Recently, series compensation is widely used in transmission. However, this creates several problems to conventional protection approaches. This paper presents overcurrent protection and fault classification approach for series compensated transmission line using support vector machine (SVM). Postfault three lines current samples for half cycle are used as inputs to SVMs. The time taken for fault classification is 10 ms after the fault inception. Four SVMs are used; three SVMs (SVMa, SVMb and SVMc) are used for faulty phase detection and last SVM (SVMg) is used for ground detection. The polynomial kernel SVM is designed to provide the optimal classification conditions. Wide variations of load angle, fault inception angle, fault resistance and fault location have been carried out with different types of faults using EMTDC program. Backward faults have also been included in the data sets. The proposed technique is tested and the results verify the fastness, accuracy and robustness of it.
Available at: http://works.bepress.com/almoataz_abdelaziz/29/