Title: An effective technique for fault detection and classification in distribution system with the aid of DWT and ANFIS

Authors: T.C. Srinivasa Rao; S.S. Tulasi Ram; J.B.V. Subrahmanyam

Addresses: JNTU College of Engineering, Hyderabad, India ' Department of Electrical and Electronics Engineering, JNTU College of Engineering, Hyderabad, India ' TKREC-Hyderabad, India

Abstract: In this paper, the location and types of faults are identified and analysed in the distributed system by using wavelet and adaptive neuro-fuzzy inference (ANFIS) technique. When fault occurring in the system, the system behaviours are monitored and signals are measured which can be seen as distorted waveforms. These distorted waveforms are composed of different frequency components and which are needed to be represented in time-frequency domain for fault analysis. For this representation of signal, discrete wavelet transform (DWT) is presented. It extracts the features and forms the datasets which are forwarded to ANFIS classifier for classifying the type of fault occurred in the distributed power systems. The proposed technique is implemented in MATLAB/Simulink platform and this is validated using statistical measures such as accuracy, sensitivity and specificity. The proposed method is compared with the existing techniques DWT-FFNN and DWT-RBFNN methods.

Keywords: distributed power system; discrete wavelet transform; DWT; adaptive neuro-fuzzy inference; ANFIS; FFNN; fault location and fault types.

DOI: 10.1504/IJAAC.2017.087055

International Journal of Automation and Control, 2017 Vol.11 No.4, pp.411 - 427

Received: 26 Aug 2016
Accepted: 03 Dec 2016

Published online: 05 Oct 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article