International Journal of Electrical and Computer Engineering (IJECE) Vol. 3, No. 4, August 2013, pp. 561~567 ISSN: 2088-8708  561 Journal homepage: http://iaesjournal.com/online/index.php/IJECE An Optimal State Feedback Controller Based Neural Networks for Synchronous Generators Moath H. Al-Qatamin Electrical Engineering Department, King Khalid University, Saudi Arabia Article Info ABSTRACT Article history: Received Feb 12, 2013 Revised Jun 26, 2013 Accepted Jul 16, 2013 In this paper, an artificial neural network (ANN) is designed to optimize the matrix gain of state feedback controller. A linear mathematical model of a synchronous generator with excitation system is used as controlled system. The conventional methods that used to find the matrix gain need tedious calculations with compared to neural networks. The simulation proves that the proposed feedback controller based neural network optimization method has the better result in order to prove the dynamic performance of a single machine connected to infinite bus system(SMIB). The robustness of the proposed controller is tested by disturbance in excitation voltage. The results are compared with results of controller based on conventional methods. The potentials of the proposed technique are investigated using MATLAB software. Keyword: Synchronuos Generator Excitation Control Neural Networks Feedback Controller Copyright © 2013 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Moath H. Al-Qatamin Department of Electrical Engineering, King Khalid University, Saudi Arabia. P.O 394, Abha 61411 Email: malqtameen@kku.edu.sa 1. INTRODUCTION There are hundreds of generating units in an interconnected power system. These units transmit the power to loads by long transmission lines. When a power system subjected to small and sudden disturbances, low frequency oscillations will be generated. If these oscillations are not well damped, they will grow in amplitude and limit the power transmission capability of the network [1]. Synchronous generator excitation control system (SGECS) is one of the most important measures to enhance power system stability and to guarantee the quality of electrical power it provides. An additional control signal in generator excitation system is usually used to improve the stability of the system. Some closed-loop feedback control theories can be used to generate control signal in excitation system. In recent years, there is a trend that the new control theories are used in the SGECS with the development of the modern control and intelligent theories [2].Studies on state feedback controller of synchronous generators system have been reported well in the literature. Many attempts were made in last years regarding the design of state feedback controller for synchronous generators. In Ref [3], an adaptive design of an automatic voltage regulator (AVR) control scheme for synchronous generators was introduced in the presence of unknown variations of power system operating conditions; the AVR design is based on pole-assignment technique and the estimation is performed by kalman filter. The main difficulty in designing the controllers based pole-placement technique is the selection of closed-loop poles locations. The author in Ref [4] designed a digital Optimal AVR of synchronous generator using Linear Quadratic Regulator. In Ref [5], the authors designed the linear quadratic regulator (LQR) weighting matrices based on Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). For these techniques, all state variables of the system must be physically measurable. From a control point view; it is known that the dynamic stability enhancement depends on the type of the excitation controller that is used for the synchronous generation units. However, the design of these control devices is far from clarity due to the nonlinear and complex