Open AccessInvestigate the Effect of Artificial Neural Network Parameters to Improve Fault Distance and Impedance Accuracy
Author(s) -
Mohammed A. H. Ali,
Ab Halim Abu Bakar,
Abd Rahim Nasrudin
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1127/1/012037
Subject(s) - fault (geology) , electrical impedance , artificial neural network , voltage , high impedance , engineering , control theory (sociology) , computer science , artificial intelligence , electrical engineering , geology , control (management) , seismology
This paper investigates the effect of artificial neural network (ANN) parameters against the ANN accuracy on cable fault location. The investigation is conducted through the fault impedance and distance estimations during the occurrence of high impedance fault (HIF) in the distribution system. The measured three-phase voltage and current signals are utilized and fed into the ANN to estimate the fault impedance and distance. The accuracy of the estimated fault impedance and distance is evaluated with respect to the variation of ANN parameters. Based on the analysis, it shows that more accurate results can be obtained by utilizing the optimal value of ANN parameters.