A proof-of-concept for automated AI-driven stellarator coil optimization with in-the-loop finite-element calculations

TL;DR

This paper presents an automated, AI-driven workflow for optimizing stellarator coils, integrating in-the-loop finite-element stress calculations to accelerate design processes for fusion reactors.

Contribution

It introduces an end-to-end automated coil optimization tool with in-the-loop stress analysis, utilizing genetic algorithms and language models for continuous, rapid design improvements.

Findings

Automated coil solutions are generated and updated on an open-source leaderboard.

Two optimization policies, genetic algorithm and LLM, are implemented for continuous improvement.

In-the-loop stress optimization enables future integration of finite-element calculations.

Abstract

Finding feasible coils for stellarator fusion devices is a critical challenge of realizing this concept for future power plants. Years of research work can be put into the design of even a single reactor-scale stellarator design. To rapidly speed up and automate the workflow of designing stellarator coils, we have designed an end-to-end ``runner'' for performing stellarator coil optimization. The entirety of pre and post-processing steps have been automated; the user specifies only a few basic input parameters, and final coil solutions are updated on an open-source leaderboard. Two policies are available for performing non-stop automated coil optimizations through a genetic algorithm or a context-aware LLM. Lastly, we construct a novel in-the-loop optimization of Von Mises stresses in the coils, opening up important future capabilities for in-the-loop finite-element calculations.