Timezone: »
Nuclear fusion using magnetic confinement holds promise as a viable method for sustainable energy. However, most fusion devices have been experimental and as we move towards energy reactors, we are entering into a new paradigm of engineering. Curating a design for a fusion reactor is a high-dimensional multi-output optimisation process. Through this work we demonstrate a proof-of-concept of an AI-driven strategy to help explore the design search space and identify optimum parameters. By utilising a Multi-Output Bayesian Optimisation scheme, our strategy is capable of identifying the Pareto front associated with the optimisation of the toroidal field coil shape of a tokamak. The optimisation helps to identify design parameters that would minimise the costs incurred while maximising the plasma stability by way of minimising magnetic ripples.
Author Information
Timothy Nunn (United Kingdom Atomic Energy Authority)
I am an *Apprentice Research Software Engineer* at the *UK Atomic Energy Authority*, working in the Advanced Computing department whilst studying part-time for my degree in Computer Science from the University of Warwick. My current work revolves around the design of nuclear fusion reactors for energy production. My two areas of work on design codes are: * Uncertainty quantification: quantifying how sensitive a design is to the uncertainties in its design parameters, and models, which will affect its operation or construction. * **Design optimisation**: Proof-of-concept Bayesian optimisation over models from aforementioned design codes. The aim is to reduce the computational cost of evaluating multiple objectives of complicated designs by employing **Bayesian optimisation** over a series of **Gaussian Process** surrogates. This work is the basis of the following Workshop Paper at *Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems*: "**Shaping of Magnetic Field Coils in Fusion Reactors using Bayesian Optimisation**"
Vignesh Gopakumar (United Kingdom Atomic Energy Authority)
Vignesh Gopakumar is a machine learning engineer specialising in fusion research with the United Kingdom Atomic Energy Authority. He spends his time building machine learning algorithms to model physics systems that help gain more understanding of the underlying phenomenons. He designs algorithms that help discover anomalies as well as predict malfunction of engineering systems. He’s working on building a model that can be augmented in real time when exposed to different physics principles.
Sebastien Kahn (UK Atomic Energy Authority)
More from the Same Authors
-
2022 : Fourier Neural Operator for Plasma Modelling »
Vignesh Gopakumar · Stanislas Pamela · Lorenzo Zanisi · Zongyi Li · Anima Anandkumar