Cyber Physical System based Proactive Collaborative Maintenance (MANTIS) is an EU project, funded through ECSEL. It is a 3 year project, starting in May 2015.
Physical systems (e.g. industrial machines, vehicles, renewable energy assets) and the environment they operate in are monitored continuously by a broad and diverse range of sensors, resulting in massive amounts of data that characterize the usage history, operational condition, location, movement and other physical properties of those systems. The goal of the MANTIS project is to develop a proactive maintenance service platform architecture based on Cyber Physical Systems that will leverage the vast amounts of collected sensor data to estimate future system performance, to predict and prevent imminent failures, and to optimize maintenance.
Our focus in this project is on applying machine learning techniques to identify patterns in the sensor data corresponding to component failures for predicting system failures. In particular, we are interested in exploring data-driven methods for root cause failure analysis, remaining useful life identification of wearing components, and failure prediction on component and system level. In this project, we cooperate with Philips Consumer Lifestyle and Philips Health Care, who provide industrial use cases in factory automation and servicing of health care scanning equipment, which will support our research and validate our research results.
We are interested in answering the following questions in the context of MANTIS: