A Preliminary Study on the Resolution of Electro-Thermal Multi-Physics Coupling Problem Using Physics-Informed Neural Network (PINN)
The problem of electro-thermal coupling is widely present in the integrated circuit (IC). The accuracy and efficiency of traditional solution methods, such as the finite element method (FEM), are tightly related to the quality and density of mesh construction. Recently, PINN (physics-informed neural...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/15/2/53 |
| _version_ | 1797483568863117312 |
|---|---|
| author | Yaoyao Ma Xiaoyu Xu Shuai Yan Zhuoxiang Ren |
| author_facet | Yaoyao Ma Xiaoyu Xu Shuai Yan Zhuoxiang Ren |
| author_sort | Yaoyao Ma |
| collection | DOAJ |
| description | The problem of electro-thermal coupling is widely present in the integrated circuit (IC). The accuracy and efficiency of traditional solution methods, such as the finite element method (FEM), are tightly related to the quality and density of mesh construction. Recently, PINN (physics-informed neural network) was proposed as a method for solving differential equations. This method is mesh free and generalizes the process of solving PDEs regardless of the equations’ structure. Therefore, an experiment is conducted to explore the feasibility of PINN in solving electro-thermal coupling problems, which include the electrokinetic field and steady-state thermal field. We utilize two neural networks in the form of sequential training to approximate the electric field and the thermal field, respectively. The experimental results show that PINN provides good accuracy in solving electro-thermal coupling problems. |
| first_indexed | 2024-03-09T22:48:52Z |
| format | Article |
| id | doaj.art-eb669a6a7e8f412099bc39d9d16e6a75 |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-09T22:48:52Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-eb669a6a7e8f412099bc39d9d16e6a752023-11-23T18:24:16ZengMDPI AGAlgorithms1999-48932022-02-011525310.3390/a15020053A Preliminary Study on the Resolution of Electro-Thermal Multi-Physics Coupling Problem Using Physics-Informed Neural Network (PINN)Yaoyao Ma0Xiaoyu Xu1Shuai Yan2Zhuoxiang Ren3Institute of Microelectronics of Chinese Academy of Sciences, Beijing 100029, ChinaInstitute of Electrical Engineering, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Electrical Engineering, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Electrical Engineering, Chinese Academy of Sciences, Beijing 100190, ChinaThe problem of electro-thermal coupling is widely present in the integrated circuit (IC). The accuracy and efficiency of traditional solution methods, such as the finite element method (FEM), are tightly related to the quality and density of mesh construction. Recently, PINN (physics-informed neural network) was proposed as a method for solving differential equations. This method is mesh free and generalizes the process of solving PDEs regardless of the equations’ structure. Therefore, an experiment is conducted to explore the feasibility of PINN in solving electro-thermal coupling problems, which include the electrokinetic field and steady-state thermal field. We utilize two neural networks in the form of sequential training to approximate the electric field and the thermal field, respectively. The experimental results show that PINN provides good accuracy in solving electro-thermal coupling problems.https://www.mdpi.com/1999-4893/15/2/53electro-thermal couplingdeep learningphysics-informed neural networkPDEs |
| spellingShingle | Yaoyao Ma Xiaoyu Xu Shuai Yan Zhuoxiang Ren A Preliminary Study on the Resolution of Electro-Thermal Multi-Physics Coupling Problem Using Physics-Informed Neural Network (PINN) Algorithms electro-thermal coupling deep learning physics-informed neural network PDEs |
| title | A Preliminary Study on the Resolution of Electro-Thermal Multi-Physics Coupling Problem Using Physics-Informed Neural Network (PINN) |
| title_full | A Preliminary Study on the Resolution of Electro-Thermal Multi-Physics Coupling Problem Using Physics-Informed Neural Network (PINN) |
| title_fullStr | A Preliminary Study on the Resolution of Electro-Thermal Multi-Physics Coupling Problem Using Physics-Informed Neural Network (PINN) |
| title_full_unstemmed | A Preliminary Study on the Resolution of Electro-Thermal Multi-Physics Coupling Problem Using Physics-Informed Neural Network (PINN) |
| title_short | A Preliminary Study on the Resolution of Electro-Thermal Multi-Physics Coupling Problem Using Physics-Informed Neural Network (PINN) |
| title_sort | preliminary study on the resolution of electro thermal multi physics coupling problem using physics informed neural network pinn |
| topic | electro-thermal coupling deep learning physics-informed neural network PDEs |
| url | https://www.mdpi.com/1999-4893/15/2/53 |
| work_keys_str_mv | AT yaoyaoma apreliminarystudyontheresolutionofelectrothermalmultiphysicscouplingproblemusingphysicsinformedneuralnetworkpinn AT xiaoyuxu apreliminarystudyontheresolutionofelectrothermalmultiphysicscouplingproblemusingphysicsinformedneuralnetworkpinn AT shuaiyan apreliminarystudyontheresolutionofelectrothermalmultiphysicscouplingproblemusingphysicsinformedneuralnetworkpinn AT zhuoxiangren apreliminarystudyontheresolutionofelectrothermalmultiphysicscouplingproblemusingphysicsinformedneuralnetworkpinn AT yaoyaoma preliminarystudyontheresolutionofelectrothermalmultiphysicscouplingproblemusingphysicsinformedneuralnetworkpinn AT xiaoyuxu preliminarystudyontheresolutionofelectrothermalmultiphysicscouplingproblemusingphysicsinformedneuralnetworkpinn AT shuaiyan preliminarystudyontheresolutionofelectrothermalmultiphysicscouplingproblemusingphysicsinformedneuralnetworkpinn AT zhuoxiangren preliminarystudyontheresolutionofelectrothermalmultiphysicscouplingproblemusingphysicsinformedneuralnetworkpinn |