Neural Network for Crack-Depth Determination from Ultrasonic Backscattering Data

A neural network approach has been developed to determine the depth of a surface breaking crack in a steel plate from ultrasonic backscattering data. The network is trained by the use of a feedforward three-layered network together with a back-propagation algorithm for error corrections[1,2]. The signal used for crack insonification is a mode converted 45° transverse wave. The plate containing a surface breaking crack is immersed in water and the crack is insonified from the opposite uncracked side of the plate. A numerical analysis of the backscattered field is carried out based on elastic wave theory, by the use of the boundary element method. The numerical data are calibrated by comparison with experimental data. The computed backscattered field provides synthetic data for the training of the network. The training data have been calculated for cracks with specified increments of the crack depth. The performance of the network has been tested on experimental data for cracks of different depths than used for network training.