Deep learning-based axial capacity prediction for cold-formed steel channel sections using Deep Belief Network

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21110%2F21%3A00351514" target="_blank" >RIV/68407700:21110/21:00351514 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1016/j.istruc.2021.05.096" target="_blank" >https://doi.org/10.1016/j.istruc.2021.05.096</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.istruc.2021.05.096" target="_blank" >10.1016/j.istruc.2021.05.096</a>

Result language
angličtina
Original language name
Deep learning-based axial capacity prediction for cold-formed steel channel sections using Deep Belief Network
Original language description
In this study, a deep learning-based axial capacity prediction for cold-formed steel channel sections is developed using Deep Belief Network (DBN). A total of 10,500 data points for training the DBN are generated from nonlinear elasto plastic finite element analysis, which incorporated both initial imperfections, as recommended by the Australian/New Zealand Standard (AS/NZS 4600:2018) and residual stresses as recommended by Moen et al. A comparison against experimental results found in the literature was conducted. It was found that the DBN was conservative by 9%, 6% and 8% for stub columns, intermediate columns, and slender columns, respectively. When compared against a typical shallow artificial neural network (Backpropagation Neural Network) and a typical machine learning model (Linear regression model based on PaddlePaddle), it was shown that DBN performed around 2% better than both with the same training data. When the same comparison was made for both the Effective Width Method and the Direct Strength Method, it was found that they were conservative by 15%, 13%, and 15%, respectively. Based on the DBN output data, new and improved design equations for AS/NZS 4600:2018 were proposed.
Czech name
—
Czech description
—

Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
20102 - Construction engineering, Municipal and structural engineering

Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)