Influence of the effective parameters on the quality of laser micro-cutting process: Experimental analysis, modeling and optimization

Abstract

Surface roughness (Ra) after the laser micro-cutting process plays an important role in the quality of the final product. On the other hand, this surface roughness depends on complex laser process parameters such as laser power, laser repetition rate, and laser scanning speed. Therefore, it is important to propose a reliable model to predict the surface roughness as well as to correlate it with important process parameters. This helps to achieve the highest required quality, reduce the effort, and save material wastage and cost for the required experimental tests. In this paper, mathematical models have been developed using Artificial Neural Network (ANN) and theoretical calculations to predicate the surface roughness for the substrate surface after laser micro-cutting. Moreover, these models can be used to find the importance of each process parameter and finally to propose the optimum process parameters. Experimental tests have been carried out to find out the relationship between the investigated process parameters and surface roughness. Moreover, these experiments are used to validate the developed ANN and theoretical models. The result of the theoretical and the proposed ANN models shows good agreement with the experimental values. The average of the recorded errors was 4.01% and 6.32% for the ANN and the theoretical models, respectively.