The influence of technological parameters on cutting force components in milling of magnesium alloys with PCD tools and prediction with artificial neural networks

Abstract

Cutting force components determined experimentally in milling of AZ91HP and AZ31 magnesium alloys with a PCD milling were compared with the data from simulation with neural networks. The process was carried out at fixed tool geometry, workpiece strength properties, technological machine properties, radial and axial depth of cut. We monitored how the change of specific technological parameters (vc, fz) affects the cutting force components Fx, Fy and Fz. Machining tests have shown a significant influence of technological parameters on the observed cutting forces and their amplitudes. The simulations with Statistica Neural Network software involved two types of neural networks: MLP (Multi-Layered Perceptron) and RBF (Radial Basis Function). The results of our present and former studies in the field are highly important for the safety of magnesium alloy machining (stability) and plastic deformation of the workpiece excessive cutting forces and temperature in the cutting area.