Power signal classification using Adaptive Wavelet Network

A new approach to classification of non-stationary power signals based on adaptive wavelet has been considered. This paper proposes a model for non-stationary power signal disturbance classification using adaptive wavelet networks (AWN). A AWN is a combination of two sub-networks consisting of a wavelet layer and adaptive probabilistic network. The AWN has the capability of automatic adjustment of learning cycles for different classes of signals, for minimizing error. AWN models are specifically suitable for application in adaptive environments with time varying nonstationary power signals. The test results showed accurate classification, fast and adaptive learning mechanism, fast processing time and overall model effectiveness in classifying various non-stationary power signals. The classification result of the AWN (Adaptive Wavelet Network) has been compared with that of the Probabilistic Neural Network (PNN).