Power system events classification using pattern recognition approach

Abstract

A new approach for power system event recognition and classification using HS-transform and RBFNN is presented in this paper. Different power system events (disturbances) like sag, swell, notch, spike, transient, and chirp are generated and processed through Hyperbolic S-transform (HS-Transform). The excellent time-frequency resolution property of HS-Transform is used to extract useful information (features) from the non-stationary signals for pattern recognition. Here HS-transform generates the S-matrix and S-matrix provides the time-frequency contours, phase contours and absolute phase of the corresponding signal. From the above extracted information, various numerical indices like standard deviation, variance, norm, energy are found out. Further these indices are used as inputs to the Radial Basis Function Neural Network (RBFNN) for classifying different power system events accordingly. The RBFNN provides accurate results even with inputs (indices) found out under high noise conditions (SNR 20 dB). Thus the proposed method provides a robust and accurate method for power system events classification.