A wide range of opportunities are emerging in the micro-system technology sector for laser micro-machining systems, because they are capable of processing a various types of materials with micro-scale precision. However, few process datasets and machine learning techniques are optimized for this industrial task. This article aims to show how the process parameters of micro-laser milling influence the final features of the microshapes that are produced and aims to identify, at the same time, the most accurate machine learning technique for the modelization of this multivariable process. We studied the capabilities of laser micromachining by performing experiments on hardened steel with a pulsed Nd:YAG laser. Arrays of micro-channels were manufactured using various scanning speeds, pulse intensities and pulse frequencies. The results are presented in terms of the main industrial requirements for any manufactured good: dimensional accuracy (in our case, depth and width of the channels), surface roughness and material removal rate (which is a measure of the productivity of the process). Different machine learning techniques were then tested on the datasets to try to build high accuracy models for each output variable. The selected techniques were: k-Nearest Neighbours, neural networks, decision trees and linear regression models. Our analysis of the correlation coefficients and the mean absolute error of all the generated models show that neural networks are better at modelling channel width and that decision trees are better at modelling surface roughness; both techniques are similar for depth and material removal rate. In all cases these two techniques are more accurate than the other two. It can be concluded that decision trees can be used for modelling laser micro-machining of micro geometries, if the dimensional accuracy of the workpiece is the main industrial requirement, while neural networks are better in the other cases.
his paper presents investigations on the effects of nanosecond laser processing parameters on depth and width of microchannels fabricated from polymethylmethacrylate (PMMA) polymer. A neodymium-doped yttrium aluminium garnet pulsed laser with a fundamental wavelength of 1,064 nm and a third harmonic wavelength of 355 nm with pulse duration of 5 ns is utilized. Hence, experiments are conducted at near-infrared (NIR) and ultraviolet (UV) wavelengths. The laser processing parameters of pulse energy (402-415 mJ at NIR and 35-73 mJ at UV wavelengths), pulse frequency (8-11 Hz), focal spot size (140-190 μm at NIR and 75 μm at UV wavelengths) and scanning rate (400-800 pulse/mm at NIR and 101-263 pulse/mm at UV wavelengths) are varied to obtain a wide range of fluence and processing rate. Microchannel width and depth profile are measured, and main effects plots are obtained to identify the effects of process parameters on channel geometry (width and depth) and material removal rate. The relationship between process variables (width and depth of laser-ablated microchannels) and process parameters is investigated. It is observed that channel width (140-430 μm at NIR and 100-150 μm at UV wavelengths) and depth (30-120 μm at NIR and 35-75 μm at UV wavelengths) decreased linearly with increasing fluence and increased non-linearly with increasing scanning rate. It is also observed that laser processing at UV wavelength provided more consistent channel profiles at lower fluences due to higher laser absorption of PMMA at this wavelength. Mathematical modeling for predicting microchannel profile was developed and validated with experimental results obtained with pulsed laser micromachining at NIR and UV wavelength
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.