An Improved Method Based on Deep Learning for Insulator Fault Detection in Diverse Aerial Images

Abstract

Insulators play a significant role in high-voltage transmission lines, and detecting insulator faults timely and accurately is important for the safe and stable operation of power grids. Since insulator faults are extremely small and the backgrounds of aerial images are complex, insulator fault detection is a challenging task for automatically inspecting transmission lines. In this paper, a method based on deep learning is proposed for insulator fault detection in diverse aerial images. Firstly, to provide sufficient insulator fault images for training, a novel insulator fault dataset named “InSF-detection” is constructed. Secondly, an improved YOLOv3 model is proposed to reuse features and prevent feature loss. To improve the accuracy of insulator fault detection, SPP-networks and a multi-scale prediction network are employed for the improved YOLOv3 model. Finally, the improved YOLOv3 model and the compared models are trained and tested on the “InSF-detection”. The average precision (AP) of the improved YOLOv3 model is superior to YOLOv3 and YOLOv3-dense models, and just a little (1.2%) lower than that of CSPD-YOLO model; more importantly, the memory usage of the improved YOLOv3 model is 225 MB, which is the smallest between the four compared models. The experimental results and analysis validate that the improved YOLOv3 model achieves good performance for insulator fault detection in aerial images with diverse backgrounds.

Insulators’ Identification and Missing Defect Detection in Aerial Images Based on Cascaded YOLO Models

“…To verify the accuracy and robustness of the proposed method, improved YOLOv3-dense model and YOLOv4-tiny model are cascaded to perform insulators' identification and their missing defect detection. The cascaded YOLO models, faster RCNN, and SSD are tested on the testing dataset of “CCIN_detection,” and YOLOv4, models in Literature [ 42 , 50 ], faster RCNN, SSD, our proposed models are used for insulator missing defect detection on the testing dataset of “InSF-detection.” The AP, precision, recall, and FPS values of the six models for the insulator missing defect prediction are listed in Table 9 . Concretely, the AP values of the six models are as follows: YOLOv4 (96.38%), model in [ 50 ] (96.5%), model in [ 42 ] (98.18%), Faster RCNN (93.2%), SSD (88.1%), and the cascaded YOLO models (98.40%).…”

“…The cascaded YOLO models, faster RCNN, and SSD are tested on the testing dataset of “CCIN_detection,” and YOLOv4, models in Literature [ 42 , 50 ], faster RCNN, SSD, our proposed models are used for insulator missing defect detection on the testing dataset of “InSF-detection.” The AP, precision, recall, and FPS values of the six models for the insulator missing defect prediction are listed in Table 9 . Concretely, the AP values of the six models are as follows: YOLOv4 (96.38%), model in [ 50 ] (96.5%), model in [ 42 ] (98.18%), Faster RCNN (93.2%), SSD (88.1%), and the cascaded YOLO models (98.40%). The precision values of the six models are as follows: YOLOv4 (98%), model in [ 50 ] (98%), model in [ 42 ] (99%), Faster RCNN (94%), SSD (85%), and the cascaded YOLO models (99%).…”

“…Simultaneously, the FPS value of our proposed model can reach 106, which is the biggest in the six models. Accordingly, it can be found that the cascaded YOLO models can be more advantageous than the faster RCNN, SSD, YOLOv4, and models in Literature [ 42 , 50 ] in insulator missing defect prediction.…”

“…e AP, precision, recall, and FPS values of the six models for the insulator missing defect prediction are listed in Table 9. Concretely, the AP values of the six models are as follows: YOLOv4 (96.38%), model in [50] (96.5%), model in [42] (98.18%), Faster RCNN (93.2%), SSD (88.1%), and the cascaded YOLO models (98.40%). e precision values of the six models are as follows: YOLOv4 (98%), model in [50] (98%), model in [42] (99%), Faster RCNN (94%), SSD (85%), and the cascaded YOLO models (99%).…”

Assembly Quality Detection Based on Class-Imbalanced Semi-Supervised Learning

“…Due to its data-driven nature, the fast-developing deep learning algorithms can extract knowledge from historical data, reducing the dependence on expert domain knowledge and avoiding artificial design of visual features. They have been widely used in the detection of key components of high-speed trains [7][8][9][10], fault diagnosis [11][12][13], high-voltage transmission line detection [14][15][16], and other industrial applications.…”