Modeling a Typical Non-Uniform Deformation of Materials Using Physics-Informed Deep Learning: Applications to Forward and Inverse Problems
Numerical methods, such as finite element or finite difference, have been widely used in the past decades for modeling solid mechanics problems by solving partial differential equations (PDEs). Differently from the traditional computational paradigm employed in numerical methods, physics-informed de...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/7/4539 |
| _version_ | 1797608346395607040 |
|---|---|
| author | Yawen Deng Changchang Chen Qingxin Wang Xiaohe Li Zide Fan Yunzi Li |
| author_facet | Yawen Deng Changchang Chen Qingxin Wang Xiaohe Li Zide Fan Yunzi Li |
| author_sort | Yawen Deng |
| collection | DOAJ |
| description | Numerical methods, such as finite element or finite difference, have been widely used in the past decades for modeling solid mechanics problems by solving partial differential equations (PDEs). Differently from the traditional computational paradigm employed in numerical methods, physics-informed deep learning approximates the physics domains using a neural network and embeds physics laws to regularize the network. In this work, a physics-informed neural network (PINN) is extended for application to linear elasticity problems that arise in modeling non-uniform deformation for a typical open-holed plate specimen. The main focus will be on investigating the performance of a conventional PINN approach to modeling non-uniform deformation with high stress concentration in relation to solid mechanics involving forward and inverse problems. Compared to the conventional finite element method, our results show the promise of using PINN in modeling the non-uniform deformation of materials with the occurrence of both forward and inverse problems. |
| first_indexed | 2024-03-11T05:42:08Z |
| format | Article |
| id | doaj.art-b5bcd84dc247424e8949424a71f48eab |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T05:42:08Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b5bcd84dc247424e8949424a71f48eab2023-11-17T16:21:48ZengMDPI AGApplied Sciences2076-34172023-04-01137453910.3390/app13074539Modeling a Typical Non-Uniform Deformation of Materials Using Physics-Informed Deep Learning: Applications to Forward and Inverse ProblemsYawen Deng0Changchang Chen1Qingxin Wang2Xiaohe Li3Zide Fan4Yunzi Li5Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaCNPC Engineering Technology R&D Company Limited, Beijing 102206, ChinaChina Petroleum Pipeline Engineering Corporation, Langfang 065000, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaSpace Systems Division, Beijing 100094, ChinaNumerical methods, such as finite element or finite difference, have been widely used in the past decades for modeling solid mechanics problems by solving partial differential equations (PDEs). Differently from the traditional computational paradigm employed in numerical methods, physics-informed deep learning approximates the physics domains using a neural network and embeds physics laws to regularize the network. In this work, a physics-informed neural network (PINN) is extended for application to linear elasticity problems that arise in modeling non-uniform deformation for a typical open-holed plate specimen. The main focus will be on investigating the performance of a conventional PINN approach to modeling non-uniform deformation with high stress concentration in relation to solid mechanics involving forward and inverse problems. Compared to the conventional finite element method, our results show the promise of using PINN in modeling the non-uniform deformation of materials with the occurrence of both forward and inverse problems.https://www.mdpi.com/2076-3417/13/7/4539physics-informed neural networksolid mechanicsnon-uniform deformationforward and inverse mechanics problems |
| spellingShingle | Yawen Deng Changchang Chen Qingxin Wang Xiaohe Li Zide Fan Yunzi Li Modeling a Typical Non-Uniform Deformation of Materials Using Physics-Informed Deep Learning: Applications to Forward and Inverse Problems Applied Sciences physics-informed neural network solid mechanics non-uniform deformation forward and inverse mechanics problems |
| title | Modeling a Typical Non-Uniform Deformation of Materials Using Physics-Informed Deep Learning: Applications to Forward and Inverse Problems |
| title_full | Modeling a Typical Non-Uniform Deformation of Materials Using Physics-Informed Deep Learning: Applications to Forward and Inverse Problems |
| title_fullStr | Modeling a Typical Non-Uniform Deformation of Materials Using Physics-Informed Deep Learning: Applications to Forward and Inverse Problems |
| title_full_unstemmed | Modeling a Typical Non-Uniform Deformation of Materials Using Physics-Informed Deep Learning: Applications to Forward and Inverse Problems |
| title_short | Modeling a Typical Non-Uniform Deformation of Materials Using Physics-Informed Deep Learning: Applications to Forward and Inverse Problems |
| title_sort | modeling a typical non uniform deformation of materials using physics informed deep learning applications to forward and inverse problems |
| topic | physics-informed neural network solid mechanics non-uniform deformation forward and inverse mechanics problems |
| url | https://www.mdpi.com/2076-3417/13/7/4539 |
| work_keys_str_mv | AT yawendeng modelingatypicalnonuniformdeformationofmaterialsusingphysicsinformeddeeplearningapplicationstoforwardandinverseproblems AT changchangchen modelingatypicalnonuniformdeformationofmaterialsusingphysicsinformeddeeplearningapplicationstoforwardandinverseproblems AT qingxinwang modelingatypicalnonuniformdeformationofmaterialsusingphysicsinformeddeeplearningapplicationstoforwardandinverseproblems AT xiaoheli modelingatypicalnonuniformdeformationofmaterialsusingphysicsinformeddeeplearningapplicationstoforwardandinverseproblems AT zidefan modelingatypicalnonuniformdeformationofmaterialsusingphysicsinformeddeeplearningapplicationstoforwardandinverseproblems AT yunzili modelingatypicalnonuniformdeformationofmaterialsusingphysicsinformeddeeplearningapplicationstoforwardandinverseproblems |