Fast Prediction Method for Steady-State Heat Convection

2012 ◽  
Vol 35 (4) ◽  
pp. 668-678 ◽  
Author(s):  
Y. Wang ◽  
B. Yu ◽  
S. Sun
Keyword(s):  
Steady State ◽  
Prediction Method ◽  
Heat Convection ◽  
State Heat ◽  
Steady State Heat ◽  
Fast Prediction

scholarly journals Data-Driven Modeling of Geometry-Adaptive Steady Heat Convection Based on Convolutional Neural Networks

Fluids ◽  
2021 ◽  
Vol 6 (12) ◽  
pp. 436
Author(s):  
Jiang-Zhou Peng ◽  
Xianglei Liu ◽  
Zhen-Dong Xia ◽  
Nadine Aubry ◽  
Zhihua Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Steady State ◽  
Network Model ◽  
Heat Convection ◽  
Data Driven ◽  
Complex Geometries ◽  
Governing Equations ◽  
Steady State Heat ◽  
Fast Prediction

Heat convection is one of the main mechanisms of heat transfer, and it involves both heat conduction and heat transportation by fluid flow; as a result, it usually requires numerical simulation for solving heat convection problems. Although the derivation of governing equations is not difficult, the solution process can be complicated and usually requires numerical discretization and iteration of differential equations. In this paper, based on neural networks, we developed a data-driven model for an extremely fast prediction of steady-state heat convection of a hot object with an arbitrary complex geometry in a two-dimensional space. According to the governing equations, the steady-state heat convection is dominated by convection and thermal diffusion terms; thus the distribution of the physical fields would exhibit stronger correlations between adjacent points. Therefore, the proposed neural network model uses convolutional neural network (CNN) layers as the encoder and deconvolutional neural network (DCNN) layers as the decoder. Compared with a fully connected (FC) network model, the CNN-based model is good for capturing and reconstructing the spatial relationships of low-rank feature spaces, such as edge intersections, parallelism, and symmetry. Furthermore, we applied the signed distance function (SDF) as the network input for representing the problem geometry, which contains more information compared with a binary image. For displaying the strong learning and generalization ability of the proposed network model, the training dataset only contains hot objects with simple geometries: triangles, quadrilaterals, pentagons, hexagons, and dodecagons, while the testing cases use arbitrary and complex geometries. According to the study, the trained network model can accurately predict the velocity and temperature field of the problems with complex geometries, which has never been seen by the network model during the model training; and the prediction speed is two orders faster than the CFD. The ability of accurate and extremely fast prediction of the network model suggests the potential of applying reduced-order network models to the applications of real-time control and fast optimization in the future.

Steady State Heat Conduction Modeling by the Generalized Finite Element Method

2018 ◽  
Author(s):  
Humberto Alves da Silveira Monteiro ◽  
Guilherme Garcia Botelho ◽  
Roque Luiz da Silva Pitangueira ◽  
Rodrigo Peixoto ◽  
FELICIO BARROS
Keyword(s):  
Finite Element Method ◽  
Finite Element ◽  
Heat Conduction ◽  
Steady State ◽  
Generalized Finite Element Method ◽  
State Heat ◽  
Steady State Heat ◽  
Generalized Finite Element ◽  
Element Method

Steady State Heat Transfer in the Left Ventricle

1983 ◽  
pp. 623-648 ◽  
Author(s):  
B. H. Smaill ◽  
J. Douglas ◽  
P. J. Hunter ◽  
I. Anderson
Keyword(s):  
Heat Transfer ◽  
Steady State ◽  
Left Ventricle ◽  
State Heat ◽  
Steady State Heat ◽  
Steady State Heat Transfer

Analytical Solution to Steady-State Heat-Conduction Problems With Irregularly Shaped Boundaries

1971 ◽  
Vol 93 (4) ◽  
pp. 449-454 ◽  
Author(s):  
D. M. France
Keyword(s):  
Heat Conduction ◽  
Steady State ◽  
Analytical Solution ◽  
Least Squares ◽  
Series Solution ◽  
Point Matching ◽  
State Heat ◽  
Temperature Heat ◽  
Steady State Heat ◽  
Least Squares Approach

A method of obtaining an analytical solution to two-dimensional steady-state heat-conduction problems with irregularly shaped boundaries is presented. The technique of obtaining the coefficients to the series solution via a direct least-squares approach is compared to the “point-matching” scheme. The two methods were applied to problems with known solutions involving the three heat-transfer boundary conditions, temperature, heat flux, and convection coefficient specified. Increased accuracy with substantially fewer terms in the series solution was obtained via the least-squares technique.

Sign in / Sign up

Export Citation Format

Share Document