Data-driven modeling of geometry-adaptive steady heat conduction based on convolutional neural networks

A data-driven model for rapid prediction of the steady-state heat conduction of a hot object with arbitrary geometry is developed. Mathematically, the steady-state heat conduction can be described by the Laplace's equation, where a heat (spatial) diffusion term dominates the governing equation....

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiang-Zhou Peng, Xianglei Liu, Nadine Aubry, Zhihua Chen, Wei-Tao Wu
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Heat transfer Heat conduction Data-driven model Convolution neural networks Signed distance function Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/f28e11a437dd48879d0f642583b7cc06
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f28e11a437dd48879d0f642583b7cc06
record_format	dspace
spelling	oai:doaj.org-article:f28e11a437dd48879d0f642583b7cc062021-11-18T04:48:57ZData-driven modeling of geometry-adaptive steady heat conduction based on convolutional neural networks2214-157X10.1016/j.csite.2021.101651https://doaj.org/article/f28e11a437dd48879d0f642583b7cc062021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2214157X21008145https://doaj.org/toc/2214-157XA data-driven model for rapid prediction of the steady-state heat conduction of a hot object with arbitrary geometry is developed. Mathematically, the steady-state heat conduction can be described by the Laplace's equation, where a heat (spatial) diffusion term dominates the governing equation. As the intensity of the heat diffusion only depends on the gradient of the temperature field, the temperature distribution of the steady-state heat conduction displays strong features of locality. Therefore, a convolution neural network-based data-driven model is proposed, which is good at capturing local features (sub-invariant) thus can be treated as numerical discretization in some sense. Furthermore, a signed distance function (SDF) is proposed to represent the geometry of the problem, which contains more information than the binary image. The hot objects in the training datasets are composed of simple geometries, the geometry is different in size, shape, orientation, and location. After training, the data-driven model can accurately predict steady-state heat conduction of hot objects with complex geometries which have never been seen by the network; and the prediction speed is more than one order faster than numerical simulation. The outstanding performance of the network model indicates the potential of the approach for applications of engineering optimization and design in future.Jiang-Zhou PengXianglei LiuNadine AubryZhihua ChenWei-Tao WuElsevierarticleHeat transferHeat conductionData-driven modelConvolution neural networksSigned distance functionEngineering (General). Civil engineering (General)TA1-2040ENCase Studies in Thermal Engineering, Vol 28, Iss , Pp 101651- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Heat transfer Heat conduction Data-driven model Convolution neural networks Signed distance function Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	Heat transfer Heat conduction Data-driven model Convolution neural networks Signed distance function Engineering (General). Civil engineering (General) TA1-2040 Jiang-Zhou Peng Xianglei Liu Nadine Aubry Zhihua Chen Wei-Tao Wu Data-driven modeling of geometry-adaptive steady heat conduction based on convolutional neural networks
description	A data-driven model for rapid prediction of the steady-state heat conduction of a hot object with arbitrary geometry is developed. Mathematically, the steady-state heat conduction can be described by the Laplace's equation, where a heat (spatial) diffusion term dominates the governing equation. As the intensity of the heat diffusion only depends on the gradient of the temperature field, the temperature distribution of the steady-state heat conduction displays strong features of locality. Therefore, a convolution neural network-based data-driven model is proposed, which is good at capturing local features (sub-invariant) thus can be treated as numerical discretization in some sense. Furthermore, a signed distance function (SDF) is proposed to represent the geometry of the problem, which contains more information than the binary image. The hot objects in the training datasets are composed of simple geometries, the geometry is different in size, shape, orientation, and location. After training, the data-driven model can accurately predict steady-state heat conduction of hot objects with complex geometries which have never been seen by the network; and the prediction speed is more than one order faster than numerical simulation. The outstanding performance of the network model indicates the potential of the approach for applications of engineering optimization and design in future.
format	article
author	Jiang-Zhou Peng Xianglei Liu Nadine Aubry Zhihua Chen Wei-Tao Wu
author_facet	Jiang-Zhou Peng Xianglei Liu Nadine Aubry Zhihua Chen Wei-Tao Wu
author_sort	Jiang-Zhou Peng
title	Data-driven modeling of geometry-adaptive steady heat conduction based on convolutional neural networks
title_short	Data-driven modeling of geometry-adaptive steady heat conduction based on convolutional neural networks
title_full	Data-driven modeling of geometry-adaptive steady heat conduction based on convolutional neural networks
title_fullStr	Data-driven modeling of geometry-adaptive steady heat conduction based on convolutional neural networks
title_full_unstemmed	Data-driven modeling of geometry-adaptive steady heat conduction based on convolutional neural networks
title_sort	data-driven modeling of geometry-adaptive steady heat conduction based on convolutional neural networks
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/f28e11a437dd48879d0f642583b7cc06
work_keys_str_mv	AT jiangzhoupeng datadrivenmodelingofgeometryadaptivesteadyheatconductionbasedonconvolutionalneuralnetworks AT xiangleiliu datadrivenmodelingofgeometryadaptivesteadyheatconductionbasedonconvolutionalneuralnetworks AT nadineaubry datadrivenmodelingofgeometryadaptivesteadyheatconductionbasedonconvolutionalneuralnetworks AT zhihuachen datadrivenmodelingofgeometryadaptivesteadyheatconductionbasedonconvolutionalneuralnetworks AT weitaowu datadrivenmodelingofgeometryadaptivesteadyheatconductionbasedonconvolutionalneuralnetworks
_version_	1718425075168837632

Data-driven modeling of geometry-adaptive steady heat conduction based on convolutional neural networks

Ejemplares similares