Damage detection based on wavelet transform and artificial intelligence for underwater metallic structures

Health monitoring is investigated for immersed structures. The environment of these structures makes their monitoring and diagnosis very difficult. In this paper, the major challenge is to make easy and efficient the monitoring of this kind of structures. The proposed detection method is based on non contact measurements with acoustic scattering. It uses artificial intelligence, with gaussian neural networks and signal processing with wavelets transformation and principal component analysis. The method is validated with experimental measurements collected from immersed plates including surface cracks with different orientations. Such plates represent a simplified model of underwater turbine blades.