Detection and Classification of Power Quality Disturbances Using Discrete Wavelet Transform and Neural Network Technique

Abstract

The nature of electric power and unsettling influences happened in power signal has become a significant issue among the electric power providers and clients. For improving the power quality ceaseless checking of power is required which is being conveyed at customer’s locales. Accordingly, recognition of PQ disturbances, and appropriate characterization of PQD is exceptionally attractive. The detection and classification of the PQD in distribution systems are important tasks for protection of power distributed network. The majority of the unsettling influences are non- stationary and transitory in nature thus it requires progressed devices and methods for the investigation of PQ disturbances. In this work a hybrid technique is utilized for portraying PQ disturbances influences utilizing wavelet change and fuzzy logic. A no of PQ events are generated and decomposed using wavelet decomposition algorithm of wavelet transform for accurate detection of disturbances. It is additionally seen that when the PQ disturbances are tainted with noise the detection becomes troublesome and the element vectors to be removed will contain a high level of noise which may debase the characterization accuracy. Consequently, a Wavelet based denoising strategy is proposed in this work before include extraction measure. Two very distinct features common to all PQ disturbances like Energy and Total Harmonic Distortion (THD) are extracted using DWTi are fed as inputs to the fuzzy expert system for accurate detection and classification of various PQ disturbances. The fuzzy expert system orders the PQ disturbances as well as demonstrates whether the disturbance is pure or contains harmonics. A neural network-based Power Quality Disturbance (PQD) location system is likewise demonstrated executing Multilayer Feed forward Neural Network (MFNN).

Keywords: Power quality, wavelet, DWT classification, ANN