Development of an artificial neural network processing technique for the analysis of damage evolution in pultruded composites with acoustic emission

Acoustic Emission (AE) is a promising technique for the damage detection and the real-time structural monitoring of composite lightweight structures; however data interpretation and discrimination among failure modes from AE data is difficult to be carried out without proper data processing techniques. In this paper, a neural-network based classification of AE signals from tensile tests of pultruded glass-fiber specimens is proposed. A self-organizing map is trained with AE data from one specimen; then the map is clustered with the k-means algorithm. The optimal number of clusters is chosen by a voting procedure that takes into account a number of quality indexes; then the clustered neural network is used to classify AE data from other specimen. Results have shown that the classifier built from a smooth specimen was able to correctly classify other specimens with the same and with a different material layup, and is capable of recognizing signals from notched specimens, thus providing interesting and encouraging indications in view of the application on real structures.