Application Research of ARIMA Model in Wind Turbine Gearbox Fault Trend Prediction

摘要

The gearbox is one of the most important equipment of the wind turbine generators, so unscheduled shutdown and unexpected breakdown of the gearboxes are considered as key factors affecting the safe operation of the wind turbine. Because of the nonlinearity and non-stationary of the monitoring data on gearbox operational condition, the advantage of the auto-regressive integrated moving average (ARIMA) model based on time series autocorrelation analysis to predict the trend of the time series is studied, and a fault trend forecasting method based on the ARIMA model is proposed. The effectiveness of the method is verified by the supervisory control and SCADA data of the outlet pressure of the gearbox oil pump. The experimental results show that this method can adapt to the changing features of monitoring data on gearbox operational condition over time, and reflect trend in operational performance to some degree. Thus, the high prediction accuracy and wide application makes it a valuable reference for the prediction of fault trend in other parts of wind turbines.