A1 Journal article (refereed), original research

Estimation of stress concentration factor in butt and T-welded joints utilizing artificial neural network-based models


Open Access publication

Publication Details
Authors: Dabiri Mohammad, Ghafouri Mehran, Björk Timo
Publisher: Finnish Association for Structural Mechanics
Publication year: 2017
Language: English
Related Journal or Series Information: Rakenteiden Mekaniikka
Volume number: 50
Issue number: 3
Start page: 362
End page: 367
Number of pages: 6
ISSN: 0783-6104
eISSN: 1797-5301
JUFO-Level of this publication: 1
Open Access: Open Access publication

Abstract
In this study, the capability of artificial neural network-based models in estimation of stress concentration factor of welds in form of butt-welded joints (single-V and double-V) and T-welded joints (as-welded and TIG-dressed conditions) was investigated. The joints were analyzed under axial-tension and bending load cases. A large set of finite element models were used for each configuration in order to train, validate and test the corresponding networks. The estimations by the neural network- based models yielded the results with higher accuracy for all configurations compared to the available parametric equations. The proposed models also cover the joints with broader range of local weld parameters.

Last updated on 2018-19-10 at 07:55