Abstract
The capability to predict the behaviour of machines is nowadays experiencing a tremendous growth of interest within Industry 4.0-based manufacturing systems. The route to this end is not straightforward when Run-To-Failure (RTF) data are poorly available or not available at all, thus a strategy must be properly defined. In this proposal, assuming no RTF data, a novelty detection is combined with random coefficient statistical modelling for Remaining Useful Life (RUL) prediction. This approach is formalized by means of a reference framework extending the ISO 13374 - OSA-CBM standards. The framework guides the integration of novelty detection and RUL prediction finally implemented in the scope of a Flexible Manufacturing Line part of the Industry 4.0 Lab of the School of Management of Politecnico di Milano.
