Modelling laser machining of nickel with spatially shaped three pulse sequences using deep learning

Abstract

Femtosecond laser machining is a complex process, owing to the high peak intensities involved. Modelling approaches for the prediction of final sample quality based on photon-atom interactions are therefore challenging to extrapolate up to the microscale and beyond. The problem is compounded when multiple exposures are used to produce a final structure, where surface modifications from previous exposures must be taken into consideration. Neural network approaches allow for the automatic creation of a model that accounts for these challenging processes, without any physical knowledge of the processes being programmed by a specialist. We present such a network for the prediction of surface quality for multi-exposure femtosecond machining on a 5µm electroless nickel layer deposited on copper, where each pulse is uniquely spatially shaped using a spatial light modulator. This neural network modelling method accurately predicts the surface profile after three, sequential, overlapping exposures of dissimilar intensity patterns. It successfully reproduces such effects as the sub-diffraction limit machining feasible with multiple exposures, and the smoothing effect on edge-burr from previous exposures expected in multi-exposure laser machining.

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

“…[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]. The authors anticipate that further breakthroughs in data‐driven machine learning for laser machining will assist in the development of a new understanding of the transient processes that occur during laser machining.…”

“…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 spatial‐intensity profile. In combining the concepts of real‐time correction and DMD‐based beam shaping, Xie et al.…”

“…Analysis of the outputs from the neural network model was used to predict a range of properties, such as the degree of debris deposition for different beam sizes. 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.…”

Modeling adult skeletal stem cell response to laser-machined topographies through deep learning

“…Deep learning has also been applied with repeated success to the biomedical imaging field [21][22][23][24][25]. Recent advances in deep learning show that, when given enough sufficiently varied training data, the need for a complete sampling of parameter space can be unnecessary [26][27][28]. Thus, as shown here, training a deep neural network on varied, yet limited, topographies and the subsequent cell response can result in predictions of cell response on topographies unseen by the network and untested in a laboratory setting.…”

Deep-Learning-Assisted Focused Ion Beam Nanofabrication

“…Deep learning is revolutionizing scientific research 9 − 14 because of its aptitude for pattern recognition and the capability to empirically establish the functional algorithms of complex systems. 15 For example, it has been shown that deep learning can improve laser machining processes, 16 − 18 including through the provision of feedback for real-time process control. 19 − 21 Here we show that deep learning can be used to simulate the postfabrication appearance of structures manufactured by FIB milling in the 2D projection of a scanning electron microscope image, as a very good (almost invariably the first, in situ) indicator of process accuracy and quality.…”