Journal of Fundamentals of Renewable Energy and Applications
Open Access
ISSN: 2090-4541
+44 1300 500008
ISSN: 2090-4541
+44 1300 500008
Zongchang Liu, Zhe Shi and Jay Lee
Intelligent Maintenance Systems � University of Cincinnati, USA
Posters & Accepted Abstracts: J Fundam Renewable Energy Appl
The emerging wind energy market has been growing exponentially during the past decade. As the number of wind turbines increases rapidly, there are fast-growing concerns for their maintenance and health management. Prognostics of turbine performance degradation and incipient faults in critical components can thus offer improvements in availability of wind turbines by enabling predictive maintenance. Supervisory control and data acquisition (SCADA) and condition monitoring system (CMS) have been widely adopted for such purpose. This paper provides a systematic framework for datadriven health prognostics of wind turbine, together with detailed analysis for different health modeling approaches adopted to various subsystems. Degradation assessment for turbine efficiency and incipient fault detection for drivetrain components will be highlighted. A cyber-physical system architecture is further proposed to integrate data analytics, decision support, and maintenance execution to adapt to big data environment of turbine fleets. Demonstration and implementation process of the proposed system on National Instruments LabVIEW platform and Watchdog Agent�® Toolkit are also provided in the case study section.
Email: liuzc@mail.uc.edu