caa a22 4500 606199608 CHVBK 20210128100939.0 cr unu---uuuuu 210128e20151001xx s 000 0 eng 10.1007/s11045-015-0342-7 doi (NATIONALLICENCE)springer-10.1007/s11045-015-0342-7 A 2D Hopfield Neural Network approach to mechanical beam damage detection [Elektronische Daten] [Juliana Almeida, Hugo Alonso, Pedro Ribeiro, Paula Rocha] 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. Springer Science+Business Media New York, 2015 2D Hopfield Neural Network nationallicence Euler-Bernoulli beam model nationallicence Timoshenko beam model nationallicence Damage detection nationallicence Almeida Juliana Research Center for Systems and Technologies (SYSTEC), Faculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, 4200-465, Porto, Portugal aut Alonso Hugo Universidade Lusófona do Porto, Rua Augusto Rosa, 4000-098, Porto, Portugal aut Ribeiro Pedro DEMec/INEGI, Faculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, 4200-465, Porto, Portugal aut Rocha Paula Research Center for Systems and Technologies (SYSTEC), Faculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, 4200-465, Porto, Portugal aut Multidimensional Systems and Signal Processing Springer US; http://www.springer-ny.com 26/4(2015-10-01), 1081-1095 0923-6082 26:4<1081 2015 26 11045 https://doi.org/10.1007/s11045-015-0342-7 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s11045-015-0342-7 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Almeida Juliana Research Center for Systems and Technologies (SYSTEC), Faculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, 4200-465, Porto, Portugal aut NATIONALLICENCE 700 1- Alonso Hugo Universidade Lusófona do Porto, Rua Augusto Rosa, 4000-098, Porto, Portugal aut NATIONALLICENCE 700 1- Ribeiro Pedro DEMec/INEGI, Faculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, 4200-465, Porto, Portugal aut NATIONALLICENCE 700 1- Rocha Paula Research Center for Systems and Technologies (SYSTEC), Faculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, 4200-465, Porto, Portugal aut NATIONALLICENCE 773 0- Multidimensional Systems and Signal Processing Springer US; http://www.springer-ny.com 26/4(2015-10-01), 1081-1095 0923-6082 26:4<1081 2015 26 11045