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

Area of Science:

• Manufacturing Engineering
• Materials Science
• Optimization Techniques

Background:

• Modern manufacturing increasingly relies on optimization and smart techniques.
• Magnesium alloys, like Mg-AZ61, are crucial in various industries but require precise machining.
• Surface quality is a critical performance indicator in precision manufacturing.

Purpose of the Study:

• To optimize the milling process parameters for enhanced surface quality of Mg-AZ61 alloy.
• To investigate the relationship between key process parameters and surface integrity.
• To validate the effectiveness of a combined Box-Behnken Design and Grey Relational Analysis approach.

Main Methods:

• Utilized Box-Behnken Design (BBD) for systematic experimental planning of milling trials.
• Applied Grey Relational Analysis (GRA) to normalize data and determine optimal parameter combinations.
• Considered spindle speed, axial depth, and cutting feed rate as key process parameters.

Main Results:

• GRA identified optimal process parameters within the experimental domain, leading to improved surface quality.
• The optimized conditions achieved a predicted surface finish of 0.3168 µm, validated by confirmation experiments.
• Demonstrated a substantial improvement in surface finish compared to non-optimized milling conditions.

Conclusions:

• The BBD-GRA framework is effective for multi-response optimization in Mg-AZ61 milling.
• The study highlights the potential of integrating GRA with machine learning for intelligent manufacturing.
• Optimized milling parameters enhance surface quality while maintaining material removal performance.