Intelligent Anomaly Detection of Machine Tools based on Mean Shift Clustering

Abstract

For a fault detection of machine tools, fixed intervention thresholds are usually necessary. In order to provide an autonomous anomaly detection without the need for fixed limits, recurring patterns must be detected in the signal data. This paper presents an approach for online pattern recognition on NC Code based on mean shift clustering that will be matched with drive signals. The intelligent fault detection system learns individual intervention thresholds based on the prevailing machining patterns. Using a self-organizing map, data captured during the machine’s operation are assigned to a normal or malfunction state.