A deep LSTM-based constitutive model for describing the impact characteristics of concrete–granite composites with different roughness interfaces
Huan Gao, Yue Zhai, Tienan Wang · 2024
Read A deep LSTM-based constitutive model for describing the impact characteristics of concrete–granite composites with different roughness interfaces by Huan Gao, Yue Zhai, Tienan Wang (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11589125.txt.
Description
Huan Gao, Yue Zhai, and Tienan Wang model how concrete and granite bonded together behave under impact, where the roughness of the joint varies. Such layered structures appear in tunnel linings against rock. The team struck samples with a split Hopkinson pressure bar and tested 144 data sets. Rougher joints raised the pair's strength and changed how strain rate and confinement shaped the response.
The authors then trained a long short-term memory network to predict the stress-strain curves. It outperformed a classic back-propagation network and a random forest on accuracy and on peak stress prediction. The forest was worse at capturing the material's springy, flowing character. Microscope views of failure patterns were matched against the curves to explain the link between small-scale damage and bulk behavior. The authors offer the network as a design tool for impact-resistant rock engineering.
Catalog record
| CREATOR | Huan Gao, Yue Zhai, Tienan Wang |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |