Wear prediction of metro wheels based on the ARIMA model

Based on the analysis of the measured wear data and the wear characteristics in terms the wheels of Guangzhou Metro Line 1, the accumulative wear prediction method of metro wheels based on the ARIMA(p,d,q) model is proposed in this paper. According to the time series modeling method of the ARIMA(p,d,q) model, the stationarity analysis and transformation of the metro wheel wear data are described at first. Then, with the application of the AIC criterion and the Maximum Likelihood Estimation method, the model order is determined and the model parameters are derived for the ARIMA(p,d,q) model. Finally, the flange thickness and the diameter of the metro wheels could be predicted by this developed ARIMA(p,d,q) model. The results show that the proposed prediction method is simple and effective for the short-term prediction of the metro wheel wear.