Heavy duty gas turbine monitoring based on adaptive neuro-fuzzy inference system: speed and exhaust temperature control

Abstract

Gas turbines are currently a popular power generation technology in countries with access to natural gas resources. However they are very complex systems the operation of which at peak performance is challenging. This paper proposes the use of a hybrid approach based on an Adaptive Neuro-Fuzzy Inference System (ANFIS) for the control of the speed and the exhaust temperature of a gas turbine. The main aim is to maintain turbine operation at optimum performance. The results obtained, based on the use of the Rowen model, clearly show the effectiveness of the proposed hybrid speed/exhaust temperature control approach for the gas turbine.