Robust clustering of acoustic emission signals using the Kohonen network

Acoustic emission-based techniques are promising for nondestructive inspection of mechanical systems. For reliable automatic fault monitoring, it is important to identify the transient crack-related signals in the presence of strong timevarying noise and other interference. In this paper we propose the application of the Kohonen network for this purpose. The principal components of the short-time Fourier transforms of the data were applied to the input of the network. The clustering results confirm the capability of the Kohonen network for reliable source identification of acoustic emission signals, assuming enough care has been taken in implementing the training algorithm of the network.