The Investigation of A Self-adjusting Tool Wear Monitoring System

The structure of a self-adjusting tool wear monitoring system was proposed to improve classifying accuracy of tool wear and solve the problems of high design cost of tool condition monitoring system under multi machining modes and different machining condition. The monitoring features extracted from various sensor signals and selected automatically by synthesis coefficients change with difference in cutting conditions, tool quality, workpiece properties, etc, and the nonlinear relation between tool wear amounts and features were built through a novel sensor-integration strategy including localized neural networks that optimized by an adaptive learning algorithm, and integrated neural networks that fuse the outputs of subnets, the final results of monitoring system was given by decision algorithm that compare tool wear values at different time intervals. As demonstrated by examples of tool wear monitoring in milling and in turning, the self-adjusting monitoring system proposed in the paper has a number of advantages over the existing methods, provided with high classifying precision, high reliability and short design periods, so it is good for popularization in industry