Influence of 3D printing parameters on ULTEM 9085 mechanical properties using experimentation and machine learning

ULTEM 9085, a polyetherimide (PEI), is the first 3D printed thermoplastic material to be qualified by the Federal Aviation Administration (FAA) for use as a high-performance aviation component due to its high strength-to-weight ratio, chemical resistance, and flame retardance properties. However, 3D printed ULTEM suffers reduction in mechanical properties compared to the bulk material. Understanding the role of 3D printing parameters on resulting mechanical performance requires lengthy qualification studies which take many years. This study investigated a combined experimental and machine learning (ML) approach for correlating density, surface profile, and mechanical properties using tensile testing and microscopy across various coupon geometries and build orientations. An ML model predicted the relationship between 3D printing parameters and resulting mechanical properties in a broad design space within 1%. This study provides a straightforward framework for rapid, ML-driven evaluation of 3D printed designs, significantly reducing experimental burden needed high-performance component qualification.