Prediction of Kerf and Groove Widths in CO2 Laser Cutting Process of PMMA Using Experimental and Machine Learning Methods

Abstract

Laser cutting has become a widely used technology in industrial production due to its high precision, fast processing capacity and widespread use in cutting many materials. Laser cutting of polymer materials is a widely preferred processing method. Polymer materials, especially thermoplastics and thermosets, have a wide range of applications and are used in various industries such as construction, automotive, packaging, medicine and electronics. Laser cutting of these materials has many advantages over other conventional cutting methods, as it cuts without contact and provides high precision and control. However, some difficulties are encountered during laser cutting. These difficulties include heat affected zone formation, kerf width at the cutting edge and surface roughness. Therefore, it is important to understand the effect of laser cutting on polymer materials and optimize the cutting parameters to improve the cutting quality. In this study, a comprehensive investigation was conducted to evaluate the effect of different laser cutting parameters (Focal plane, Cutting speed, Laser power) on the cutting quality of polymer materials. 27 different experimental trials were conducted with various combinations and the data obtained were analyzed using machine learning techniques such as artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS). The results of this study provide an important contribution towards determining the optimal cutting parameters for laser cutting of polymer materials and improving the cutting quality.