Health Monitoring of Line Insulators Through Artificial Intelligence-Based Surveillance System

High-tension (HT) power line insulators are critical components of electrical transmission systems, and their failure due to cracks can lead to power outages and safety hazards. Traditional inspection methods are time-consuming, costly, and pose significant risks to the workers. This paper proposes an artificial intelligence (AI) based surveillance system for detecting insulator cracks. The surveillance system uses drones to capture high-resolution images of insulators and incorporates a target detection algorithm based on YOLOv11 (You Only Look Once), which utilizes the powerful learning ability of deep convolutional neural network (CNN) to classify the insulators as defective or non-defective. This method is trained on a large dataset of annotated samples. The experimental results show that the YOLOv11-based insulator defect detection method can effectively identify defective insulators from the drone-captured aerial images. Compared with the previous insulator defect identification methods, the accuracy and detection time are significantly improved. The proposed solution offers a safer, faster, and more cost-effective alternative to manual inspections, with potential applications in large-scale power line monitoring.