Application of neural networks to quantitative nondestructive evaluation

This paper concentrates on the quantitative analysis of reflection and transmission characteristics of structural waves in notched beams using neural networks. At one end of a rod a piezoelectric transducer excites a flexural guided wave, which propagates through the structure and is reflected from the notch as well as from the ends of the rod. At another point, a laser interferometer measures the resulting displacement versus time, which is recorded and serves as the digital fingerprint of the experiment. Our aim is to obtain quantitative information about the notch characteristics, i.e. its location and depth, on the basis of these digital recordings. This requires an inverse problem to be solved using neural networks. For the training of the network, synthetically produced wave patterns are used. The results of the corresponding wave experiment simulations compare well with experimental data. For fixed location, the calculated wave patterns could be quantitatively analysed to yield the depth of the notch if it is greater than a twentieth of the diameter. Another network could be trained for the localization with an accuracy of 2 cm for 93% of the training patterns. On the basis of these results a strategy is formulated on how neural networks could be trained to evaluate quantitatively both of the notch characteristics.