Research on Fault Diagnosis Method of High Voltage Switchgear Based on LPWAN Multi-Source Information Fusion

• Published in: 2023 2nd International Conference on Clean Energy Storage and Power Engineering (CESPE) pp. 1 - 6
• Main Authors: Liang, Qinqin, Tang, Bin, Han, Fangyuan, Yu, Min, Luo, Zongchang, Zhang, Longfei, Luo, Chuansheng, Hu, Mengzhu, Wang, Jialin, Zhu, Liping
• Format: Conference Proceeding
• Language: English
• Published: IEEE 15.12.2023
• Subjects: characteristic gas; Computer architecture; Fault diagnosis; high voltage switchgear; High-voltage techniques; information fusion; LPWAN; Neural networks; Switches; Switchgear; Voltage
• DOI: 10.1109/CESPE60923.2023.00012

As one of the most important power equipment in the power system, high voltage switchgear plays a role in power generation, transmission, distribution, etc. In this study, a fault monitoring method for high voltage switchgear based on LPWAN (Low-Power Wide-Area Network) multi-source information fusion is proposed. By collecting the operating data of the switchgear, a self-organizing network based on LPWAN technology is established, and a management system based on the B/S architecture is constructed for human-computer interaction and analysis. The management system standardizes and preprocesses the original monitoring data of the switchgear, performs feature fusion on the samples using PCA (Principal Components Analysis), and uses PNN (Probabilistic Neural Network) for comprehensive decision analysis to establish a PCA-PNN multi-source information fusion fault diagnosis model for judging the operating status of the switchgear. The test results show that this method effectively improves the efficiency and accuracy of high voltage switchgear fault diagnosis, and plays a very important role in improving the safety level of high voltage switchgear operation.