Practical Applications of Gaussian Process with Uncertainty Quantification and Sensitivity Analysis for Digital Twin for Accident-Tolerant Fuel

Kazuma Kobayashi; Dinesh Kumar; Matthew Bonney; Syed Alam

doi:10.1007/978-3-030-72322-4_191-1

Practical Applications of Gaussian Process with Uncertainty Quantification and Sensitivity Analysis for Digital Twin for Accident-Tolerant Fuel

Kazuma Kobayashi, Dinesh Kumar, Matthew Bonney, Syed Alam

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

The application of digital twin (DT) technology to the nuclear field is one of the challenges in the future development of nuclear energy. Possible applications of DT technology in the nuclear field are expected to be very wide: operate commercial nuclear reactors, monitor spent fuel storage and disposal facilities, and develop new nuclear systems. As the US Nuclear Regulatory Committee (NRC) recently announced, machine learning (MI) and artificial intelligence (AI) is a new domain in the nuclear field. This chapter focuses on the DT framework for developing advanced nuclear fuel and explains the utilizations of MI-based surrogate model, Gaussian process (GP) regression, in the framework.

Original language	English (US)
Title of host publication	Handbook of Smart Energy Systems
Editors	Mahdi Fathi, Enrico Zio, Panos M. Pardalos
Publisher	Springer
Chapter	191-1
Pages	1-12
ISBN (Electronic)	978-3-030-72322-4
DOIs	https://doi.org/10.1007/978-3-030-72322-4_191-1
State	Published - Nov 19 2022
Externally published	Yes

Keywords

Machine learning
Nuclear power
Accident tolerant fuel
Modeling methods
Gaussian process
Kriging

Online availability

10.1007/978-3-030-72322-4_191-1

Library availability

Discover UIUC Full Text

Cite this

Practical Applications of Gaussian Process with Uncertainty Quantification and Sensitivity Analysis for Digital Twin for Accident-Tolerant Fuel. / Kobayashi, Kazuma; Kumar, Dinesh; Bonney, Matthew et al.
Handbook of Smart Energy Systems. ed. / Mahdi Fathi; Enrico Zio; Panos M. Pardalos. Springer, 2022. p. 1-12.

Research output: Chapter in Book/Report/Conference proceeding › Chapter

@inbook{3420fe9bb8564a12b47e65395ff0331a,

title = "Practical Applications of Gaussian Process with Uncertainty Quantification and Sensitivity Analysis for Digital Twin for Accident-Tolerant Fuel",

abstract = "The application of digital twin (DT) technology to the nuclear field is one of the challenges in the future development of nuclear energy. Possible applications of DT technology in the nuclear field are expected to be very wide: operate commercial nuclear reactors, monitor spent fuel storage and disposal facilities, and develop new nuclear systems. As the US Nuclear Regulatory Committee (NRC) recently announced, machine learning (MI) and artificial intelligence (AI) is a new domain in the nuclear field. This chapter focuses on the DT framework for developing advanced nuclear fuel and explains the utilizations of MI-based surrogate model, Gaussian process (GP) regression, in the framework.",

keywords = "Machine learning, Nuclear power, Accident tolerant fuel, Modeling methods, Gaussian process, Kriging",

author = "Kazuma Kobayashi and Dinesh Kumar and Matthew Bonney and Syed Alam",

year = "2022",

month = nov,

day = "19",

doi = "10.1007/978-3-030-72322-4_191-1",

language = "English (US)",

pages = "1--12",

editor = "Mahdi Fathi and Enrico Zio and Pardalos, {Panos M.}",

booktitle = "Handbook of Smart Energy Systems",

publisher = "Springer",

address = "Germany",

}

TY - CHAP

T1 - Practical Applications of Gaussian Process with Uncertainty Quantification and Sensitivity Analysis for Digital Twin for Accident-Tolerant Fuel

AU - Kobayashi, Kazuma

AU - Kumar, Dinesh

AU - Bonney, Matthew

AU - Alam, Syed

PY - 2022/11/19

Y1 - 2022/11/19

N2 - The application of digital twin (DT) technology to the nuclear field is one of the challenges in the future development of nuclear energy. Possible applications of DT technology in the nuclear field are expected to be very wide: operate commercial nuclear reactors, monitor spent fuel storage and disposal facilities, and develop new nuclear systems. As the US Nuclear Regulatory Committee (NRC) recently announced, machine learning (MI) and artificial intelligence (AI) is a new domain in the nuclear field. This chapter focuses on the DT framework for developing advanced nuclear fuel and explains the utilizations of MI-based surrogate model, Gaussian process (GP) regression, in the framework.

AB - The application of digital twin (DT) technology to the nuclear field is one of the challenges in the future development of nuclear energy. Possible applications of DT technology in the nuclear field are expected to be very wide: operate commercial nuclear reactors, monitor spent fuel storage and disposal facilities, and develop new nuclear systems. As the US Nuclear Regulatory Committee (NRC) recently announced, machine learning (MI) and artificial intelligence (AI) is a new domain in the nuclear field. This chapter focuses on the DT framework for developing advanced nuclear fuel and explains the utilizations of MI-based surrogate model, Gaussian process (GP) regression, in the framework.

KW - Machine learning

KW - Nuclear power

KW - Accident tolerant fuel

KW - Modeling methods

KW - Gaussian process

KW - Kriging

U2 - 10.1007/978-3-030-72322-4_191-1

DO - 10.1007/978-3-030-72322-4_191-1

M3 - Chapter

SP - 1

EP - 12

BT - Handbook of Smart Energy Systems

A2 - Fathi, Mahdi

A2 - Zio, Enrico

A2 - Pardalos, Panos M.

PB - Springer

ER -

Practical Applications of Gaussian Process with Uncertainty Quantification and Sensitivity Analysis for Digital Twin for Accident-Tolerant Fuel

Abstract

Keywords

Online availability

Library availability

Fingerprint

Cite this