CaltechAUTHORS
  A Caltech Library Service

Neural networks for trajectory evaluation in direct laser writing

Bauhofer, Anton and Daraio, Chiara (2020) Neural networks for trajectory evaluation in direct laser writing. International Journal of Advanced Manufacturing Technology, 107 (5-6). pp. 2563-2577. ISSN 0268-3768. https://resolver.caltech.edu/CaltechAUTHORS:20200323-104524705

[img] PDF - Supplemental Material
See Usage Policy.

655Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200323-104524705

Abstract

Material shrinkage commonly occurs in additive manufacturing and compromises the fabrication quality by causing unwanted distortions or residual stresses in fabricated parts. Even though it is known that the resulting deformations and stresses are highly dependent on the writing trajectory, no effective strategy for choosing suitable trajectories has been reported to date. Here, we present a path to achieve this goal in direct laser writing, an additive manufacturing method based on photopolymerization that commonly suffers from strong shrinkage-induced effects. First, we introduce a method for measuring the shrinkage of distinct direct laser written lines. We then introduce a semi-empirical numerical model to capture the interplay of sequentially polymerized material and the resulting macroscopic effects. Finally, we implement an artificial neural network to evaluate given laser trajectories in terms of the resulting part quality. The presented approach proves feasibility of using artificial neural networks to assess the quality of 3D printing trajectories and thereby demonstrates a potential route for reducing the impact of material shrinkage on 3D printed parts.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1007/s00170-020-05086-3DOIArticle
ORCID:
AuthorORCID
Daraio, Chiara0000-0001-5296-4440
Additional Information:© 2020 Springer Nature Switzerland AG. Received 18 October 2019; Accepted 09 February 2020; Published 23 March 2020. We would like to thank Jan Rys and Matthew Hunt for their kind help with SEM. This work was partially funded by the Swiss National Science Foundation through grant “MechNanoTruss-Mechanical response of polymer nanotruss scaffolds” (No. 164375). The experiments were conducted with support from the Kavli Nanoscience Institute at Caltech.
Group:Kavli Nanoscience Institute
Funders:
Funding AgencyGrant Number
Swiss National Science Foundation (SNSF)164375
NSFOAC-1835735
Subject Keywords:Advanced manufacturing; Direct laser writing; Artificial neural networks; Residual stresses
Issue or Number:5-6
Record Number:CaltechAUTHORS:20200323-104524705
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200323-104524705
Official Citation:Bauhofer, A., Daraio, C. Neural networks for trajectory evaluation in direct laser writing. Int J Adv Manuf Technol 107, 2563–2577 (2020). https://doi.org/10.1007/s00170-020-05086-3
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:102047
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:23 Mar 2020 17:52
Last Modified:10 Apr 2020 16:15

Repository Staff Only: item control page