Identifıcation of optimum milling parameters through machine learning

Milling operations are commonly utilized in many industries. Productivity ratebecomes prominent in the industries such as automotive due to the need for high-volumemanufacturing or the requirement to produce large die casts, whereas the aerospace andelectronics industry must focus on precise manufacturing that does not exceed tolerancebands. This condition results in different types of optimization equations such as maximizingmaterial removal rate with respect to machining center limits or minimizing the tooldeflection and chatter risk to achieve conforming parts. Both optimizations will indicate amajor effect on the unit cost of the product, hence they should describe the trade-off betweenthe machining time and tool cost and help the selection of the optimum cutting parametersand tool dimensions.The increase in AI implementations and their promising accuracy levels were themain reasons to choose the supervised machine learning (ML) to investigate the optimumsolution. In this thesis, Titanium alloy (Ti-6-4) workpiece material cutting process withcarbide tool has been simulated for many different cutting tool and process parameterscenarios to calculate cutting forces, chatter status, surface form errors, machining time, toollife and tool breakage. Following the data preparation step, Gaussian Process Regressionmodel has been computed for the optimization step with Bayesian approach.