Productivity improvements have major impact on economy and competitiveness in manufacturing industry. Industrial maintenance contributes largely to this competitiveness through reliability and availability of production equipment. In continuous production industries (energy, chemical, food, cement or paper sectors) the ratio “maintenance costs/added value product” is even higher than 25%. Default component or process failure stop the whole production, therefore predictive maintenance is a critical issue. In this context, the project SUPREME, funded within the 7th Framework Program of the European Commission, aims to provide new tools to adapt dynamically the maintenance and operation strategies to the current condition of the critical components in production equipment. It also proposes to develop a reference model to achieve an integrated approach to optimal energy consumption. The main goal of the department‘s Intelligent Data Analysis (IDA) lab within the project is to develop machine-learning based predictors of failures (paper breakages) in a paper mill plant.