Wavelet Packet Transform and Support Vector Machine Based Discrimination of Power Transformer Inrush Current from Internal Fault Currents

Abstract

This paper presents a Wavelet packet transform with entropy features and support vector machine (SVM) based differential protection of power transformer by using internal fault and inrush current. The wavelet packet transform one of the powerful signal-processing tool and it is used to extract the information of differential current from third level using Db 9 mother wavelet. A two cycles of transformer fault current data is processed through wavelet packet transform to obtain wavelet coefficients and then features are extracted by using Shannon entropy principle. Subsequently, the extracted features are applied as inputs to SVM for distinguishing inrush current from internal fault. The application of this method is studied through detailed simulation of different faults on a power transformer using MATLAB/SIMULINK software. The results of the proposed new technique were found to be reliable, fast and accurate in identifying the fault condition.

Transformer winding faults classification based on transfer function analysis by support vector machine

“…Its ability for detection of electrical faults in transformer [33 -35] is proved. Another valuable use of SVM is for discrimination of transformer inrush current from internal fault currents [3].…”

“…This property will also be beneficial in fault classification, because the number of features to be the basis of fault diagnosis do not have to be limited. Also, SVM-based classifiers are claimed to have good generalisation properties compared with conventional classifiers, because in training the SVM classifier, the socalled structural misclassification risk is to be minimised, whereas traditional classifiers are usually trained so that the empirical risk is minimised [3]. SVM is recognised as one of the standard tools for machine learning and data mining, which is based on advances in statistical learning theory.…”

“…A survey of pertinent literature reveals that most publications on this topic can be classified in two main groups. Ozgonenel et al [2], Subramanian et al [3] and Ozgonenel and Onbilgin [4] presented a method to distinguish the inrush current from internal fault currents in order to differentiate protection of power transformer. Some of the related studies [5 -8], employing the transmission line method, have presented a transformer model for identification of incipient and internal faults [such as turn-toturn short circuit (SC) faults].…”

Characterization of internal disturbances and external faults in transformers using an S-transform--based algorithm

“…Discrete wavelet transform (DWT)-based algorithms for discriminating between the magnetizing inrush current and short circuit current were suggested in [8] and * Correspondence: az.ashrafian@gmail.com [9]. Moreover, protective methods have been proposed using a combination of DWT and fuzzy logic [10,11], neural networks [5,12], Gaussian mixture model [13], correlation factor [14], and support vector machine [15,16]. However, DWT-based methods are easily influenced by noise [17].…”