An artificial neural network model for laser transmission welding of biodegradable polyethylene terephthalate/polyethylene vinyl acetate (PET/PEVA) blends

Laser transmission welding is a quick, easy, and viable method to join plastic materials for several industrial domains. The main challenge for manufacturers is still on how to choose the input process parameters to achieve the best joint performance. Joining between PET (polyethylene terephthalate) films does not make an exception, with quality strictly depending on laser joining parameters. The purpose of the present study is to estimate the weldability of a polymeric material couple according to their thermal and optical properties. This paper investigates an experimental study of laser transmission welding of PET 100% and PET-PEVA (polyethylene vinyl acetate) 5%, 10%, and 15% sheets by a diode laser. In the present work, laser power and scan speed were considered as operational parameters, which have a significant influence on the quality of the joint zone. Then, the influence of PEVA aliquots in PET/PEVA blends, which altered the mechanical properties, such as joining behavior, mechanical characterization, and degradation level, was analyzed. In addition, an artificial neural network model is developed to achieve the optimal laser parameters. The obtained results proved the advantage of this model, as a prediction tool, for developing laser welding parameters.