Combining simulations and data with deep learning and uncertainty quantification for advanced energy modeling
Abstract
A novel and modern framework for energy modeling is developed in this paper with a focus on nuclear energy modeling and simulation. The framework combines multiphysics simulations and real data, with validation by uncertainty quantification tasks and facilitation by machine and deep learning methods. The hybrid framework is built on the basis of a wide range of physical models, real data, mathematical and statistical methods, and artificial intelligence techniques. The framework is demonstrated in different applications, including quantifying uncertainties in computer simulations, multiphysics coupling, analysis of variance using machine learning surrogate models, deep learning of time series phenomena, and propagating parametric uncertainties of nuclear data. The applications demonstrated are oriented to nuclear engineering simulations, even though majority of the methods are applicable to other energy sources (eg, renewable). Efficient utilization of this framework is expected to yield a much better understanding of the physical phenomena analyzed as well as an improvement in the performance of the energy design/model under construction.
- Authors:
-
- Univ. of Illinois at Urbana-Champaign, IL (United States)
- Publication Date:
- Research Org.:
- Univ. of Illinois at Urbana-Champaign, IL (United States)
- Sponsoring Org.:
- USDOE Office of Nuclear Energy (NE), Nuclear Energy University Program (NEUP); USDOE
- OSTI Identifier:
- 1801252
- Alternate Identifier(s):
- OSTI ID: 1563010
- Grant/Contract Number:
- NE0008573; 16-10908
- Resource Type:
- Accepted Manuscript
- Journal Name:
- International Journal of Energy Research
- Additional Journal Information:
- Journal Volume: 43; Journal Issue: 14; Journal ID: ISSN 0363-907X
- Publisher:
- Wiley
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 42 ENGINEERING; energy & fuels; nuclear science & technology; data science; deep learning; modeling and simulation; nuclear energy; sensitivity analysis; uncertainty quantification
Citation Formats
Radaideh, Majdi I., and Kozlowski, Tomasz. Combining simulations and data with deep learning and uncertainty quantification for advanced energy modeling. United States: N. p., 2019.
Web. doi:10.1002/er.4698.
Radaideh, Majdi I., & Kozlowski, Tomasz. Combining simulations and data with deep learning and uncertainty quantification for advanced energy modeling. United States. https://doi.org/10.1002/er.4698
Radaideh, Majdi I., and Kozlowski, Tomasz. Fri .
"Combining simulations and data with deep learning and uncertainty quantification for advanced energy modeling". United States. https://doi.org/10.1002/er.4698. https://www.osti.gov/servlets/purl/1801252.
@article{osti_1801252,
title = {Combining simulations and data with deep learning and uncertainty quantification for advanced energy modeling},
author = {Radaideh, Majdi I. and Kozlowski, Tomasz},
abstractNote = {A novel and modern framework for energy modeling is developed in this paper with a focus on nuclear energy modeling and simulation. The framework combines multiphysics simulations and real data, with validation by uncertainty quantification tasks and facilitation by machine and deep learning methods. The hybrid framework is built on the basis of a wide range of physical models, real data, mathematical and statistical methods, and artificial intelligence techniques. The framework is demonstrated in different applications, including quantifying uncertainties in computer simulations, multiphysics coupling, analysis of variance using machine learning surrogate models, deep learning of time series phenomena, and propagating parametric uncertainties of nuclear data. The applications demonstrated are oriented to nuclear engineering simulations, even though majority of the methods are applicable to other energy sources (eg, renewable). Efficient utilization of this framework is expected to yield a much better understanding of the physical phenomena analyzed as well as an improvement in the performance of the energy design/model under construction.},
doi = {10.1002/er.4698},
journal = {International Journal of Energy Research},
number = 14,
volume = 43,
place = {United States},
year = {Fri Aug 16 00:00:00 EDT 2019},
month = {Fri Aug 16 00:00:00 EDT 2019}
}
Web of Science
Works referenced in this record:
Hybrid reduced order modeling applied to nonlinear models: HYBRID APPLICATION OF ORDER REDUCTION METHODS
journal, July 2012
- Bang, Youngsuk; Abdel-Khalik, Hany S.; Hite, Jason M.
- International Journal for Numerical Methods in Engineering, Vol. 91, Issue 9
Coupled neutronic thermo-hydraulic analysis of full PWR core with Monte-Carlo based BGCore system
journal, September 2011
- Kotlyar, D.; Shaposhnik, Y.; Fridman, E.
- Nuclear Engineering and Design, Vol. 241, Issue 9
Multidimensional multiphysics simulation of nuclear fuel behavior
journal, April 2012
- Williamson, R. L.; Hales, J. D.; Novascone, S. R.
- Journal of Nuclear Materials, Vol. 423, Issue 1-3
Verification and validation of simulation models
conference, December 2010
- Sargent, Robert G.
- 2010 Winter Simulation Conference - (WSC 2010), Proceedings of the 2010 Winter Simulation Conference
Nuclear data sensitivity, uncertainty and target accuracy assessment for future nuclear systems
journal, May 2006
- Aliberti, G.; Palmiotti, G.; Salvatores, M.
- Annals of Nuclear Energy, Vol. 33, Issue 8
Deep learning
journal, May 2015
- LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
- Nature, Vol. 521, Issue 7553
Dimensionality reducibility for multi-physics reduced order modeling
journal, December 2017
- Huang, Dongli; Abdel-Khalik, Hany; Rabiti, Cristian
- Annals of Nuclear Energy, Vol. 110
Factorial Sampling Plans for Preliminary Computational Experiments
journal, May 1991
- Morris, Max D.
- Technometrics, Vol. 33, Issue 2
NUPEC BWR Full-size Fine-mesh Bundle Test (BFBT) Benchmark
journal, November 2006
- Utsuno, H.; Hochreiter, L.; Kasahara, F.
- OECD Papers, Vol. 6, Issue 7
David Draper and E. I. George, and a rejoinder by the authors
journal, November 1999
- Volinsky, Chris T.; Raftery, Adrian E.; Madigan, David
- Statistical Science, Vol. 14, Issue 4
Surrogate models for uncertainty quantification: An overview
conference, March 2017
- Sudret, Bruno; Marelli, Stefano; Wiart, Joe
- 2017 11th European Conference on Antennas and Propagation (EUCAP)
Polynomial Theory of Complex Systems
journal, October 1971
- Ivakhnenko, A. G.
- IEEE Transactions on Systems, Man, and Cybernetics, Vol. SMC-1, Issue 4
Application of implicit Roe-type scheme and Jacobian-Free Newton-Krylov method to two-phase flow problems
journal, September 2018
- Hu, Guojun; Kozlowski, Tomasz
- Annals of Nuclear Energy, Vol. 119
Loss of coolant accident analysis under restriction of reverse flow
journal, September 2019
- Radaideh, Majdi I.; Kozlowski, Tomasz; Farawila, Yousef M.
- Nuclear Engineering and Technology, Vol. 51, Issue 6
A study of double functions and load matching of a phosphoric acid fuel cell/heat-driven refrigerator hybrid system
journal, April 2016
- Chen, Xiaohang; Wang, Yuan; Zhao, Yingru
- Energy, Vol. 101
A generalized adjoint framework for sensitivity and global error estimation in time-dependent nuclear reactor simulations
journal, February 2013
- Stripling, H. F.; Anitescu, M.; Adams, M. L.
- Annals of Nuclear Energy, Vol. 52
Global sensitivity analysis using polynomial chaos expansions
journal, July 2008
- Sudret, Bruno
- Reliability Engineering & System Safety, Vol. 93, Issue 7
Phosphoric acid fuel cells: Fundamentals and applications
journal, October 2004
- Sammes, Nigel; Bove, Roberto; Stahl, Knut
- Current Opinion in Solid State and Materials Science, Vol. 8, Issue 5
Adaptive sparse polynomial chaos expansion based on least angle regression
journal, March 2011
- Blatman, Géraud; Sudret, Bruno
- Journal of Computational Physics, Vol. 230, Issue 6
Multi-objective optimisation analysis and load matching of a phosphoric acid fuel cell system
journal, February 2012
- Zhang, Houcheng; Lin, Guoxing; Chen, Jincan
- International Journal of Hydrogen Energy, Vol. 37, Issue 4
SCALE 6: Comprehensive Nuclear Safety Analysis Code System
journal, May 2011
- Bowman, S. M.
- Nuclear Technology, Vol. 174, Issue 2
Rod Internal Pressure Distribution and Uncertainty Analysis Using FRAPCON
journal, January 2017
- Bratton, Ryan N.; Jessee, Matt A.; Wieselquist, William A.
- Nuclear Technology, Vol. 197, Issue 1
Challenges in coupled thermal–hydraulics and neutronics simulations for LWR safety analysis
journal, June 2007
- Ivanov, Kostadin; Avramova, Maria
- Annals of Nuclear Energy, Vol. 34, Issue 6
Coupling of system thermal–hydraulics and Monte-Carlo code: Convergence criteria and quantification of correlation between statistical uncertainty and coupled error
journal, January 2015
- Wu, Xu; Kozlowski, Tomasz
- Annals of Nuclear Energy, Vol. 75
Advanced BWR criticality safety part II: Cask criticality, burnup credit, sensitivity, and uncertainty analyses
journal, August 2019
- Price, Dean; Radaideh, Majdi I.; O'Grady, Daniel
- Progress in Nuclear Energy, Vol. 115
Estimating Sobol sensitivity indices using correlations
journal, November 2012
- Glen, Graham; Isaacs, Kristin
- Environmental Modelling & Software, Vol. 37
A Statistical Sampling Method for Uncertainty Analysis with SCALE and XSUSA
journal, September 2013
- Williams, M. L.; Ilas, G.; Jessee, M. A.
- Nuclear Technology, Vol. 183, Issue 3
Validation and Uncertainty Quantification for Wall Boiling Closure Relations in Multiphase-CFD Solver
journal, September 2018
- Liu, Yang; Dinh, Nam
- Nuclear Science and Engineering, Vol. 193, Issue 1-2
The Serpent Monte Carlo code: Status, development and applications in 2013
journal, August 2015
- Leppänen, Jaakko; Pusa, Maria; Viitanen, Tuomas
- Annals of Nuclear Energy, Vol. 82
Integrated framework for model assessment and advanced uncertainty quantification of nuclear computer codes under Bayesian statistics
journal, September 2019
- Radaideh, Majdi I.; Borowiec, Katarzyna; Kozlowski, Tomasz
- Reliability Engineering & System Safety, Vol. 189
Least Squares Support Vector Machine Classifiers
journal, June 1999
- Suykens, J. A. K.; Vandewalle, J.
- Neural Processing Letters, Vol. 9, Issue 3, p. 293-300
Data-Driven and Precursor-Group Uncertainty Propagation of Lattice Kinetic Parameters in UAM Benchmark
journal, May 2019
- Radaideh, Majdi I.; Kozlowski, Tomasz; Wieselquist, William A.
- Science and Technology of Nuclear Installations, Vol. 2019
Advanced BWR criticality safety part I: Model development, model benchmarking, and depletion with uncertainty analysis
journal, May 2019
- Radaideh, Majdi I.; Price, Dean; O'Grady, Daniel
- Progress in Nuclear Energy, Vol. 113
A Bayesian approach for quantification of model uncertainty
journal, July 2010
- Park, Inseok; Amarchinta, Hemanth K.; Grandhi, Ramana V.
- Reliability Engineering & System Safety, Vol. 95, Issue 7
Data-driven modeling for boiling heat transfer: using deep neural networks and high-fidelity simulation results
text, January 2018
- Liu, Yang; Dinh, Nam; Sato, Yohei
- arXiv
Verification, validation, and predictive capability in computational engineering and physics
journal, September 2004
- Oberkampf, William L.; Trucano, Timothy G.; Hirsch, Charles
- Applied Mechanics Reviews, Vol. 57, Issue 5
Data-driven modeling for boiling heat transfer: Using deep neural networks and high-fidelity simulation results
journal, November 2018
- Liu, Yang; Dinh, Nam; Sato, Yohei
- Applied Thermal Engineering, Vol. 144
Inverse Uncertainty Quantification using the Modular Bayesian Approach based on Gaussian Process, Part 1: Theory
text, January 2018
- Wu, Xu; Kozlowski, Tomasz; Meidani, Hadi
- arXiv
Verification and validation of simulation models
journal, February 2013
- Sargent, R. G.
- Journal of Simulation, Vol. 7, Issue 1
Thermal-Hydraulic System Codes in Nulcear Reactor Safety and Qualification Procedures
journal, January 2008
- Petruzzi, Alessandro; D'Auria, Francesco
- Science and Technology of Nuclear Installations, Vol. 2008
Inverse Uncertainty Quantification using the Modular Bayesian Approach based on Gaussian Process, Part 2: Application to TRACE
text, January 2018
- Wu, Xu; Kozlowski, Tomasz; Meidani, Hadi
- arXiv
Modern Nuclear Data Evaluation with the TALYS Code System
journal, December 2012
- Koning, A. J.; Rochman, D.
- Nuclear Data Sheets, Vol. 113, Issue 12
Inverse uncertainty quantification using the modular Bayesian approach based on Gaussian process, Part 1: Theory
journal, August 2018
- Wu, Xu; Kozlowski, Tomasz; Meidani, Hadi
- Nuclear Engineering and Design, Vol. 335
Inverse uncertainty quantification using the modular Bayesian approach based on Gaussian Process, Part 2: Application to TRACE
journal, August 2018
- Wu, Xu; Kozlowski, Tomasz; Meidani, Hadi
- Nuclear Engineering and Design, Vol. 335
Review of Metamodeling Techniques in Support of Engineering Design Optimization
journal, May 2006
- Wang, G. Gary; Shan, S.
- Journal of Mechanical Design, Vol. 129, Issue 4
Efficient Subspace Methods-Based Algorithms for Performing Sensitivity, Uncertainty, and Adaptive Simulation of Large-Scale Computational Models
journal, July 2008
- Abdel-Khalik, Hany S.; Turinsky, Paul J.; Jessee, Matthew A.
- Nuclear Science and Engineering, Vol. 159, Issue 3
The Serpent Monte Carlo Code: Status, Development and Applications in 2013
conference, June 2014
- Leppänen, Jaakko; Pusa, Maria; Viitanen, Tuomas
- SNA + MC 2013 - Joint International Conference on Supercomputing in Nuclear Applications + Monte Carlo
Use of Kriging Models to Approximate Deterministic Computer Models
journal, April 2005
- Martin, Jay D.; Simpson, Timothy W.
- AIAA Journal, Vol. 43, Issue 4
Shapley effect application for variance-based sensitivity analysis of the few-group cross-sections
journal, July 2019
- Radaideh, Majdi I.; Surani, Stuti; O’Grady, Daniel
- Annals of Nuclear Energy, Vol. 129
Delayed-Neutron Data for Reactor-Physics Analysis
journal, January 1975
- Tuttle, R. J.
- Nuclear Science and Engineering, Vol. 56, Issue 1
Nuclide Composition Benchmark Data Set for Verifying Burnup Codes on Spent Light Water Reactor Fuels
journal, February 2002
- Nakahara, Yoshinori; Suyama, Kenya; Inagawa, Jun
- Nuclear Technology, Vol. 137, Issue 2
Bayesian calibration of computer models
journal, August 2001
- Kennedy, Marc C.; O'Hagan, Anthony
- Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 63, Issue 3
ENDF/B-VII.1 Nuclear Data for Science and Technology: Cross Sections, Covariances, Fission Product Yields and Decay Data
journal, December 2011
- Chadwick, M. B.; Herman, M.; Obložinský, P.
- Nuclear Data Sheets, Vol. 112, Issue 12
PSI Methodologies for Nuclear Data Uncertainty Propagation with CASMO-5M and MCNPX: Results for OECD/NEA UAM Benchmark Phase I
journal, January 2013
- Wieselquist, W.; Zhu, T.; Vasiliev, A.
- Science and Technology of Nuclear Installations, Vol. 2013
A roe-type numerical solver for the two-phase two-fluid six-equation model with realistic equation of state
journal, January 2018
- Hu, Guojun; Kozlowski, Tomasz
- Nuclear Engineering and Design, Vol. 326
Aleatory or epistemic? Does it matter?
journal, March 2009
- Kiureghian, Armen Der; Ditlevsen, Ove
- Structural Safety, Vol. 31, Issue 2
Delayed Neutrons from Fissionable Isotopes of Uranium, Plutonium, and Thorium
journal, August 1957
- Keepin, G. R.; Wimett, T. F.; Zeigler, R. K.
- Physical Review, Vol. 107, Issue 4
An effective screening design for sensitivity analysis of large models
journal, October 2007
- Campolongo, Francesca; Cariboni, Jessica; Saltelli, Andrea
- Environmental Modelling & Software, Vol. 22, Issue 10
Quantification of model-form and parametric uncertainty using evidence theory
journal, November 2012
- Park, Inseok; Grandhi, Ramana V.
- Structural Safety, Vol. 39
Surrogate-based methods for black-box optimization: Surrogate-based methods for black-box optimization
journal, April 2016
- Vu, Ky Khac; D'Ambrosio, Claudia; Hamadi, Youssef
- International Transactions in Operational Research, Vol. 24, Issue 3
A new framework for sampling-based uncertainty quantification of the six-group reactor kinetic parameters
journal, May 2019
- Radaideh, Majdi I.; Wieselquist, William A.; Kozlowski, Tomasz
- Annals of Nuclear Energy, Vol. 127
Gaussian Processes in Machine Learning
book, January 2004
- Rasmussen, Carl Edward
- Advanced Lectures on Machine Learning
Nuclear Data Uncertainty Quantification: Past, Present and Future
journal, January 2015
- Smith, D. L.
- Nuclear Data Sheets, Vol. 123
Deep learning in neural networks: An overview
journal, January 2015
- Schmidhuber, Jürgen
- Neural Networks, Vol. 61
Design optimization under uncertainty of hybrid fuel cell energy systems for power generation and cooling purposes
journal, January 2020
- Radaideh, Majdi I.; Radaideh, Mohammed I.; Kozlowski, Tomasz
- International Journal of Hydrogen Energy, Vol. 45, Issue 3
A machine learning approach for efficient uncertainty quantification using multiscale methods
journal, February 2018
- Chan, Shing; Elsheikh, Ahmed H.
- Journal of Computational Physics, Vol. 354
Uncertainty quantification and sensitivity analysis with CASL Core Simulator VERA-CS
journal, September 2016
- Brown, C. S.; Zhang, Hongbin
- Annals of Nuclear Energy, Vol. 95
Verification and Validation of Simulation Models
conference, January 2005
- Sargent, R. G.
- Proceedings of the Winter Simulation Conference, 2005.
A machine learning approach for efficient uncertainty quantification using multiscale methods
text, January 2017
- Chan, Shing; Elsheikh, Ahmed H.
- arXiv