Vibration-based tool condition monitoring in milling of Ti-6Al-4V using an optimization model of GM(1,N) and SVM

Titanium alloys are the difficult to cut metals due their low thermal conductivity and chemical affinity with tool material. Since vibration is a replica of wear surface roughness, present study has proposed methodology for estimating roughness based on milling Ti-6Al-4V alloy using cemented carbide mill cutter. Experiments conducted at optimum levels cutting speed, feed per tooth, depth cut, experimental results vibration, wear, collected until flank reached 0.3 mm (ISO3685:1993). In next stage, an optimization model grey prediction GM(1,N) system support vector machine (SVM) used estimated related vibration. The predicted values compared results. average error 3.03% as 0.7% respectively while SVM 7.67% 4.45%, respectively.