A Self-Aware Machine Platform in Manufacturing Shop Floor Utilizing MTConnect Data

We propose a framework of self-aware machines based on data collected using the MTConnect protocol. Beyond existing applications of OEE (Overall Equipment Effectiveness) reporting, the proposed framework integrates multiple sources of information for work-piece and machine condition monitoring, and equipment time to failure prediction in manufacturing processes, and provides feedback to shop supervisor. Firstly, we propose a method to predict component wear and failure based on operational data. ICP (Interactive Closest Point) algorithm is used to find the best matching tool path given a certain tool number to identify similar machining processes. The result of ICP tool path matching, together with other parameters such as spindle speed, feed rate and tool number, are used to adaptively cluster the machining processes. For each process cluster, a particle filter based prognostic algorithm is used to predict tool wear and/or spindle bearing failure. Secondly, we propose to use anomaly detection methods to detect changes in normal behavior of the machines. Various machine learning algorithms are utilized to detect anomalies based on real-time data, and a voting mechanism is used to decide when to trigger an alarm. Thirdly, the axes traverse is aggregated to provide a measure of the wear on various axes in the machine, which is correlated to errors in position comparing to the commanded positions and nominal tool paths. Spindle load verse rotating speed is also examined to facilitate shop floor scheduling to avoid damage caused by unintentionally excessive machine usage. The proposed framework has been demonstrated using published data Linxia Liao et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. from two Mazak machine tools.