Title :
Damage detection based on wavelet transform and artificial intelligence for underwater metallic structures
Author :
Yaya, Sidibe ; Dimitri, Lefebvre ; Fabrice, Druaux ; Gerard, Maze ; Fernand, Leon
Author_Institution :
Groupe de Rech. en Electrotech. et Autom. du Havre, Normandie Univ., Le Havre, France
Abstract :
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.
Keywords :
Gaussian processes; acoustic signal processing; acoustic wave scattering; artificial intelligence; blades; condition monitoring; failure analysis; fault diagnosis; hydraulic turbines; neural nets; plates (structures); principal component analysis; structural engineering computing; surface cracks; wavelet transforms; Gaussian neural networks; acoustic scattering; artificial intelligence; damage detection method; health monitoring; immersed plates; noncontact measurement; principal component analysis; signal processing; surface cracks; underwater metallic structures; underwater turbine blades; wavelet transformation; Continuous wavelet transforms; Dispersion; Equations; Feature extraction; Neural networks; Transducers; Damage detection; gaussian neural network; signal processing;
Conference_Titel :
Control Conference (ECC), 2014 European
Conference_Location :
Strasbourg
Print_ISBN :
978-3-9524269-1-3
DOI :
10.1109/ECC.2014.6862233
