Abstract
Achieving optimal lubrication during machining processes, particularly turning of stainless steel, remains a significant challenge due to dynamic variations in cutting conditions that affect tool life, surface quality, and environmental impact. Conventional Minimum Quantity Lubrication (MQL) systems provide fixed flow rates and often fail to adapt to changing process parameters, limiting their effectiveness under fluctuating thermal and mechanical loads. To address these limitations, this study proposes an ambient-aware adaptive Auto-Tuned MQL (ATM) system that intelligently controls both nanofluid concentration and lubricant flow rate in real time. The system employs embedded sensors to monitor cutting zone temperature, surface roughness, and ambient conditions, linked through a feedback-driven control algorithm designed to optimize lubrication delivery dynamically. A Taguchi L9 design was used for experimental validation on AISI 304 stainless steel turning, investigating feed rate, cutting speed, and nanofluid concentration. Results demonstrate that the ATM system substantially improves machining outcomes, reducing surface roughness by more than 50% and cutting force by approximately 20% compared to conventional MQL. Regression models achieved high predictive accuracy, with R-squared values exceeding 99%, and surface analyses confirmed reduced adhesion and wear under adaptive lubrication. The proposed system offers a robust approach to enhancing machining performance and sustainability through intelligent, real-time lubrication control.