서브메뉴
검색
AI-Based Prediction and Control of Tokamaks: Combining Simulations and Experimental Data
AI-Based Prediction and Control of Tokamaks: Combining Simulations and Experimental Data
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151030
- ISBN
- 9798382806853
- DDC
- 530
- 서명/저자
- AI-Based Prediction and Control of Tokamaks: Combining Simulations and Experimental Data
- 발행사항
- [Sl] : Princeton University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 138 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
- 주기사항
- Advisor: Kolemen, Egemen.
- 학위논문주기
- Thesis (Ph.D.)--Princeton University, 2024.
- 초록/해제
- 요약A unified AI (artificial intelligence) approach to predict and control the dynamics of kinetic plasma profiles in fusion reactors is presented. On one hand, it is demonstrated that empirical models trained on experimental data ("data-driven models") significantly outperform the state-of-the-art ASTRA and TRANSP codes ("simulations") when predicting within the distribution of the training set. On the other hand, it is demonstrated that simulations can perform as well or better than data-driven models when extrapolating outside of the training distribution. Multiple AI-based methodologies for combining the data-driven models and simulations, leveraging data from multiple machines (DIII-D and AUG), are presented. One of the methodologies better extrapolates to new regimes than either data-driven models or simulations alone. Applications of the holistic approach to the task of commissioning a new reactor such as ITER are discussed. A successful model-predictive control test at DIII-D based on the methodology is described.
- 일반주제명
- Plasma physics
- 일반주제명
- Mechanical engineering
- 일반주제명
- Astrophysics
- 키워드
- Control test
- 키워드
- Fusion reactors
- 키워드
- Plasma profiles
- 키워드
- Prediction
- 키워드
- Tokamak
- 기타저자
- Princeton University Astrophysical Sciences-Plasma Physics Program
- 기본자료저록
- Dissertations Abstracts International. 85-12B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017160497
■00520250211151030
■006m o d
■007cr#unu||||||||
■020 ▼a9798382806853
■035 ▼a(MiAaPQ)AAI30997202
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a530
■1001 ▼aAbbate, Joseph Albert.▼0(orcid)0000-0002-5463-6552
■24510▼aAI-Based Prediction and Control of Tokamaks: Combining Simulations and Experimental Data
■260 ▼a[Sl]▼bPrinceton University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a138 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-12, Section: B.
■500 ▼aAdvisor: Kolemen, Egemen.
■5021 ▼aThesis (Ph.D.)--Princeton University, 2024.
■520 ▼aA unified AI (artificial intelligence) approach to predict and control the dynamics of kinetic plasma profiles in fusion reactors is presented. On one hand, it is demonstrated that empirical models trained on experimental data ("data-driven models") significantly outperform the state-of-the-art ASTRA and TRANSP codes ("simulations") when predicting within the distribution of the training set. On the other hand, it is demonstrated that simulations can perform as well or better than data-driven models when extrapolating outside of the training distribution. Multiple AI-based methodologies for combining the data-driven models and simulations, leveraging data from multiple machines (DIII-D and AUG), are presented. One of the methodologies better extrapolates to new regimes than either data-driven models or simulations alone. Applications of the holistic approach to the task of commissioning a new reactor such as ITER are discussed. A successful model-predictive control test at DIII-D based on the methodology is described.
■590 ▼aSchool code: 0181.
■650 4▼aPlasma physics
■650 4▼aMechanical engineering
■650 4▼aAstrophysics
■653 ▼aData-driven models
■653 ▼aControl test
■653 ▼aFusion reactors
■653 ▼aPlasma profiles
■653 ▼aPrediction
■653 ▼aTokamak
■653 ▼aAI-based methodologies
■690 ▼a0759
■690 ▼a0800
■690 ▼a0548
■690 ▼a0596
■71020▼aPrinceton University▼bAstrophysical Sciences-Plasma Physics Program.
■7730 ▼tDissertations Abstracts International▼g85-12B.
■790 ▼a0181
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160497▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
