Intelligent System for Material Hardness Detection in Milling

This study introduces a methodology to address multi-objective optimization challenges in the milling of Ti-6Al-4V, focusing on roughness, material removal rate (MRR), and cutting time. Input parameters such as lubricant type, tool type, cutting speed, feed rate, and depth of cut were considered. Neural networks were employed to model objective functions, which were then optimized using a particle cluster optimization technique. The analysis revealed that cutting time, influenced by the feed rate, significantly impacts cutting temperature due to increased friction between the tool and workpiece. Using coolant effectively regulates cutting temperature, maintaining stability even with varying cutting parameters. A Pareto-optimal solution set was developed, enabling the simultaneous minimization of roughness and cutting time while maximizing MRR. The integration of neural network-based models with particle cluster optimization demonstrates a robust approach to achieving balanced performance in high-demand machining applications.