Deep learning for the monitoring and process control of femtosecond laser machining

Abstract

Whilst advances in lasers now allow the processing of practically any material, further optimisation in precision and efficiency is highly desirable, in particular via the development of real-time detection and feedback systems. Here, we demonstrate the application of neural networks for system monitoring via visual observation of the work-piece during laser processing. Specifically, we show quantification of unintended laser beam modifications, namely translation and rotation, along with real-time closed-loop feedback capable of halting laser processing immediately after machining through a ∼450 nm thick copper layer. We show that this approach can detect translations in beam position that are smaller than the pixels of the camera used for observation. We also show a method of data augmentation that can be used to significantly reduce the quantity of experimental data needed for training a neural network. Unintentional beam translations and rotations are detected concurrently, hence demonstrating the feasibility for simultaneous identification of many laser machining parameters. Neural networks are an ideal solution, as they require zero understanding of the physical properties of laser machining, and instead are trained directly from experimental data.

Lasers that learn: The interface of laser machining and machine learning

“…This work was enhanced by McDonnell et al [196], who extended it to include three laser pulses and showed that the cGAN was able to predict that multiple pulses could enable a higher machining resolution than a single laser pulse when each pulse had a specific spatialintensity profile. In combining the concepts of real-time correction and DMD-based beam shaping, Xie et al [197] showed that a DMD can be used in a real-time feedback loop to provide corrections to the beam shape and position during laser machining, along with the demonstration of the real-time ceasing of laser machining at task completion, despite not knowing the task length beforehand. As presented here, recent results have demonstrated the potential for using ANNs to model thermal and structural effects during laser machining [198,199] and using cGANs for 3-D visualisation of surfaces, such as those produced for single [98] and multiple laser pulses [196].…”

Autonomous and Self-correcting Laser Subtractive Patterning Using Reinforcement Learning

“…In this manuscript, a novel laser material removal patterning process, actuated by reinforcement learning-controlled XYZ stages, is demonstrated, aiming to provide automatic path-planning and a self-correction ability to the patterning process. This work builds upon previous work by the authors that showed the capability of reinforcement learning (RL) for automated movement of small particles through a maze via the laser tweezers effect [1], and for deep learning for controlling the number of pulses used for machining through a thin film [2]. Here the application of reinforcement learning for experimental control of the spatial positions of laser pulses during laser machining is presented.…”

Machine Learning-Driven Process of Alumina Ceramics Laser Machining

“…This strategy has been shown to be effective in modelling laser machining [24][25][26][27][28][29], and it is significantly faster in terms of computational speed. Different ML methods have been demonstrated to be able to model physical phenomena directly from experimental data without considering any underlying physical equations [10,27,30]. For instance, Mc-Donnell et al [16] applied ML techniques to grey cast iron and studied the height of the laser produced crown and dimple depth as a function of the laser pulse energy, its repetition rate and the number of pulses.…”