Open AccessFault location on a series‐compensated three‐terminal transmission line using deep neural networks
Author(s) -
Mirzaei Mahdi,
Vahidi Behrooz,
Hosseinian Seyed Hossein
Publication year - 2018
Publication title -
iet science, measurement and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.418
H-Index - 49
eISSN - 1751-8830
pISSN - 1751-8822
DOI - 10.1049/iet-smt.2018.0036
Subject(s) - fault (geology) , artificial neural network , transmission line , terminal (telecommunication) , series (stratigraphy) , electric power transmission , line (geometry) , transmission (telecommunications) , algorithm , computer science , wavelet transform , wavelet , compensation (psychology) , fault indicator , real time computing , engineering , control theory (sociology) , pattern recognition (psychology) , electronic engineering , artificial intelligence , fault detection and isolation , mathematics , telecommunications , electrical engineering , geometry , psychology , paleontology , control (management) , seismology , psychoanalysis , biology , geology , actuator
In this study, discrete wavelet transform (DWT) and deep neural network (DNN) are utilised for fault location in a series‐compensated three‐terminal transmission line. The series compensation causes challenges in fault location schemes of the three‐terminal transmission lines. The presented fault location method has been extensively tested using the SIMULINK model of a three‐terminal transmission line. Features extracted from synchronous measurements of fault currents at the three terminals using DWT are fed to the DNN. Faulted section determination and fault distance calculation are carried out using a single intelligent network simultaneously. Faulted section is determined with 100% accuracy, and the efficiency of algorithm is validated for symmetrical and unsymmetrical faults, and different values of fault resistance, inception angle, and location. The accuracy of the algorithm is acceptable for large fault resistances (above 100 Ω) and fault inception angles near zero. Total mean error for test data is 0.0458% which is much improved with respect to other similar works.