Tunable-Q Wavelet Transform and Dual Multiclass SVM for Online Automatic Detection of Power Quality Disturbances

Abstract

A new automated recognition approach based on tunable-Q wavelet transform (TQWT) and a dual multiclass support vector machines (MSVM) has been proposed for detection of power quality disturbances. The proposed approach first investigates the presence of low-frequency interharmonics and then tunes the wavelet for decomposition of signal into fundamental and harmonic components. The tuning of Q-factor and redundancy makes the filter design to accurately extract the fundamental frequency component from a distorted input signal. Then, a unique set of features, which clearly reveal the characteristics of disturbances, are extracted. The power quality disturbances are broadly categorized into two groups based on the pre-obtained information of low-frequency interharmonics. Therefore, multiple disturbances are recognized by employing a dual MSVM, one for each group. Results demonstrate the applicability, strength, and accuracy of the proposed approach for classification of single and combined disturbances under different noisy conditions. Moreover, to illustrate the prominence of the features extracted from TQWT, two more classifiers based on decision tree and feedforward neural network have been employed for classification of power quality disturbances.