An intelligent approach using SVM to enhance turn-to-turn fault detection in power transformers

This paper proposes the use of the SVMs classification technique for power transformer protection, in order to enhance the detection of minor internal turn-to-turn faults. The proposed scheme has been also tested through external faulted cases as well as energizing inrush phenomenon. In addition, it has been compared with a conventional differential algorithm. The results have shown that the proposed intelligent technique provides fast, sensitive and reliable detection of minor internal turn-to-turn faults in power transformers. The dynamic simulations of a test benchmark have been conducted using the PSCAD/EMTDC software.