A data-driven approach for fault diagnosis in gearbox of wind energy conversion system

With a fast growing of wind power installed capacity, an efficient monitoring system for wind energy conversion system (WEC) is required to ensure operational reliability, high availability of energy production and at the same time reduce operating and maintenance costs. In this paper, an efficient, scaleable data-driven on-line WEC monitoring method is introduced, which consists of three parts: 1) off-line training process 2) on-line monitoring phase 3) on-line diagnosis phase. The performance and effectiveness of this method for the detection of process abnormalities are demonstrated using the data obtained from different wind turbines in a wind farm.