Vibration-based Damage Identification in Sandwich Beams using Artificial Neural Networks


ŞAHİN M.

10th International Conference on Computational Structures Technology, Valencia, İspanya, 14 - 17 Eylül 2010, cilt.93 identifier

  • Cilt numarası: 93
  • Basıldığı Şehir: Valencia
  • Basıldığı Ülke: İspanya

Özet

This study investigates the effectiveness of the combination of global (natural frequency) and local (curvature mode shape) vibration characteristics of a glass fibre reinforced plastic sandwich beam-like structure when introduced to artificial neural networks for severity and location prediction of various damage with different extent at different locations. A finite element modelling and analysis tool is used to obtain the dynamic characteristics of both intact and damaged cantilever sandwich structures and the sensitivity analyses aiming at finding the necessary features are performed. Finally, predictions are made for the damage quantification and localisation via designed supervised feed-forward backpropagation artificial neural networks.