Swarm intelligence based selection of optimal end-milling parameters under minimum quantity nano-green lubricating environment

Abstract

With the development of ideas such as green and sustainable processing, recently evolved lubrication methods are commonly used to resolve the disadvantages of the flood lubrication approach. In the minimum quantity lubrication (MQL) technology, a small lubricant mist is inserted into the tool-workpiece interface to achieve better lubrication. The present study, therefore, explored the viability of alumina-reinforced palm oil as a lubricant in the MQL environment. A diverse volume fraction of aluminium (0-1.4%) was mixed with palm oil, and the optimal concentration of nanoparticles (0.8%) was chosen through spectroscopic analysis. Subsequently, twenty-seven milling operations were carried out on Inconel 690 material under the best lubricating medium. Statistical analysis of the machining values was conducted using the main effect plot (MEP), empiric cumulative distribution (ECD), and analysis of variance (ANOVA). Besides, Response surface methodology (RSM) was used to create a mathematical equation between input and machining responses. Finally, the Particle Swarm Optimization (PSO) approach was applied to achieve an optimal machining environment: cutting speed = 88.348 m/min, feed rate = 0.108 mm/tooth, and depth of cut = 1 mm. The optimal machining conditions were confirmed by functional experimentation, which has shown that the mean error between the experimental and the predictive outputs is minimal (less than 2%).