Data-driven modeling for boiling heat transfer: using deep neural networks and high-fidelity simulation results

Boiling heat transfer occurs in many situations and can be used for thermal management in various engineered systems with high energy density, from power electronics to heat exchangers in power plants and nuclear reactors. Essentially, boiling is a complex physical process that involves interactions between heating surface, liquid, and vapor. For engineering applications, the boiling heat transfer is usually predicted by empirical correlations or semi-empirical models, which has relatively large uncertainty. In this paper, a data-driven approach based on deep feedforward neural networks is studied. The proposed networks use near wall local features to predict the boiling heat transfer. The inputs of networks include the local momentum and energy convective transport, pressure gradients, turbulent viscosity, and surface information. The outputs of the networks are the quantities of interest of a typical boiling system, including heat transfer components, wall superheat, and near wall void fraction. The networks are trained by the high-fidelity data processed from first principle simulation of pool boiling under varying input heat fluxes. State-of-the-art algorithms are applied to prevent the overfitting issue when training the deep networks. The trained networks are tested in interpolation cases and extrapolation cases which both demonstrate good agreement with the original high-fidelity simulation results.

[1]  Shuangquan Shao,et al.  Numerical investigation on onset of significant void during water subcooled flow boiling , 2016 .

[2]  G. Kocamustafaogullari,et al.  Pressure dependence of bubble departure diameter for water , 1983 .

[3]  Mohamed A. Habib,et al.  Numerical predictions of flow boiling characteristics: Current status, model setup and CFD modeling for different non-uniform heating profiles , 2015 .

[4]  Chul-Hwa Song,et al.  A bubble dynamics-based model for wall heat flux partitioning during nucleate flow boiling , 2017 .

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[7]  T. Theofanous,et al.  The boiling crisis phenomenon. Part I: nucleation and nucleate boiling heat transfer , 2002 .

[8]  G. Tryggvason,et al.  Using statistical learning to close two-fluid multiphase flow equations for a simple bubbly system , 2015 .

[9]  Karthik Duraisamy,et al.  A paradigm for data-driven predictive modeling using field inversion and machine learning , 2016, J. Comput. Phys..

[10]  Yuxin Wu,et al.  Modeling of subcooled boiling by extending the RPI wall boiling model to ultra-high pressure conditions , 2017 .

[11]  N. Dinh,et al.  Classification of machine learning frameworks for data-driven thermal fluid models , 2018, International Journal of Thermal Sciences.

[12]  Mehrzad Shams,et al.  Optimization of subcooled flow boiling in a vertical pipe by using artificial neural network and multi objective genetic algorithm , 2017 .

[13]  T. Yabuki,et al.  Heat transfer mechanisms in isolated bubble boiling of water observed with MEMS sensor , 2014 .

[14]  Tomasz Kozlowski,et al.  Inverse uncertainty quantification of TRACE physical model parameters using sparse gird stochastic collocation surrogate model , 2017 .

[15]  Heng Xiao,et al.  Data-Driven, Physics-Based Feature Extraction from Fluid Flow Fields using Convolutional Neural Networks , 2018, Communications in Computational Physics.

[16]  V. Dhir,et al.  Effect of Surface Wettability on Active Nucleation Site Density During Pool Boiling of Water on a Ve , 1993 .

[17]  Ohad Shamir,et al.  The Power of Depth for Feedforward Neural Networks , 2015, COLT.

[18]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[19]  R. Cole.  Bubble frequencies and departure volumes at subatmospheric pressures , 1967 .

[20]  Yuanzhi Li,et al.  Convergence Analysis of Two-layer Neural Networks with ReLU Activation , 2017, NIPS.

[21]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[22]  S. Azizi,et al.  Prediction of water holdup in vertical and inclined oil–water two-phase flow using artificial neural network , 2016 .

[23]  Behzad Vaferi,et al.  Estimation of pool boiling heat transfer coefficient of alumina water-based nanofluids by various artificial intelligence (AI) approaches , 2018 .

[24]  Eckart Laurien,et al.  Heat transfer prediction of supercritical water with artificial neural networks , 2018 .

[25]  Jiyuan Tu,et al.  Modeling subcooled flow boiling in vertical channels at low pressures – Part 1: Assessment of empirical correlations , 2014 .

[26]  D. Drew.  Mathematical Modeling of Two-Phase Flow , 1983 .

[27]  D. Colorado,et al.  New void fraction equations for two-phase flow in helical heat exchangers using artificial neural networks , 2018 .

[28]  Vijay K. Dhir,et al.  Wall Heat Flux Partitioning During Subcooled Flow Boiling: Part 1—Model Development , 2005 .

[29]  J. Templeton,et al.  Reynolds averaged turbulence modelling using deep neural networks with embedded invariance , 2016, Journal of Fluid Mechanics.

[30]  Jinlong Wu,et al.  Physics-informed machine learning approach for reconstructing Reynolds stress modeling discrepancies based on DNS data , 2016, 1606.07987.

[31]  J. Nathan Kutz,et al.  Deep learning in fluid dynamics , 2017, Journal of Fluid Mechanics.

[32]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[33]  Giancarlo Scalabrin,et al.  Modeling flow boiling heat transfer of pure fluids through artificial neural networks , 2006 .

[34]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[35]  Yohei Sato,et al.  A sharp-interface phase change model for a mass-conservative interface tracking method , 2013, J. Comput. Phys..

[36]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[37]  Michael Z. Podowski,et al.  MULTIDIMENSIONAL EFFECTS IN FORCED CONVECTION SUBCOOLED BOILING , 1990 .

[38]  Brian Williams,et al.  A Bayesian calibration approach to the thermal problem , 2008 .

[39]  R. Gaertner.  Photographic Study of Nucleate Pool Boiling on a Horizontal Surface , 1965 .

[40]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[41]  Emilio Baglietto,et al.  A self-consistent, physics-based boiling heat transfer modeling framework for use in computational fluid dynamics , 2017 .

[42]  Bojan Niceno,et al.  Nucleate pool boiling simulations using the interface tracking method: Boiling regime from discrete bubble to vapor mushroom region , 2017 .

[43]  Dexian Huang,et al.  Modelling of a post-combustion CO2 capture process using deep belief network , 2018 .

[44]  Pietro Poesio,et al.  Uncertainty quantification and global sensitivity analysis of mechanistic one-dimensional models and flow pattern transition boundaries predictions for two-phase pipe flows , 2017 .

[45]  Yohei Sato,et al.  A depletable micro-layer model for nucleate pool boiling , 2015, J. Comput. Phys..

[46]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[47]  Samrendra Singh,et al.  1D/3D transient HVAC thermal modeling of an off-highway machinery cabin using CFD-ANN hybrid method , 2018 .

[48]  Quanshi Zhang,et al.  Visual interpretability for deep learning: a survey , 2018, Frontiers of Information Technology & Electronic Engineering.

[49]  Mamoru Ishii,et al.  Active nucleation site density in boiling systems , 2003 .

[50]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.