ICM-Wind: Semantics-Empowered Fluid Condition Monitoring of Wind Turbines

Matthias Klusch, Ankush Prabhu Meshram, Patrick Kapahnke, A. Schuetze

In: Proc. 29th ACM Symposium On Applied Computing. ACM Symposium On Applied Computing (SAC-14) 29th ACM Symposium on Applied Computing March 24-28 South Korea ACM Press 2014.


Condition-based maintenance of wind turbines requires experts to interpret highly complex interdependencies between measured sensor data and system conditions for failure recognition and diagnosis. We present the first system, called ICM-Wind, for semantics-empowered fluid condition monitoring (FCM) in wind turbines. It monitors the condition of fluids, specifically lube oil in the wind turbine gearbox, and does not only recognize actual and the onset of failures of FCM sensors, the gear and related components of the turbine, but provides knowledge-based failure diagnosis support to non-experts. For this purpose, the ICM-Wind system performs in particular off-line semantic sensor data analysis by applying different means of semantic reasoning, either individually or in combination, on FCM relevant data and domain knowledge encoded in OWL2 and with SPIN rules. The practical application of the system prototype was successfully tested in cooperation with the HYDAC Filter Systems GmbH based on a two-year recording of FCM multi-sensor and operational data for two wind turbines of a regional on-shore wind farm operated by the ABO Wind AG.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence