A new application of neural network approach to estimate fault location of short Medium voltage underground cables is demonstrated in this study. Different faults on a protected cable should be classified and location should be estimated. This study presents, the use of neural networks as a pattern classifier algorithm to perform these tasks. The proposed algorithm has a good performance to variation of different parameters such as fault type, fault resistance and fault inception angle. Studies show that the proposed technique is able to offer acceptable accuracy in estimation of fault location.
Marouf Pirouti . Neural-Network-Based Fault Location Estimator for Short Medium Voltage Underground Cable.
DOI: https://doi.org/10.36478/ijepe.2008.340.344
URL: https://www.makhillpublications.co/view-article/1990-7958/ijepe.2008.340.344