Simulated Inspection Mechanics for Artificial Intelligence Defect Detection (SIM-AID)

In this study, we propose to use X-Ray simulation to generate synthetic training data for artificial intelligence (AI) defect detection, applied to aerospace additively manufactured (AM) metal components. The team has extensive experience with nondestructive evaluation, metallic AM, X-Ray simulation, AI / machine learning, and data science. We intend to perform head-to-head comparisons of leading AI defect detection algorithms trained with simulated data, and demonstrate performance for critical defects in an aerospace-relevant metallic AM component.

NASA and US aerospace intend to increase application of metallic AM components for weight and cost savings on earth, and critical manufacturing capabilities in-space. Currently, AM components frequently present with defects that limit their performance and reliability. By using our knowledge and application of X-Ray physics, we expect to demonstrate a means of bridging training data gaps, allowing us to employ leading AI defect detection algorithms to emerging AM applications.

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.