Imperial College London
Portrait Picture

DrNanLi

Faculty of Engineering, Dyson School of Design Engineering

Senior Lecturer
 
 
 
//

Contact

 

+44 (0)20 7594 8853n.li09 Website

 
 
//

Location

 

1M03Royal College of ScienceSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Xu:2021:10.1115/1.4052195,
author = {Xu, Q and Nie, Z and Xu, H and Zhou, H and Attar, HR and Li, N and Xie, F and Liu, X-J},
doi = {10.1115/1.4052195},
journal = {Journal of Applied Mechanics},
pages = {1--10},
title = {SuperMeshing: a new deep learning architecture for increasing the mesh density of physical fields in metal forming numerical simulation},
url = {http://dx.doi.org/10.1115/1.4052195},
volume = {89},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - In stress field analysis, the finite element method is a crucial approach, in which the mesh-density has a significant impact on the results. High mesh density usually contributes authentic to simulation results but costs more computing resources. To eliminate this drawback, we propose a data-driven mesh-density boost model named SuperMeshingNet that uses low mesh-density as inputs, to acquire high-density stress field instantaneously, shortening computing time and cost automatically. Moreover, the Res-UNet architecture and attention mechanism are utilized, enhancing the performance of SuperMeshingNet. Compared with the baseline that applied the linear interpolation method, SuperMeshingNet achieves a prominent reduction in the mean squared error (MSE) and mean absolute error (MAE) on the test data. The well-trained model can successfully show more excellent performance than the baseline models on the multiple scaled mesh-density, including 2X, 4X, and 8X. Enhanced by SuperMeshingNet with broaden scaling of mesh density and high precision output, FEA can be accelerated with seldom computational time and cost.
AU  - Xu,Q
AU  - Nie,Z
AU  - Xu,H
AU  - Zhou,H
AU  - Attar,HR
AU  - Li,N
AU  - Xie,F
AU  - Liu,X-J
DO  - 10.1115/1.4052195
EP  - 10
PY  - 2021///
SN  - 0021-8936
SP  - 1
TI  - SuperMeshing: a new deep learning architecture for increasing the mesh density of physical fields in metal forming numerical simulation
T2  - Journal of Applied Mechanics
UR  - http://dx.doi.org/10.1115/1.4052195
UR  - https://asmedigitalcollection.asme.org/appliedmechanics/article/doi/10.1115/1.4052195/1115883/SuperMeshing-A-New-Deep-Learning-Architecture-for
UR  - http://hdl.handle.net/10044/1/91416
VL  - 89
ER  -
Download