Detection of hydrophobicity grade of insulators based on AHC-YOLO algorithm

Abstract Thanks to the rapid development of image processing technology, the efficiency and accuracy of power inspection have been enhanced through deep learning techniques. However, during on-site inspections, the complexity of the background images of composite insulators often makes it difficult...

Full description

Saved in:
Bibliographic Details
Main Authors: Shaotong Pei, Weiqi Wang, Peng Wu, Chenlong Hu, Haichao Sun, Keyu Li, Mianxiao Wu, Bo Lan
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-92696-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850094872713756672
author Shaotong Pei
Weiqi Wang
Peng Wu
Chenlong Hu
Haichao Sun
Keyu Li
Mianxiao Wu
Bo Lan
author_facet Shaotong Pei
Weiqi Wang
Peng Wu
Chenlong Hu
Haichao Sun
Keyu Li
Mianxiao Wu
Bo Lan
author_sort Shaotong Pei
collection DOAJ
description Abstract Thanks to the rapid development of image processing technology, the efficiency and accuracy of power inspection have been enhanced through deep learning techniques. However, during on-site inspections, the complexity of the background images of composite insulators often makes it difficult to directly extract key features for accurately assessing hydrophobicity levels. Moreover, considering the real-time requirements for insulator hydrophobicity detection in practical operations, the model must be lightweight to speed up the detection process. To address this issue, this paper proposes a YOLO algorithm for the precise detection of composite insulator hydrophobicity. The algorithm integrates a high-performance GPU network (HGNetv2), a mixed local channel attention mechanism (MLCA), lightweight convolution (CSPPC), and the Inner-WIoU loss function, significantly reducing the network’s burden and improving the accuracy of recognizing composite insulator sheds and classifying their hydrophobicity levels. By adopting a strategy of identifying insulator sheds and then classifying their hydrophobicity levels, precise detection of hydrophobicity is achieved. Experimental results show that the proposed AHC-YOLO algorithm has increased the detection accuracy of sheds by 5.77%, with GFLOPs reduced to 5.8. In the task of classifying hydrophobicity levels, the Top-1 accuracy has been improved by 4.994%, with GFLOPs reduced to 1.9. These achievements not only meet the needs for the detection and classification of composite insulator hydrophobicity but also further demonstrate the effectiveness and superiority of the algorithm through ablation and comparative experiments.
format Article
id doaj-art-e645d1d8e99546049b17c8a5c45cfa06
institution DOAJ
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e645d1d8e99546049b17c8a5c45cfa062025-08-20T02:41:33ZengNature PortfolioScientific Reports2045-23222025-03-0115111210.1038/s41598-025-92696-0Detection of hydrophobicity grade of insulators based on AHC-YOLO algorithmShaotong Pei0Weiqi Wang1Peng Wu2Chenlong Hu3Haichao Sun4Keyu Li5Mianxiao Wu6Bo Lan7Hebei Provincial Key Laboratory of Power Transmission Equipment Security Defense, North China Electric Power UniversityHebei Provincial Key Laboratory of Power Transmission Equipment Security Defense, North China Electric Power UniversityHebei Provincial Key Laboratory of Power Transmission Equipment Security Defense, North China Electric Power UniversityHebei Provincial Key Laboratory of Power Transmission Equipment Security Defense, North China Electric Power UniversityHebei Provincial Key Laboratory of Power Transmission Equipment Security Defense, North China Electric Power UniversityHebei Provincial Key Laboratory of Power Transmission Equipment Security Defense, North China Electric Power UniversityHebei Provincial Key Laboratory of Power Transmission Equipment Security Defense, North China Electric Power UniversityHebei Provincial Key Laboratory of Power Transmission Equipment Security Defense, North China Electric Power UniversityAbstract Thanks to the rapid development of image processing technology, the efficiency and accuracy of power inspection have been enhanced through deep learning techniques. However, during on-site inspections, the complexity of the background images of composite insulators often makes it difficult to directly extract key features for accurately assessing hydrophobicity levels. Moreover, considering the real-time requirements for insulator hydrophobicity detection in practical operations, the model must be lightweight to speed up the detection process. To address this issue, this paper proposes a YOLO algorithm for the precise detection of composite insulator hydrophobicity. The algorithm integrates a high-performance GPU network (HGNetv2), a mixed local channel attention mechanism (MLCA), lightweight convolution (CSPPC), and the Inner-WIoU loss function, significantly reducing the network’s burden and improving the accuracy of recognizing composite insulator sheds and classifying their hydrophobicity levels. By adopting a strategy of identifying insulator sheds and then classifying their hydrophobicity levels, precise detection of hydrophobicity is achieved. Experimental results show that the proposed AHC-YOLO algorithm has increased the detection accuracy of sheds by 5.77%, with GFLOPs reduced to 5.8. In the task of classifying hydrophobicity levels, the Top-1 accuracy has been improved by 4.994%, with GFLOPs reduced to 1.9. These achievements not only meet the needs for the detection and classification of composite insulator hydrophobicity but also further demonstrate the effectiveness and superiority of the algorithm through ablation and comparative experiments.https://doi.org/10.1038/s41598-025-92696-0Composite insulatorsHydrophobicityDefect detection classificationYOLO
spellingShingle Shaotong Pei
Weiqi Wang
Peng Wu
Chenlong Hu
Haichao Sun
Keyu Li
Mianxiao Wu
Bo Lan
Detection of hydrophobicity grade of insulators based on AHC-YOLO algorithm
Scientific Reports
Composite insulators
Hydrophobicity
Defect detection classification
YOLO
title Detection of hydrophobicity grade of insulators based on AHC-YOLO algorithm
title_full Detection of hydrophobicity grade of insulators based on AHC-YOLO algorithm
title_fullStr Detection of hydrophobicity grade of insulators based on AHC-YOLO algorithm
title_full_unstemmed Detection of hydrophobicity grade of insulators based on AHC-YOLO algorithm
title_short Detection of hydrophobicity grade of insulators based on AHC-YOLO algorithm
title_sort detection of hydrophobicity grade of insulators based on ahc yolo algorithm
topic Composite insulators
Hydrophobicity
Defect detection classification
YOLO
url https://doi.org/10.1038/s41598-025-92696-0
work_keys_str_mv AT shaotongpei detectionofhydrophobicitygradeofinsulatorsbasedonahcyoloalgorithm
AT weiqiwang detectionofhydrophobicitygradeofinsulatorsbasedonahcyoloalgorithm
AT pengwu detectionofhydrophobicitygradeofinsulatorsbasedonahcyoloalgorithm
AT chenlonghu detectionofhydrophobicitygradeofinsulatorsbasedonahcyoloalgorithm
AT haichaosun detectionofhydrophobicitygradeofinsulatorsbasedonahcyoloalgorithm
AT keyuli detectionofhydrophobicitygradeofinsulatorsbasedonahcyoloalgorithm
AT mianxiaowu detectionofhydrophobicitygradeofinsulatorsbasedonahcyoloalgorithm
AT bolan detectionofhydrophobicitygradeofinsulatorsbasedonahcyoloalgorithm