Artificial Intelligence for Spacecraft Thermal Control Systems

The proposed innovation involves the creation of a user-friendly software tool for the generation of surrogate models for thermal modeling using Physics-Informed Neural Networks (PINNs) and Physics-Informed Deep Operator Networks (PI-DeepONets). When users provide basic system parameters (e.g., geometry, material properties, nominal boundary conditions), the software will generate the relevant physics-based loss functions and boundary/initial conditions for PINN or DeepONet models. Under the hood, adaptive training schedules adjust the relative weighting of physics losses and data-driven losses, ensuring consistent convergence across a wide parameter space. Users will be provided feedback on training progress, residual errors, and parameter coverage, helping engineers quickly diagnose convergence issues or refine the problem setup. We will also investigate the reliability of generating thermal results directly from CAD geometry, which would significantly reduce the human labor involved with thermal modeling by avoiding the need to mesh geometry. With this automated pipeline, spacecraft thermal engineers can rapidly explore numerous configurations of spacecraft designs without the overhead of manually re-deriving equations or building new surrogate models from scratch. We will use our validated heat transfer software TAITherm/MuSES to generate training and validation data for the physics-informed surrogate models. Once trained, the surrogate models generate reliable temperature predictions in near- real-time, enabling accelerated design iterations and on-demand thermal analysis for operational missions. The tool will target NASA and aerospace industry markets, including commercial and government spacecraft engineers seeking streamlined, cost-effective, and reliable thermal modeling solutions.

The physics-informed machine learning (PI-ML) surrogate models developed under this proposal will have direct application to many NASA spacecraft thermal control challenges, including design efforts under dynamic boundary conditions, virtual system model training for optimization, and assessment of current spacecraft thermal performance. Some of the main applications are: • Thermal management systems: Spacecraft thermal management systems are continuing to increase in complexity to maintain performance for higher power density electronics and increased power requirements. PI-ML surrogate models will enable rapid development of controls systems with improved performance over a wider range of operating conditions. • Spacecraft performance studies: The performance of power generation, power storage, and power electronics systems are often performance limited under extreme conditions because of thermal performance. The transient thermal prediction of spacecraft controls is essential to understanding system performance trade-offs and reliability. • Human engineering: The performance of environmental control systems (ECS) aboard manned spacecraft is increasing in complexity for longer missions including potential Lunar and Mars missions. Using PI-ML surrogate models can help develop improved smart ECS controls. Our primary software products are TAITherm and MuSES. Both products have a growing customer base, and two major software releases every year. New features and enhancements are selected based on feedback from current users, potential future users, and research by ThermoAnalytics into new markets and applications. The PI-ML surrogate model advantages listed above for NASA applications also apply to automotive commercial design and defense thermal analysis needs. The rapid pace of commercial design cycles is an application where engineers benefit from a rapid but accurate thermal solution. PI-ML surrogate models model can be applied to many applications beyond spacecraft, including automotive electronics cooling and power management. ThermoAnalytics believes we will be able to expand our market share of automotive modeling since our customers have indicated that they often seek a solution for improved thermal controls. We work with many OEMs and Prime Contractors who currently integrate our 3D thermal software and 1D system models for controls. We have many requests from these existing customers to be able to reduce the 3D model simulation time and accelerate the development of smart control systems. In the Defense market, there are similar thermal control applications for military vehicles, ships, aircraft, and satellites. One potential defense application would be the simulation of directed energy effects on supersonic or hypersonic systems. These systems operate in extreme thermal environments and there are both offensive and defensive needs to model the potential impact of directed energy on a military system.

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.