Author:
Baensch Franziska,Sause Markus G.R.,Brunner Andreas J.,Niemz Peter
Abstract
Abstract
Tensile tests on miniature spruce specimens have been performed by means of acoustic emission (AE) analysis. Stress was applied perpendicular (radial direction) and parallel to the grain. Nine features were selected from the AE frequency spectra. The signals were classified by means of an unsupervised pattern recognition approach, and natural classes of AE signals were identified based on the selected features. The algorithm calculates the numerically best partition based on subset combinations of the features provided for the analysis and leads to the most significant partition including the respective feature combination and the most probable number of clusters. For both specimen types investigated, the pattern recognition technique indicates two AE signal clusters. Cluster A comprises AE signals with a relatively high share of low-frequency components, and the opposite is true for cluster B. It is hypothesized that the signature of rapid and slow crack growths might be the origin for this cluster formation.
Reference72 articles.
1. frequency spectra of acoustic emission;Stephens;Acoust Soc Am,1971
2. Sause Quantification of failure mechanisms in mode loading of fiber reinforced plastics utilizing acoustic emission analysis;Müller;Sci Technol,2012
3. Frequency analysis of two types of simulated acoustic emissions;Pardee;Acoust Soc Am,1978
4. Effects of cell wall anatomy on the plastic and elastic behaviour of different wood species loaded perpendicular to grain;Müller;IAWA J,2003
5. cluster separation measure Pattern;Davies;IEEE Trans Anal Intell,1979
Cited by
22 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献