No Detail Found!

Multilayer perceptron network application in electrical alternator excitation system.

Author(s)
Aslam Pervez Memon Department of Electrical Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan
Abdul Rashid Shaikh Department of Electrical Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan
Mukhtiar Ali Unar Department of Electronic, Telecommunication & Biomedical Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan
Abstract
ANN (Artificial Neural Network) based controller for the excitation system of electrical alternator (synchronous generator) is presented in this paper. Feedforward neural network architecture of ANNs has enjoyed many successful applications in the field of power systems and control. These networks include two major categories: MLP (Multilayer Perceptrons) and RBF (Radial Basis Function) networks. This paper explores the suitability and applicability of MLP architecture of ANNs in the excitation system of electrical alternator or mostly called synchronous generator. Computer based simulation of a synchronous generator subject to different operating conditions is performed to demonstrate the effectiveness of the proposed excitation system. The performance of trained neural network is compared with PID (Proportional Integral Derivative) excitation system of synchronous generator and it is found that the MLP architecture of ANNs can show not only a good scope of application but they are also suitable for various operating conditions of synchronous generator.
Publication Details
Page(s) 95-104
DOI DOI not available
Published Journal: Mehran University Research Journal of Engineering and Technology, Volume: 24, Issue: 2, Year: 2005

Request the full text from PASTIC

0

Citations

0

Downloads

43

Views