Proactive maintenance, performance forecast, root causes analysis, cyber physical system
Maintenance is an important activity that creates additional value in the business process as well as new business models with a stronger service orientation. Physical systems (e.g. industrial machines, vehicles, renewable energy assets) and the environment where they operate, are monitored continuously by a broad and diverse range of intelligent sensors. This produce a massive amount of data that can be exploited to characterise the usage history, operational condition, location, movement and other physical properties of those systems.
These systems are part of a larger network of heterogeneous and collaborative systems (e.g. vehicle fleets or photovoltaic and wind turbine parks) connected via communication mechanisms able to operate in challenging environments. In this context, the overall concept of MANTIS was to provide a proactive maintenance service platform architecture based on Cyber Physical Systems. This platform provided performance forecast, prediction and prevention of imminent failures and scheduling of proactive maintenance activities.
Within the MANTIS project, we were involved in exploiting and analysing the data provided by Ilias Solutions and 3E. The Ilias Solution use case focused on providing a pragmatic end-to-end predictive maintenance solution for a large and diverse fleet of special purpose vehicles. The 3E use case focused on improving the performance of photovoltaic plants by understanding their losses and identifying root causes.
Within the MANTIS project, we developed generic exploratory data-driven methodologies to characterize the health state of an asset, based on a set of features (time-based, frequency-based, density-based and pattern-based) extracted from event logs and time series data.
Belgian consortium partners
Start date: 01/05/2015
End date: 31/07/2018
With the financial support of