Back to Search
Start Over
Machine learning prediction model for the axial strength of longitudinal branch plate-to-CHS T-connections.
- Source :
- Ain Shams Engineering Journal; Dec2023, Vol. 14 Issue 12, pN.PAG-N.PAG, 1p
- Publication Year :
- 2023
-
Abstract
- Circular hollow sections (CHS) are widely used in construction, particularly in space structures. This paper aims at investigating the feasibility of employing a machine leaning approach to predict the axial strength of longitudinal branch plate-to-CHS connections subjected to branch loadings. Using nonlinear finite element analysis, numerical models are developed for the connections subjected to tensile or compressive branch loading. The difference between the load–displacement responses for the connections under compressive and under tensile loading is established. Furthermore, the influence of various geometric and material parameters on the strength is investigated in depth. Using the results, two different strength models for the prediction of both tensile and compressive strength of longitudinal branch plate-to-CHS T-connections are developed. One prediction model is attained using traditional nonlinear regression analysis, and the other model is attained through symbolic regression. Finally, theoretical predictions are compared with numerical results, and strengths predicted with current design methodologies. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 20904479
- Volume :
- 14
- Issue :
- 12
- Database :
- Supplemental Index
- Journal :
- Ain Shams Engineering Journal
- Publication Type :
- Academic Journal
- Accession number :
- 174319294
- Full Text :
- https://doi.org/10.1016/j.asej.2023.102557