27 GA Based Multi Objective Optimization of the Predicted Models of Cutting Temperature, Chip Reduction Co-Efficient and Surface Roughness in Turning AISI 4320 Steel by Uncoated Carbide Insert under HPC Condition
Download citation file:
This paper deals with the optimization of the cutting variables which are cutting speed (Vc), feed rate (f), pressure (P) and flow rate (Q) of high pressure coolant (HPC) to obtain improved machining performances in turning AISI-4320 steel by uncoated carbide insert. An experimental study along with predictive models of cutting temperature (θ), chip reduction co-efficient (ξ) and surface roughness (Ra) has been carried out under response surface methodology (RSM). Multi-objective optimization has been carried out based on genetic algorithm (GA). Two conflicting objectives, minimizing cutting temperature and cutting force are simultaneously optimized against the constraint of surface roughness being less than 3 µm. The results show that θ, ξ and Ra can be well estimated through the models. Optimizing the models also returns a pareto optimality chart which returns optimized cutting variables.