東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

AI-Based Prediction and Control of T...

Abbate, Joseph Albert.

Linked to FindBook

Google Book

Amazon

博客來

AI-Based Prediction and Control of Tokamaks: Combining Simulations and Experimental Data.

Record Type:	Electronic resources : Monograph/item
Title/Author:	AI-Based Prediction and Control of Tokamaks: Combining Simulations and Experimental Data./
Author:	Abbate, Joseph Albert.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2024,
Description:	138 p.
Notes:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
Subject:	Plasma physics. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30997202
ISBN:	9798382806853

AI-Based Prediction and Control of Tokamaks: Combining Simulations and Experimental Data.
Abbate, Joseph Albert.

AI-Based Prediction and Control of Tokamaks: Combining Simulations and Experimental Data. - Ann Arbor : ProQuest Dissertations & Theses, 2024 - 138 p.

Source: Dissertations Abstracts International, Volume: 85-12, Section: B.

Thesis (Ph.D.)--Princeton University, 2024.

A 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.

ISBN: 9798382806853Subjects--Topical Terms:

3175417
Plasma physics.
Subjects--Index Terms:

Data-driven models

AI-Based Prediction and Control of Tokamaks: Combining Simulations and Experimental Data.
LDR:02270nmm a2200421 4500 001 2402950
005 20241104055826.5
006 m o d
007 cr#unu||||||||
008 251215s2024 ||||||||||||||||| ||eng d
020 $a 9798382806853
035 $a (MiAaPQ)AAI30997202
035 $a AAI30997202
040 $a MiAaPQ $c MiAaPQ
100 1 $a Abbate, Joseph Albert. $0 (orcid)0000-0002-5463-6552 $3 3773209
245 1 0 $a AI-Based Prediction and Control of Tokamaks: Combining Simulations and Experimental Data.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 138 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
500 $a Advisor: Kolemen, Egemen.
502 $a Thesis (Ph.D.)--Princeton University, 2024.
520 $a A 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 $a School code: 0181.
650 4 $a Plasma physics. $3 3175417
650 4 $a Mechanical engineering. $3 649730
650 4 $a Astrophysics. $3 535904
653 $a Data-driven models
653 $a Control test
653 $a Fusion reactors
653 $a Plasma profiles
653 $a Prediction
653 $a Tokamak
653 $a AI-based methodologies
690 $a 0759
690 $a 0800
690 $a 0548
690 $a 0596
710 2 $a Princeton University. $b Astrophysical Sciences-Plasma Physics Program. $3 3437719
773 0 $t Dissertations Abstracts International $g 85-12B.
790 $a 0181
791 $a Ph.D.
792 $a 2024
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30997202