Gas Turbine Fault Detection and Isolation Using Adaptive Neurofuzzy Inference System (ANFIS)


Article Preview

This paper is focused on the application of Adaptive Nuerofuzzy Inference system (ANFIS) techniques in the model-based Fault Detection and Isolation (FDI). The objective of this study has been to create an online system for condition monitoring and diagnosis of specific faults for a Gas Turbine (GT) power plant. In order to study FDI and condition monitoring, accurate model of GT is needed. In this paper, the nonlinear Rowen's model is developed in Matlab/Simulink software to simulate the GT system behavior. Then, regarding the gain of artificial intelligence systems in FDI, the neurofuzzy inference system with capability of reliable learning and data approximating, is employed in developing the proposed FDI algorithm. In this paper, three types of faults have been considered, fault in the fuel flow rate, fault in the performance of turbine which affects the turbine exit gas temperature, and fault in the turbine which affects the turbine output torque. The results illustrate the effectiveness of the method in detecting and isolating the specified faults. Regarding the quality and the accuracy of the proposed algorithm, the method is introduced as the remarkable FDI methods of the stationary GT systems possibly extending to other similar applications.



Edited by:

Dashnor Hoxha, Francisco E. Rivera and Ian McAndrew




B. Shahriari et al., "Gas Turbine Fault Detection and Isolation Using Adaptive Neurofuzzy Inference System (ANFIS)", Advanced Materials Research, Vol. 1016, pp. 721-725, 2014

Online since:

August 2014




[1] S. Simani and C. Fantuzzi, Dynamic System Identification and Model-based Fault Diagnosis of an Industrial Gas Turbine Prototype, Mechatronics, Vol. 16, 341-363 (2006).

[2] R. Isermann and P. Balle, Trends in the application of Model-based Fault Detection and Diagnosis of Technical Processes, Control Engineering Practice, Vol. 5, 709-719 (1997).


[3] W. I. Rowen, Simplified Mathematical Representations of Heavy Duty Gas Turbines, ASME J. Eng. Power, Vol. 105, 865-869 (1983).

[4] M. Brown and C. Harris, Neurouzzy Adaptive Modelling and Control, Prentice-Hall, New York (1994).

[5] J. Chen and R. Patton, Robust Model-based Fault Diagnosis for Dynamic Systems, Kluwer Academic Publishers (1999).