DATA-DRIVEN DECISION SUPPORT FOR ADAPTIVE TURNING PROCESS OPTIMIZATION

Abstract

Adaptive turning process optimization has become increasingly important in intelligent manufacturing because machining quality, production efficiency, and operational sustainability depend on timely and accurate process decisions. Conventional turning parameter selection is generally based on static machining guidelines that cannot effectively respond to changing machining conditions during production. This paper proposes a data-driven decision support framework integrating machine learning, predictive analytics, Industrial Internet of Things (IIoT), Digital Twin technology, cloud manufacturing, intelligent sensors, and adaptive process control for optimizing turning operations in real time. The proposed methodology continuously analyzes machining data, predicts machining performance, and recommends optimal cutting parameters to improve surface quality, reduce tool wear, minimize energy consumption, and increase productivity. Experimental evaluation demonstrates improvements in machining quality, production efficiency, decision accuracy, operational reliability, tool utilization, and manufacturing sustainability. The proposed framework provides an intelligent, scalable, and Industry 4.0-ready solution for adaptive turning process optimization.