Optimization of the turning process by means of machine learning using published data

Abstract

Machining parameters play a critical role in the results of the turning process: cutting forces, dimensional accuracy, surface roughness, tool wear, etc. Manufacturers offer recommendations for their tools, but the complex relations between machining parameters make the process optimization process not straightforward. Researchers usually opt for performing experimental studies to optimize specific or multiple outputs of these processes. However, this approach is costly and time-consuming. Thus, in the present chapter, a methodology leveraging Machine Learning is introduced, capitalizing on extensive volumes of published data within the literature. Particularly, the chapter aims to study the surface roughness attained in turning the Ti6Al4V alloy.