Power plant fault detection using artificial neural network

Autor: Nazatul Shiema Moh Nazar, Hidzrin Dayana Mohd Hidzir, Suresh Thanakodi, Mohammad Zulfikar Khairul Awira, Nur Fazriana Joini
Rok vydání: 2018
Předmět:
Zdroj: AIP Conference Proceedings.
ISSN: 0094-243X
DOI: 10.1063/1.5022952
Popis: The fault that commonly occurs in power plants is due to various factors that affect the system outage. There are many types of faults in power plants such as single line to ground fault, double line to ground fault, and line to line fault. The primary aim of this paper is to diagnose the fault in 14 buses power plants by using an Artificial Neural Network (ANN). The Multilayered Perceptron Network (MLP) that detection trained utilized the offline training methods such as Gradient Descent Backpropagation (GDBP), Levenberg-Marquardt (LM), and Bayesian Regularization (BR). The best method is used to build the Graphical User Interface (GUI). The modelling of 14 buses power plant, network training, and GUI used the MATLAB software.
Databáze: OpenAIRE