Optimization of process parameter in AI7075 turning using grey relational, desirability function and metaheuristics

Even though metal may be effectively shaped by a variety of other manufacturing techniques, machining continues to play a significant role in industries. Turning is a conventional chip-forming operation that removes undesirable or surplus material from a cylindrical workpiece. The major objective of process optimization in turning operation research is focusing on the development of statistical modeling and optimization techniques for boosting production rate, lowering costs, and reducing product rejection. The current work aims to improve the CNC turning process of Al 7075 using coated carbide inserts. This investigation uses grey relational analysis, desirability function analysis, Multi-objective Genetic Algorithm (MOGA) and Multi-objective Genetic Particle Swarm Optimization (MOPSO) to optimize factors to minimize responses like surface roughness and cutting force. Comparative evaluation of results of optimum input parameter sets results in close agreement, both in traditional optimization and metaheuristic-based optimization. In particular, MOGA is found to be more efficient to solve this stated multi-criterion decision-making problem as compared to other methods.