Model-based monitoring and failure detection methodology for ball-nose end milling

Abstract

This paper presents a model-based monitoring and failure detection approach in ball-nose end milling process. A mechanistic force model has been established for high speed milling on hardened stavax steel with 6mm micro-grain tungsten carbide 2 flute ball-nose end mill. The threshold curve can be obtained off-line based on the process model as the cutting engagement conditions along the tool path are determined at the simulation stage. The measured cutting forces are monitored on-line to detect the faults by comparing them with the threshold curve at machining stage. If a fault is detected at certain position along the tool path, an intelligent predictive method developed in [1] is utilized to predict whether this fault will result in catastrophic failure. Experimental results are provided to demonstrate the feasibility of this approach. © 2007 IEEE.