Presentation
9 March 2020 Machine Learning predicts printing parameters for multi-photon polymerization three-dimensional direct laser writing (3D-DLW) (Conference Presentation)
Areti Mourka, Georgios D. Barmparis, Dimitra Ladika, Vasileia Melissinaki, David Gray, Maria Farsari
Author Affiliations +
Proceedings Volume 11271, Laser 3D Manufacturing VII; 112710A (2020) https://doi.org/10.1117/12.2544839
Event: SPIE LASE, 2020, San Francisco, California, United States
Abstract
We are presenting a model for a quantitative description of the polymerization process in 3D-laser microfabrication. With aim to assist in estimating the necessary power threshold to obtain certain feature size, particularly the line characteristics, depending on the laser power and writing speed. The focal distribution as well as the photoresist is taken into account. We do not try to gain any chemical insight into the processes involved, and restrict us to a quantitative study of a multi-photon process. Machine learning is used to classify the input SEM images providing a look-up table as a custom field for optimized parameter selection.
Conference Presentation
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Areti Mourka, Georgios D. Barmparis, Dimitra Ladika, Vasileia Melissinaki, David Gray, and Maria Farsari "Machine Learning predicts printing parameters for multi-photon polymerization three-dimensional direct laser writing (3D-DLW) (Conference Presentation)", Proc. SPIE 11271, Laser 3D Manufacturing VII, 112710A (9 March 2020); https://doi.org/10.1117/12.2544839
Advertisement
Advertisement
KEYWORDS
Polymerization

Machine learning

Multiphoton lithography

Printing

3D printing

Photoresist materials

Absorption

Back to Top