Artificial Intelligence/Deep Learning FRNN Software for Prediction & Real-Time Control of DIII-D Plasma Control System (PCS)

Lin, Zhihong Lin · 2025

Read Artificial Intelligence/Deep Learning FRNN Software for Prediction & Real-Time Control of DIII-D Plasma Control System (PCS) by Lin, Zhihong Lin (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/doe-osti-2588687-artificial-intelligence-deep-learning-fr.txt.

Description

Zhihong Lin of the University of California, Irvine, led this final report for award DE-SC0023640, covering September 2022 through August 2025. The project integrated FRNN, an artificial intelligence and deep learning prediction and control package, into the real-time plasma control system of the DIII-D tokamak.

The hard problem is speed. First-principles instability analysis is too slow for real-time control, so the team built a surrogate. Their SGTC code, derived from the global gyrokinetic code GTC, supplies detailed instability physics. Deep learning models train on it to form a synthetic plasma simulator fast enough to run inside the control loop. Measured signals such as electron cyclotron emission imaging feed the system, supplemented by synthetic SGTC data. Published results include deep learning reconstruction of the tokamak safety factor profile. Fusion transfer learning also rebuilt nonlinear kink mode structures from limited simulation data.

Catalog record

CREATORLin, Zhihong Lin
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE10 KB
LICENSEPublic Domain
RIGHTSPUBLIC DOMAIN
SOURCEDOE OSTI

Source: https://www.osti.gov/biblio/2588687

Browse the full library · About the Tower of Babel