Gas-Turbine Power-Plant Neural-Network Models for Synthesis and Tuning of Control Systems

Abstract: This article discusses the possibility of using neural-network models of gas-turbine power plants for automatic tuning and synthesis of control systems. The considered neural-network models represent a gas-turbine plant and a synchronous generator as a single model of a gas-turbine power plant. The rationale for the architecture of an artificial neural network is given, which, after training, is capable of reproducing the operation of gas-turbine power plants with various configurations of electric-power systems. The results of the application of a neural-network model of a gas-turbine power plant for automatic tuning of the free-turbine speed-control loop are presented. The results of mathematical modeling confirming the effectiveness of the method are presented. © 2022, Allerton Press, Inc.