Advanced cyclostationary-based analysis for condition monitoring of complex systems

Wind energy experiences a significant growth during the last decades but the industry is still challenged by premature turbine component failures, which are quite expensive due to the increase of turbines size. The core of wind turbine drivetrains is a planetary gearbox and its rolling element bearings are often responsible for machinery breakdowns. The failure signs of an early bearing damage are usually weak compared to the gear excitation and are hardly detected. As a result there is a special need for advanced signal processing tools which can detect accurately bearing faults. Cyclic Spectral Coherence (CSC) appears to be a strong diagnostic tool but its interpretation is complicated for a non-expert. In this paper a novel CSC based methodology is proposed in order to extract an Improved Envelope Spectrum exploiting a specific domain of the CSC map optimally selected by a proposed criterion. The methodology is tested and validated on a wind turbine gearbox benchmarking dataset provided by the National Renewable Energy Laboratory (NREL), USA.