Robust Lifetime Estimation with Small Sample Sized High Speed Railway ETCS Component Data

Railway maintenance and efficient operation has been an important issue for a safe rail traffic. When an unexpected malfunction occurs on various components on the train or on the railway system, it may result in unscheduled maintenance which may cause the rail traffic to stop. In this paper, we study the random failure model of some frequently malfunctioning high-speed railway equipment based on the statistical analysis of the real data of failure records in Turkey. Popular distribution functions and parameter estimation methods have been used considering that the data has a small sample size, and it may contain outliers. In this study, we showed that for the case of a few numbers of failure data, the L-moments method gives effective results when there exists no outlier and the robust-M method gives effective results when there exists an outlier or outliers.