Neural Networks in Crashworthiness Analysis of Thin-Walled Profile with Foam Filling
Więcej
Ukryj
1
Faculty of Mechanical Engineering, Lublin University of Technology, Lublin, Poland
Data publikacji: 01-09-2020
Autor do korespondencji
Michał Karol Rogala
Faculty of Mechanical Engineering, Lublin University of Technology, Lublin, Poland
Adv. Sci. Technol. Res. J. 2020; 14(3):93-99
SŁOWA KLUCZOWE
DZIEDZINY
STRESZCZENIE
This article presents numerical tests of thin-walled compressed columns with square cross-section. Crush efficiency indicators were determined using finite element method (Abaqus) and neural networks of MLP. The models had a constant circular trigger, with a diameter of 32mm. During dynamic analysis the samples were loaded with 1700J. The numerical models were filled with aluminum foam from 40mm to 180mm every 20mm. The study presents conclusions for thin-walled models with crushable foam.