A Quality Assessment Network for Failure Detection in 3D Printing for Future Space-Based Manufacturing

The application of space manufacturing technology holds tremendous potential for the advancement of space exploration. With significant investment from respected research institutions such as NASA, ESA, and CAST, along with private companies such as Made In Space, OHB System, Incus, and Lithoz, this sector has recently experienced a notable surge in development. Among the available manufacturing technologies, 3D printing has been successfully tested in the microgravity environment onboard the International Space Station (ISS), emerging as a versatile and promising solution for the future of space manufacturing. In this paper, an automated Quality Assessment (QA) approach for space-based 3D printing is proposed, aiming to enable the autonomous evaluation on the 3D printed results, thus freeing the system from reliance on human intervention, an essential requirement for the operation of space-based manufacturing platforms functioning in the exposed space environment. Specifically, this study investigates three types of common 3D printing failures, namely, indentation, protrusion, and layering to design an effective and efficient fault detection network that outperforms its counterparts backboned with other existing networks. The proposed approach has achieved a detection rate of up to 82.7% with an average confidence of 91.6% by training with the artificial samples, demonstrating promising results for the future implementation of 3D printing in space manufacturing.