Presentation + Paper
5 March 2021 Mitigating scattering effects in DMD-based microscale 3D printing using machine learning
Author Affiliations +
Abstract
The effect of light scattering is non-negligible in micro-scale DMD-based 3D printing. Light scattering results in unwanted exposure and polymerization, thus deteriorating the fabrication resolution and fidelity. We report using machine learning (ML) approach to mitigate the effect of light scattering. A neural network (NN) was designed to study the highly-sophisticated relationship between the input digital masks and their corresponding output 3D printed structures. After trained with 300 pairs of digital masks and printed structures, the neural network was able to optimize the 3D printing process by suggesting the optimal grayscale digital masks which are not necessarily identical to the desired structures. Verification results showed that using NN-generated digital masks yielded significant improvements in printing resolution and fidelity compared to using masks that are identical to the desired structures.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shangting You, Jiaao Guan, and Shaochen Chen "Mitigating scattering effects in DMD-based microscale 3D printing using machine learning", Proc. SPIE 11698, Emerging Digital Micromirror Device Based Systems and Applications XIII, 1169804 (5 March 2021); https://doi.org/10.1117/12.2577129
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Light scattering

3D printing

Scattering

Machine learning

Neural networks

Photopolymerization

Polymerization

Back to Top