in-service deployment. The accumulation of dust, bird droppings, rain, and snow leads to contaminated insulators, which can cause contamination flashovers, resulting in faults. Currently, manual contact-based detection of insulator contamination is costly and hazardous. In non-contact detection, image-based methods have developed rapidly, but the large data volume makes cloud transmission bandwidth-intensive and may result in high-latency, which hinders real-time detection. This paper aims to ensure the accuracy of contamination detection while reducing model complexity and parameter count, enabling low-cost real-time contamination inference on edge devices. The existing YOLOv11n-seg (a segmentation variant of YOLOv11) can already meet the accuracy requirements for insulator segmentation; therefore, this paper proposes the YOLOv11-ssL (a lightweight variant of YOLOv11) network to reduce the model size. First, to accurately capture insulator features, this paper designs a novel C3k2-star structure to enhance the information representation capability. Second, a Lightweight Shared Convolutional Separated BN Detection Head (LSCSBD) structure is proposed to reduce the model size. Finally, Layer-adaptive Magnitude-based Pruning (LAMP) is applied to YOLOv11-ssL to prune weights, significantly reducing the model size and computational workload. After segmenting the insulator, this paper introduces the DEMIC-mRMR algorithm to select the color features most correlated with the insulator contamination level; further, Gaussian Process Regression (GPR), a non-parametric regression model, is used to predict the insulator contamination level effectively. Experimental results showed that YOLOv11-ssL reduces the computational load and the number of parameters by 44.1% and 82.8%, respectively, while maintaining a mean Average Precision (mAP) without substantial decrease, and achieves an inference frame rate of 1144.5. Meanwhile, the R2 of insulator contamination detection reached 0.8674, satisfying the requirements for real-time and accurate contamination detection on edge inspection devices.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
科研通AI6.2的应助被露稚采纳,获得10
3秒前
wanci的应助被啊唔采纳,获得10
13秒前
19秒前
19秒前
学不完了完成签到 ,获得积分10
22秒前
无私的迎蓉完成签到,获得积分10
23秒前
啊唔发布了新的文献求助10
23秒前
平淡的白翠完成签到,获得积分10
23秒前
2589发布了新的文献求助10
23秒前
云墨琉年完成签到 ,获得积分10
30秒前
万能图书馆的应助被2589采纳,获得10
31秒前
啊唔完成签到 ,获得积分10
33秒前
linghanlan完成签到,获得积分10
49秒前
深情安青的应助被专注凌柏采纳,获得10
49秒前
诚心铅笔完成签到,获得积分10
56秒前
obedVL完成签到,获得积分10
1分钟前
1分钟前
1分钟前
慈蔼的人完成签到 ,获得积分10
1分钟前
Onebyby发布了新的文献求助10
1分钟前
上官若男的应助被一颗柿子树采纳,获得10
1分钟前
小绵羊完成签到,获得积分10
1分钟前
1分钟前
梦的光点发布了新的文献求助10
1分钟前
乐观凝云完成签到,获得积分10
1分钟前
lihaoran完成签到,获得积分10
1分钟前
王哪跑12发布了新的文献求助10
1分钟前
酷波er的应助被Wd采纳,获得30
1分钟前
1分钟前
1分钟前
1分钟前
Wd完成签到,获得积分10
1分钟前
专注凌柏发布了新的文献求助10
1分钟前
Wd发布了新的文献求助30
1分钟前
molihuakai的应助被王哪跑12采纳,获得10
1分钟前
1分钟前
悦耳的翠绿完成签到,获得积分10
1分钟前
2分钟前
南曦发布了新的文献求助10
2分钟前
FashionBoy的应助被啊唔采纳,获得10
2分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8185124
求助须知:如何正确求助?哪些是违规求助? 9574047
关于积分的说明 21834014
捐赠科研通 7782575
什么是DOI,文献DOI怎么找? 3434500
关于科研通互助平台的介绍 2558743
邀请新用户注册赠送积分活动 2481201