Abstract
Data collected from the supervisory control and data acquisition (SCADA) system are used widely in wind farms to obtain operation and performance information about wind turbines. The paper presents a three-way model by means of parallel factor analysis (PARAFAC) for wind turbine fault detection and sensor selection, and evaluates the method with SCADA data obtained from an operational farm. The main characteristic of this new approach is that it can be used to simultaneously explore measurement sample profiles and sensors profiles to avoid discarding potentially relevant information for feature extraction. With K-means clustering method, the measurement data indicating normal, fault and alarm conditions of the wind turbines can be identified, and the sensor array can be optimised for effective condition monitoring.
Highlights
Nowadays, wind power is considered as one of the most viable and sustainable resources worldwide [1]
There are 52 sensor signals left for parallel factor analysis (PARAFAC) analysis, which are associated are associated with the parameters defining the of the turbine such as the with the parameters defining the performance of performance the turbine operations, suchoperations, as the nacelle position nacelle 1); position
In order to examine whether each measurement value is indication of normal or abnormal operation, the first dimension is arranged with the 5002 measurement samples and the second dimension is only one associated with time
Summary
Wind power is considered as one of the most viable and sustainable resources worldwide [1]. In order for the SCADA system to work more accurately, it is essential to obtain enough information about the wind turbine’s operational condition and performance. This can be done by using different types of sensors and by monitoring different locations within the wind turbine. By using an appropriate clustering method, measurement samples can be classified and the sensor array can be optimised This method has not previously been applied to condition monitoring of wind turbines.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
