Autonomous in-situ correction of fused deposition modeling printers using computer vision and deep learning

Fused deposition modeling, a widely used additive manufacturing process, currently faces challenges in printed part quality such as under-extrusion and over-extrusion. In this paper, a real-time monitoring and autonomous correction system is developed, where a deep learning model and a feedback loop is used to modify 3D-printing parameters iteratively and adaptively. Results show that our system is capable of detecting in-plane printing conditions and in-situ correct defects faster than the speed of a human's response. The fundamental elements in the framework proposed can be extended to various 3D-printing technologies to reliably fabricate high-performance materials in challenging environments without human interaction. (C) 2019 Society of Manufacturing Engineers (SME). Published by Elsevier Ltd. All rights reserved.