Robust fault detection for wind turbines using reference model-based approach

Abstract

This paper presents a reference model-based approach for detection of different faults in a wind turbine. Stochastic uncertainty has been considered in the model of wind turbine. The fault detection scheme is so designed that the generated residual is robust against the uncertainty. For residual evaluation purpose, generalized likelihood ratio (GLR) test has been performed. Threshold is computed using the table of chi-square distribution with one degree of freedom. Occurrence of a fault is concluded whenever evaluated residual crosses the threshold. Using this approach an actuator and a sensor fault in the pitch system and a sensor fault in the drive train system are successfully detected. Results are compared with Combined Observer and Kalman Filter (COK) approach (Chen et al. 2011) used for wind turbine fault detection with this approach requiring less detection time thus providing a more useful solution to the wind industry.