Abstract
Stochastic heat transfer simulations play a pivotal role in capturing real-world uncertainties, where randomness in material properties and boundary conditions is present. Traditional methods, such as Monte Carlo simulation, perturbation methods, and polynomial chaos expansion, have provided valuable insights but face challenges in efficiency and accuracy, particularly in high-dimensional systems. This paper introduces a methodology for one-dimensional heat transfer modeling that incorporates random boundary conditions and treats thermal conductivity as a random process The proposed approach integrates Monte Carlo simulation with Cholesky decomposition to generate a vector of thermal conductivity realizations, capturing the inherent randomness in material properties. Finite element method (FEM) simulations based on these realizations yield rich datasets of temperatures at various locations. A deep neural network (DNN) is then trained on this FEM data, enabling not only rapid and accurate temperature predictions but also bidirectional computations—predicting temperatures based on thermal conductivity and inversely estimating thermal conductivity from observed temperatures.
Similar content being viewed by others
Data Availability
The data that support the findings of this study are available upon request from the corresponding author. Please contact Rakesh Kumar at kumar.137@iitj.ac.in for access to the data.
References
Billah MM, Khan AI, Liu J, Dutta P (2023) Physics-informed deep neural network for inverse heat transfer problems in materials. Mater Today Commun 106336
Branicki M, Majda AJ (2013) Fundamental limitations of polynomial chaos for uncertainty quantification in systems with intermittent instabilities. Commun Math Sci 11(1):55–103
Chakraborty S, Dey S (1995) Stochastic finite element method for spatial distribution of material properties and external loading. Comput Struct 55(1):41–45
Chen C, Pan Z (2023) A neural network-based method for real-time inversion of nonlinear heat transfer problems. Energies 16(23):7819
Cheong HT, Sivasankaran S, Bhuvaneswari M (2017) Natural convection in a wavy porous cavity with sinusoidal heating and internal heat generation. International Journal of Numerical Methods for Heat & Fluid Flow 27(2):287–309
Das SK, Kumar A, Das B, Burnwal A et al (2013) On soft computing techniques in various areas. Comput Sci Inf Technol 3(59):166
de Lima BS, Ebecken NF (2000) A comparison of models for uncertainty analysis by the finite element method. Finite Elem Anal Des 34(2):211–232
Edalatifar M, Tavakoli MB, Ghalambaz M, Setoudeh F (2021) Using deep learning to learn physics of conduction heat transfer. J Therm Anal Calorim 146:1435–1452
Fudym O, Orlande HRB, Bamford M, Batsale JC (2008) Bayesian approach for thermal diffusivity mapping from infrared images with spatially random heat pulse heating. In: Journal of Physics: Conference Series, Vol. 135, IOP Publishing, pp 012042
Gates R, Choi M, Biswas SK, Helferty JJ (1993) Stabilization of flexible structures using artificial neural networks. In: Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan), Vol. 2, IEEE, pp 1817–1820
Ghanem R (1999) The nonlinear gaussian spectrum of log-normal stochastic processes and variables
Ghanem RG, Spanos PD (2003) Stochastic finite elements: a spectral approach, Courier Corporation
Guo Y, Li G, Mabuchi T, Surblys D, Ohara T, Tokumasu T (2022) Prediction of nanoscale thermal transport and adsorption of liquid containing surfactant at solid-liquid interface via deep learning. J Colloid Interface Sci 613:587–596
Hien T, Kleiber M (1990) Finite element analysis based on stochastic hamilton variational principle. Comput Struct 37(6):893–902
Jiang T, Guo L, Sun G, Chang W, Yang Z, Wang Y (2024) Pdi-hfp: An intelligent method for heat flux prediction on hypersonic aircraft based on projection depth images. Eng Appl Artif Intell 127:107366
Kamiński M (2010) Generalized stochastic perturbation technique in engineering computations. Math Comput Model 51(3–4):272–285
Liu WK, Belytschko T, Mani A (1986) Probabilistic finite elements for nonlinear structural dynamics. Comput Methods Appl Mech Eng 56(1):61–81
Liu WK, Belytschko T, Mani A (1986) Random field finite elements. Int J Numer Meth Eng 23(10):1831–1845
Lucor D, Karniadakis GE (2004) Adaptive generalized polynomial chaos for nonlinear random oscillators. SIAM J Sci Comput 26(2):720–735
Marcel C, Clausse A, Frankiewicz C, Betz A, Attinger D (2017) Numerical investigation into the effect of surface wettability in pool boiling heat transfer with a stochastic-automata model. Int J Heat Mass Transf 111:657–665
Papadrakakis M, Papadopoulos V (1996) Robust and efficient methods for stochastic finite element analysis using monte carlo simulation. Comput Methods Appl Mech Eng 134(3–4):325–340
Pluch P (2007) Some theory for the analysis of random fields-with applications to geostatistics. arXiv:math/0701323
Sun B, Tenneti S, Subramaniam S, Koch DL (2016) Pseudo-turbulent heat flux and average gas-phase conduction during gas-solid heat transfer: flow past random fixed particle assemblies. J Fluid Mech 798:299–349
Vadyala SR, Betgeri SN, Matthews JC, Matthews E (2022) A review of physics-based machine learning in civil engineering. Results Eng 13:100316
Wang F, Li X (2017) The stagnant thermal conductivity of porous media predicted by the random walk theory. Int J Heat Mass Transf 107:520–533
Wang Y, Ren Q (2022) A versatile inversion approach for space/temperature/time-related thermal conductivity via deep learning. Int J Heat Mass Transf 186:122444
Wang T, Zhou G, Wang J, Zhou L (2018) Stochastic analysis of uncertain thermal parameters for random thermal regime of frozen soil around a single freezing pipe. Heat Mass Transf 54:2845–2852
Wang Y, Wang N, Ren Q (2022) Predicting surface heat flux on complex systems via conv-lstm. Case Studies in Thermal Engineering 33:101927
Xiu D, Karniadakis GE (2002) The wiener-askey polynomial chaos for stochastic differential equations. SIAM J Sci Comput 24(2):619–644
Xiu D, Karniadakis GE (2003) A new stochastic approach to transient heat conduction modeling with uncertainty. Int J Heat Mass Transf 46(24):4681–4693
Acknowledgements
I would like to express my gratitude to Dr. Vivek Vijay, Assistant Professor in the Department of Mathematics at the Indian Institute of Technology Jodhpur (IITJ), for his invaluable assistance in helping me understand the lognormal distribution of random processes. Additionally, I extend my heartfelt thanks to Prof. B. Ravindran Professor in the Department of Mechanical Engineering at IITJ, for his consistent support in preparing this manuscript. I am also deeply grateful to my supervisors, Prof. C. Venkataesan from the Department of Mechanical Engineering at IITJ, and Dr. Abir Bhattacharyya from the Department of Metallurgical and Materials Engineering at IITJ, for their guidance and mentorship throughout this research endeavor.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kumar, R. Heat transfer in material having random thermal conductivity using Monte Carlo simulation and deep neural network. Multiscale and Multidiscip. Model. Exp. and Des. (2024). https://doi.org/10.1007/s41939-024-00388-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s41939-024-00388-5