A Novel Approach on Power System Fault Detection Using Bayes Optimisation
V. Vijay Kumar1, Jillella Gopinath2

1V.Vijay Kumar, Department of EEE, Godavari Institute of Engineering and Technology A, Rajahmundry (Andhra Pradesh), India.
2Jillella Gopinath, Department of EEE, Godavari Institute of Engineering and Technology A, Rajahmundry (Andhra Pradesh), India.
Manuscript received on 07 April 2019 | Revised Manuscript received on 20 April 2019 | Manuscript published on 30 April 2019 | PP: 1084-1091 | Volume-8 Issue-6, April 2019 | Retrieval Number: F5026048619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: One of the substantial tools for the diagnosis of the transmission line faults is the artificial neural network, due to its ability to distinguish between variegated configurations. The data fed to the network get noisy sometimes that cause miscalculate at the output of the plant. By using Bayesian optimization techniques which commission the naive baye’sprocess [11] that minimize the sample data to quench the misreading at the output. “This process scrutinizes the use of an optimization technique to pinout the selective collection of data set in real time using limited amount of sample data. Importantly, this paper investigates with the Bayesian approach that mixes the strengths of bayesian optimization [13]. The usage of gaussian regression strategies [15] requires just a few number of information factors to model the complex goal gadget. Moreover because of using trust place constraint on sampling process, bayesian analysis tends to growth the target cost and converge toward near the superior. Simulation research the use of analytical features display that the Bayesian optimization can achieve an almost optimizing in a target value with rapid convergence. And these converged data sets are used to rehearse artificial neural networks (ANNs) for the fault classification in” high voltage transmission lines. The back propagation algorithm [19] and gradient boosting function has been employed for detection and classification of the fault type.
Keyword: Power System Faults, Neural Networks, Optimization.
Scope of the Article: Expert Systems