Machine learning for real-time monitoring and control of additive manufacturing
| DWPI Title: Method for realizing in-situ process monitoring and optimization of direct ink write printing, involves providing direct ink write printer for printing ink subject to printing parameters, and measuring output of ink using computer vision |
| Abstract: A machine learning (ML) approach enables real-time direct ink write (DIW) print-parameter optimization through in-situ monitoring of printed line geometry. The method can use an invertible neural network (INN) to solve both forward and inverse, or optimization, problems using a single network. By combining in-situ computer vision and INNs, DIW printing parameters can be autonomously optimized to print a target line width in a matter of seconds. Furthermore, defects that occur during printing can be rapidly identified and corrected autonomously. The method eliminates user-intensive, time-consuming, iterative parameter discovery approaches that currently limit accelerated implementation of DIW and other extrusion-based additive manufacturing processes. |
| Use: Method for realizing in-situ process monitoring and optimization of direct ink write (DIW) printing. Uses include but are not limited to epoxies and other thermosets for high strength composites, intelligent materials for soft robotics, dielectric and conductive inks for electronics, bioprinting for organ replacement or drug delivery, and chocolates for food printing. |
| Advantage: The method enables accurately representing relationship between the input printing parameters and a specific DIW output, eliminating need for extensive operator experience or substantial trial-and-error time, and common defects that occur during DIW printing. |
| Novelty: The method involves providing a direct ink write (DIW) printer for printing an ink subject to multiple printing parameters. An output of the printed ink is measured in real-time using computer vision. The measured output is compared to a target output. The printing parameters of the DIW printer are adjusted in real-time using a pre-trained invertible neural network model to produce the target output when the target output differs from the target. The ink is printed on a substrate subject to the optimized printing parameters in a single printing step, where the printing parameters are provided with nozzle diameter, print speed, linear extrusion rate or height from the substrate. |
| Filed: 10/10/2023 |
| Application Number: US18483958A |
| Tech ID: SD 16367.1 |
| This invention was made with Government support under Contract No. DE-NA0003525 awarded by the United States Department of Energy/National Nuclear Security Administration. The Government has certain rights in the invention. |
| Data from Derwent World Patents Index, provided by Clarivate All rights reserved. Republication or redistribution of Clarivate content, including by framing or similar means, is prohibited without the prior written consent of Clarivate. Clarivate and its logo, as well as all other trademarks used herein are trademarks of their respective owners and used under license. |