MACHINE LEARNING-BASED SURFACE QUALITY PREDICTION IN INTELLIGENT TURNING OPERATIONS

Abstract

Surface quality is one of the most important indicators of machining performance in precision turning operations because it directly influences dimensional accuracy, fatigue strength, wear resistance, corrosion behavior, and product reliability. Conventional surface quality assessment relies on post-process inspection, which increases production time and manufacturing costs. Machine learning provides an intelligent approach for predicting surface quality using real-time machining data before the completion of machining operations. This paper proposes a machine learning-based framework integrating intelligent sensors, predictive analytics, Industrial Internet of Things (IIoT), cloud-based manufacturing analytics, and adaptive process monitoring for accurate surface quality prediction in turning operations. The proposed methodology utilizes machining parameters, sensor measurements, and historical production data to develop predictive models capable of estimating surface roughness under varying machining conditions. Experimental evaluation demonstrates improvements in prediction accuracy, machining stability, tool utilization, production efficiency, and manufacturing quality. The proposed framework provides a scalable and intelligent solution for predictive surface quality monitoring in Industry 4.0 manufacturing environments. Keywords— Machine Learning, Surface Quality Prediction, Turning Operations, Surface Roughness, Intelligent Manufacturing, Predictive Analytics, IIoT, Smart Manufacturing.