Real-time virtual circuits for plasma shape control via neural network emulators: experimental demonstration on MAST Upgrade
Abstract
Conventional plasma shape control in tokamaks relies on virtual circuits (VCs) that are computed offline from linearisations around a small, tailored number of reference equilibria, and deployed as expertly prepared schedules during the discharge. Here, we report on the first experimental deployment of real-time VCs. We replace pre-set look up tables with VCs updated in real time using surrogates of the plasma response. Both the existing control architecture and the interpretability of VC-based control are retained. Previous work showed that neural network emulators can produce accurate VCs, and validated their performance in closed-loop shape control simulations. Here, we report their first experimental validation on MAST Upgrade (MAST-U). Dedicated experiments spanning different scenarios, including prescribed shape perturbations, feedback-driven divertor-leg motion, and strongly evolving plasma configurations, show that real-time VCs can realise plasma shape control tasks within the MAST-U plasma control system. These results establish the experimental feasibility of real-time linearisations as a practical extension of conventional plasma shape control in tokamaks. The present implementation demonstrates a central step towards a simpler control workflow, in which manually constructed, phased VC schedules are replaced by VCs generated automatically online from a trained surrogate model, without scenario-specific retraining.
Related
- Real-time virtual circuits for plasma shape control via neural network emulators
- Identification of effective transport physics and optimal feedback control: Experimental demonstration on a 1600-fan wind generator
- Experimental Demonstration of Autonomous Class Aware Optimization via Digital Twin Aided Optical Network Agent
- Experimental demonstration of finite-size general security via discrete-modulated CVQKD with real time postprocessing
- Experimental Demonstration of 7-Dimensional N-Vector Model with Dimensional Inflation and Annealing
BibTeX
@misc{amorisco2026realtime,
title = {{Real-time virtual circuits for plasma shape control via neural network emulators: experimental demonstration on MAST Upgrade}},
author = {Nicola C. Amorisco and Kamran Pentland and Adriano Agnello and George K. Holt and Alasdair Ross and Matthew J. Marshall and Edward Jones and Graham J. McArdle and Charles Vincent and Timothy Nunn and Martin Kochan and Pedro Cavestany and Aran Garrod and Stanislas Pamela and James Buchanan},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.28468},
eprint = {2608.28468},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.28468},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Real-time virtual circuits for plasma shape control via neural network emulators: experimental demonstration on MAST Upgrade
AU - Nicola C. Amorisco
AU - Kamran Pentland
AU - Adriano Agnello
AU - George K. Holt
AU - Alasdair Ross
AU - Matthew J. Marshall
AU - Edward Jones
AU - Graham J. McArdle
AU - Charles Vincent
AU - Timothy Nunn
AU - Martin Kochan
AU - Pedro Cavestany
AU - Aran Garrod
AU - Stanislas Pamela
AU - James Buchanan
PY - 2026
DA - 2026/08/28
PB - arXiv
DO - 10.48550/arxiv.2608.28468
UR - https://arxiv.org/abs/2608.28468
AB - Conventional plasma shape control in tokamaks relies on virtual circuits (VCs) that are computed offline from linearisations around a small, tailored number of reference equilibria, and deployed as expertly prepared schedules during the discharge. Here, we report on the first experimental deployment of real-time VCs. We replace pre-set look up tables with VCs updated in real time using surrogates of the plasma response. Both the existing control architecture and the interpretability of VC-based control are retained. Previous work showed that neural network emulators can produce accurate VCs, and validated their performance in closed-loop shape control simulations. Here, we report their first experimental validation on MAST Upgrade (MAST-U). Dedicated experiments spanning different scenarios, including prescribed shape perturbations, feedback-driven divertor-leg motion, and strongly evolving plasma configurations, show that real-time VCs can realise plasma shape control tasks within the MAST-U plasma control system. These results establish the experimental feasibility of real-time linearisations as a practical extension of conventional plasma shape control in tokamaks. The present implementation demonstrates a central step towards a simpler control workflow, in which manually constructed, phased VC schedules are replaced by VCs generated automatically online from a trained surrogate model, without scenario-specific retraining.
ER -