Analytical Prediction of Steel Grid-Shell Stability and Dynamic Behaviors Using Neural Networks - Part 1
Résumé
Artificial Intelligence is a cutting-edge technology expanding very quickly into every industry. It has made its way into structural engineering and it has shown its benefits in predicting structural performance as well as saving modelling and experimenting time. This paper is the first one (out of three) of a broader research where artificial intelligence was applied to the stability and dynamic analyzes of steel grid-shells. In that study, three Artificial Neural Networks (ANN) with 8 inputs were independently designed for the prediction of a single target variable, namely: (i) the critical buckling factor for uniform loading (i.e. over the entire roof), (ii) the critical buckling factor for uniform loading over half of the roof, and (iii) the fundamental frequency of the structure. This paper addresses target variable (i). The ANN simulations were based on 1098-point datasets obtained via thorough finite element analyzes.
The proposed ANN for the prediction of the critical buckling factor in steel grid-shells under uniform loading yields mean and maximum errors of 1.1% and 16.3%, respectively, for all 1098 data points. Only in 10.6% of those examples (points), the prediction error exceeds 3%.
Domaines
Intelligence artificielle [cs.AI] Ingénierie, finance et science [cs.CE] Vibrations [physics.class-ph] Apprentissage [cs.LG] Ingénierie assistée par ordinateur Réseau de neurones [cs.NE] Mécanique [physics.med-ph] Génie civil Structures Génie mécanique [physics.class-ph] Mécanique des matériaux [physics.class-ph] Matériaux et structures en mécanique [physics.class-ph] Mécanique des structures [physics.class-ph]
Fichier principal
Abambres and Cabello 2020 (final).pdf (1.09 Mo)
Télécharger le fichier
Bug sources and solutions + Final note.pdf (122.25 Ko)
Télécharger le fichier
Software Bugs Found on March 2021.pdf (170.33 Ko)
Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)