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

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 6 mm 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 is utilized to predict whether this fault will result in catastrophic failure. Experimental results are provided to demonstrate the feasibility of this approach.