Learning Plasma Dynamics and Robust Rampdown Trajectories with Predict-First Experiments at TCV

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Allen M., Pau, Alessandro, Rea, Cristina, So, Oswin, Dawson, Charles, Sauter, Olivier, Boyer, Mark D., Vu, Anna, Galperti, Cristian, Fan, Chuchu, Merle, Antoine, Poels, Yoeri, Venturini, Cristina, Marchioni, Stefano, Team, the TCV
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915422708695040
author Wang, Allen M.
Pau, Alessandro
Rea, Cristina
So, Oswin
Dawson, Charles
Sauter, Olivier
Boyer, Mark D.
Vu, Anna
Galperti, Cristian
Fan, Chuchu
Merle, Antoine
Poels, Yoeri
Venturini, Cristina
Marchioni, Stefano
Team, the TCV
author_facet Wang, Allen M.
Pau, Alessandro
Rea, Cristina
So, Oswin
Dawson, Charles
Sauter, Olivier
Boyer, Mark D.
Vu, Anna
Galperti, Cristian
Fan, Chuchu
Merle, Antoine
Poels, Yoeri
Venturini, Cristina
Marchioni, Stefano
Team, the TCV
contents The rampdown phase of a tokamak pulse is difficult to simulate and often exacerbates multiple plasma instabilities. To reduce the risk of disrupting operations, we leverage advances in Scientific Machine Learning (SciML) to combine physics with data-driven models, developing a neural state-space model (NSSM) that predicts plasma dynamics during Tokamak à Configuration Variable (TCV) rampdowns. The NSSM efficiently learns dynamics from a modest dataset of 311 pulses with only five pulses in a reactor-relevant high-performance regime. The NSSM is parallelized across uncertainties, and reinforcement learning (RL) is applied to design trajectories that avoid instability limits. High-performance experiments at TCV show statistically significant improvements in relevant metrics. A predict-first experiment, increasing plasma current by 20% from baseline, demonstrates the NSSM's ability to make small extrapolations. The developed approach paves the way for designing tokamak controls with robustness to considerable uncertainty and demonstrates the relevance of SciML for fusion experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12327
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Plasma Dynamics and Robust Rampdown Trajectories with Predict-First Experiments at TCV
Wang, Allen M.
Pau, Alessandro
Rea, Cristina
So, Oswin
Dawson, Charles
Sauter, Olivier
Boyer, Mark D.
Vu, Anna
Galperti, Cristian
Fan, Chuchu
Merle, Antoine
Poels, Yoeri
Venturini, Cristina
Marchioni, Stefano
Team, the TCV
Plasma Physics
Artificial Intelligence
Machine Learning
Systems and Control
The rampdown phase of a tokamak pulse is difficult to simulate and often exacerbates multiple plasma instabilities. To reduce the risk of disrupting operations, we leverage advances in Scientific Machine Learning (SciML) to combine physics with data-driven models, developing a neural state-space model (NSSM) that predicts plasma dynamics during Tokamak à Configuration Variable (TCV) rampdowns. The NSSM efficiently learns dynamics from a modest dataset of 311 pulses with only five pulses in a reactor-relevant high-performance regime. The NSSM is parallelized across uncertainties, and reinforcement learning (RL) is applied to design trajectories that avoid instability limits. High-performance experiments at TCV show statistically significant improvements in relevant metrics. A predict-first experiment, increasing plasma current by 20% from baseline, demonstrates the NSSM's ability to make small extrapolations. The developed approach paves the way for designing tokamak controls with robustness to considerable uncertainty and demonstrates the relevance of SciML for fusion experiments.
title Learning Plasma Dynamics and Robust Rampdown Trajectories with Predict-First Experiments at TCV
topic Plasma Physics
Artificial Intelligence
Machine Learning
Systems and Control
url https://arxiv.org/abs/2502.12327