Condition monitoring of three-axis ultra-precision milling machine tool for anomaly detection

Abstract

Accurately and continuously monitoring ultra-precision machining (UPM) process is the foundation for subsequent diagnosis and optimization, then facilitating energy-saving, efficient production, and high-quality machining. However, comprehensive monitoring of UPM process has hardly been investigated systematically in previous studies. To cover the gap, this study examined the linkages among these parameters monitored in UPM process using a five-layers network for the first time. Subsequently, we proposed an advanced monitoring platform that integrates G-code command, installation sensors, and controller interface. This proposed platform incorporated with anomalies detection algorithm was finally employed and validated on a three-axis ultra-preciisiion miilllliing machiine tooll. Results showed that this proposed platform could successfully achieve anomaly identification using power consumption and X/Y/Z components force signals.