Bird pecking damage risk assessment of UHV transmission line composite insulators based on deep learning

Here, a method for assessing the risk of bird pecking damage of composite insulators in ultra high voltage (UHV) lines is proposed using electric field (E‐field) simulation and deep learning. The distribution of E‐field on composite insulators is analysed via numerical simulation for different damage locations and damage sizes. Then, using the defective images of composite insulator strings captured in real inspection environments, the corresponding annotation image data set is constructed according to the finite element calculation results of E‐field under different damage conditions, and through the application of the YOLOX deep learning neural network, the risk assessment of the damage caused by bird pecking of insulators for UHV lines is conducted. Furthermore, to prevent overfitting of YOLOX with small‐scale images, transfer learning, as well as data enhancement, are applied to the YOLOX training process. According to the results, the mean average precision (mAP) of the model is 0.79, indicating that it is capable of high accuracy recognition, provides guidance for operation and maintenance personnel. Here, a bird pecking risk assessment method for UHV composite insulators is proposed, which combines E‐field analysis and deep learning object detection to reflect the hazard degree of bird pecking damage of composite insulators on power lines. It provides reliable and effective guidance for operation and maintenance personnel and is of great significance to the safe operation of power transmission lines.