13 April 2012 Damage detection in carbon composite material typical of wind turbine blades using auto-associative neural networks
Author Affiliations +
The structure of a wind turbine blade plays a vital role in the mechanical and structural operation of the turbine. As new generations of offshore wind turbines are trying to achieve a leading role in the energy market, key challenges such as a reliable Structural Health Monitoring (SHM) of the blades is significant for the economic and structural efficiency of the wind energy. Fault diagnosis of wind turbine blades is a "grand challenge" due to their composite nature, weight and length. The damage detection procedure involves additional difficulties focused on aerodynamic loads, environmental conditions and gravitational loads. It will be shown that vibration dynamic response data combined with AANNs is a robust and powerful tool, offering on-line and real time damage prediction. In this study the features used for SHM are Frequency Response Functions (FRFs) acquired via experimental methods based on an LMS system by which identification of mode shapes and natural frequencies is accomplished. The methods used are statistical outlier analysis which allows a diagnosis of deviation from normality and an Auto-Associative Neural Network (AANN). Both of these techniques are trained by adopting the FRF data for normal and damage condition. The AANN is a method which has not yet been widely used in the condition monitoring of composite materials of blades. This paper is trying to introduce a new scheme for damage detection, localisation and severity assessment by adopting simple measurements such as FRFs and exploiting multilayer neural networks and outlier novelty detection.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
N. Dervilis, N. Dervilis, R. J. Barthorpe, R. J. Barthorpe, I. Antoniadou, I. Antoniadou, W. J. Staszewski, W. J. Staszewski, K. Worden, K. Worden, "Damage detection in carbon composite material typical of wind turbine blades using auto-associative neural networks", Proc. SPIE 8348, Health Monitoring of Structural and Biological Systems 2012, 834806 (13 April 2012); doi: 10.1117/12.914710; https://doi.org/10.1117/12.914710

Back to Top