Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics
The recently developed physics-informed neural network (PINN) has achieved success in many science and engineering disciplines by encoding physics laws into the loss functions of the neural network such that the network not only conforms to the measurements and initial and boundary conditions but al...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
American Chemical Society (ACS)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/138718.2 |
| _version_ | 1811074179688038400 |
|---|---|
| author | Ji, Weiqi Qiu, Weilun Shi, Zhiyu Pan, Shaowu Deng, Sili |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Ji, Weiqi Qiu, Weilun Shi, Zhiyu Pan, Shaowu Deng, Sili |
| author_sort | Ji, Weiqi |
| collection | MIT |
| description | The recently developed physics-informed neural network (PINN) has achieved success in many science and engineering disciplines by encoding physics laws into the loss functions of the neural network such that the network not only conforms to the measurements and initial and boundary conditions but also satisfies the governing equations. This work first investigates the performance of the PINN in solving stiff chemical kinetic problems with governing equations of stiff ordinary differential equations (ODEs). The results elucidate the challenges of utilizing the PINN in stiff ODE systems. Consequently, we employ quasi-steady-state assumption (QSSA) to reduce the stiffness of the ODE systems, and the PINN then can be successfully applied to the converted non-/mild-stiff systems. Therefore, the results suggest that stiffness could be the major reason for the failure of the regular PINN in the studied stiff chemical kinetic systems. The developed stiff-PINN approach that utilizes QSSA to enable the PINN to solve stiff chemical kinetics shall open the possibility of applying the PINN to various reaction-diffusion systems involving stiff dynamics. |
| first_indexed | 2024-09-23T09:44:41Z |
| format | Article |
| id | mit-1721.1/138718.2 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T09:44:41Z |
| publishDate | 2021 |
| publisher | American Chemical Society (ACS) |
| record_format | dspace |
| spelling | mit-1721.1/138718.22021-12-17T23:17:03Z Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics Ji, Weiqi Qiu, Weilun Shi, Zhiyu Pan, Shaowu Deng, Sili Massachusetts Institute of Technology. Department of Mechanical Engineering The recently developed physics-informed neural network (PINN) has achieved success in many science and engineering disciplines by encoding physics laws into the loss functions of the neural network such that the network not only conforms to the measurements and initial and boundary conditions but also satisfies the governing equations. This work first investigates the performance of the PINN in solving stiff chemical kinetic problems with governing equations of stiff ordinary differential equations (ODEs). The results elucidate the challenges of utilizing the PINN in stiff ODE systems. Consequently, we employ quasi-steady-state assumption (QSSA) to reduce the stiffness of the ODE systems, and the PINN then can be successfully applied to the converted non-/mild-stiff systems. Therefore, the results suggest that stiffness could be the major reason for the failure of the regular PINN in the studied stiff chemical kinetic systems. The developed stiff-PINN approach that utilizes QSSA to enable the PINN to solve stiff chemical kinetics shall open the possibility of applying the PINN to various reaction-diffusion systems involving stiff dynamics. 2021-12-17T23:17:02Z 2021-12-17T18:55:27Z 2021-12-17T23:17:02Z 2021-08 2021-12-17T18:52:55Z Article http://purl.org/eprint/type/JournalArticle 1520-5215 https://hdl.handle.net/1721.1/138718.2 Ji, Weiqi, Qiu, Weilun, Shi, Zhiyu, Pan, Shaowu and Deng, Sili. 2021. "Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics." Journal of Physical Chemistry A, 125 (36). en https://dx.doi.org/10.1021/ACS.JPCA.1C05102 Journal of Physical Chemistry A Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/octet-stream American Chemical Society (ACS) arXiv |
| spellingShingle | Ji, Weiqi Qiu, Weilun Shi, Zhiyu Pan, Shaowu Deng, Sili Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics |
| title | Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics |
| title_full | Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics |
| title_fullStr | Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics |
| title_full_unstemmed | Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics |
| title_short | Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics |
| title_sort | stiff pinn physics informed neural network for stiff chemical kinetics |
| url | https://hdl.handle.net/1721.1/138718.2 |
| work_keys_str_mv | AT jiweiqi stiffpinnphysicsinformedneuralnetworkforstiffchemicalkinetics AT qiuweilun stiffpinnphysicsinformedneuralnetworkforstiffchemicalkinetics AT shizhiyu stiffpinnphysicsinformedneuralnetworkforstiffchemicalkinetics AT panshaowu stiffpinnphysicsinformedneuralnetworkforstiffchemicalkinetics AT dengsili stiffpinnphysicsinformedneuralnetworkforstiffchemicalkinetics |