Modeling and optimization of kerf taper and surface roughness in laser cutting of titanium alloy sheet

Laser cutting of titanium and its alloys is difficult due to it's poor thermal conductivity and chemical reactivity at elevated temperatures. But demand of these materials in different advanced industries such as aircraft, automobile and space research, require accurate geometry with high surface quality. The present research investigates the laser cutting process behavior of titanium alloy sheet (Ti-6Al-4V) with the aim to improve geometrical accuracy and surface quality by minimizing the kerf taper and surface roughness. The data obtained from L-27 orthogonal array experiments have been used for developing neural network (NN) based models of kerf taper and surface roughness. A hybrid approach of neural network and genetic algorithm has been proposed and applied for the optimization of different quality characteristics. The optimization results show considerable improvements in both the quality characteristics. The results predicted by NN models are well in agreement with the experimental data.