2020 VOL.3 Feb No.1

• Title: Research on Fault Identification Method of Low-voltage Transmission and Distribution Network Based on Artificial Intelligence Al
• Name: Po-Hsun Suzuki
• Company: Kyungpook National University
• Abstract:

  Low-voltage transmission and distribution network is the carrier of power supply. Once a failure occurs, it not only affects the quality of power supply, but also reduces the safety and reliability of the low-voltage distribution network. This time, based on artificial intelligence algorithms, research on fault identification methods for low-voltage transmission and distribution networks. This method is divided into two parts. First, an improved matrix algorithm is used to locate the location of the fault in the low-voltage transmission and distribution network, which lays the foundation for subsequent fault type identification. Then, the immune clustering algorithm combining artificial immune algorithm and clustering algorithm is used to identify the fault type based on the positioning results. The results show that compared with several methods proposed in the literature, the results identified by this method are completely consistent with the real results, and the recognition accuracy is high.

• Keyword: Artificial Intelligence Algorithm; Low-Voltage Transmission And Distribution Network; Fault Identification
• DOI: 10.12250/jpciams2020010119
• Citation form: Po-Hsun Suzuki.Research on Fault Identification Method of Low-voltage Transmission and Distribution Network Based on Artificial Intelligence Al[J]. Computer Informatization and Mechanical System, 2020, vol. 3, pp. 107-113.

[1]Hu Wei, Li Yong, Cao Jia, et al. Fault identification based on LOF and SVM for smart distribution network [J]. Electric Power Automation Equipment, 2016, 36 (6): 7-12.

[2]Mei Yang, Xu Daxin. Distribution network fault identification method based on BP neural network [J]. Journal of Hennan Institute of Engineering(Natural Science Edition), 2017, 29 (2): 40-45.

[3]Qin Bo, Liu Yongliang, Wang Jianguo, et al. The GA-SVM Rolling Bearing Fault Diagnosis Method Research Based on Wavelet Packet and Singular Value Decomposition [J]. Machinery Design & Manufacture, 2016 (6): 38-42.

[4]Qin Xue, Liu Yadong, Sun Peng, et al. Study on the line fault root-cause identification method in distribution networks based on time-frequency characteristics of fault waveforms [J]. Chinese Journal of Scientific Instrument, 2017, 38 (1): 41-49.

[5]Gong Qunying. Study on wavelet transform based simulation of single-phase grounding fault in power distribution network [J]. Modern Electronics Technique, 2016,39(20): 142-145.

[6]Zuo Hang, Chen Si, Zhao Hailin, et al. Research on fault location of distribution network based on improved matrix algorithm [J]. Zhongzhou Coal, 2017 (12): 153-157.

[7]Yan Fangguo, Li Xiaoming, Yang Junjie, etc. Improved matrix-based algorithm and its application in practice [J]. Electrical Measurement & Instrumentation, 2017, 54 (12): 21-27.

[8]Fu Longtian, Yu Yumei. Fault detection model based on artificial immune theory [J]. Journal of Henan Institute of Science and Technology(Natural Sciences Edition), 2017, 45 (3): 57-64.

[9]Zhang Yuxue, Pan Hongxia, Automaton fault diagnosis based on EEMD and FCM clustering [J]. CHINA MEASUREMENT & TESTING TECHNOLOGY, 2017 (3): 106-110.

[10]Zhang Jian, Wang Xiaozhu. Traffic Flow Analysis Based on Artificial Immune Clustering Algorithm [J]. Journal of MinZu University of China(Natural Sciences Edition), 2017, 26 (1): 56-60.