@inproceedings{c167760e833444e485de1d34150a304b,
title = "Physics Informed Surrogate Model for Linear Elasticity",
abstract = "Simulation of linear elasticity problems is widely applied in mechanical and architectural engineering, and surrogate models driven by sample data have become an effective approach to perform fast simulation. However, due to the scarce and expensive data in engineering, traditional data-driven surrogate models suffer from low accuracy. This paper proposes a new Physics Informed Surrogate Model (PISM), with the objective to accelerate the numerical simulation of linear elasticity problems. The governing equations are incorporated into the training process of neural networks as effective supplement information to sample data, which improves the prediction accuracy of surrogate models in small data scenarios. A ResNet structure is introduced to further improve predicting performance of the model. Experimental results show that the prediction accuracy of PISM is significantly higher than that of pure data-driven surrogate models under small data conditions, and the solving speed reaches 8-9 times that of the finite element method.",
keywords = "Linear elasticity, Physics informed deep learning, Surrogate models",
author = "Jin Huang and Zhicheng Zhu and Jia Hao and Jiaqi Li and Hanqing Ouyang",
note = "Publisher Copyright: {\textcopyright} 2023 The authors and IOS Press.; 2nd International Conference on New Materials, Machinery, and Vehicle Engineering, NMMVE 2023 ; Conference date: 02-06-2023 Through 04-06-2023",
year = "2023",
month = sep,
day = "21",
doi = "10.3233/ATDE230121",
language = "English",
series = "Advances in Transdisciplinary Engineering",
publisher = "IOS Press BV",
pages = "35--47",
editor = "Jinyang Xu and Davim, \{J. Paulo\}",
booktitle = "New Materials, Machinery and Vehicle Engineering - Proceedings of the 2nd International Conference, NMMVE 2023",
address = "Netherlands",
}