期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2019
卷号：242
期号：3
页码：1-7
DOI：10.1088/1755-1315/242/3/032013
出版社：IOP Publishing
摘要：The fault line selection of traditional resonant system method has low reliability and poor accuracy. Although the ordinary intelligent line selection method improves the line selection accuracy, the system has a long running time and is not effective. In this paper, an improved intelligent line selection method based on particle swarm optimization (PSO-SVM) is proposed. The traditional particle swarm optimization algorithm is improved, which makes the SVM model parameters faster and less likely to fall into local optimum. Combining the fifth harmonic method and the wavelet packet variation method to achieve efficient selection of grounding faults in resonant systems. The simulation results show that the proposed method has high accuracy and is not affected by factors such as grounding resistance and fault distance.
