Neurocontrol of Turbogenerators with Derivative Adaptive Critics

Abstract

This paper presents the design of a neuro-controller for a turbogenerator that augments/replaces the traditional Automatic Voltage Regulator (AVR) and the turbine governor using a novel technique based on the Adaptive Critic Designs (ACDs) with emphasis on the Dual Heuristic Programming (DHP). Simulation results are presented to show that the neuro-controller derived with the DHP approach is robust and its performance is better when compared with that derived with Heuristic Dynamic Programming (HDP) approach and other neural network techniques, especially when system conditions and configuration changes.