Abstract
This study presents a method of anomaly detection within a gearbox by way of standardising temperature data. Assessing measured parameters in isolation is not sufficient to detect faults within a wind turbine. This technique uses temperature, rotational speed, and generator torque to detect a bearing fault within the gearbox. Standardising data allows a parameter to be analysed which also takes into consideration the operating state of the wind turbine, therefore providing a more holistic view of the health of the wind turbine and component being monitored.
Highlights
Wind power is the second largest energy producer in Europe with an installed capacity of 169GW [1]
Condition monitoring systems are beginning to play a major role in reducing the operations and maintenance costs by allowing better scheduling of maintenance and the avoidance of major component failures
Detecting anomalies within the wind turbine gearbox is made more challenging by the stochastic nature of the wind and the different operating states of the wind turbine
Summary
Wind power is the second largest energy producer in Europe with an installed capacity of 169GW [1]. The method presented builds a model which represents normal behaviour for the wind turbine generator. NNs have the ability to model nonlinear complex relationships between numerous input parameters and their associated outputs They have been used with high levels of accuracy for detecting faults in a number of methods presented in literature [6, 7]. The work presented in this paper describes a method of detecting abnormal behaviour through standardising data for multiple parameters. This standardised data can be used to construct a probability density function (PDF) for normal operating behaviour and thresholds applied based on the probability of a failure occurring. This is convenient for anomaly detection by allowing standardised raw temperature data to be analysed in relation to the thresholds to detect a fault or abnormal behaviour
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
