A classification approach using SVM to detect magnetic inrush in power transformers
Journal: International Journal of Innovation and Applied Studies (Vol.3, No. 3)Publication Date: 2013-07-02
Authors : Selvi V. Thamarai; Malathi V.;
Page : 693-700
Keywords : Inrush Current; Support Vector Machine; Fault current; Sequential minimization method; Radial basis function;
Abstract
In Order to avoid mal operation of differential relay in transformer it is essential to distinguish between inrush and fault conditions. For accurate discrimination between inrush and fault current SVM technique is proposed. The merit of this method is demonstrated by simulation of different faults and switching conditions using MATLAB/SIMULINK. The inrush current values are obtained by varying the switching angle and the fault currents are obtained by varying the fault resistance. The Proposed method is tested on a 3000MVA, 230 kV Y-Y connected transformer by varying fault resistance, and switching angle. The performance of SVM is compared in terms of classification accuracy. The accuracy obtained using SVM is found to be more than other methods such as neural networks, ANFIS, etc. The results obtained with SVM are far better than other methods earlier used. SVM is preferred here over other methods because it is based on structural risk minimization whereas neural networks and ANFIS are empirical based. Moreover this method seems to be very effective for modern transformers with high harmonic contents and it requires less training. A SVM based protective field programmable gate array relay logic can be implemented further in future which will be verified against the simulation results.
Other Latest Articles
- Online Tracking of Maximum Panel Power Output in Photovoltaic Stand Alone System with Different Insolation
- Ultra Wideband Slotted Microstrip Patch Antenna for Downlink and Uplink Satellite Application in C band
- Metallurgical Characterisation of Recovered Aluminium Alloys in Cameroon
- Analysis of Psychological Well-being and Turnover intentions of Hotel Employees: An Empirical Study
- Using Geographic Information System to Maintenance and Upgrading Public Utility Networks Using Technology AM / FM
Last modified: 2013-08-21 22:28:24