Abstract
One of the problems of current monitoring systems is lack of flexibility against changes in machining environment. The purpose of this research is to construct a monitoring system that can flexibly cope with changes in the machining environment without sacrificing the accuracy of detection. Developed monitoring system is conducted by plural decision-making systems, and is applied to monitoring of chipping of the end mill. The subsystems employ artificial neural networks based on the cutting force signals and the cutting conditions. It is concluded that the flexibility and the reliability of the monitoring system is much improved by operating the subsystems in parallel.
