Application effect of YOLOv8 algorithm combined with AIFI technology in insulator detection of power system

In power systems, insulators are critical components whose damage or failure can lead to equipment malfunctions or power interruptions, presenting significant challenges for operation and maintenance. Traditional manual inspection methods are inefficient and prone to human error, failing to meet the high-precision and high-efficiency demands required for fault detection in modern power systems. To address this, the present study proposes combining the YOLOv8 algorithm with AIFI technology for the intelligent detection and fault diagnosis of insulators in power systems. The mean average accuracy (MAP) of the YOLOv8 algorithm before improvement is 0.919, with a model weight of 6.3MB. After integrating AIFI technology, the MAP of the model increased to 0.921, and the weight slightly decreased to 6.1MB. AIFI technology enhanced YOLOv8’s detection accuracy and robustness in complex environments by improving data quality, optimizing fault recognition, and reducing false positives and false negatives. The improved system provide a more accurate and efficient solution for health monitoring and fault diagnosis of power equipment.