Reducing Experimental Testing in Space Propulsion Film Cooling Analyses by Pixelwise Generative Image Interpolation
arXiv:2605.29911v1 Announce Type: new Abstract: We propose a machine learning approach for image regression from sparse experimental measurements. We show the application of the proposed method on film cooling studies in propulsion system development, aiming to reduce the need for extensive physical testing. Our method employs a lightweight feed-forward neural network with positional encoding to generate images conditioned by input parameters. Validated on real and synthetic data, it achieves high image similarity (RMSE 93 %) while maintaining accuracy with a 30 \% reduction of measurements. W
The rapid advancement in AI, particularly in generative models and image regression, enables sophisticated applications like predictive materials testing that were previously infeasible.
This development allows for significant reductions in physical testing required for complex engineering systems, accelerating development cycles and reducing costs in critical sectors like aerospace and defense.
The reliance on extensive physical experimentation for design validation in specific engineering domains will decrease, shifting towards AI-driven simulation and interpolation.
- · Aerospace and Defense Industry
- · AI/ML Software Developers
- · Advanced Manufacturing
- · Space Propulsion System Developers
- · Traditional Materials Testing Facilities
- · Excessive physical prototype production
Propulsion system development becomes faster and more cost-efficient through reduced physical testing.
AI-driven design and testing methodologies become standard in other high-consequence engineering fields.
National defense capabilities could be enhanced by accelerated innovation cycles for advanced propulsion and thermal management systems.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG