7 papers
Real-time virtual circuits for plasma shape control via neural network emulators: dynamic validation in closed-loop simulations
K. Pentland, A. Ross, N. C. Amorisco +5
Reliable confinement and stable performance of tokamak fusion plasmas require accurate real-time magnetic shape control. A promising route to reduced latency and increased flexibil…
Real-time virtual circuits for plasma shape control via neural network emulators
Alasdair Ross, George K. Holt, Kamran Pentland +7
Reliable position and shape control in tokamak plasmas requires accurate real-time regulation of several strongly coupled shape parameters. The control vectors that disentangle the…
The FreeGSNKE Pulse Design Tool (FPDT): a computational framework for evolutive plasma scenario and control design
K. Pentland, N. C. Amorisco, A. Ross +8
We present the FreeGSNKE Pulse Design Tool (FPDT), an open-source, Python-based computational framework that enables in silico testing and predictive design of tokamak plasma scena…
TokaMark: A Comprehensive Benchmark for MAST Tokamak Plasma Models
Cécile Rousseau, Samuel Jackson, Rodrigo H. Ordonez-Hurtado +13
Development and operation of commercially viable fusion energy reactors such as tokamaks require accurate predictions of plasma dynamics from sparse, noisy, and incomplete sensors…
TokaMind: A Multi-Modal Transformer Foundation Model for Tokamak Plasma Dynamics
Tobia Boschi, Andrea Loreti, Nicola C. Amorisco +13
We present TokaMind, to our knowledge the first open-source foundation model for tokamak plasma dynamics, based on a Multi-Modal Transformer (MMT) and pretrained on heterogeneous d…
Real-Time Applicability of Emulated Virtual Circuits for Tokamak Plasma Shape Control
Pedro Cavestany, Alasdair Ross, Adriano Agnello +5
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 quantif…