Gas turbine Control using Neural-Network 2-DOF PID Controller

Since a gas turbine is made use of generating electricity for peak time, it is a very important to operate a peak time load with safety. The main components of a gas turbine are the compressor, the combustion chamber and the turbine. So, there also must be modeled a component of gas turbines for the control with safety but it is not easy. In this paper we acquire a transfer function based on the operations data of Gun-san gas turbine and study to apply Neural-Network 2-DOF PID controler to control loop of gas turbine to reduce phenomena caused by integral and derivative actions through simulation. We obtained satisfactory results to disturbances of subcontrol loop such as, fuel flow, air flow, turbine extraction temperature.