https://jorisparet.github.io/tag/bayesian-optimization/Bayesian OptimizationWowchemy (https://wowchemy.com)en-usTue, 21 Oct 2025 00:00:00 +0000https://jorisparet.github.io/media/icon_huf5b7e9305d8ca00c36bcf7194f7e4936_69678_512x512_fill_lanczos_center_3.pnghttps://jorisparet.github.io/tag/bayesian-optimization/https://jorisparet.github.io/post/2025-10-21_fed/Tue, 21 Oct 2025 00:00:00 +0000https://jorisparet.github.io/post/2025-10-21_fed/<h1 id="authors">Authors</h1> <ul> <li>Joris Paret</li> <li>Daniel Iglesias</li> <li>Hyogeon Bak</li> <li>Matthew Clough</li> <li>George Vayakis</li> <li>Michael Walsh</li> </ul> <h1 id="abstract">Abstract</h1> <p>A machine learning-based calibration strategy for the ITER Tokamak Systems Monitor (TSM) is presented, focusing on the optimization of dynamic finite-element method (FEM) models essential for monitoring and assessing the structural health of the tokamak. Traditional finite-element model updating techniques are unsuitable for the ITER environment due to constraints such as limited sensor placement and the inability to perform controlled excitations. To overcome these challenges, an automated calibration procedure is proposed, leveraging Bayesian optimization with Gaussian Process regression. The parameter space is efficiently explored by sequentially sampling model configurations, minimizing the discrepancy between simulated and reference modal characteristics. This preliminary work establishes a foundation for calibrating other numerical models within the TSM.</p> <h1 id="article-availability">Article availability</h1> <p>This paper is published in <a href="https://doi.org/10.1016/j.fusengdes.2025.115485" target="_blank" rel="noopener">Fusion Engineering and Design</a>.</p>https://jorisparet.github.io/publication/2025_fed/Tue, 21 Oct 2025 00:00:00 +0000https://jorisparet.github.io/publication/2025_fed/