Machine learning for 3D simulated visualization of laser machining

• DOI: 10.1364/oe.26.021574
• Publication Date: 2018-08-29T20:23:37Z
• Authors: Daniel J. Heath; James A. Grant-Jacob; Yunhui Xie; Benita S. Mackay; James A. G. Baker; Robert W. Eason; Ben Mills
• Keywords: 0103 physical sciences; 500; 530; 01 natural sciences

Laser machining can depend on the combination of many complex and nonlinear physical processes.Simulations laser that are built from first-principles, such as photon-atom interaction, therefore challenging to scale-up experimentally useful dimensions.Here, we demonstrate a simulation approach using neural network, which requires zero knowledge underlying processes instead uses experimental data directly create model experiment.The network modelling was shown accurately predict 3D surface profile machined after exposure various spatial intensity profiles, used discover trends inherent within would have otherwise been difficult discover.