A 2D Hopfield Neural Network approach to mechanical beam damage detection

• Autor(a) principal: Almeida, Juliana
• Data de Publicação: 2015
• Outros Autores: Alonso, Hugo, Ribeiro, Pedro, Rocha, Paula
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10773/14915
• topic: 2D Hopfield Neural Network; Euler-Bernoulli beam model; Timoshenko beam model; Damage detection

The aim of this paper is to present a method based on a 2D Hopfield Neural Network for online damage detection in beams subjected to external forces. The underlying idea of the method is that a significant change in the beam model parameters can be taken as a sign of damage occurrence in the structural system. In this way, damage detection can be associated to an identification problem. More concretely, a 2D Hopfield Neural Network uses information about the way the beam vibrates and the external forces that are applied to it to obtain time-evolving estimates of the beam parameters at the different beam points. The neural network organizes its input information based on the Euler-Bernoulli model for beam vibrations. Its performance is tested with vibration data generated by means of a different model, namely Timonshenko's, in order to produce more realistic simulation conditions.