Defective insulators seriously threaten the safe operation of transmission lines. This paper proposes an insulator defect detection method based on an improved YOLOv4 algorithm. An insulator image sample set was established according to the aerial images from the power grid and the public dataset on the Internet, combining with the image augmentation method based on GraphCut. The insulator images were preprocessed by Laplace sharpening method. To solve the problems of too many parameters and low detection speed of the YOLOv4 object detection model, the MobileNet lightweight convolutional neural network was used to improve YOLOv4 model structure. Combining with the transfer learning method, the insulator image samples were used to train, verify, and test the improved YOLOV4 model. The detection results of transmission line insulator and defect images show that the detection accuracy and speed of the proposed model can reach 93.81% and 53 frames per second (FPS), respectively, and the detection accuracy can be further improved to 97.26% after image preprocessing. The overall performance of the proposed lightweight YOLOv4 model is better than traditional object detection algorithms. This study provides a reference for intelligent inspection and defect detection of suspension insulators on transmission lines.

Foreign objects suspended on transmission and distribution lines like nests, kites, balloons, and trash, etc. may lead discharge faults and greatly affect the safety of power grid. How to perform accurate and timely detection of these foreign objects is an urgent problem. This paper proposes a lightweight YOLOv4 model with embedded dual attention mechanism (YOLOv4-EDAM) to detect foreign objects from visible images, using MobileNetV2 embedded with the squeeze and excitation networks (SENet) to replace the CSPDarkNet53 feature extraction network, the depthwise separable convolutions (DSC) to replace the standard convolutions in SPP and PANet module, and embedding the convolutional block attention module (CBAM) into SPP and PANet module to improve the detection accuracy. Firstly, an image dataset was constructed using inspection images and public datasets, and expanded by Poisson blending and some data augmentation methods. The denoising convolutional neural network (DnCNN) was applied for image preprocessing. Next, the lightweight YOLOv4-EDAM model was trained combining Mosaic data enhancement, cosine annealing and label smoothing skills. Several detection cases were carried out and the experimental results show that the proposed model has a high accuracy with the mean average precision (mAP) of 96.71%, and a fast detection speed with the frames per second (FPS) of 45, whose overall performance is better than other object detection models. This study offers a reference for power line inspection and provides a possible way to deploy edge computing devices on unmanned aerial vehicles.

Efficient bird damage prevention of transmission lines is a long‐term challenge for power grid operation and maintenance. An approach combined lightweight convolutional neural network (CNN), image processing and object detection is presented in this paper to detect typical bird species related to transmission line faults. An image dataset of 20 bird species that threaten transmission line security is constructed. The YOLOv4‐tiny algorithm model is constructed and trained combining stage‐wise training, mosaic data enhancement, cosine annealing, and label smoothing. The mean average precision (mAP) can reach 92.04% on the test set by adjusting the parameters of the training process. Then, the validity of the proposed method is verified according to the test results and performance indexes by comparing with other methods, including Faster RCNN, SSD, YOLOv4 etc. Some image pre‐processing methods such as motion blur, defocus blur, contrast and brightness adjustment are used to simulate the scenarios in practical engineering applications. The proposed method can detect bird species perched around transmission lines with high‐efficiency, which is useful for differential prevention of bird‐related outages of power grids.

The correct identification of partial discharge types is of great significance to the stable operation of GIS. In order to improve the recognition accuracy and result of partial discharge, and to meet the requirements of real-time monitoring of GIS equipment, this paper proposes a GIS partial discharge defect recognition model based on YOLOv5. First, the GIS partial discharge simulation experiment is established to create the dataset of partial discharge PRPD map. Then, a YOLOv5-based GIS partial discharge defect recognition model is constructed, and different training methods are used to optimize the parameters of the model. By comparing with target detection models based on other deep learning methods, such as Faster-RCNN and YOLOv4, the YOLOv5 model discussed in the paper has significantly improved the recognition efficiency and recognition accuracy, in which mAP value is 95.89% and FPS is 28.89. In addition, the model can realize the distinction and identification of multiple PD types in a single PRPD map. At last, the YOLOv5-based GIS partial discharge defect identification model is applied to the test in a 500 kV substation. The model accurately determines the type of GIS partial discharge, which verifies the accuracy and validity of the model.