Using Deep Learning to Explore Local Physical Similarity for Global-scale Bridging in Thermal-hydraulic Simulation

Current system thermal-hydraulic codes have limited credibility in simulating real plant conditions, especially when the geometry and boundary conditions are extrapolated beyond the range of test facilities. This paper proposes a data-driven approach, Feature Similarity Measurement FFSM), to establish a technical basis to overcome these difficulties by exploring local patterns using machine learning. The underlying local patterns in multiscale data are represented by a set of physical features that embody the information from a physical system of interest, empirical correlations, and the effect of mesh size. After performing a limited number of high-fidelity numerical simulations and a sufficient amount of fast-running coarse-mesh simulations, an error database is built, and deep learning is applied to construct and explore the relationship between the local physical features and simulation errors. Case studies based on mixed convection have been designed for demonstrating the capability of data-driven models in bridging global scale gaps.

[1]  Francesco Saverio D'Auria,et al.  Scaling in System Thermal-Hydraulics Applications to Nuclear Reactor Safety and Design: a State-of-the-Art Report. , 2017 .

[2]  Igor A. Bolotnov,et al.  Interfacial force study on a single bubble in laminar and turbulent flows , 2017 .

[3]  Haihua Zhao,et al.  A Study of BWR Mark I Station Blackout Accident with GOTHIC Modeling , 2016 .

[4]  Ozkan Emre Ozdemir,et al.  Fukushima Daiichi Unit 1 power plant containment analysis using GOTHIC , 2015 .

[5]  Nam Dinh,et al.  Computationally Efficient CFD Prediction of Bubbly Flow using Physics-Guided Deep Learning , 2019, International Journal of Multiphase Flow.

[6]  Nam Dinh,et al.  Demonstration of a Data-Driven Approach for Error Estimation in Two-Phase Flow Simulation Using Coarse-Mesh CFD , 2019 .

[7]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[8]  I. Catton,et al.  Quantifying reactor safety margins part 1: An overview of the code scaling, applicability, and uncertainty evaluation methodology , 1990 .

[9]  Ivan Catton,et al.  Application of fractional scaling analysis (FSA) to loss of coolant accidents (LOCA): Methodology development , 2007 .

[10]  Haihua Zhao,et al.  Safe reactor depressurization windows for BWR Mark I Station Blackout accident management strategy , 2018 .

[11]  Robert Youngblood,et al.  A data-driven framework for error estimation and mesh-model optimization in system-level thermal-hydraulic simulation , 2018, Nuclear Engineering and Design.

[12]  D. W. Scott,et al.  Multivariate Density Estimation, Theory, Practice and Visualization , 1992 .

[13]  Brendan D. Tracey,et al.  A Machine Learning Strategy to Assist Turbulence Model Development , 2015 .

[14]  Geoffrey E. Hinton,et al.  Visualizing non-metric similarities in multiple maps , 2011, Machine Learning.

[15]  Robert Youngblood,et al.  Machine-learning based error prediction approach for coarse-grid Computational Fluid Dynamics (CG-CFD) , 2020 .

[16]  Liang-Che Dai,et al.  Pressure and temperature analyses using GOTHIC for Mark I containment of the Chinshan Nuclear Power Plant , 2011 .

[17]  B. E. Boyack,et al.  An integrated structure and scaling methodology for severe accident technical issue resolution: Development of methodology , 1998 .

[18]  Julia Ling,et al.  Machine learning strategies for systems with invariance properties , 2016, J. Comput. Phys..

[19]  Jinlong Wu,et al.  A Physics-Informed Machine Learning Approach of Improving RANS Predicted Reynolds Stresses , 2017 .

[20]  Yang Liu,et al.  Data-driven modeling for boiling heat transfer: using deep neural networks and high-fidelity simulation results , 2018, Applied Thermal Engineering.