Discrimination of Internal Faults and Other Transients in an Interconnected System With Power Transformers and Phase Angle Regulators

This study solves the problem of accurate detection of internal faults and\nclassification of transients in a 5-bus interconnected system for Phase Angle\nRegulators (PAR) and Power Transformers. The analysis prevents mal-operation of\ndifferential relays in case of transients other than faults which include\nmagnetizing inrush, sympathetic inrush, external faults with CT saturation,\ncapacitor switching, non-linear load switching, and ferroresonance. A gradient\nboosting classifier (GBC) is used to distinguish the internal faults from the\ntransient disturbances based on 1.5 cycles of 3-phase differential currents\nregistered by a change detector. After the detection of an internal fault, GBCs\nare used to locate the faulty unit (Power Transformer, PAR series, or exciting\nunit) and identify the type of fault. In case a transient disturbance is\ndetected, another GBC classifies them into the six transient disturbances. Five\nmost relevant frequency and time domain features obtained using Information\nGain are used to train and test the classifiers. The proposed algorithm\ndistinguishes the internal faults from the other transients with a balanced\naccuracy of 99.95%. The faulty transformer unit is located with a balanced\naccuracy of 99.5% and the different transient disturbances are identified with\na balanced accuracy of 99.3%. Moreover, the reliability of the scheme is\nverified for different rating and connection of the transformers involved, CT\nsaturation, and noise levels in the signals. These GBC classifiers can work\ntogether with a conventional differential relay and offer a supervisory control\nover its operation. PSCAD/EMTDC software is used for simulation of the\ntransients and to develop the two and three-winding transformer models for\ncreating the internal faults including inter-turn and inter-winding faults.\n