Quantitative and Real‐Time Control of 3D Printing Material Flow Through Deep Learning

Abstract

3D printing could revolutionize manufacturing through local and on‐demand production while enabling uniquely complex and custom products. However, 3D printing's propensity for production errors prevents autonomous operation and the quality assurance necessary to realize this vision. Human operators cannot continuously monitor or correct errors in real time, while automated approaches predominantly only detect errors. New methodologies correct parameters either offline or with slow response times and poor prediction granularity, limiting their utility. A commonly available 3D printing process metadata is harnessed, alongside the video of the printing process, to build a unique image dataset. Regression models are trained to precisely predict how printing material flow should be altered to correct errors and this should be used to build a fast control loop capable of 3D printing parameter discovery and few‐shot correction. Demonstrations show that the system can learn optimal parameters for unseen complex materials, and achieve rapid error correction on new parts. Similar metadata exists in many manufacturing processes and this approach could enable the adoption of fast data‐driven control systems more widely in manufacturing.

Proceedings - The Eleventh International Symposium GRID 2022

“…In 3D printing AI can be used for remote defect detection (Paraskevoudis, Karayannis & Koumoulos, 2020), to control the material flow (Brion & Pattinson, 2022), as well as for automating the workflow (AMFG, 2022). Software packages based on AI are also able to evaluate and optimize design files by implementing machine learning in generative design approach (Vasilev, 2022).…”

Spatially Resolved Defect Characterization and Fidelity Assessment for Complex and Arbitrary Irregular 3D Printing Based on 3D P-OCT and GCode

“…In Fused Deposition Modeling (FDM), optical sensors have been widely used for process monitoring and defect detection, such as of short fiber Bragg grating (FBG) [ 23 ], with cameras [ 24 ] and infrared thermography [ 25 ]. Laser displacement scanners are capable of acquiring high-precision point cloud data, although this is limited to surface point information and is susceptible to environmental light and reflections.…”

Towards smart scanning probe lithography: a framework accelerating nano-fabrication process with in-situ characterization via machine learning

“…Recent advances in artificial intelligence (AI) are shaping the future of nearly every industry. Machine learning (ML) techniques have been developed and applied to manufacturing for modeling 28 , optimization 29 , 30 , control 31 , monitoring 32 , and prediction 33 , 34 . In terms of fabrication and characterization of the nanoscale, ML plays a pivotal role in aspect of identification of nanotubes 35 , image super-resolution 36 , nano-structure detection 37 , feature segmentation 38 and electrostatic characterization 39 .…”