Continuous improvement of HSM process by data mining

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.