Opt Express. 2021 Oct 25;29(22):36469-36486. doi: 10.1364/OE.431441.
Laser machining involves many complex processes, especially when using femtosecond pulses due to the high peak intensities involved. Whilst conventional modelling, such as those based on photon-electron interactions, can be used to predict the appearance of the surface after machining, this generally becomes unfeasible for micron-scale features and larger. The authors have previously demonstrated that neural networks can simulate the appearance of a sample when machined using different spatial intensity profiles. However, using a neural network to model the reverse of this process is challenging, as diffractive effects mean that any particular sample appearance could have been produced by a large number of beam shape variations. Neural networks struggle with such one-to-many mappings, and hence a different approach is needed. Here, we demonstrate that this challenge can be solved by using a neural network loss function that is a separate neural network. Here, we therefore present a neural network that can identify the spatial intensity profiles needed, for multiple laser pulses, to produce a specific depth profile in 5 μm thick electroless nickel.
激光加工涉及许多复杂的过程，尤其是在使用飞秒脉冲时，因为涉及到高的峰值强度。虽然传统的建模方法，如基于光子-电子相互作用的方法，可以用来预测加工后的表面外观，但对于微米级特征和更大的特征，这种方法通常是不可行的。作者之前已经证明，神经网络可以模拟使用不同空间强度分布进行加工的样品的外观。然而，使用神经网络来模拟这个过程的逆过程是具有挑战性的，因为衍射效应意味着任何特定的样品外观都可能是由大量光束形状变化产生的。神经网络在这种一对多的映射中遇到困难，因此需要一种不同的方法。在这里，我们证明通过使用一个单独的神经网络作为神经网络损失函数，可以解决这个挑战。因此，在这里我们提出了一种神经网络，可以识别出多个激光脉冲所需的空间强度分布，以在 5 微米厚的化学镀镍中产生特定的深度分布。
