Abstract
Deep learning’s role in tackling complicated engineering problems becomes more and more effective by advances in computer science. One of the classical problems in physics is representing the solution of heat propagation in the arbitrary 2-D domain. Study of two-dimensional heat transfer provides a precious bed for related physical issues. In this work, by using finite volume method, we solved the two-dimensional heat equation on the arbitrary domain with specified limitations (considering three heated rectangular obstacles inside the main domain) for 100000 different cases. These cases were divided into big batches in order to reduce the computational cost. The solution for each case was used as sample data to train our deep neural network. After the training process, deep learning results have been compared to results which were produced by the commercial program (ANSYS). After analyzing deep learning efficiency, obviously, our network successfully was able to predict the solution of heat transfer physics with satisfactory precision.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ascher, U.M.: Numerical Methods for Evolutionary Differential Equations. vol. 5. Siam (2008)
Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. arXiv preprint arXiv:1611.02167 (2016)
Bergman, T.L., Incropera, F.P., Lavine, A.S., Dewitt, D.P.: Introduction to Heat Transfer. Wiley (2011)
Bruch Jr., J.C., Zyvoloski, G.: Transient two-dimensional heat conduction problems solved by the finite element method. Int. J. Numer. Methods Eng. 8(3), 481–494 (1974)
Chakraverty, S., Mall, S.: Artificial Neural Networks for Engineers and Scientists: Solving Ordinary Differential Equations. CRC Press (2017)
Crowdy, D.G.: Analytical solutions for uniform potential flow past multiple cylinders. Eur. J. Mech. B/Fluids 25(4), 459–470 (2006)
Dirichlet, P.G.L.: Über einen neuen Ausdruck zur Bestimmung der Dichtigkeit einer unendlich dünnen Kugelschale, wenn der Werth des Potentials derselben in jedem Punkte ihrer Oberfläche gegeben ist. Dümmler in Komm (1852)
Fan, E.: Extended tanh-function method and its applications to nonlinear equations. Phys. Lett. A 277(4–5), 212–218 (2000)
Grattan-Guinness, I., Fourier, J.B.J., et al.: Joseph Fourier, 1768-1830; a survey of his life and work, based on a critical edition of his monograph on the propagation of heat, presented to the Institut de France in 1807. MIT Press (1972)
Han, J., Jentzen, A., Weinan, E.: Solving high-dimensional partial differential equations using deep learning. Proc. Nat. Acad. Sci. 115(34), 8505–8510 (2018)
Jeong, S., Solenthaler, B., Pollefeys, M., Gross, M., et al.: Data-driven fluid simulations using regression forests. ACM Trans. Graph. (TOG) 34(6), 199 (2015)
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 675–678. ACM (2014)
Kim, B., Azevedo, V.C., Thuerey, N., Kim, T., Gross, M., Solenthaler, B.: Deep fluids: a generative network for parameterized fluid simulations. arXiv preprint arXiv:1806.02071 (2018)
Kreyszig, E.: Advanced Engineering Mathematics. Wiley (2010)
Krogh, A., Hertz, J.A.: A simple weight decay can improve generalization. In: Advances in Neural Information Processing Systems, pp. 950–957 (1992)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)
Li, H., Mulay, S.S.: Meshless Methods and Their Numerical Properties. CRC Press (2013)
Ling, J., Kurzawski, A., Templeton, J.: Reynolds averaged turbulence modelling using deep neural networks with embedded invariance. J. Fluid Mech. 807, 155–166 (2016)
Minkowycz, W.: Advances in Numerical Heat Transfer. vol. 1. CRC Press (1996)
Miyanawala, T.P., Jaiman, R.K.: An efficient deep learning technique for the Navier-Stokes equations: application to unsteady wake flow dynamics. arXiv preprint arXiv:1710.09099 (2017)
Nabian, M.A., Meidani, H.: A deep neural network surrogate for high-dimensional random partial differential equations. arXiv preprint arXiv:1806.02957 (2018)
Narasimhan, T.: Fourier’s heat conduction equation: history, influence, and connections. Rev. Geophys. 37(1), 151–172 (1999)
Robinson, J.C.: Infinite-Dimensional Dynamical Systems: An Introduction to Dissipative Parabolic PDEs and the Theory of Global Attractors. vol. 28. Cambridge University Press (2001)
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)
Ruthotto, L., Haber, E.: Deep neural networks motivated by partial differential equations. arXiv preprint arXiv:1804.04272 (2018)
Sharma, R., Farimani, A.B., Gomes, J., Eastman, P., Pande, V.: Weakly-supervised deep learning of heat transport via physics informed loss. arXiv preprint arXiv:1807.11374 (2018)
Singhal, A., Sinha, P., Pant, R.: Use of deep learning in modern recommendation system: a summary of recent works. arXiv preprint arXiv:1712.07525 (2017)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Stewart, I., Tall, D.: Complex Analysis. Cambridge University Press (2018)
Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: International Conference on Machine Learning, pp. 1139–1147 (2013)
Tompson, J., Schlachter, K., Sprechmann, P., Perlin, K.: Accelerating eulerian fluid simulation with convolutional networks. arXiv preprint arXiv:1607.03597 (2016)
Versteeg, H.K., Malalasekera, W.: An Introduction to Computational Fluid Dynamics: The Finite Volume Method. Pearson Education (2007)
Yadav, N., Yadav, A., Kumar, M.: An Introduction to Neural Network Methods for Differential Equations. Springer (2015)
Zhang, K., Li, D., Chang, K., Zhang, K., Li, D.: Electromagnetic Theory for Microwaves and Optoelectronics. Springer (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zakeri, B., Monsefi, A.K., Darafarin, B. (2020). Deep Learning Prediction of Heat Propagation on 2-D Domain via Numerical Solution. In: Bohlouli, M., Sadeghi Bigham, B., Narimani, Z., Vasighi, M., Ansari, E. (eds) Data Science: From Research to Application. CiDaS 2019. Lecture Notes on Data Engineering and Communications Technologies, vol 45. Springer, Cham. https://doi.org/10.1007/978-3-030-37309-2_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-37309-2_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37308-5
Online ISBN: 978-3-030-37309-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)