Wind turbine blades condition assessment based on vibration measurements and the level of an empirically decomposed feature

Vibration based monitoring techniques are well understood and widely adopted for monitoring the condition of rotating machinery. However, in the case of wind turbines the measured vibration is complex due to the high number of vibration sources and modulation phenomenon. Therefore, extracting condition related information of a specific element e.g. blade condition is very difficult. In the work presented in this paper wind turbine vibration sources are outlined and then a three bladed wind turbine vibration was simulated by building its model in the ANSYS finite element program. Dynamic analysis was performed and the fundamental vibration characteristics were extracted under two healthy blades and one blade with one of four cracks introduced. The cracks were of length (10 mm, 20 mm, 30 mm and 40 mm), all had a consistent 3 mm width and 2 mm depth. The tests were carried out for three rotation speeds; 150, 250 and 360 r/min. The effects of the seeded faults were revealed by using a novel approach called empirically decomposed feature intensity level (EDFIL). The developed EDFIL algorithm is based on decomposing the measured vibration into its fundamental components and then determines the shaft rotational speed amplitude. A real model of the simulated wind turbine was constructed and the simulation outcomes were compared with real-time vibration measurements. The cracks were seeded sequentially in one of the blades and their presence and severity were determined by decomposing the measured vibration signal into its main components and evaluating the intensity level at the main shaft rotating speed. The application of the developed monitoring approach on empirical vibration data gave reasonable results and was in good agreement with the simulation predicted levels. (C) 2012 Elsevier Ltd. All rights reserved.