Simulation studies with a continuously online trained artificial neural network controller for a micro-turbogenerator

This paper reports on the simulation studies carried out using MATLAB/SIMULINK and the practical implementation of a continuously online trained (COT) artificial neural network (ANN) controller to identify the continuous changing complex nonlinear dynamics of the power system, and another COT ANN to control a micro-turbogenerator which consists of a turbine simulator and a micro-alternator connected to an infinite bus through a short transmission line in a laboratory environment. This neural network controller augments/replaces the traditional automatic voltage regulator (AVR) and the turbine governor of the generator. Simulation and practical results are presented to show that this COT ANN identifier/controller has the potential to allow turbogenerators to operate more closely to their steady state stability limits