Anomaly detection using electrical signature analysis and machine learning: application to a CNC mill

Electrical Signature Analysis (ESA) is a powerful tool that uses the voltage and current signals of a machine to infer its health status. ESA can serve as a predictive maintenance tool for detecting common faults at an early stage, thus preventing expensive catastrophic failures and production outages, and extending equipment lifetime. In this study, a novel application of ESA and Machine Learning (ML) for working condition monitoring and health status assessment of a CNC mill is presented. Experimental results show the effectiveness of the proposed approach.