Continuous improvement of HSM process by data mining
- 136 Downloads
The efficient use of digital manufacturing data is a key leverage point of the factories of the future. Automatic analysis tools are required to provide smart and comprehensible information from large process databases collected on shopfloor machines-tools. In this paper, an original and dedicated approach is proposed for the data mining of HSM (High Speed Machining) flexible productions. It relies on an unsupervised learning (by statistical modelling of machining vibrations) for the classification of machining critical events and their aggregation. Moreover, a contextual clustering is suggested for a better data selection, and a visualization of machining KPI for decision aiding. It results in new leverages for decision making and process improvement; through automatic detection of the main faulty programs, tools or machine conditions. This analysis has been performed over two spindle lifespans (18 months) of industrial HSM production in aeronautics and results are presented, which assess the proposed approach.
KeywordsMonitoring Machining Data mining
The financial support of the French government on FUI QuaUsi and ANR SmartEmma (ANR-16-CE10-0005) is acknowledged. The authors also thank the contributions of the industrial partners.
- Abellan-Nebot, J. V., & Romero Subirón, F. (2010). A review of machining monitoring systems based on artificial intelligence process models. International Journal of Advanced Manufacturing Technology, 47(1), 1–21.Google Scholar
- Ben Chabane, S., Stoica Maniu, C., Camacho, E., Alamo, T., & Dumur, D. (2016). Fault detection using set-membership estimation based on multiple model systems. In European control conference, Aalborg, Denmark (pp. 1105–1110).Google Scholar
- Eleftheriadis, R. J., & Myklebust, O. (2015). Benchmark and best practice of IFaCOM industrial demonstrators. In 2015, 9th CIRP conference on intelligent computation in manufacturing engineering, procedia CIRP (Vol. 33, pp. 311–314).Google Scholar
- IEC 62541-1. (2016). OPC unified architecture—Part 1: Overview and concepts. International Electrotechnical Commission.Google Scholar
- Ritou, M., Rabréau, C., Loch, S. Le, & Furet, B. (2018). Influence of spindle condition on the dynamic behaviour. Annals of the CIRP, 67(1), 413–416.Google Scholar
- Vijayaraghavan, A., Huet, L., Dornfeld, D., Sobel, W., & Blomquist, B., & Conley, M. , (2009). Process planning and verification with MTConnect. Transactions of NAMRI/SMI, 37, 443–450.Google Scholar
- Whittaker, J. (2009). Graphical models in applied multivariate statistics. New York: Wiley.Google Scholar