Paper Key : IRJ************590
Author: Pratishtha Khare
Date Published: 01 Nov 2022
Abstract
When two or more conductors come into touch with the earth or each other, a fault happens. More than 80% of all defects are believed to be ground faults, which are one of the major issues in power systems. The topic of this essay is the detection of defects in transmission lines for electric power. Artificial neural networks have been used to detect errors. The ANN is supplied with either signal characteristic that have been retrieved using specific measurement procedures or simply raw samples of the input signals. The design and development of a neural network model for a three-phase transmission line failure are done in this research article. We have seen the many fault kinds that can exist in a transmission line system. It has been examined for line-to-line and line-to-ground faults. The failure causes significant fluctuations in the transmission line's current and voltage. The NN model is trained using this data. A variety of training algorithms have been used to train the NN model. The Bayesian approach is shown to be the most effective, even if the NN network is performing satisfactorily and the error is decreasing with the number of epochs.