Aiming at the problems of traditional centralized cloud computing which occupies large computing resources and creates high latency

this paper proposes a fault detection scheme for insulator self-explosion based on edge computing and DL (deep learning). In order to solve the high amount of computation brought by the deep neural network and meet the limited computing resources at the edge

a lightweight SSD (Single Shot MultiBox Detector) target recognition network is designed at the edge

which adopts the MobileNets network to replace VGG16 network in the original model to reduce redundant computing. In the cloud

three detection algorithms (Faster-RCNN

Retinanet

YOLOv3) with obvious differences in detection performance are selected to obtain the coordinates and confidence of the insulator self-explosion area

and then the self-explosion fault detection of the overhead transmission line is realized by a novel multimodel fusion algorithm. The experimental results show that the proposed scheme can effectively reduce the amount of uploaded data

and the average recognition accuracy of the cloud is 95.75%. In addition

it only increases the power consumption of edge devices by about 25.6W/h in their working state. Compared with the existing online monitoring technology of insulator selfexplosion at home and abroad

the proposed scheme has the advantages of low transmission delay

low communication cost and high diagnostic accuracy

which provides a new idea for online monitoring research of power internet of things equipment.