PZT-induced Lamb waves and pattern recognitions for on-line health monitoring of jointed steel plates

This paper presents a non-destructive evaluation (NDE) technique for detecting damages on a jointed steel plate on the basis of the time of flight and wavelet coefficient, obtained from wavelet transforms of Lamb wave signals. Probabilistic neural networks (PNNs) and support vector machines (SVMs), which are tools for pattern classification problems, were applied to the damage estimation. Two kinds of damages were artificially introduced by loosening bolts located in the path of the Lamb waves and those out of the path. The damage cases were used for the establishment of the optimal decision boundaries which divide each damage class's region from the intact class. In this study, the applicability of the PNNs and SVMs was investigated for the damages in and out of the Lamb wave path. It has been found that the present methods are very efficient in detecting the damages simulated by loose bolts on the jointed steel plate.