Shaping of Magnetic Field Coils in Fusion Reactors using Bayesian Optimisation (2310.01455v1)
Abstract: 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.
- J. Wesson and D.J. Campbell. Tokamaks. International series of monographs on physics. Clarendon Press, 2004.
- Demo design activity in europe: Progress and updates. Fusion Engineering and Design, 136:729–741, 2018. Special Issue: Proceedings of the 13th International Symposium on Fusion Nuclear Technology (ISFNT-13).
- M. Coleman and S. McIntosh. Blueprint: A novel approach to fusion reactor design. Fusion Engineering and Design, 139:26–38, 2019.
- MIRA: a multi-physics approach to designing a fusion power plant. Nuclear Fusion, 62(7):076042, jun 2022.
- M. Coleman. An integrated design framework for future nuclear fusion power reactors. PhD thesis, University of Cambridge, September 2021.
- Toroidal field ripple effects in large tokamaks. 1 1975.
- J. Narl Davidson. Effect of toroidal field ripple on particle and energy transport in a tokamak. Nuclear Fusion, 16(5):731–742, nov 1976.
- Johner Jean. Helios: A zero-dimensional tool for next step and reactor studies. Fusion Science and Technology, 59(2):308–349, 2011.
- Botorch: A framework for efficient monte-carlo bayesian optimization. 2019.
- Gpytorch: Blackbox matrix-matrix gaussian process inference with gpu acceleration. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS’18, page 7587–7597, Red Hook, NY, USA, 2018. Curran Associates Inc.
- Ae: A domain-agnostic platform for adaptive experimentation. 2018.
- I.M Sobol’. On the distribution of points in a cube and the approximate evaluation of integrals. USSR Computational Mathematics and Mathematical Physics, 7(4):86–112, 1967.
- Gaussian Processes for Machine Learning. Adaptive Computation and Machine Learning series. MIT Press, 2005.
- Single- and multiobjective evolutionary optimization assisted by gaussian random field metamodels. IEEE Transactions on Evolutionary Computation, 10(4):421–439, 2006.
- A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE Transactions on Evolutionary Computation, 6(2):182–197, 2002.
- Optimal tracking for a divergent-type parabolic pde system in current profile control. Abstract and Applied Analysis, 2014:1–8, 06 2014. CC BY 4.0 https://creativecommons.org/licenses/by/4.0, via Wikimedia Commons.