Surrogate models to unlock the optimal design of stiffened panels accounting for ultimate strength reduction due to welding residual stress
Andrea Coraddu (TU Delft - Ship Design, Production and Operations)
Luca Oneto (University of Genova)
Fu shen Li (University of Strathclyde)
Miltiadis Kalikatzarakis (University of Strathclyde)
O. Karpenko (TU Delft - Steel & Composite Structures)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
In this paper, for the first time, a three-step approach for the optimal design of stiffened panels accounting for the ultimate limit state due to welding residual stress is developed. First, authors rely on state-of-the-art analytical approaches coupled with recently data-driven nonlinear finite element methods surrogates characterized by functional which are computationally expensive to build but computationally inexpensive to use. Then, surrogates are used within a design optimization loop to find new optimal designs since nonlinear finite element methods are too computationally demanding for this purpose. Finally, the new designs are reassessed with the original nonlinear finite element methods to verify that substituting them with their surrogates in the optimization loop actually leads to better designs. Results obtained optimizing a series of parameters of a commonly used stiffened panel geometry under different scenarios will support the authors’ novel approach.
help_outline