Incipient fault classification using a combination of S-transform and Hilbert transform method

Abstract

SUMMARY Incipient faults such as those caused by tree contacts are difficult to detect by conventional relaying algorithms. These faults impact distribution feeder reliability by advancing –over time– into a full‐blown fault if not detected in time. This paper proposes a combined technique using S‐transform technique and Hilbert transform to extract the features of incipient fault. A least square support vector machine classifier is developed based on the features so that incipient faults can be distinguished from the normal disturbances. The comparison of the results of different feature selection methods has been conducted. The simulation results show that the proposed feature selection method is feasible and suitable. Copyright © 2012 John Wiley & Sons, Ltd.

Application of extreme learning machine for underground cable fault location

“…It is an extension of continuous wavelet transform with phase correction [7] and combines the elements of short time Fourier transform and wavelet transform [7]. Frequency-dependent resolution of the s-transform is used [8,9]. It has the property of retaining the absolute phase of each frequency and has a direct link with the Fourier spectrum.…”