Abstract：When a single line to ground fault occurs in a resonant grounding system, the fault current is weak, and the ambient noise further weakens the fault current, making it difficult to obtain field data. This paper presents an algorithm for line selection and section location based on self-organizing map (SOM) and K-means clustering. Compared with the supervised learning algorithm, this method can extract fault features faster and does not require a large number of samples for training. The fault features extracted by the SOM algorithm are used as the input of K-means clustering, and no threshold is needed to identify fault lines and locate fault segments. Considering different ground resistance, fault angle, and fault distance, as well as the influence of environmental noise and sampling asynchrony, simulation analysis and experimental data validation are conducted. Simulation and experimental results show that this method can effectively identify fault lines and locate fault segments.
欧逸哲, 术茜. 基于SOM和K均值聚类的谐振接地系统故障选线及区段定位方法[J]. 电气技术, 2023, 24(10): 23-30.
OU Yizhe, ZHU Xi. Fault line detection and fault section location method in resonant grounding systems based on SOM and K-means clustering. Electrical Engineering, 2023, 24(10): 23-30.
2023, Vol. 24 
