We propose a framework of self-aware machines based on data collected using the MTConnect protocol. Beyond exist- ing 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 pro- cesses. 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 pro- cesses. 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 from two Mazak machine tools.
How to Cite
condition monitoring, early fault detection, self-aware machine
Chen, C., Zhang, B., Vachtsevanos, G., & Orchard, M. (2011). Machine condition prediction based on adaptive neuro-fuzzy and high-order particle filtering. IEEE Transactions on Industrial Electronics, 58(9), 4353- 4364.
Coble, J., & Hines, J. W. (2009). Identifying optimal prognostic parameters from data: a genetic algorithms approach. In Proceedings of the annual conference of the prognostics and health management society.
Filzmoser, P., Garrett, R. G., & Reimann, C. (2005). Multivariate outlier detection in exploration geochemistry. Computers & Geosciences, 31(5), 579-587.
Filzmoser, P., Maronna, R., & Werner, M. (2008). Out- lier identification in high dimensions. Computational Statistics & Data Analysis, 52(3), 1694-1711.
Hodge, V. J., & Austin, J. (2004). A survey of outlier detection methodologies. Artificial Intelligence Review,22(2), 85-126.
Kohonen, T. (Ed.). (2001). Self-organizing maps. Springer. Liao, L., Edmondson, Z., & Ludwig, H. (2012). Plug and prognosis - condition monitoring, diagnosis and life time prediction. ATP edition, 54(10), 52-56.
Liao, L., & Pavel, R. (2012). Machine tool feed axis health monitoring using plug-and-prognose technology. In Proceedings of the 2012 conference of the society for
machinery failure prevention technology.
Meinshausen, N. (2006). Quantile regression forests. Journal of Machine Learning Research, 7, 983-999. MTConnect. (2009). Mtconnect standard part 1-overview and protocol, version 1.01 (Tech. Rep.). MTConnect Institute.
Rougier, N., Boniface, Y., & Universit, L. (2011). Dynamic self-organising map. Neurocomputing, 11(74), 1840-1847.
Savoye, Y. (2012). Iterative cage-based registration for dynamic shape capture. In Acm Siggraph 2012 posters.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author 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.