A Decision-Making Approach for Sustainable Machining Processes Using Data Clustering and Multi-Objective Optimization

Achieving sustainable machining processes has become crucial in many industries order to support development goals (e.g., good health and well-being, decent work economic growth, affordable clean energy). Many attempts have been made optimize the sustainability aspect during offer optimized cutting conditions. However, there is a vital need develop decision-making approach that can be flexible optimal solutions for different scenarios. The current study offers new using data clustering (i.e., K-means clustering) multi-objective optimization methods grey relational analysis). Utilizing after phase provides decision maker with conditions clusters. developed validated through case includes five design variables feed, speed, nose radius, cooling strategy, rake angle), three outputs surface roughness, specific energy, unit volume time), four scenarios finishing, roughing, balanced, entropy). Three clusters were generated, obtained results compatible physical meaning of each studied scenario. Such an provide sufficient flexibility select settings various scenarios, as well freedom switch between and/or minimal effort.