Using Probabilistic Neural Network for Classification High Impedance Faults on Power Distribution Feeders

• Main Authors: Sulaiman , Marizan, Adnan, Tawafan, Ibrahim, Zulkifilie
• Format: Article
• Language: English
• Published: IDOSI Publications 2013
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utem.edu.my/id/eprint/9340/1/marizan%2310.pdf; http://eprints.utem.edu.my/id/eprint/9340/; http://www.idosi.org/wasj/wasj23(10)13/1.pdf
• Institution: Universiti Teknikal Malaysia Melaka

An intelligent approach probabilistic Neural Network (PNN) combined with advanced signalprocessing techniques such as Discrete Wavelet Transform (DWT) is presented for detection High impedance faults (HIFs) on power distribution networks. HIFs detection is usually very difficult using the common over current devices, both frequency and time data are needed to get the exact information to classify and detect no fault from HIF. In this proposed method, DWT is used to extract features of the no fault and HIF signals. The features extracted using DWT which comprises the energy, standard deviation, mean, root mean square and mean of energy of detail and approximate coefficients of the voltage, current and power signals are utilized to train and test the PNN for a precise classification of no fault from HIFs. The proposed method shows that it is more convenient for HIF detection in distribution systems with ample varying in operating cases.