New 2-DOF PID Controller Tuning by Adaptive Neural Fuzzy Inference System for Gas Turbine Control System
Dong Hwa Kim* and Chang Kee Jung**
*Department of I&C, Taejon National University of Technology 16-1 San Duck myong-dong Yusung-gu Taejon city Seoul Korea, 305-320. Tel:+82-42-821-1170, Fax:+82-42-821-1164
**Korea Power Research Institute Tel: +82-42-865-5251
The purpose of introducing a combined cycle with gas turbines in power plants is to reduce loss of energy. Their main role lies in the utilization of waste heat that may be found in exhaust gases from the gas turbine or at some other points of the process to produce additional electricity. The efficiency of the plant exceeds 50%, while the traditional steam turbine plants is approximately 35% ∼ 40% or so. To date, the PID controller has been used to operate under such systems, but since PID controller gain manually has to be tuned by trial and error procedures, getting optimal PID gains is very difficult manually without control design experience. We studied acquiring transfer function from operating data on the Gun-san gas turbine in Korea and a new 2-DOF PID controller tuning by ANFIS is designed for the optimum control of the Guns-san gas turbine’s variables. Since the shape of a membership function in the ANFIS vary on the characteristics of plant, ANFIS-based control is effective for plants whose variables vary. Its results are compared to the conventional 2-DOF PID controller and represents satisfactory response. We expect this method will be used for another process because it is studied using actual operating data.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.