Automated Testing and Characterization of Additive Manufacturing (ATCAM)

Abstract The sensitivity of additive manufacturing (AM) to the variability feedstock quality, machine calibration, and accuracy drives need for frequent characterization fabricated objects a robust material process. constant testing is fiscally logistically intensive, often requiring coupons that are manufactured tested in independent facilities. As step toward integrating into AM process while reducing cost, we propose automated (ATCAM). ATCAM configured fused deposition modeling (FDM) introduces concept dynamic generate large quantities basic samples. An situ actuator printed on build surface deploy through impact, which sensed by load cell system utilizing learning (ML) correlate data. We test ATCAM’s ability distinguish quality three PLA at differing price points generating comparing 3000 10 repetitions 100 coupon cycles per material. correlated each visualized fatigue actuators over cycle. Three ML algorithms were then compared, with Gradient Boost regression demonstrating 71% correlation their parent provided confidence data generates.