1
|
Oktavian M, Nistor J, Gruenwald J, Xu Y. Preliminary development of machine learning-based error correction model for low-fidelity reactor physics simulation. ANN NUCL ENERGY 2023. [DOI: 10.1016/j.anucene.2023.109788] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
|
2
|
Dzianisau S, Saeju K, Lee HC, Lee D. Development of an artificial neural network model for generating macroscopic cross-sections for RAST-AI. ANN NUCL ENERGY 2023. [DOI: 10.1016/j.anucene.2023.109777] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
|
3
|
Lilley B, Palmer TS. Core Reload Design Using Genetic Optimization for Cost Savings in a Two-Reactor Power Plant With Used Fuel Sharing. NUCL SCI ENG 2023. [DOI: 10.1080/00295639.2023.2171273] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/31/2023]
|
4
|
Andersen B, Kropaczek DJ. MOOGLE: A Multi-Objective Optimization tool for three-dimensional nuclear fuel assembly design. PROGRESS IN NUCLEAR ENERGY 2023. [DOI: 10.1016/j.pnucene.2022.104518] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
|
5
|
Gu X, Radaideh MI, Liang J. OpenNeoMC: A framework for design optimization in particle transport simulations based on OpenMC and NEORL. ANN NUCL ENERGY 2023. [DOI: 10.1016/j.anucene.2022.109450] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
6
|
Price D, Radaideh MI, Kochunas B. Multiobjective optimization of nuclear microreactor reactivity control system operation with swarm and evolutionary algorithms. NUCLEAR ENGINEERING AND DESIGN 2022. [DOI: 10.1016/j.nucengdes.2022.111776] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
7
|
Che Y, Yurko J, Seurin P, Shirvan K. Machine learning-assisted surrogate construction for full-core fuel performance analysis. ANN NUCL ENERGY 2022. [DOI: 10.1016/j.anucene.2021.108905] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/01/2022]
|
8
|
Liu Y, Hu R, Kraus A, Balaprakash P, Obabko A. Data-driven modeling of coarse mesh turbulence for reactor transient analysis using convolutional recurrent neural networks. NUCLEAR ENGINEERING AND DESIGN 2022. [DOI: 10.1016/j.nucengdes.2022.111716] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|
9
|
Beeler C, Yahorau U, Coles R, Mills K, Whitelam S, Tamblyn I. Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning. Phys Rev E 2022; 104:064128. [PMID: 35030917 DOI: 10.1103/physreve.104.064128] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2021] [Accepted: 11/24/2021] [Indexed: 11/07/2022]
Abstract
Using a model heat engine, we show that neural-network-based reinforcement learning can identify thermodynamic trajectories of maximal efficiency. We consider both gradient and gradient-free reinforcement learning. We use an evolutionary learning algorithm to evolve a population of neural networks, subject to a directive to maximize the efficiency of a trajectory composed of a set of elementary thermodynamic processes; the resulting networks learn to carry out the maximally efficient Carnot, Stirling, or Otto cycles. When given an additional irreversible process, this evolutionary scheme learns a previously unknown thermodynamic cycle. Gradient-based reinforcement learning is able to learn the Stirling cycle, whereas an evolutionary approach achieves the optimal Carnot cycle. Our results show how the reinforcement learning strategies developed for game playing can be applied to solve physical problems conditioned upon path-extensive order parameters.
Collapse
Affiliation(s)
- Chris Beeler
- Department of Mathematics and Statistics, University of Ottawa, Ottawa, Ontario, Canada K1N 6N5.,National Research Council of Canada, Ottawa, Ontario, Canada K1A 0R6
| | - Uladzimir Yahorau
- Department of Physics, University of Ontario Institute of Technology, Oshawa, Ontario, Canada L1G 0C5
| | - Rory Coles
- Department of Physics and Astronomy, University of Victoria, Victoria, British Columbia, Canada V8P 5C2
| | - Kyle Mills
- Department of Physics, University of Ontario Institute of Technology, Oshawa, Ontario, Canada L1G 0C5.,Vector Institute for Artificial Intelligence, Toronto, Ontario, Canada M5G 1M1
| | - Stephen Whitelam
- Molecular Foundry, Lawrence Berkeley National Laboratory, Berkeley, California 94720, USA
| | - Isaac Tamblyn
- Department of Physics, University of Ontario Institute of Technology, Oshawa, Ontario, Canada L1G 0C5.,Vector Institute for Artificial Intelligence, Toronto, Ontario, Canada M5G 1M1.,Department of Physics, University of Ottawa, Ottawa, Ontario, Canada K1N 6N5
| |
Collapse
|
10
|
Machalek D, Quah T, Powell KM. A novel implicit hybrid machine learning model and its application for reinforcement learning. Comput Chem Eng 2021. [DOI: 10.1016/j.compchemeng.2021.107496] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
11
|
Pevey J, Hiscox B, Williams A, Chvála O, Sobes V, Hines JW. Gradient-Informed Design Optimization of Select Nuclear Systems. NUCL SCI ENG 2021. [DOI: 10.1080/00295639.2021.1987133] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Affiliation(s)
- John Pevey
- University of Tennessee, Department of Nuclear Engineering, Knoxville, Tennessee
| | - Briana Hiscox
- Oak Ridge National Laboratory, Reactor and Nuclear Systems Division, Oak Ridge, Tennessee
| | - Austin Williams
- University of Tennessee, Department of Nuclear Engineering, Knoxville, Tennessee
| | - Ondřej Chvála
- University of Tennessee, Department of Nuclear Engineering, Knoxville, Tennessee
| | - Vladimir Sobes
- University of Tennessee, Department of Nuclear Engineering, Knoxville, Tennessee
| | - J. Wesley Hines
- University of Tennessee, Department of Nuclear Engineering, Knoxville, Tennessee
| |
Collapse
|
12
|
Ortiz-Servin JJ, Pelta DA, Cadenas JM, Castillo A. A new methodology to speed-up fuel lattice design optimization using decision trees and new objective functions. ANN NUCL ENERGY 2021. [DOI: 10.1016/j.anucene.2021.108445] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|