NameExeura S.r.l. - Spin-off dell'Università della Calabria


TitleFault Detection and Explanation through Big Data Analysis on Sensor Streams
Project id.117
Reference sectorICT
IP Protection LevelNo patent as yet
Description of the innovation projectFault prediction has become an important topic for the recent years as, by providing effective methods for predictive maintenance, it allows companies to perform important time and cost savings. We developed an application to predict and explain, based on diagnostic data, door failures on metro trains. Hence, the aim of the project was twofold: first, devising supervised techniques that are capable of early detecting door failures; second, describing failures in terms of properties distinguishing them from normal behavior. An experimental evaluation was performed to assess the quality of the proposed approach.
State of dev.Concept
Industrial applicationPrognostics
Market segmentBig Data Analytics (in Italy, Business Analytics market grew in 2015 by 14%, reaching 790 M€, 16% of which is Big Data)
Advantage factorEnabling predictive maintenance as opposed to corrective maintenance
Commercial challengeGeneralise analysis approach developed so far, in order to bring maintenance cost reduction to different vertical markets (such as energy&utilities, aerospace, healthcare)
Publications and Customer ReferecesSebastian Kauschke, Frederik Janssen, and Immanuel Schweizer. On the challenges of real world data in predictive maintenance scenarios: A railway application. In KDML: Workshop on Knowledge Discovery,Data Mining and Machine Learning, October 2015