Exploit fleet of machines data to optimise its performance and maintenance

After two successful editions, a third edition of the ‘Fleet-based analytics for data-driven operation and maintenance optimisation’ seminar is organised on 13 December. The seminar focuses on the challenges of optimising the operation and maintenance of a fleet of machines by means of data-driven analytics and hybrid modelling strategies.

Many companies operate a fleet of (nearly identical) machines, e.g. wind turbines, compressors, professional vehicles, etc., and are able to continuously monitor the operation of these machines thanks to ever-ongoing evolutions in sensor, communication and data storage technologies. Today however, they still do not exploit the enormous amount of collected data to its full potential. Maintenance and service personnel predominantly make use of the data for monitoring the proper machine operation or as heuristics to diagnose failures after they have occurred.

Some lead user companies are investigating more advanced exploitation of this data, e.g. for moving from reactive to proactive maintenance, but they still mostly consider the individual machine level. This leaves a huge potential untapped at the fleet level: a specific machine might function within its operational boundaries but might be underperforming in comparison to similar machines due to misconfiguration or imminent failure, for example. By considering the behaviour of a single machine with respect to that of its fleet, more detailed and more accurate actionable insights can be extracted.

During this seminar, we will have a keynote by Przemyslaw Jakub Gromala from the Robert Bosch GmbH on Prognostics and Health Management of safety relevant electronics for future application in autonomous driving, who will certainly inspire you and give you realistic insights from an industrial perspective. Furthermore, the opportunities that fleet-based analytics create as well as the challenges encountered in exploiting fleet-based data will be illustrated with several industrial real-world use cases showing the potential of the approach in for example industrial machinery, and (renewable) energy.

This event is organised in the context of the SBO-project HYMOP, in which VUB, Sirris, KU Leuven, imec and the University of Antwerp study hyper-modelling strategies on multi-stream time-series data for operational optimisation, in collaboration with an industrial advisory committee. During this workshop, the technologies that were realised in the past three years of the project will be detailed and the possibilities for industrial valorisation will be explored. More information on this project can be found here.

Interested to know more about this topic? Ready to get inspired? Then join us on 13 December for our seminar!