Research on Early Fault Diagnostic Method of Wind Turbines

Abstract

Challenging environmental factors combined with high and turbulent winds make serious demands on wind turbines and result in significant component fault rates. In this paper, an early fault diagnostic research is conducted upon wind turbines. Firstly, the SCADA (Supervisory Control and Data Acquisition) system is used to analyze the units’ long-hour operating data, preparing for the further modeling work. Then the MSET (Multivariate State Estimation Technique) is adopted to estimate the temperature of the gear box and to obtain a result of high accuracy; with the Moving Window Calculation (MWC), the residual value between the estimated value and the real value is studied to get the dynamic trend of its average value; according to this trend in training, we define the threshold region of the residual mean value. Considering a man-made deviation in the observation vectors, faults of the gear box are simulated and studied. When the residual mean value curve exceeds the setting thresholds, an alert will be given to remind the operators of hidden problems in the unit. Research shows that this early diagnostic method is quite effective in detecting the abnormal performance of wind turbines in a real-time manner.

DOI: http://dx.doi.org/10.11591/telkomnika.v11i5.2457