Modelling and optimization of laser engraving qualitative characteristics of Al-SiC composite using response surface methodology and artificial neural networks

This work deals with the study of laser engraving process of Al-SiC composite by Q-switched Nd:YAG laser. A series of experiments have been conducted to investigate the effect of process parameters such as assistant gas flow, distance between surface of workpiece and beam focus location (defocus), repetition rate frequency, and pumping current on the quality parameters such as depth, width, and contrast of engraved zone. A central composite design method was used to design experiments based on the response surface methodology (RSM). Empirical models were developed to create relationships between control factors and response variables by considering analysis of variance (ANOVA). To estimate the qualitative characteristics of the process, a feed forward back-propagation neural network (FF-BPNN) was used and accuracy of BPNN method was compared with mathematical models based on RSM model. Finally, the desirability function was used to optimize the multiple responses.