Data mining-based high impedance fault detection using mathematical morphology

作者：Sekar Kavaskar^*; Mohanty Nalin Kant

来源：Computers & Electrical Engineering, 2018, 69: 129-141.

DOI：10.1016/j.compeleceng.2018.05.010

• High impedance fault
• Distribution system
• Mathematical morphology
• Decision tree
• Data mining

High impedance fault (HIF) detection is a challenging task in power system protection because of the random nature of current. HIFs are not efficiently detected by conventional protection systems because of their low current magnitudes. The proposed method presents an intelligent HIF protection technique using Mathematical Morphology (MM) and a data mining-based Decision Tree (DT) model. The current signals are produced by a MATLAB / SIMULINK model of an actual distribution system with real data. The features of these current signals are computed after processing with MM filter. A data mining-based DT model is then generated using these features of the current signals, and this DT model makes a final decision on classification into HIF and non-HIF. The proposed scheme is tested on different HIF and non-HIF cases and the results were found to be encouraging.

• 出版日期2018-7