Convolutional neural networks for heat conduction
This paper presents a data-driven approach to solve heat conduction problems, in particular 2D heat conduction problems. The physical laws which govern such problems are modeled by partial differential equations. We examine temperature distributions of conductors that have square geometry subjected...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-10-01
|
| Series: | Case Studies in Thermal Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214157X22003355 |
| _version_ | 1798002134318317568 |
|---|---|
| author | Sidharth Tadeparti Vishal V.R. Nandigana |
| author_facet | Sidharth Tadeparti Vishal V.R. Nandigana |
| author_sort | Sidharth Tadeparti |
| collection | DOAJ |
| description | This paper presents a data-driven approach to solve heat conduction problems, in particular 2D heat conduction problems. The physical laws which govern such problems are modeled by partial differential equations. We examine temperature distributions of conductors that have square geometry subjected to various boundary conditions, both Dirichlet and Neumann. The data consists of images of these distributions in a semi-continuous form. Conventionally, such problems may be solved analytically or using numerical methods which can be computationally expensive. We attempt to use Image-Based Deep Learning algorithms such as encoder-decoders and variational auto-encoders which do not involve the physical laws of the problem. We also study the efficacy of deterministic models against probabilistic models and the feasibility of using image-based deep-learning methods for engineering applications. |
| first_indexed | 2024-04-11T11:47:19Z |
| format | Article |
| id | doaj.art-23cb2f0270614bafb21f165a6a38de9c |
| institution | Directory Open Access Journal |
| issn | 2214-157X |
| language | English |
| last_indexed | 2024-04-11T11:47:19Z |
| publishDate | 2022-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Case Studies in Thermal Engineering |
| spelling | doaj.art-23cb2f0270614bafb21f165a6a38de9c2022-12-22T04:25:30ZengElsevierCase Studies in Thermal Engineering2214-157X2022-10-0138102089Convolutional neural networks for heat conductionSidharth Tadeparti0Vishal V.R. Nandigana1Membrane Technology and Deep Learning Laboratory, CFD Laboratory, Department of Mechanical Engineering, Indian Institute of Technology Madras, Chennai, 600036, Tamilnadu, IndiaCorresponding author.; Membrane Technology and Deep Learning Laboratory, CFD Laboratory, Department of Mechanical Engineering, Indian Institute of Technology Madras, Chennai, 600036, Tamilnadu, IndiaThis paper presents a data-driven approach to solve heat conduction problems, in particular 2D heat conduction problems. The physical laws which govern such problems are modeled by partial differential equations. We examine temperature distributions of conductors that have square geometry subjected to various boundary conditions, both Dirichlet and Neumann. The data consists of images of these distributions in a semi-continuous form. Conventionally, such problems may be solved analytically or using numerical methods which can be computationally expensive. We attempt to use Image-Based Deep Learning algorithms such as encoder-decoders and variational auto-encoders which do not involve the physical laws of the problem. We also study the efficacy of deterministic models against probabilistic models and the feasibility of using image-based deep-learning methods for engineering applications.http://www.sciencedirect.com/science/article/pii/S2214157X22003355Heat conductionDeep learningImage-based algorithmConvolutional neural networks |
| spellingShingle | Sidharth Tadeparti Vishal V.R. Nandigana Convolutional neural networks for heat conduction Case Studies in Thermal Engineering Heat conduction Deep learning Image-based algorithm Convolutional neural networks |
| title | Convolutional neural networks for heat conduction |
| title_full | Convolutional neural networks for heat conduction |
| title_fullStr | Convolutional neural networks for heat conduction |
| title_full_unstemmed | Convolutional neural networks for heat conduction |
| title_short | Convolutional neural networks for heat conduction |
| title_sort | convolutional neural networks for heat conduction |
| topic | Heat conduction Deep learning Image-based algorithm Convolutional neural networks |
| url | http://www.sciencedirect.com/science/article/pii/S2214157X22003355 |
| work_keys_str_mv | AT sidharthtadeparti convolutionalneuralnetworksforheatconduction AT vishalvrnandigana convolutionalneuralnetworksforheatconduction |