Optimization of milling operation parameters using Python-assisted GRA for enhanced surface quality and material...

Modern manufacturing's paradigm has changed a lot with the inclusion of optimization and smart manufacturing techniques. In this work, the performance of milling operation of magnesium alloy (Mg-AZ61) has been studied by using Box-Behnken Design (BBD) with Grey Relational Analysis (GRA). The main aim of this work is to optimize the operating parameters for better surface quality. In the milling experiments, important key process parameters namely spindle speed, axial depth and cutting feed rate were considered. The Box-Behnken experimental design matrix is prepared to conduct the milling trials in a systematic manner. Then GRA is applied to evaluate the relationship between the operating parameters and the surface integrity. The measured data were normalized and the best parameter combination was obtained by GRA. The GRA identified the optimum process parameters within the investigated experimental domain. The optimized operating conditions produced improved surface quality while maintaining satisfactory material removal performance. The obtained results demonstrate the effectiveness of the proposed BBD-GRA framework for multi-response optimization of Mg-AZ61 milling. The proposed BBD-GRA model predicted an optimized surface finish of 0.3168 µm, which was subsequently validated through confirmation experiments. This indicates a substantial, improvement as compared to the non-optimized conditions. Moreover, this paper presents the potential of combining GRA with machine learning models for adaptive and intelligent manufacturing systems.