Real-Time Applicability of Emulated Virtual Circuits for Tokamak Plasma Shape Control

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cavestany, Pedro, Ross, Alasdair, Agnello, Adriano, Garrod, Aran, Amorisco, Nicola C., Holt, George K., Pentland, Kamran, Buchanan, James
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911133511712768
author Cavestany, Pedro
Ross, Alasdair
Agnello, Adriano
Garrod, Aran
Amorisco, Nicola C.
Holt, George K.
Pentland, Kamran
Buchanan, James
author_facet Cavestany, Pedro
Ross, Alasdair
Agnello, Adriano
Garrod, Aran
Amorisco, Nicola C.
Holt, George K.
Pentland, Kamran
Buchanan, James
contents Machine learning has recently been adopted to emulate sensitivity matrices for real-time magnetic control of tokamak plasmas. However, these approaches would benefit from a quantification of possible inaccuracies. We report on two aspects of real-time applicability of emulators. First, we quantify the agreement of target displacement from VCs computed via Jacobians of the shape emulators with those from finite differences Jacobians on exact Grad-Shafranov solutions. Good agreement ($\approx$5-10%) can be achieved on a selection of geometric targets using combinations of neural network emulators with $\approx10^5$ parameters. A sample of $\approx10^{5}-10^{6}$ synthetic equilibria is essential to train emulators that are not over-regularised or overfitting. Smaller models trained on the shape targets may be further fine-tuned to better fit the Jacobians. Second, we address the effect of vessel currents that are not directly measured in real-time and are typically subsumed into effective "shaping currents" when designing virtual circuits. We demonstrate that shaping currents can be inferred via simple linear regression on a trailing window of active coil current measurements with residuals of only a few Ampères, enabling a choice for the most appropriate shaping currents at any point in a shot. While these results are based on historic shot data and simulations tailored to MAST-U, they indicate that emulators with few-millisecond latency can be developed for robust real-time plasma shape control in existing and upcoming tokamaks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_01789
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Real-Time Applicability of Emulated Virtual Circuits for Tokamak Plasma Shape Control
Cavestany, Pedro
Ross, Alasdair
Agnello, Adriano
Garrod, Aran
Amorisco, Nicola C.
Holt, George K.
Pentland, Kamran
Buchanan, James
Plasma Physics
Machine Learning
Systems and Control
Data Analysis, Statistics and Probability
I.2; I.6
Machine learning has recently been adopted to emulate sensitivity matrices for real-time magnetic control of tokamak plasmas. However, these approaches would benefit from a quantification of possible inaccuracies. We report on two aspects of real-time applicability of emulators. First, we quantify the agreement of target displacement from VCs computed via Jacobians of the shape emulators with those from finite differences Jacobians on exact Grad-Shafranov solutions. Good agreement ($\approx$5-10%) can be achieved on a selection of geometric targets using combinations of neural network emulators with $\approx10^5$ parameters. A sample of $\approx10^{5}-10^{6}$ synthetic equilibria is essential to train emulators that are not over-regularised or overfitting. Smaller models trained on the shape targets may be further fine-tuned to better fit the Jacobians. Second, we address the effect of vessel currents that are not directly measured in real-time and are typically subsumed into effective "shaping currents" when designing virtual circuits. We demonstrate that shaping currents can be inferred via simple linear regression on a trailing window of active coil current measurements with residuals of only a few Ampères, enabling a choice for the most appropriate shaping currents at any point in a shot. While these results are based on historic shot data and simulations tailored to MAST-U, they indicate that emulators with few-millisecond latency can be developed for robust real-time plasma shape control in existing and upcoming tokamaks.
title Real-Time Applicability of Emulated Virtual Circuits for Tokamak Plasma Shape Control
topic Plasma Physics
Machine Learning
Systems and Control
Data Analysis, Statistics and Probability
I.2; I.6
url https://arxiv.org/abs/2509.01789