Advanced USP laser process with deep learning and triangular beam shaping for micro Fresnel lenses fabrication

Alexandre Miazek; Julien Dupuy; Ivan Gusachenko; Gwenn Pallier; Yves Hernandez

doi:10.1117/12.2649063

17 March 2023 Advanced USP laser process with deep learning and triangular beam shaping for micro Fresnel lenses fabrication

Alexandre Miazek, Julien Dupuy, Ivan Gusachenko, Gwenn Pallier, Yves Hernandez

Author Affiliations +

Proceedings Volume 12408, Laser Applications in Microelectronic and Optoelectronic Manufacturing (LAMOM) XXVIII; 1240802 (2023) https://doi.org/10.1117/12.2649063
Event: SPIE LASE, 2023, San Francisco, California, United States

Abstract

Industrial molds used to manufacture new type of Fresnel lenses require significant control over the size and shape of the ablation grooves. In particular, for demanding patterns, the objective is to obtain asymmetrical triangular grooves of around 10-20 μm width, micromachined with an ultra-short pulse (USP) laser for a better quality. To obtain this ablation profile we use a specific triangular beam shape obtained thanks to a reflection beam-shaping module. The idea is to move and rotate this triangular shape to have one of the edges of the triangle on one side of the groove, and its opposite point on the other side. In order to have total control of the laser process, we have collected a large amount of data of laser parameters, beam profiles and ablated groove profiles. This database allows us, thanks to the use of a deep learning algorithm, to predict the ablation profile from a set of laser parameters and beam profile pictures used for machining. The use of an artificial intelligence algorithm is justified by the fact that, at such a low resolution and with femtosecond laser pulses, light-matter interactions become complex, in particular due to nonlinear effects, which make using simulations difficult. Our deep learning model has the particularity of being a ”hybrid” model using several types of data: laser parameters, curves and images. This allows the algorithm to have an overview of the process but also to give the end-user a very fine control.

Conference Presentation

Citation Download Citation

Alexandre Miazek, Julien Dupuy, Ivan Gusachenko, Gwenn Pallier, and Yves Hernandez "Advanced USP laser process with deep learning and triangular beam shaping for micro Fresnel lenses fabrication", Proc. SPIE 12408, Laser Applications in Microelectronic and Optoelectronic Manufacturing (LAMOM) XXVIII, 1240802 (17 March 2023); https://doi.org/10.1117/12.2649063

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available