Shaping of Magnetic Field Coils in Fusion Reactors using Bayesian Optimisation
This work addresses the engineering challenge of designing cost-effective and stable fusion reactors for sustainable energy production, representing an incremental step in applying AI to fusion reactor optimization.
The authors tackled the high-dimensional multi-output optimization of toroidal field coil shapes in tokamak fusion reactors using a Multi-Output Bayesian Optimization scheme, resulting in a proof-of-concept that identifies Pareto-optimal designs to minimize costs and maximize plasma stability by reducing magnetic ripples.
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.