Enhanced Wind Turbine Main Drivetrain Gearbox and Bearing Monitoring and Diagnostics Via Information Fusion of Acoustic, Electrical, and Vibration Signatures

Main Drivetrain components are widely acknowledged as one of the most significant contributors to wind turbine downtime. This paper investigates the possibility of using acoustic signals to detect various wind turbine drivetrain defects, and proposes an enhanced wind turbine main drivetrain monitoring solution, where acoustic analysis is combined with electrical and vibration analysis via Gaussian model-based fusion algorithm. A 25hp wind turbine simulator is set up in the lab and is used to validate the proposed fusion algorithm. It is shown by experimental results that the proposed fusion-based monitoring solution significantly outperformed solutions using individual signals in detecting drivetrain gear and bearing defects at different load and speed operation conditions. This work turns out to be the first effort to fuse/combine acoustic, electrical and vibration signatures to monitor wind turbine main drivetrain anomalies.