|
|
Publications
Lima, J.P.S., Evangelista Jr., F. and Guedes Soares, C. (2023), Bi-fidelity Kriging model for reliability analysis of the ultimate strength of stiffened panels, Marine Structures, Vol. 91, 103464
The present paper proposes a two-stage Bi-Fidelity Deep Neural Network surrogate model to quantify the uncertainty of a structural analysis using low fidelity data samples added to the model to predict high fidelity values. An assessment of the Multi-Fidelity Model efficiency for structural reliability problems that demand high computational burden such as nonlinear Finite Element Analysis structural models is carried out. The efficiency assessment is performed through a comparison of the probability of failure predictions accuracy based on the Monte Carlo and First-order Reliability Method using the Multi-Fidelity Model surrogate for the performance function. The proposed method is compared with a Multi-fidelity Co-Kriging method through an engineering case considering Bi-fidelity Finite Elements using a coarse and fine mesh to create the multi-fidelity scenario. The results show that the proposed Multi-fidelity Method is a good strategy because it can provide an accurate probability of failure estimation with a less computational cost and when compared with the Co-Kriging method, the proposed Model reduced the time consumption by up to 65%.
If you did not manage to obtain a copy of this paper: Request a copy of this article
For information about all CENTEC publications you can download: Download the Complete List of CENTEC Publications
|