In the present paper, to predict the process relation between laser-assisted machining parameters and machinability characteristics, statistical models are formulated by employing surface response methodology along with artificial neural network. Machining parameters such as speed of cut; the rate of feed; along with the power of laser are taken as model input variables. For developing confidence limit in collected raw experimental data, the full factorial experimental design was applied to cutting force; surface roughness; along with flank wear. Response surface method (RSM) with the least square method is used to develop the theoretical equation. Furthermore, artificial neural network method has been done to model the laser-assisted machining process. Then, both the models (RSM and ANN) are compared for accuracy regarding root mean square error (RMSE); model predicted error (MPE) along with the coefficient of determination (R2). The results show that the ANN model estimates the machinability indices with high accuracy that provides a maximum precision benefit range of about 10% - 22% than RSM model.
Empirical and Artificial Neural Network Modeling of Laser Assisted Hybrid Machining Parameters of Inconel 718 Alloy
Sae Technical Papers
International Conference on Advances in Design, Materials, Manufacturing and Surface Engineering for Mobility ; 2018
2018-07-09
Aufsatz (Konferenz)
Englisch
NUMERICAL AND EXPERIMENTAL INVESTIGATION OF LASER-ASSISTED MACHINING OF INCONEL 718
British Library Online Contents | 2008
|Modeling subsurface deformation induced by machining of Inconel 718
British Library Online Contents | 2017
|Optimization of Nd:YAG-Laser Welding Process for Inconel 718 Alloy
British Library Conference Proceedings | 2007
|