ACOUSTIC EMISSION & NDT SCIENTIFIC PUBLICATIONS

 

Unsupervised Classification of Acoustic Emission Sources from Aerial Man Lift Devices

 

Proceedings of 15th World Conference on NDT, Rome, Italy, 15-21 October, 2000

A. Anastasopoulos, D. Kouroussis, A. Tsimogiannis

 

Where complicated Acoustic Emission (AE) signatures are present, (e.g. in cases where high background noise exists, or in composite structures where several failure mechanisms have to be discriminated), conventional graphical and statistical analysis may not provide the necessary resources for source discrimination. In such cases, Unsupervised Pattern Recognition (UPR) techniques extend the AE userís capabilities in identifying the hidden structure and correlation of data categories in a multidimensional space. In this work, Unsupervised Pattern Recognition techniques are applied for the analysis and evaluation of AE data recorded during testing of five Insulated Aerial Man Lift devices.

Various types of AE sources are expected during testing of Aerial Man Lift Devises, arising from the fibreglass components, the metal parts of the arm, the high strength pins, the welds, as well as the hydraulic systems and the lift mechanisms. The use of pattern recognition analysis, as applied in the present work, aims to identify noise sources from the mechanisms used to manipulate the arm movements and to discriminate signals from various failure mechanisms arising from the different materials.

Results from different unsupervised classification schemes, applied either on the AE feature set, or to its principal component projection are presented. Discussion is focused on the validity of the resulting partitions by using numerical optimisation criteria and common Acoustic Emission practices such as cumulative plots and emissions during load hold.

The proposed methodology proved efficient for the discrimination of AE sources recorded during proof testing of Aerial Man Lift Devices and can be used as a basis for automating the evaluation of Acoustic Emission data from future tests of similar devices.