Uncertainty Quantification and Sensitivity Analysis for Digital Twin Enabling Technology: Application for BISON Fuel Performance Code

Kazuma Kobayashi; Dinesh Kuma; Matthew Bonney; Souvik Chakraborty; Kyle Paaren; Shoaib Usman; Syed Alam

doi:10.1007/978-3-030-97940-9_205

Uncertainty Quantification and Sensitivity Analysis for Digital Twin Enabling Technology: Application for BISON Fuel Performance Code

Kazuma Kobayashi, Dinesh Kuma, Matthew Bonney, Souvik Chakraborty, Kyle Paaren, Shoaib Usman, Syed Alam

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

Abstract

As US Nuclear Regulatory Committee (NRC) recently announced machine learning (ML) and artificial intelligence (AI) will be the main research topics in the nuclear industry. One of the applications is the development of new nuclear fuels using digital twin technology, in which machine learning-based data analysis methods will significantly contribute to accelerate developments. This chapter introduces the ML-based uncertainty quantification and sensitivity analysis methods and shows its actual application to nuclear fuel development codes: a finite element-based nuclear fuel performance code BISON.

Original language	English (US)
Title of host publication	Handbook of Smart Energy Systems
Subtitle of host publication	Volume 1-4
Publisher	Springer
Pages	2265-2277
Number of pages	13
Volume	1-4
ISBN (Electronic)	9783030979409
ISBN (Print)	9783030979393
DOIs	https://doi.org/10.1007/978-3-030-97940-9_205
State	Published - Jan 1 2023
Externally published	Yes

Keywords

BISON
Fuel performance code
Machine Learning
Nuclear power system
Sensitivity analysis
Uncertainty quantification

ASJC Scopus subject areas

General Economics, Econometrics and Finance
General Business, Management and Accounting
General Mathematics
General Environmental Science
General Energy
General Engineering

Online availability

10.1007/978-3-030-97940-9_205

Library availability

Discover UIUC Full Text

Cite this

@inbook{a0a9d2c8b2df49d4afb7b06c6609b986,

title = "Uncertainty Quantification and Sensitivity Analysis for Digital Twin Enabling Technology: Application for BISON Fuel Performance Code",

abstract = "As US Nuclear Regulatory Committee (NRC) recently announced machine learning (ML) and artificial intelligence (AI) will be the main research topics in the nuclear industry. One of the applications is the development of new nuclear fuels using digital twin technology, in which machine learning-based data analysis methods will significantly contribute to accelerate developments. This chapter introduces the ML-based uncertainty quantification and sensitivity analysis methods and shows its actual application to nuclear fuel development codes: a finite element-based nuclear fuel performance code BISON.",

keywords = "BISON, Fuel performance code, Machine Learning, Nuclear power system, Sensitivity analysis, Uncertainty quantification",

author = "Kazuma Kobayashi and Dinesh Kuma and Matthew Bonney and Souvik Chakraborty and Kyle Paaren and Shoaib Usman and Syed Alam",

note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2023.",

year = "2023",

month = jan,

day = "1",

doi = "10.1007/978-3-030-97940-9_205",

language = "English (US)",

isbn = "9783030979393",

volume = "1-4",

pages = "2265--2277",

booktitle = "Handbook of Smart Energy Systems",

publisher = "Springer",

address = "Germany",

}

TY - CHAP

T1 - Uncertainty Quantification and Sensitivity Analysis for Digital Twin Enabling Technology

T2 - Application for BISON Fuel Performance Code

AU - Kobayashi, Kazuma

AU - Kuma, Dinesh

AU - Bonney, Matthew

AU - Chakraborty, Souvik

AU - Paaren, Kyle

AU - Usman, Shoaib

AU - Alam, Syed

N1 - Publisher Copyright: © Springer Nature Switzerland AG 2023.

PY - 2023/1/1

Y1 - 2023/1/1

N2 - As US Nuclear Regulatory Committee (NRC) recently announced machine learning (ML) and artificial intelligence (AI) will be the main research topics in the nuclear industry. One of the applications is the development of new nuclear fuels using digital twin technology, in which machine learning-based data analysis methods will significantly contribute to accelerate developments. This chapter introduces the ML-based uncertainty quantification and sensitivity analysis methods and shows its actual application to nuclear fuel development codes: a finite element-based nuclear fuel performance code BISON.

AB - As US Nuclear Regulatory Committee (NRC) recently announced machine learning (ML) and artificial intelligence (AI) will be the main research topics in the nuclear industry. One of the applications is the development of new nuclear fuels using digital twin technology, in which machine learning-based data analysis methods will significantly contribute to accelerate developments. This chapter introduces the ML-based uncertainty quantification and sensitivity analysis methods and shows its actual application to nuclear fuel development codes: a finite element-based nuclear fuel performance code BISON.

KW - BISON

KW - Fuel performance code

KW - Machine Learning

KW - Nuclear power system

KW - Sensitivity analysis

KW - Uncertainty quantification

UR - http://www.scopus.com/inward/record.url?scp=85208347956&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85208347956&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-97940-9_205

DO - 10.1007/978-3-030-97940-9_205

M3 - Chapter

AN - SCOPUS:85208347956

SN - 9783030979393

VL - 1-4

SP - 2265

EP - 2277

BT - Handbook of Smart Energy Systems

PB - Springer

ER -

Uncertainty Quantification and Sensitivity Analysis for Digital Twin Enabling Technology: Application for BISON Fuel Performance Code

Abstract

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this