The wind energy market is growing rapidly and the environmental consciousness even more. Wind turbine technology plays a significant role towards this perspective. Nowadays there is a need for more cost-effective and reliable operation of wind turbines. This can be achieved by improving the operation monitoring of the wind turbine especially by using the process signals for creating different kinds of health monitoring systems. This would help service to do predictive maintenance and limit unscheduled service time. One of the most important subsystems in wind turbines is pitch system, which controls the blade angles according to the operation strategy.
The aim of this research is to develop an online fault detection and identification system of hydraulic pitch system of wind turbines and analysis of the common failures, both tribological and hydraulics related, which appear at this system. The project consists of two parts. The first part will focus on implementing advanced signal processing techniques including machine learning and other artificial intelligence techniques in order to detect and predict failures in the pitch system. The second part include the physics based (or hydrid) simulations of failures in order to investigate the root causes of main failure types and consequently this knowledge will provide support for more accurate decisions and actions related to operation of wind turbines.