Using a wavelet network for reconstruction of fatigue crack depth profile from AC field measurement signals

This paper presents a wavelet-network-based technique for reconstructing the crack depth profile of a fatigue crack in a metal from the output signal of an alternating current field measurement (ACFM) probe. The main feature of this technique is that it requires only the ACFM probe output signals along the crack opening. The database for training the network is established by developing a random crack-depth generator, using a fast pseudo-analytic ACFM probe output simulator. The validity of the proposed technique is demonstrated by comparing the actual and reconstructed depth profiles of several simulated and machine-made cracks with no predetermined geometries.