On the prediction of critical heat flux using a physics-informed machine learning-aided framework

Abstract The critical heat flux (CHF) corresponding to the departure from nucleate boiling (DNB) crisis is essential to the design and safety of a two-phase flow boiling system. Despite the abundance of predictive tools available to the thermal engineering community, the path for an accurate, robust CHF model remains elusive due to lack of consensus on the DNB triggering mechanism. This work aims to apply a physics-informed machine learning (ML)-aided hybrid framework to achieve superior predictive capabilities. Such a hybrid approach takes advantage of existing understanding in the field of interest (i.e., domain knowledge) and uses ML to capture undiscovered information from the mismatch between the actual and domain knowledge-predicted target. A detailed case study is carried out with an extensive DNB-specific CHF database to demonstrate (1) the improved performance of the hybrid approach as compared to traditional domain knowledge-based models, and (2) the hybrid model’s superior generalization capabilities over standalone ML methods across a wide range of flow conditions. The hybrid framework could also readily extend its applicability domain and complexity on the fly, showing an elevated level of flexibility and robustness. Based on the case study conclusions, the window-type extrapolation mapping methodology is further proposed to better inform high-cost experimental work.

[1]  Badia Amrouche,et al.  Artificial neural network based daily local forecasting for global solar radiation , 2014 .

[2]  Jinlong Wu,et al.  Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework , 2018, Physical Review Fluids.

[3]  H. Allelein,et al.  CFD modeling of critical heat flux in flow boiling: Validation and assessment of closure models , 2019, Applied Thermal Engineering.

[4]  I. Mudawar,et al.  Assessment of dimensionless CHF correlations for subcooled flow boiling in microgravity and Earth gravity , 2007 .

[5]  M. Kazimi,et al.  Nuclear Systems Volume I , 2020 .

[6]  P. A. Minderman,et al.  INTEGRATING NEURAL NETWORKS WITH FIRST PRINCIPLES MODELS FOR DYNAMIC MODELING , 1992 .

[7]  B. Thompson,et al.  BOILING WATER HEAT TRANSFER BURNOUT IN UNIFORMLY HEATED ROUND TUBES: A COMPILATION OF WORLD DATA WITH ACCURATE CORRELATIONS , 1964 .

[8]  Guanghui Su,et al.  Applications of ANNs in flow and heat transfer problems in nuclear engineering: A review work , 2013 .

[9]  A. Mariani,et al.  Rationalization of existing mechanistic models for the prediction of water subcooled flow boiling critical heat flux , 1994 .

[10]  Lutz Prechelt,et al.  Automatic early stopping using cross validation: quantifying the criteria , 1998, Neural Networks.

[11]  S. Moghaddam,et al.  A New Paradigm for Understanding and Enhancing the Critical Heat Flux (CHF) Limit , 2017, Scientific Reports.

[12]  Jacopo Buongiorno,et al.  Nanofluids for Enhanced Economics and Safety of Nuclear Reactors: An Evaluation of the Potential Features, Issues, and Research Gaps , 2008 .

[13]  C. Lee,et al.  A mechanistic critical heat flux model for subcooled flow boiling based on local bulk flow conditions , 1988 .

[14]  V. Subbotin,et al.  5 – THE CRITICAL HEAT FLUX FOR THE FLOW OF STEAM–WATER MIXTURES THROUGH PIPES , 1969 .

[15]  H. Nariai,et al.  Prediction of critical heat flux for subcooled flow boiling , 2000 .

[16]  N. Zuber.  Hydrodynamic aspects of boiling heat transfer (thesis) , 1959 .

[17]  Pedro M. Domingos.  A few useful things to know about machine learning , 2012, Commun. ACM.

[18]  H. Nariai,et al.  Critical heat flux of subcooled flow boiling for water in uniformly heated straight tubes , 1992 .

[19]  Soon Heung Chang,et al.  Parametric trends analysis of the critical heat flux based on artificial neural networks , 1996 .

[20]  Y. Katto,et al.  Prediction of the critical heat flux in water subcooled flow boiling using a new mechanistic approach , 1999 .

[21]  T. Sattelmayer,et al.  Critical Heat Flux in Flow Boiling—Review of the Current Understanding and Experimental Approaches , 2017 .

[22]  R. Azizian,et al.  A margin missed: The effect of surface oxidation on CHF enhancement in IVR accident scenarios , 2018, Nuclear Engineering and Design.

[23]  Jules Thibault,et al.  Comparison of methods for training grey-box neural network models , 1999 .

[24]  A. Durmayaz,et al.  The 2006 CHF look-up table , 2007 .

[25]  U. Forssell,et al.  COMBINING SEMI-PHYSICAL AND NEURAL NETWORK MODELING: AN EXAMPLE OF ITS USEFULNESS U. FORSSELL AND P. LINDSKOG , 1997 .

[26]  Fausto Pedro García Márquez,et al.  A survey of artificial neural network in wind energy systems , 2018, Applied Energy.

[27]  E. Janssen,et al.  BURNOUT CONDITIONS FOR SINGLE ROD IN ANNULAR GEOMETRY, WATER AT 600 TO 1400 PSIA , 1963 .

[28]  C. Williams,et al.  Critical heat flux experiments in a circular tube with heavy water and light water. (AWBA Development Program) , 1980 .

[29]  Youho Lee,et al.  Application of machine learning for prediction of critical heat flux: Support vector machine for data-driven CHF look-up table construction based on sparingly distributed training data points , 2018 .

[30]  A. S. Nafey.  Neural network based correlation for critical heat flux in steam-water flows in pipes , 2009 .

[31]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[32]  Lyle H. Ungar,et al.  A hybrid neural network‐first principles approach to process modeling , 1992 .

[33]  D. C. Groeneveld,et al.  Diameter effect on critical heat flux , 2009 .

[34]  Tienmo Shih.  Measurement of transient critical heat flux by fluid modeling , 1974 .

[35]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[36]  S. Garribba,et al.  STUDIES ON BURNOUT. PART 3. A NEW CORRELATION FOR ROUND DUCTS AND UNIFORM HEATING AND ITS COMPARISON WITH WORLD DATA. , 1967 .

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

[38]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[39]  J. Randles.  HEAT TRANSFER IN WATER COOLED NUCLEAR REACTORS , 1963 .

[40]  Ricardo Nicolau Nassar Koury,et al.  Using machine learning algorithms to predict the pressure drop during evaporation of R407C , 2018 .

[41]  Y. Katto.  A physical approach to critical heat flux of subcooled flow boiling in round tubes , 1990 .

[42]  Mark A. Kramer,et al.  Modeling chemical processes using prior knowledge and neural networks , 1994 .

[43]  Guanghui Su,et al.  Application of an Artificial Neural Network in Reactor Thermohydraulic Problem: Prediction of Critical Heat Flux , 2002 .