Multiple Regression Method of Daily Average Mileage to Predict the Overhaul Plan of China Railway High-speed Electric Motor Unit

摘要

The total operation mileage of China high-speed railway network is more than 30 thousand kilometers, and over 3600 high-speed electric motor unit (EMU) come into service, which ranks China in the first place all over the world. It is of great significance to improve the operation efficiency of high speed railway by scientifically planning the overhaul process of EMU. The estimation of the average daily running mileage of EMUs is the basis of the calculation of the overhaul plans of EMU. This paper analyzed the influence of EMU routing, allocated number, on-line rate and advanced repair time coefficient on daily average mileage. Considering the relevance and regularity of EMU in the time dimension, this paper constructed a two-stage daily average mileage regression model. Firstly, based on the time series analysis of the daily average number of EMU, a prediction model of the daily average number of EMU in the next year was built, and then applied the multiple regression model to calculate the daily average mileage of future EMU. Finally, this paper predicted the average daily mileage of one type of EMU in 2020 by the model. Compared with the actual data, the final prediction error is less than 5.143%.