In this section
@inproceedings{Attar:2021:1/012079,
author = {Attar, HR and Zhou, H and Li, N},
doi = {1/012079},
pages = {1--11},
publisher = {IOP Publishing},
title = {Deformation and thinning field prediction for HFQ® formed panel components using convolutional neural networks},
url = {http://dx.doi.org/10.1088/1757-899x/1157/1/012079},
year = {2021}
}
TY - CPAPER
AB - The novel Hot Forming and cold die Quenching (HFQ®) process can provide cost-effective and complex deep drawn solutions through high strength aluminium alloys. However, the unfamiliarity of the new process prevents its widescale adoption in industrial settings, while accurate Finite Element (FE) simulations using the most advanced material models take place late in design processes and require forming process expertise. Machine learning technologies have recently been proven successful in learning complex system behaviour from representative examples and have the potential to be used as design support tools for new forming technologies such as HFQ®. This study, for the first time, presents a novel application of a Convolutional Neural Network (CNN) based surrogate to predict the deformation and thinning fields for variable deep drawn geometries formed using HFQ® technology. A dataset based on deep drawn geometries and corresponding FE results is generated and used to train the model. The results show that near indistinguishable full field predictions in real time are obtained from the surrogate when compared with HFQ® simulations. This technique can be adopted in industrial settings to aid in both concept and detailed component design for complex-shaped panel components formed under HFQ® conditions, without underlying knowledge of the forming process.
AU - Attar,HR
AU - Zhou,H
AU - Li,N
DO - 1/012079
EP - 11
PB - IOP Publishing
PY - 2021///
SN - 1757-8981
SP - 1
TI - Deformation and thinning field prediction for HFQ® formed panel components using convolutional neural networks
UR - http://dx.doi.org/10.1088/1757-899x/1157/1/012079
UR - https://iopscience.iop.org/issue/1757-899X/1157/1
UR - http://hdl.handle.net/10044/1/89991
ER -
Dyson School of Design Engineering
Imperial College London
25 Exhibition Road
South Kensington
London
SW7 2DB
design.engineering@imperial.ac.uk
Tel: +44 (0) 20 7594 8888