AI Thermal Prediction Module for Electric Motors

This project proposes to develop a machine learning-driven model for electric aircraft propulsion, aiming to bridge a critical modeling and validation gap in electrified aviation. Instead of relying on conventional empirical or finite element models, it trains neural networks on experimental datasets to create scalable, architecture-agnostic thermal predictions across different electric motor designs. Researchers seek to integrate the AI thermal modeul into the physics-based real-time powertrain modeling (RTPM) tool and release combined software on the NASA software repository.

This innovation will allow us to: (1) inform rapid motor architecture trades, (2) assist integrated sizing efforts which rely on thermal margin, (3) leapfrog unavailable OEM-specific thermal modeling, and (4) predict key hot-soak loads for transient maneuvers which require significant motor operations. Stakeholders inlcude aircraft developers and propulsion system integrators. A generalizable thermal model supports engineering design efforts which require digital twins. This model could help designers size primary components to inform a more detailed FEA analysis. For certification, it is likely that detailed thermal modeling would still be required (i.e., hot spatial zones), but the generalizable thermal model can provide thermal solutions well in advance to inform the need for systemic changes in the propulsion architecture.

This is a mature technology (TRL 7+) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.

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.