Carbide tool life prediction and modeling in SiCp/Al turning process via artificial neural network approach

The experimental research and theoretical analysis of tool life and attached wear with the tool during turning operation of SiCp/Al 45%vol: Fraction has been carried out. This research proposed the machining factors affecting the wear of carbide tool and the laws of wear affecting the life expectancy of the tool. Artificial neural network (ANN) was utilized for analyzing the cutting process, the training of ANN achieved by back-propagation on the basis of three input parameters such as cutting speed, feed and depth of cut. The wear and damage of cutting tools in the machining process of composite materials also depend on SiC reinforced particles size and volume. The effects of workpiece material components and different cutting process parameters on the tool wear mechanism were thoroughly analyzed and measured. The main wear form on the cutting tool and its major causes for different wear patterns were recognized as adhesive and abrasive, for such phenomena the cutting speed held as a most influencing factor.