Optimization of milling process parameters and prediction of abrasive wear rate increment based on cutting force experiment

Tuning the parameters of Computerized Numerical Control (CNC) is essential for practical manufacturers. Well configured ensure efficiency production and accuracy products. However, with abrasive wear on flank milling cutter, processing should re-configure to adapt increment wear. This paper aims propose a method predict rate cutter optimize CNC milling. Firstly, we set cutting data acquisition system sample time force among X, Y coordinates based five-factor four-level orthogonal experiments. Then, sampled transformed into by applying incremental model. Next, five are optimized gray relational method, which takes limited face non-increasing as constrained conditions. We obtain relationship between increment. also find basic principle selecting process reduce without increasing time. The experimental results verify that make degree increase 0.02, decreases 0.42432 × 10 −10 mm 3 /s affecting efficiency. In prediction section, Back Propagation (BP) neural network, an accurate model from measurable factors cutter. maximum error predicted value actual 0.0003, curve fits well curve. From perspective prediction, it provides new idea online tool monitoring.