Mixed Taguchi-Genetic Algorithms for Multiple Objectives Optimization Based on Mild Steel Turning Parameters

This research applied a hybrid approach integrating Taguchi method and Genetic Algorithms to address multi-objectives optimization (MOO) for turning operation with high-speed steel (HSS) cutting tools. The objective of this algorithm are to maximize the material removal rate (MRR) while minimizing cutting power consumption. The L9 orthogonal array experimental design plan was used in the experiments, which included four dependents variables: rake angle, cutting speed, feed rate and depth of cut. The experimental results were used to derive the prediction models for MRR and cutting power consumption in term of linear polynomial regression, demonstrating strong correlations and statistical significance. The cutting speed, feed rate, and depth of cut significantly influenced both MRR and power consumption. The rake angle of the HSS tool had slightly impact on MRR but can affect cutting power. A genetic algorithm was then used to optimize machining parameters, resulting in an optimal combination of rake angle, feed rate, cutting depth, and cutting speed. Verification experiments confirmed the effectiveness of the optimization process, exhibiting minimal deviations between predicted and actual results. The findings of this study offer significant insights for optimizing machining operations, enhancing efficiency, and minimizing energy consumption. The developed predictive models and optimized parameters can enhance the efficacy of high-speed steel tools in the turning of mild steel.