The identification of particular types of damage in wind turbine blades using acoustic emission (AE) techniques is a significant emerging field. In this work, a 45.7-m turbine blade was subjected to flap-wise fatigue loading for 21 days, during which AE was measured by internally mounted piezoelectric sensors. This paper focuses on using unsupervised pattern recognition methods to characterize different AE activities corresponding to different fracture mechanisms. A sequential feature selection method based on a k-means clustering algorithm is used to achieve a fine classification accuracy. The visualization of clusters in peak frequency−frequency centroid features is used to correlate the clustering results with failure modes. The positions of these clusters in time domain features, average frequency−MARSE, and average frequency−peak amplitude are also presented in this paper (where MARSE represents the Measured Area under Rectified Signal Envelope). The results show that these parameters are representative for the classification of the failure modes.
Offshore installations are subject to perpetual fatigue loading and are usually very hard to inspect. Close visual inspection from the turret is usually too hazardous for divers and is not possible with remotely operated vehicles (ROVs) because of the limited access. Conventional nondestructive techniques (NDTs) have been used in the past to carry out inspections of mooring chains, floating production storage and offloading systems (FPSOs), and other platforms. Although these have been successful at detecting and assessing fatigue cracks, the hazardous nature of the operations calls for remote techniques that could be applied continuously to identify damage initiation and progress. The aim of the present work is to study the capabilities of acoustic emission (AE) as a monitoring tool to detect fatigue crack initiation and propagation in mooring chains. A 72-day large-scale experiment was designed for this purpose. A detailed analysis of the different AE signal time domain features was not conclusive, possibly due to the high level of noise. However, the frequency content of the AE signals offers a promising indication of fatigue crack growth.