본문 바로가기

Development of an artificial neural network model for generating macroscopic cross-sections for RAST-AI

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q2Scopus Q2
저널
ANNALS OF NUCLEAR ENERGY186 · #109777 · 2023
피인용
Web of Science 10Scopus 12
FWCI (Scopus)
1.18
JCR IF
JCR 2022 1.9
ISSN
0306-4549

저자

  1. Dzianisau, Siarhei제1저자Ulsan Natl Inst Sci & Technol, Dept Nucl Engn, 50 UNIST Gil, Ulsan 44919, South Korea
  2. Saeju, KorawitUlsan Natl Inst Sci & Technol, Dept Nucl Engn, 50 UNIST Gil, Ulsan 44919, South Korea
  3. 이현철Pusan Natl Univ, Sch Mech Engn, 2,Busandaehak ro 63beon Gil, Pusan 46241, South Korea
  4. Lee, Deokjung교신저자Ulsan Natl Inst Sci & Technol, Dept Nucl Engn, 50 UNIST Gil, Ulsan 44919, South Korea

초록

Homogenized macroscopic cross-sections (XS) are necessary for running core-wise nodal diffusion calculations. XS sets are usually generated using time-consuming lattice physics codes. In this study, a pre-trained artificial neural network was developed and used for XS generation. The model was trained to produce macroscopic XS, pin powers, and assembly discontinuity factors for 16 x 16 and 17 x 17 fuel assembly types with independent variable enrichments of each fuel pin loaded with fresh UO2 fuel without burnable poisons. The training dataset optimization method was described and used for defining the required number of variations in input parameters, such as pin arrangements and thermal hydraulics parameters. The optimized dataset's generation took only 248 core-hours, which is below 3 days on a modern 4-core CPU. For the worst-case out-of-range testing data, the maximum observed difference with the reference was found below 3% for pin powers, and below 4.5% for XS values.

키워드

Artificial neural networkCross-sectionPin powerNuclear engineeringNEUTRON-TRANSPORTVALIDATION

식별자

Scopus EID
2-s2.0-85149369484
WoS UID
000954824900001