Predictive visualization of fiber laser cutting topography via deep learning with image inpainting
Predictive visualization of fiber laser cutting topography via deep learning with image inpainting
复制标题
DOI：
10.2351/7.0000957
复制
发表时间：
2023-06
影响因子：
2.1
通讯作者：
Alex Courtier;M. Praeger;J. Grant-Jacob;Christophe Codemard;Paul Harrison;M. Zervas;B. Mills
中科院分区：
文献类型：
--
作者：
Alex Courtier;M. Praeger;J. Grant-Jacob;Christophe Codemard;Paul Harrison;M. Zervas;B. Mills
激光切割是一种快速、精确、非接触的加工技术，广泛应用于工业生产中。然而，在切割过程中可能会形成特定于参数的缺陷，从而对切割质量产生负面影响。虽然光-物质相互作用是高度非线性的，因此对分析建模具有挑战性，但深度学习提供了直接从数据对这些相互作用建模的能力。在这里，我们展示了深度学习可以用来放大对切割过程中产生的参数特定缺陷的视觉预测，以及用于预测未经实验测量的参数的缺陷。此外，视觉预测还可以用来模拟激光切割缺陷与激光切割参数之间的关系。
Laser cutting is a fast, precise, and noncontact processing technique widely applied throughout industry. However, parameter specific defects can be formed while cutting, negatively impacting the cut quality. While light-matter interactions are highly nonlinear and are, therefore, challenging to model analytically, deep learning offers the capability of modeling these interactions directly from data. Here, we show that deep learning can be used to scale up visual predictions for parameter specific defects produced in cutting as well as for predicting defects for parameters not measured experimentally. Furthermore, visual predictions can be used to model the relationship between laser cutting defects and laser cutting parameters.