Optimization of process parameters for turning of titanium alloy (Grade Ⅱ) in MQL environment using multi‑CI algorithm

摘要

The advancement of materials science during the last few decades has led to the development of many hard-to-machinematerials, such as titanium, stainless steel, high-strength temperature-resistant alloys, ceramics, refractories, fibre-reinforcedcomposites, and superalloys. Titanium is a prominent material and widely used for several industrial applications.However, it has poor machinability and hence efficient machining is critical. Machining of titanium alloy (Grade II) inminimum quantity lubrication (MQL) environment is one of the recent approaches towards sustainable manufacturing.This problem has been solved using various approaches such as experimental investigation, desirability, and with optimizationalgorithms. In the group of socio-inspired optimization algorithm, an artificial intelligence (AI)-based methodologyreferred to as Cohort Intelligence (CI) has been developed. In this paper, CI algorithm and Multi-CI algorithm havebeen applied for optimizing process parameters associated with turning of titanium alloy (Grade II) in MQL environment.The performance of these algorithms is exceedingly better as compared with particle swarm optimization algorithm,experimental and desirability approaches. The analysis regarding the convergence and run time of all the algorithms isalso discussed. It is important to mention that for turning of titanium alloy in MQL environment, Multi-CI achieved 8%minimization of cutting force, 42% minimization of tool wear, 38% minimization of tool-chip contact length, and 15%minimization of surface roughness when compared with PSO. For desirability and experimental approaches, 12% and 8%minimization of cutting force, 42% and 47% minimization of tool wear, 53% and 40% minimization of tool-chip contactlength, and 15% and 20% minimization of surface roughness were attained, respectively.