Inverse optimal neural control with speed gradient for a power electric system with changes in loads

Author

Lastire, E.A. ; Alanis, Alma Y. ; Sanchez, Edgar N.

Author_Institution

CINVESTAV, Unidad Guadalajara, Jalisco, Mexico

fYear

2012

fDate

26-28 Sept. 2012

Firstpage

1

Lastpage

6

Abstract

In this paper an inverse optimal neural controller with speed gradient (SG) for discrete-time unknown nonlinear systems, in presence of external disturbances and parameter uncertainties is presented. It is based on a discrete-time recurrent high order neural network (RHONN) trained with an extended Kalman filter (EKF)-based algorithm. A reduced neural model for synchronous machine is proposed for the stabilization of nine bus system in the presence of a fault in a line of transmission with some variations in loads.

Keywords

Kalman filters; angular velocity control; discrete time systems; gradient methods; machine control; neurocontrollers; nonlinear control systems; optimal control; reduced order systems; stability; synchronous machines; uncertain systems; EKF; RHONN; SG; discrete-time recurrent high order neural network; discrete-time unknown nonlinear systems; extended Kalman filter-based algorithm; external disturbances; inverse optimal neural control; load changes; nine bus system stabilization; parameter uncertainties; power electric system; reduced neural model; speed gradient; synchronous machine; Equations; Kalman filters; Neural networks; Optimal control; Synchronous generators; Training; Extended Kalman filter; High-order neural network; Optimal control; Synchronous generators;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Engineering, Computing Science and Automatic Control (CCE), 2012 9th International Conference on

Conference_Location

Mexico City

Print_ISBN

978-1-4673-2170-9

Type

conf

DOI

10.1109/ICEEE.2012.6421116

Filename

6421116