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

Zhao, Xingang; Shirvan, Koroush; Salko Jr, Robert; Guo, Fengdi

doi:10.1016/j.applthermaleng.2019.114540

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

Journal Article · 31 December 2019 · Applied Thermal Engineering

DOI: https://doi.org/10.1016/j.applthermaleng.2019.114540 · OSTI ID:1630524

Zhao, Xingang ^[1]; Shirvan, Koroush ^[1];

^[2]; Guo, Fengdi ^[1]

Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

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.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 1630524

Journal Information:: Applied Thermal Engineering, Journal Name: Applied Thermal Engineering Journal Issue: C Vol. 164; ISSN 1359-4311

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (34)

A hybrid neural network-first principles approach to process modeling Psichogios, Dimitris C.; Ungar, Lyle H. AIChE Journal, Vol. 38, Issue 10 https://doi.org/10.1002/aic.690381003	journal	October 1992
Modeling chemical processes using prior knowledge and neural networks Thompson, Michael L.; Kramer, Mark A. AIChE Journal, Vol. 40, Issue 8 https://doi.org/10.1002/aic.690400806	journal	August 1994
A physical approach to critical heat flux of subcooled flow boiling in round tubes Katto, Y. International Journal of Heat and Mass Transfer, Vol. 33, Issue 4 https://doi.org/10.1016/0017-9310(90)90160-V	journal	April 1990
Rationalization of existing mechanistic models for the prediction of water subcooled flow boiling critical heat flux Celata, G. P.; Cumo, M.; Mariani, A. International Journal of Heat and Mass Transfer, Vol. 37 https://doi.org/10.1016/0017-9310(94)90035-3	journal	March 1994
Heat transfer in water-cooled nuclear reactors Tong, L. S. Nuclear Engineering and Design, Vol. 6, Issue 4 https://doi.org/10.1016/0029-5493(67)90111-2	journal	November 1967
Parametric trends analysis of the critical heat flux based on artificial neural networks Moon, Sang Ki; Baek, Won-Pil; Chang, Soon Heung Nuclear Engineering and Design, Vol. 163, Issue 1-2 https://doi.org/10.1016/0029-5493(95)01178-1	journal	June 1996
A mechanistic critical heat flux model for subcooled flow boiling based on local bulk flow conditions Lee, C. H.; Mudawwar, I. International Journal of Multiphase Flow, Vol. 14, Issue 6 https://doi.org/10.1016/0301-9322(88)90070-5	journal	November 1988
Multilayer feedforward networks are universal approximators Hornik, Kurt; Stinchcombe, Maxwell; White, Halbert Neural Networks, Vol. 2, Issue 5 https://doi.org/10.1016/0893-6080(89)90020-8	journal	January 1989
Critical heat flux of subcooled flow boiling for water in uniformly heated straight tubes Inasaka, Fujio; Nariai, Hideki Fusion Engineering and Design, Vol. 19, Issue 4 https://doi.org/10.1016/0920-3796(92)90007-Q	journal	December 1992
The Critical Heat Flux For The Flow Of Steam–Water Mixtures Through Pipes Peskov, O. L.; Subbotin, V. I.; Zenkevich, B. A. Problems of Heat Transfer and Hydraulics of Two-Phase Media, p. 48-62 https://doi.org/10.1016/B978-0-08-012077-5.50010-5	book	January 1969
Prediction of the critical heat flux in water subcooled flow boiling using a new mechanistic approach Celata, G. P.; Cumo, M.; Katto, Y. International Journal of Heat and Mass Transfer, Vol. 42, Issue 8 https://doi.org/10.1016/S0017-9310(98)00286-5	journal	April 1999
Prediction of critical heat flux for subcooled flow boiling Liu, W.; Nariai, H.; Inasaka, F. International Journal of Heat and Mass Transfer, Vol. 43, Issue 18 https://doi.org/10.1016/S0017-9310(99)00373-7	journal	September 2000
Comparison of methods for training grey-box neural network models Acuña, Gonzalo; Cubillos, Francisco; Thibault, Jules Computers & Chemical Engineering, Vol. 23 https://doi.org/10.1016/S0098-1354(99)80138-0	journal	June 1999
Automatic early stopping using cross validation: quantifying the criteria Prechelt, Lutz Neural Networks, Vol. 11, Issue 4 https://doi.org/10.1016/S0893-6080(98)00010-0	journal	June 1998
Combining Semi-Physical and Neural Network Modeling: An Example ofIts Usefulness Forssell, U.; Lindskog, P. IFAC Proceedings Volumes, Vol. 30, Issue 11 https://doi.org/10.1016/S1474-6670(17)42938-7	journal	July 1997
Integrating Neural Networks with First Principles Models for Dynamic Modeling Su, Hong-Te; Bhat, N.; Minderman, P. A. IFAC Proceedings Volumes, Vol. 25, Issue 5 https://doi.org/10.1016/S1474-6670(17)51013-7	journal	April 1992
Artificial neural network based daily local forecasting for global solar radiation Amrouche, Badia; Le Pivert, Xavier Applied Energy, Vol. 130 https://doi.org/10.1016/j.apenergy.2014.05.055	journal	October 2014
A survey of artificial neural network in wind energy systems Marugán, Alberto Pliego; Márquez, Fausto Pedro García; Perez, Jesus María Pinar Applied Energy, Vol. 228 https://doi.org/10.1016/j.apenergy.2018.07.084	journal	October 2018
Using machine learning algorithms to predict the pressure drop during evaporation of R407C Khosravi, A.; Pabon, J. J. G.; Koury, R. N. N. Applied Thermal Engineering, Vol. 133 https://doi.org/10.1016/j.applthermaleng.2018.01.084	journal	March 2018
CFD modeling of critical heat flux in flow boiling: Validation and assessment of closure models Pothukuchi, Harish; Kelm, S.; Patnaik, B. S. V. Applied Thermal Engineering, Vol. 150 https://doi.org/10.1016/j.applthermaleng.2019.01.030	journal	March 2019
Assessment of dimensionless CHF correlations for subcooled flow boiling in microgravity and Earth gravity Zhang, Hui; Mudawar, Issam; Hasan, Mohammad M. International Journal of Heat and Mass Transfer, Vol. 50, Issue 23-24 https://doi.org/10.1016/j.ijheatmasstransfer.2007.03.030	journal	November 2007
Neural network based correlation for critical heat flux in steam-water flows in pipes Nafey, Ahmed Safwat International Journal of Thermal Sciences, Vol. 48, Issue 12 https://doi.org/10.1016/j.ijthermalsci.2009.04.010	journal	December 2009
Diameter effect on critical heat flux Tanase, A.; Cheng, S. C.; Groeneveld, D. C. Nuclear Engineering and Design, Vol. 239, Issue 2 https://doi.org/10.1016/j.nucengdes.2008.10.008	journal	February 2009
A margin missed: The effect of surface oxidation on CHF enhancement in IVR accident scenarios Trojer, Mathias; Azizian, Reza; Paras, Jonathan Nuclear Engineering and Design, Vol. 335 https://doi.org/10.1016/j.nucengdes.2018.05.011	journal	August 2018
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 He, Mingfu; Lee, Youho Nuclear Engineering and Design, Vol. 338 https://doi.org/10.1016/j.nucengdes.2018.08.005	journal	November 2018
Applications of ANNs in flow and heat transfer problems in nuclear engineering: A review work Cong, Tenglong; Su, Guanghui; Qiu, Suizheng Progress in Nuclear Energy, Vol. 62 https://doi.org/10.1016/j.pnucene.2012.09.003	journal	January 2013
A New Paradigm for Understanding and Enhancing the Critical Heat Flux (CHF) Limit Fazeli, Abdolreza; Moghaddam, Saeed Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/s41598-017-05036-2	journal	July 2017
Critical Heat Flux in Flow Boiling—Review of the Current Understanding and Experimental Approaches Bruder, Moritz; Bloch, Gregor; Sattelmayer, Thomas Heat Transfer Engineering, Vol. 38, Issue 3 https://doi.org/10.1080/01457632.2016.1189274	journal	September 2016
Application of an Artificial Neural Network in Reactor Thermohydraulic Problem: Prediction of Critical Heat Flux Su, Guanghui; Fukuda, Kenji; Jia, Dounan Journal of Nuclear Science and Technology, Vol. 39, Issue 5 https://doi.org/10.1080/18811248.2002.9715235	journal	May 2002
Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework Wu, Jin-Long; Xiao, Heng; Paterson, Eric Physical Review Fluids, Vol. 3, Issue 7 https://doi.org/10.1103/PhysRevFluids.3.074602	journal	July 2018
Networks for approximation and learning Poggio, T.; Girosi, F. Proceedings of the IEEE, Vol. 78, Issue 9 https://doi.org/10.1109/5.58326	journal	January 1990
Random decision forests Proceedings of 3rd International Conference on Document Analysis and Recognition https://doi.org/10.1109/ICDAR.1995.598994	conference	January 1995
A few useful things to know about machine learning Domingos, Pedro Communications of the ACM, Vol. 55, Issue 10 https://doi.org/10.1145/2347736.2347755	journal	October 2012
Nanofluids for Enhanced Economics and Safety of Nuclear Reactors: An Evaluation of the Potential Features, Issues, and Research Gaps Buongiorno, Jacopo; Hu, Lin-Wen; Kim, Sung Joong Nuclear Technology, Vol. 162, Issue 1 https://doi.org/10.13182/NT08-A3934	journal	April 2008

Linked Research (2)

Similar Records

Improved departure from nucleate boiling prediction in rod bundles using a physics-informed machine learning-aided framework

Journal Article · 2021 · Nuclear Engineering and Design · OSTI ID:1766421

Zhao, Xingang; Salko, Robert K.; Shirvan, Koroush

Predicting departure from nucleate boiling with advanced data- and physics-driven approaches

Technical Report · 2018 · OSTI ID:1651417

Zhao, Xingang

A ROBUST MECHANISTIC APPROACH TO PREDICTION OF DEPARTURE FROM NUCLEATE BOILING

Conference · 2019 · OSTI ID:1651399

Zhao, Xingang; Shirvan, Koroush; Salko Jr, Robert

Related Subjects

42 ENGINEERING
Critical heat flux
Departure from nucleate boiling
Domain knowledge
Hybrid framework
Machine learning

Data for: On the prediction of critical heat flux using a physics-informed machine learning-aided framework Zhao, Xingang https://doi.org/10.17632/5p5h37tyv7 The current record is supplemented by this dataset	dataset	January 2020
Data for: On the prediction of critical heat flux using a physics-informed machine learning-aided framework Zhao, Xingang https://doi.org/10.17632/5p5h37tyv7.1 The current record is supplemented by this dataset	dataset	January 2020

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

Citation Formats

References (34)

Linked Research (2)

Similar Records

Related Subjects