Substation Equipment Defect Detection Based on Improved YOLOv8

The detection of equipment defects in substations is crucial for maintaining the normal operation of power systems. This paper proposes an object detection algorithm for substation equipment defect detection based on improvements to the YOLOv8 model. First, the backbone of YOLOv8 is replaced with Ef...

Full description

Saved in:
Bibliographic Details
Main Authors: Yiwei Sun, Xiangran Sun, Ying Lin, Yi Yang, Zhuangzhuang Li, Lun Du, Chaojun Shi
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3410
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850158937192529920
author Yiwei Sun
Xiangran Sun
Ying Lin
Yi Yang
Zhuangzhuang Li
Lun Du
Chaojun Shi
author_facet Yiwei Sun
Xiangran Sun
Ying Lin
Yi Yang
Zhuangzhuang Li
Lun Du
Chaojun Shi
author_sort Yiwei Sun
collection DOAJ
description The detection of equipment defects in substations is crucial for maintaining the normal operation of power systems. This paper proposes an object detection algorithm for substation equipment defect detection based on improvements to the YOLOv8 model. First, the backbone of YOLOv8 is replaced with EfficientViT, which not only reduces computational redundancy but also enhances the model’s feature extraction capabilities, thereby improving overall performance. Second, a Squeeze-and-Excitation (SE) attention mechanism module is incorporated at the terminal stage of the backbone network to reinforce channel-wise feature representation in input feature maps. Finally, the Bottleneck component within YOLOv8’s C2f module is substituted with FasterBlock, which significantly accelerates inference speed while maintaining model accuracy. Experimental results on the substation equipment defect dataset demonstrate that the improved algorithm achieves a mean average precision (mAP) of 92.8%, representing a 1.8% enhancement over the baseline model. The substantial improvement in average precision confirms the feasibility and effectiveness of the proposed modifications to the YOLOv8 architecture.
format Article
id doaj-art-8fd33587f98e428d9a4e383cb933a234
institution OA Journals
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-8fd33587f98e428d9a4e383cb933a2342025-08-20T02:23:44ZengMDPI AGSensors1424-82202025-05-012511341010.3390/s25113410Substation Equipment Defect Detection Based on Improved YOLOv8Yiwei Sun0Xiangran Sun1Ying Lin2Yi Yang3Zhuangzhuang Li4Lun Du5Chaojun Shi6State Grid Shandong Electric Power Research Institute, Jinan 250003, ChinaState Grid Tancheng Power Supply Company, Linyi 276100, ChinaState Grid Shandong Electric Power Research Institute, Jinan 250003, ChinaState Grid Shandong Electric Power Research Institute, Jinan 250003, ChinaState Grid Shandong Electric Power Research Institute, Jinan 250003, ChinaState Grid Shandong Electric Power Research Institute, Jinan 250003, ChinaDepartment of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, ChinaThe detection of equipment defects in substations is crucial for maintaining the normal operation of power systems. This paper proposes an object detection algorithm for substation equipment defect detection based on improvements to the YOLOv8 model. First, the backbone of YOLOv8 is replaced with EfficientViT, which not only reduces computational redundancy but also enhances the model’s feature extraction capabilities, thereby improving overall performance. Second, a Squeeze-and-Excitation (SE) attention mechanism module is incorporated at the terminal stage of the backbone network to reinforce channel-wise feature representation in input feature maps. Finally, the Bottleneck component within YOLOv8’s C2f module is substituted with FasterBlock, which significantly accelerates inference speed while maintaining model accuracy. Experimental results on the substation equipment defect dataset demonstrate that the improved algorithm achieves a mean average precision (mAP) of 92.8%, representing a 1.8% enhancement over the baseline model. The substantial improvement in average precision confirms the feasibility and effectiveness of the proposed modifications to the YOLOv8 architecture.https://www.mdpi.com/1424-8220/25/11/3410object detectionsubstation equipmentdefect detectionYOLOv8
spellingShingle Yiwei Sun
Xiangran Sun
Ying Lin
Yi Yang
Zhuangzhuang Li
Lun Du
Chaojun Shi
Substation Equipment Defect Detection Based on Improved YOLOv8
Sensors
object detection
substation equipment
defect detection
YOLOv8
title Substation Equipment Defect Detection Based on Improved YOLOv8
title_full Substation Equipment Defect Detection Based on Improved YOLOv8
title_fullStr Substation Equipment Defect Detection Based on Improved YOLOv8
title_full_unstemmed Substation Equipment Defect Detection Based on Improved YOLOv8
title_short Substation Equipment Defect Detection Based on Improved YOLOv8
title_sort substation equipment defect detection based on improved yolov8
topic object detection
substation equipment
defect detection
YOLOv8
url https://www.mdpi.com/1424-8220/25/11/3410
work_keys_str_mv AT yiweisun substationequipmentdefectdetectionbasedonimprovedyolov8
AT xiangransun substationequipmentdefectdetectionbasedonimprovedyolov8
AT yinglin substationequipmentdefectdetectionbasedonimprovedyolov8
AT yiyang substationequipmentdefectdetectionbasedonimprovedyolov8
AT zhuangzhuangli substationequipmentdefectdetectionbasedonimprovedyolov8
AT lundu substationequipmentdefectdetectionbasedonimprovedyolov8
AT chaojunshi substationequipmentdefectdetectionbasedonimprovedyolov8