MACHINE LEARNING-BASED OPTIMIZATION OF TURNING PARAMETERS FOR SURFACE ROUGHNESS AND TOOL WEAR

Abstract

Machining industries continuously seek higher productivity, improved surface quality, reduced tool wear, and optimized manufacturing costs to remain competitive in modern manufacturing environments. Conventional turning operations rely heavily on predefined machining parameters and operator experience, often resulting in inconsistent product quality, excessive tool wear, increased production costs, and inefficient resource utilization. Machine learning provides intelligent predictive capabilities by continuously analyzing machining conditions and identifying optimal cutting parameters that improve manufacturing performance. This paper proposes a machine learning-based optimization framework for turning parameters by integrating manufacturing data acquisition, predictive analytics, cloud computing, Industrial Internet of Things (IIoT), and intelligent decision support. The proposed framework continuously evaluates spindle speed, feed rate, depth of cut, cutting temperature, vibration, machining forces, and tool condition to optimize surface roughness while minimizing tool wear. Experimental analysis demonstrates significant improvements in machining quality, production efficiency, tool life, manufacturing consistency, and operational decision-making compared with conventional turning parameter selection approaches. Keywords: Machine Learning, Turning Operations, Surface Roughness, Tool Wear, Predictive Analytics, Smart Manufacturing, Industrial IoT, Manufacturing Optimization, CNC Machining, Intelligent Manufacturing.