Physics-Informed Machine Learning for the Optimization of Hybrid Rocket Motors

Hybrid rockets have been identified as a potential technology for cost effective delivery of micro and nano satellites into Lower Earth Orbit (LEO). Compared to solid rockets, hybrids are far more maneuverable, while simultaneously maintaining a simplistic design compared to liquid engines. However, achieving high fuel regression rates has been a challenge due to the lack of fundamental understanding of the diffusion-controlled combustion that occurs in the motor. Lack of high-fidelity modeling capabilities have resulted in reliance on costly test campaigns for design iteration. To address this issue, this project seeks to develop an understanding of the underlying mechanisms parametrizing hybrid fuel burning behavior by developing a physics informed machine learning model. Physics informed machine learning is a novel approach that has been shown to enhance generalizability and reduce overfitting, in addition to requiring less training data than traditional machine learning approaches. The developed model will be used to optimize experimental conditions by using Bayesian statistical setting. Training data will then be collected using additively manufactured fuel grains in a small scale optically accessible 2D hybrid rocket motor. Finally, model fidelity will be verified by completing a test campaign focused on 3D hybrid rocket motors capable of approximating the performance of LEO launch vehicles. The creation of a generalizable high-fidelity model will enable the efficient design of hybrid rockets, bringing down their development costs.

This is early/mid-stage (TRL 2) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.