Buy article PDF
The purchased file will be sent to you
via email after the payment is completed.
US$ 35
|
Computers and Concrete Volume 34, Number 6, December 2024 , pages 791-804 DOI: https://doi.org/10.12989/cac.2024.34.6.791 |
|
|
|
Hardware accelerated nonlinear FEA of RC beams using the ML-based material model |
||
Hyunseung Chung and Hyo-Gyoung Kwak
|
||
| Abstract | ||
| This paper performs a materially nonlinear finite element analysis (FEA) of reinforced concrete (RC) beams with the adoption of a machine learning (ML) based material model. Among the ML-based material models that can compensate for the coarseness in the conventional constitutive material models induced by the limited amount of experimental data and have the flexibility for the supplementation of additional experimental data, the Gaussian process approach is considered to construct the material models of concrete and steel. Despite many benefits including accuracy and reliability, however, the ML-based material model requires a drastic increase in the computational cost and memory consumption. In addition, it is difficult to use in the nonlinear analysis of large complex RC structures composed of numerous members. To address this limitation, optimization, and computing strategies with ML-integrated FEA is designed in this paper. The hardware acceleration is based upon the constitution of a parallelized computing structure, and Python-based FEA process is developed to trace the nonlinear behavior of RC beams. Comparison with experimental data for two representative RC beams is performed to verify the efficiency and reliability of the introduced solution procedures. The obtained results from the developed program show that the introduced solution procedure adopting the hardware acceleration process with the use of the ML-based material models can be used in the nonlinear analysis of large structures composed of numerous RC members. | ||
| Key Words | ||
| Gaussian process; hardware acceleration; machine learning; nonlinear FEA | ||
| Address | ||
| Department of Civil and Environmental Engineering, Korean Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea | ||