Advanced beam shaping for laser materials processing based on diffractive neural networks
Optics Express, vol. 30, pp. 22798
Abstract
We propose a method based on neural network training algorithms for the design of diffractive neural networks - with the aim to perform advanced laser beam shaping in the NIR/VIS spectrum for laser materials processing. The method enables the efficient design of systems including multiple cascaded diffractive optical elements (DOEs) and allows the simultaneous optimization for complex (intensity and phase) target field distributions in multiple target planes. The multi-target boundary condition in the optimization method offers great potential for advanced laser beam shaping.
Authors 5
-
Paul Buske Aachen
Affiliation as printed
RWTH Aachen University TOS - Chair for Technology of Optical Systems
-
Annika Bonhoff Aachen
Affiliation as printed
RWTH Aachen University TOS - Chair for Technology of Optical Systems
-
Moritz Eisebitt Aachen
Affiliation as printed
RWTH Aachen University TOS - Chair for Technology of Optical Systems
-
Fraunhofer Institute for Laser Technology · RWTH Aachen University
Affiliation as printed
Fraunhofer ILT - Institute for Laser Technology
RWTH Aachen University TOS - Chair for Technology of Optical Systems
-
Carlo Holly Aachen
Affiliation as printed
RWTH Aachen University TOS - Chair for Technology of Optical Systems
Cited by 53 stored of 54
Cited by patents worldwide 1 (Lens.org)
-
METHOD AND ARRANGEMENT FOR DYNAMIC LASER BEAM SHAPING BASED ON OPTICAL TRANSCODERSWO2026041345A1 2026-02-26 Pending