LMD-YOLO: A lightweight algorithm for multi-defect detection of power distribution network insulators based on an improved YOLOv8

• Published in: PloS one Vol. 20; no. 2; p. e0314225
• Main Authors: Han, Weiyu, Cai, Zixuan, Li, Xin, Ding, Anan, Zou, Yuelin, Wang, Tianjun
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 21.02.2025; Public Library of Science (PLoS)
• Subjects: Accuracy; Algorithms; Complexity; Datasets; Deep learning; Defects; Electric insulators; Electric Power Supplies; Electricity distribution; Feature extraction; Inspection; Insulators; Machine vision; Maintenance and repair; Models, Theoretical; Modules; Neural networks; Object recognition; Parameters; Redundancy; Smart grid; Target detection; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0314225

Insulator defect detection is a critical task in distribution network inspections. To address issues such as low detection accuracy, high model complexity, and large parameter counts caused by the variety of insulator defect types, this study propose a lightweight multi-defect detection network, LMD-YOLO, based on YOLOv8. The network improves the backbone by introducing SCConv module to improve C2f module, which reduces spatial and channel redundancy, lowering both computational complexity and the number of parameters. The SimAM attention mechanism is integrated to suppress irrelevant features and enhance feature extraction capabilities without adding extra parameters. The SIoU loss function is used in place of CIoU to accelerate model convergence and improve detection accuracy. Additionally, this study creates a target detection dataset that encompasses four types of insulators: insulator, absent insulator, broken insulator, and shedding insulator. Experimental results show that LMD-YOLO achieves a 2% higher average accuracy on the insulator dataset compared to YOLOv8n, with a 24.6% reduction in model parameters, offering an effective solution for smart grid inspections.