A new wind turbine fault diagnosis method based on the local mean decomposition

This paper proposed a novel wind turbine fault diagnosis method based on the local mean decomposition (LMD) technology. Wind energy is a renewable power source that produces no atmospheric pollution. The condition monitoring and fault diagnosis in wind turbine system are important in avoiding serious damage. Vibration analysis is a normal and useful technology in wind turbine condition monitoring and fault diagnosis. However, the relatively slow speed of the wind turbine components set a limitation in early fault diagnosis using vibration monitoring method. The traditional time-frequency analysis techniques have some drawbacks which make them not suitable for the nonlinear, non-Gaussian signal analysis. LMD is a new iterative approach to demodulate amplitude and frequency modulated signals, which is suitable for obtaining instantaneous frequencies in wind turbine condition monitoring and fault diagnosis. The experiment analysis of the wind turbine vibration signal proves the validity and availability of the new method.

► A novel wind turbine fault diagnosis method based on the local mean decomposition (LMD) technology is proposed.
► Wind turbine vibration signal have nonlinear, non-Gaussian characteristics.
► LMD is a new iterative approach to demodulating amplitude and frequency modulated signals.
► LMD is suitable to get the instantaneous frequency in wind turbine vibration condition monitoring and fault diagnosis.
► Experimental analysis proved the feasibility and availability of this new method.