arXiv subjects

Allen M. Wang

Publications and source records attributed to Allen M. Wang.

5 recordsLinked to original sources

arXiv2026

An Inverse Grad-Shafranov Neural Network Approach to Tokamak Magnetic Control

A new approach to tokamak magnetic control enabling high-precision plasma shaping and novel real-time adaptability is experimentally demonstrated on the Tokamak a Configuration Variable (TCV). The method is motivated by the insight that, under appropriate assumptions, a real-time inverse Grad-Shafranov solver approximates an optimal control policy for plasma boundary regulation. Building on this, a control architecture is developed in which classical controllers enforce operational constraints while a fast surrogate model provides a real-time inverse mapping from the desired plasma boundary to Poloidal Field Coil currents. Experimental results on TCV demonstrate improved plasma shaping with respect to the standard discharge preparation procedure --- albeit without explicit real-time shape feedback --- while enabling flexible response to asynchronous events. It is shown that a single network provides satisfactory performance across a range of plasma magnetic configurations. Real-time adaptivity is demonstrated in simulation, and partially in experiment, through adaptive strike point motion and early termination in response to a real-time trigger. These results suggest a viable path toward magnetic control architectures that reduce reliance on dense diagnostic coverage while maintaining high-accuracy plasma shaping, with potential relevance for future fusion power plant operation.

physics.plasm-ph↗

arXiv2025

Technical Aspects of Plasma Operational Simulation (POPSIM): A Framework for Data-Driven Simulation and Control

This paper reports on technical aspects of Plasma Operational Simulation (POPSIM), a research framework for data-driven simulation and control built in the machine learning framework JAX. The objective of the project is to address the extremely challenging simulation and modeling requirements of tokamak operations and control by combining simple principles-based models with data-driven models, spanning everything from power laws to new neural network architectures. This paper reports on key software and operations problems that the framework addresses, with examples from ongoing modeling activities for illustration.

physics.plasm-ph↗

arXiv2025

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

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.

physics.plasm-ph↗

arXiv2024

Active Disruption Avoidance and Trajectory Design for Tokamak Ramp-downs with Neural Differential Equations and Reinforcement Learning

The tokamak offers a promising path to fusion energy, but plasma disruptions pose a major economic risk, motivating considerable advances in disruption avoidance. This work develops a reinforcement learning approach to this problem by training a policy to safely ramp-down the plasma current while avoiding limits on a number of quantities correlated with disruptions. The policy training environment is a hybrid physics and machine learning model trained on simulations of the SPARC primary reference discharge (PRD) ramp-down, an upcoming burning plasma scenario which we use as a testbed. To address physics uncertainty and model inaccuracies, the simulation environment is massively parallelized on GPU with randomized physics parameters during policy training. The trained policy is then successfully transferred to a higher fidelity simulator where it successfully ramps down the plasma while avoiding user-specified disruptive limits. We also address the crucial issue of safety criticality by demonstrating that a constraint-conditioned policy can be used as a trajectory design assistant to design a library of feed-forward trajectories to handle different physics conditions and user settings. As a library of trajectories is more interpretable and verifiable offline, we argue such an approach is a promising path for leveraging the capabilities of reinforcement learning in the safety-critical context of burning plasma tokamaks. Finally, we demonstrate how the training environment can be a useful platform for other feed-forward optimization approaches by using an evolutionary algorithm to perform optimization of feed-forward trajectories that are robust to physics uncertainty

physics.plasm-ph↗

arXiv2023

Hybridizing Physics and Neural ODEs for Predicting Plasma Inductance Dynamics in Tokamak Fusion Reactors

While fusion reactors known as tokamaks hold promise as a firm energy source, advances in plasma control, and handling of events where control of plasmas is lost, are needed for them to be economical. A significant bottleneck towards applying more advanced control algorithms is the need for better plasma simulation, where both physics-based and data-driven approaches currently fall short. The former is bottle-necked by both computational cost and the difficulty of modelling plasmas, and the latter is bottle-necked by the relative paucity of data. To address this issue, this work applies the neural ordinary differential equations (ODE) framework to the problem of predicting a subset of plasma dynamics, namely the coupled plasma current and internal inductance dynamics. As the neural ODE framework allows for the natural inclusion of physics-based inductive biases, we train both physics-based and neural network models on data from the Alcator C-Mod fusion reactor and find that a model that combines physics-based equations with a neural ODE performs better than both existing physics-motivated ODEs and a pure neural ODE model.

physics.plasm-ph↗