Extreme learning machine-based non-linear observer for fault detection and isolation of wind turbine

ABSTRACT

This paper presents a robust fault detection and isolation (FDI) scheme for a variable speed wind turbine. The proposed scheme (extreme learning machine–state-dependent differential Riccati equation (ELM-SDDRE)) is an observer model-based approach, especially, a non-linear observer using SDDRE based on an improved model of the wind turbine by using the ELM. The standard SDDRE can be used for small model uncertainties. However, when the uncertainties are large, the SDDRE cannot detect and isolate the faults. The main objective of the ELM is the prediction of unknown nominal model dynamics to construct a new improved nominal model used by the observer for FDI. This makes the effect of uncertainties weak and consequently allows better faults detection. The faults considered in this paper are sensor faults in the rotating speeds of the rotor and generator outputs. The effectiveness of the proposed approach is illustrated through simulation.

KEYWORDS:

• Extreme learning machine
• fault detection and isolation
• non-linear observer
• state-dependent differential Riccati equation
• wind turbine

Additional information

Notes on contributors

Ayoub El Bakri

Ayoub El Bakri is currently a Ph.D. student in the faculty of sciences Dhar El Mehraz, at Sidi Mohamed Ben Abdellah University. His research focuses on fault detection and isolation in nonlinear systems with application to the wind turbine, machine learning and robust control of nonlinear systems.

Miloud Koumir

Miloud Koumir is a Professor of Physics at the Ecole Normale Superieure, Sidi Mohamed Ben Abdellah University, Fez, Morocco.  He received his M.Sc. degree from the Faculty of Sciences Dhar El Mehraz, at Sidi Mohamed Ben Abdellah University in 2013. He is currently pursuing the Ph.D. degree at Sidi Mohammed Ben Abdellah University. The main research interests include nonlinear systems, intelligent control systems with application to the wind turbine, machine learning, energy conversion, and artificial intelligence.

Ismail Boumhidi

Ismail Boumhidi is a Professor of electronics at the Faculty of Sciences, Fez Morocco. He received from Sidi Mohamed Ben  Abdellah University, Faculty of sciences his "Doctorat de 3ième cycle" degree in 1994 and "Doctorat d'Etat"  degree in 1999. His research areas include adaptive robust control, multivariable nonlinear systems, and fuzzy logic control with applications.