A Faults Recognition Method of Transmission Line Insulators Based on Generalized Neural Networks
DOI:
https://doi.org/10.54097/6wa6y198Keywords:
Generalized Neural Networks, Transmission Line Insulators, Faults Recognition.Abstract
Regular recognition of transmission line insulators (TLI) and rapid diagnosis of their condition are crucial for the stable operation of power systems. To enhance the speed and accuracy of fault diagnosis for TLI, deep learning algorithms are applied to the recognition of TLI faults. However, traditional neural networks suffer from slow convergence speed and low accuracy in fault diagnosis. This paper proposes a recognition method for TLI based on generalized neural networks (GNN). A database for TLI is established by using aerial images, with image coordinates extracted as the sample input set. Then, by studying the characteristics and applications of GNN, a suitable network of GNN is developed to complete the selection and design of the recognition method for TLI. The simulation experiments show that GNN is able to accurately and quickly identify faulty TLI. Compared with the traditional method, the GNN converges faster, and the loss rate decreases by 27%.
Downloads
References
[1] Zhang X，Zhang Y，Liu J,et al.InsuDet: A Fault Detection Method for Insulators of Overhead Tr ansmission Lines Using Convolutional Neural Networks[J] EEE Transactions on Instrumentation a nd Measurement，2021,70:1-12.
[2] Jafari M. and Sarkar P.Buffeting and self-excited load measurements to evaluate ice and dry galloping of yawed power transmission lines. journal of structural engineering[J], 2021, 147(11): 1-14.
[3] Tao X，Zhang D，Wang Z, et al. Detection of Power Line Insulator Defects Using Aerial Images Analyzed with Convolutional Neural Networks[J]. IEEE Transactions on Systems, Man, and Cybe rnetics: Systems，2020,50(4):1486-1498.
[4] Tan P, Li X, Xu J, et al. Catenary insulator defect detection based on contour features and gray similarity matching[J]. Journal of Zhejiang University-SCIENCE A, 2020, 21(1): 64-73.
[5] Liu J, Jia R, Li W, et al. High precision detection algorithm based on improved RetinaNet for defect recognition of transmission lines[J]. Energy Reports, 2020, 6: 2430-2440.
[6] Lu J., Ye Y., Xu X., et al. Application research of convolution neural network in image classification of icing monitoring in power grid[J]. EURASIP Journal on Image and Video Processing, 2019, 2019(49): 1-11.
[7] Liu X, Jiang H, Chen J, et al. Insulator detection in aerial images based on faster regions with convolutional neural network[C]//2018 IEEE 14th international conference on control and automation (ICCA). IEEE, 2018: 1082-1086.
[8] Wang Q, Liao Z, Xu M. Wire Insulator Fault and Foreign Body Detection Algorithm Based on YOLO v5 and YOLO v7[C]//2023 IEEE International Conference on Electrical, Automation and Computer Engineering (ICEACE). Changchun, China, 2023: 1412-1417.
[9] Yan B, Chen Q, Ye R, et al. Insulator detection and recognition of explosion based on convolutional neural networks[J]. International Journal of Wavelets Multiresolution and Information Processing, 2019, 17(2): 81-103.
[10] ZHENG H B, SUN Y H, LIU X H, et al. Infrared Image Detection of Substation Insulators Using an Improved Fusion Single Shot Multibox Detector[J]. IEEE Transactions on Power Delivery, 2021, 36(6): 3351-3359.
[11] GUOYING LU, BENHAO LI, YINING CHEN,Wu Y , Liu J , et al. Precision in Aerial Surveillance: Integrating YOLOv8 With PConv and CoT for Accurate Insulator Defect Detection [J]. IEEE Access, 2025:49062-49075
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
