Designed orthogonal wavelet based feature extraction and classification of underlying causes of power quality disturbance using probabilistic neural network

Abstract

ABSTRACT – Finding the reasons responsible behind PQ disturbances is as much important as detection of various inconspicuous PQ disturbances to have timely and accurate mitigation. Therefore, this paper proposes a robust solution for detection and classification of different voltage sag causes. For efficient feature extraction, a novel method is proposed for designing of wavelet using vector-quantised signal information to instil signal information into the wavelet. Multiresolution analysis of voltage signals is carried out to decompose voltage signals to multiple scales. In this way, sag-related information is more effectively captured and utilised in classification of voltage sag signals into one of the classes of sag causes. Probabilistic neural network is trained and tested using five-fold cross-validation on the data simulated in MATLAB/Simulink. Another challenge in PQ analysis, i.e. noisy data, is also addressed here by considering noise of 30dB in voltage sag signals. Quantitative evaluation of classifier performance using two measures, such as classification rate and false alarm rate, proves the proposed method efficient for voltage sag detection and classification.