OPTIMAL PREDICTION AND DESIGN OF SURFACE ROUGHNESS FOR CNC TURNING OF AL7075-T6 BY USING THE TAGUCHI HYBRID QPSO ALGORITHM

This paper combines the Taguchi-based response surface methodology (RSM) with a multi-objective hybrid quantum-behaved particle swarm optimization (MOHQPSO) to predict the optimal surface roughness of Al7075-T6 workpiece through a CNC turning machining. First, the Taguchi orthogonal array L-27 (3(6)) was applied to determine the crucial cutting parameters: feed rate, tool relief angle, and cutting depth. Subsequently, the RSM was used to construct the predictive models of surface roughness (R-a, R-max, and R-z). Finally, the MOHQPSO with mutation was used to determine the optimal roughness and cutting conditions. The results show that, compared with the non-optimization, Taguchi and classical multi-objective particle swarm optimization methods (MOPSO), the roughness R-a using MOHQPSO along the Pareto optimal solution are improved by 68.24, 59.31 and 33.80%, respectively. This reveals that the predictive models established can improve the machining quality in CNC turning of Al7075-T6.