• Prerana P. Wasnik

The paper presents a novel approach of Machine learning for the protection of power system. The decision tree algorithm based on semi-supervised-machine learning is designed for the automated detection as well as classification of the transmission line faults. The decision tree makes the predictions based on the decisions for constructing optimal-classification tree. To extract the features in the current and voltage signal, discrete wavelet transform is applied, which decomposes the signals into smaller components. This feature vector is used by the classifier for class prediction. The performance of the algorithm is tested on the Three phase series compensated network in MATLAB environment. The results shows that the proposed algorithm can detect and classify the different faults reliably while keeping the computation burden suitably low which make the implementation more feasible.

Fault classification, fault detection, decision Tree, dwt, machine learning

"Fault detection and classification in transmission line by using decision tree", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 5, page no.481-485, May-2020, Available :http://www.jetir.org/papers/JETIR2005378.pdf

"Fault detection and classification in transmission line by using decision tree", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 5, page no. pp481-485, May-2020, Available at : http://www.jetir.org/papers/JETIR2005378.pdf