https://omid-bidar.github.io/tags/symbolic-regression/Symbolic RegressionHugo Blox Builder (https://hugoblox.com)en-usWed, 27 May 2026 00:00:00 +0000https://omid-bidar.github.io/media/icon_hu18016986673377086699.pnghttps://omid-bidar.github.io/tags/symbolic-regression/https://omid-bidar.github.io/student-project/symbolic-regression-boiling-2026/Wed, 27 May 2026 00:00:00 +0000https://omid-bidar.github.io/student-project/symbolic-regression-boiling-2026/<h2 id="project-details">Project details</h2> <ul> <li><strong>Student:</strong> Samuel Williams</li> <li><strong>Programme:</strong> MEng Mechanical Engineering</li> <li><strong>Project type:</strong> Final-year dissertation</li> <li><strong>Academic year:</strong> 2025-26</li> <li><strong>Supervisor:</strong> Dr Omid Bidar</li> </ul> <h2 id="overview">Overview</h2> <p>Accurate prediction of bubble departure diameter is important in heat flux partitioning models for subcooled flow boiling, where relatively small errors can propagate strongly into predicted evaporation and quenching heat fluxes. This project investigated symbolic regression as a route to developing computationally efficient, interpretable, closed-form expressions that bridge mechanistic boiling models and data-driven optimisation.</p> <p>Samuel first implemented a deterministic mechanistic baseline in MATLAB, based on the Klausner force-balance model with Colombo and Fairweather improvements, and validated it against a multi-source database containing 378 experimental measurements. Symbolic regression was then applied using PySR in two complementary forms: a hybrid correction to the mechanistic baseline and a standalone correlation for bubble departure diameter. Leave-one-dataset-out cross-validation was used to assess generalisation beyond individual experimental datasets.</p> <h2 id="key-outcomes">Key outcomes</h2> <ul> <li>The mechanistic baseline achieved mean absolute percentage errors between 21.0% and 32.4% across the validation data.</li> <li>Both symbolic-regression approaches identified superheat-driven growth, cap condensation and flow-shear inertia as the dominant physical drivers.</li> <li>The hybrid model reduced log-RMSE by approximately 15% relative to the mechanistic baseline.</li> <li>The standalone correlation achieved a mean absolute percentage error of 27.8% on held-out vertical-upflow data, improving on the empirical correlations used for comparison.</li> <li>The work demonstrated the potential of symbolic regression for producing transparent and physically interpretable closure models for subcooled flow boiling.</li> </ul>