Statistical fault diagnosis of wind turbine drivetrain applied to a 5MW floating wind turbine

Abstract

Deployment of larger scale wind turbine systems, particularly offshore wind turbine, requires more organized operation and maintenance strategies to make it as competitive as the classical electric power stations. It is important to ensure systems are safe, profitable and cost-effective. In this regards, the ability to detect, isolate, estimate faults play an important role. One of the critical wind turbine components is the gearbox. Failures in the gearbox are costly both due to the cost of the gearbox itself, but also due to high repair downtime. In order to detect faults as fast as possible to prevent them to develop into failure, statistical change detection is used. In this paper, Cumulative Sum method (CUSUM) is used to diagnose fault in downwind main bearing in a high fidelity gearbox model of a 5-MW spar-type wind turbine. Residuals are found to be non-Gaussian following a t-distribution with multivariable characteristic parameters. Results show CUSUM method could detect change and estimate change time very agile with desired false alarm and detection probabilities