Enhancing grid reliability through advanced insulator defect identification

The article presents an innovative approach for detecting defects in insulators used in high-voltage power transmission lines, employing an enhanced Detection Transformer (DETR) model, termed IF-DETR. The study addresses the significant challenges in traditional insulator defect detection methods, such as the loss of small defect features and confusion with background features. Firstly, we propose a multi-scale backbone network to better extract features of small objects. Secondly, as the contextual information surrounding objects plays a critical role in detecting small objects, we introduce a fusion module composed of ECA-Net and SAU to replace the original attention module for improved contextual information extraction. Lastly, we introduce the insulator defect (IDIoU) loss to optimize the instability in the matching process caused by small defects. Extensive experiments demonstrate the model's effectiveness, particularly in detecting small defects, marking a notable advancement in insulator defect detection technology. The IF-DETR achieved a 2.3% increase in AP compared to existing advanced methods. This method not only enhances the accuracy of defect detection, crucial for maintaining the reliability and safety of power transmission systems but also has broader implications for the maintenance and inspection of high-voltage power infrastructure.