Please use this identifier to cite or link to this item: http://localhost:8081/xmlui/handle/123456789/8011
Title: FAULT CLASSIFICATION AND LOCATION IN TRANSMISSION LINE USING eWAVELET TRANSFORM AND SUPPORT VECTOR MACHINE
Authors: Gangadharan, Renju
Keywords: ELECTRICAL ENGINEERING;FAULT CLASSIFICATION;eWAVELET TRANSFORM;VECTOR MACHINE
Issue Date: 2010
Abstract: In the present economic scenario more emphasis is been given to judiciously exploit the current power infrastructure as the addition of new energy sources is complicated, both in economic and environmental sense. FACTS devices are one such family of devices that help in improving the efficiency of the power transmitted through a transmission line. But, the use of such devices has introduced a problem in terms of protection of transmission lines. Apparently, the FACTS devices change the dynamics of the transmission line, mainly the apparent impedance. This makes the traditional distance protection scheme to be obsolete because it is based on the apparent impedance of the line. In this thesis, the focus is on the analysis of the faults to extract ,patterns so that the problem of fault diagnosis can be changed into a pattern classification problem. The' FACTS device used here is the Thyristor Controlled Series-Capacitor (TCSC). Two. problems are dealt in this thesis regarding the fault diagnosis; fault classification and location of the fault by identifying the zone in which the fault has occurred i.e. on which side of the TCSC has the fault occurred. The use of Wavelet Transforms have been done to analyze the current and the voltage waveforms and to extract useful features from. them. A learning algorithm called the Support Vector Machine is then used to classify the features extracted with the use of Wavelet Transforms for both the fault classification and the fault zone identification problem. The method presented in this thesis is a unique one regarding the combined use of Wavelet Transforms and Support Vector Machine for the fault analysis. An extended number of cases have been tested for both the problems and significantly higher accuracy is observed
URI: http://hdl.handle.net/123456789/8011
Other Identifiers: M.Tech
Research Supervisor/ Guide: Gupta, Indra
Pillai, G. N.
metadata.dc.type: M.Tech Dessertation
Appears in Collections:MASTERS' THESES (Electrical Engg)

Files in This Item:
File Description SizeFormat 
EED G20040.pdf3.37 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.