Control of Heavy-duty Gas Turbine Plants for Parallel Operation Using Soft Computing Techniques

Abstract

Gas turbine generators, normally used in isolated operation, require an effective control and design for their parallel operation. Otherwise, the load variations and set-point variations may cause severe stability problems. Soft computing techniques, such as genetic algorithms, artificial neural networks, and fuzzy logic, have been utilized for developing a controller for a gas turbine plant. The proportional-integral-derivative controller is used to control the gas turbine plant because of its versatility, high reliability, and ease of operation. For better performance, the gains of the proportional-integral-derivative controller have been tuned using the Ziegler–Nichols method and genetic algorithm. The artificial neural network and fuzzy controllers are developed, and the performance is compared with the conventional proportional-integral-derivative controller. The results show that the optimal time domain performance of the system can be achieved with the fuzzy logic controller. The fuzzy logic controller removes the steady-state error in less time with no overshoot and oscillation.

Keywords:

• gas turbine
• proportional-integral-derivative controller
• genetic algorithm
• neural network
• fuzzy logic