A Linear Forecasting Model and Algorithm for Running Time of Urban Rail Transit

A modified linear forecasting model is established in order to accurately forecast the running time of trains of urban rail transit.This proposed model computes the linear prediction coefficients based on orthogonal function and the rule of integrating minimum mean square error (MMSE).Sample data with different lengths is used to construct forecasting models.The effect of length of sample data and order of prediction on forecasting accuracy is analyzed by comparing computed results.The adjustment mechanism of sequential iteration-based data is then incorporated into this model to improve the accuracy of data in computing coefficients.The effects of the inter-station distances on forecasting accuracy are analyzed by comparing the results of this model before and after the transformation of distance under the unequal inter-station distances scenario.A linear transformation method of inter-station distances is incorporated into this proposed model to improve the precision of forecast.The results show that the average accuracy of forecast of this proposed model is 95.43% while which of the original model is 92.53%, increases by 3.13%;the accuracy of this model can be slightly improved by increasing the order of prediction, predictive accuracy of running time can be obviously improved by using the modified model in contrast with the original model.This proposed model is used to forecast the running time of trains of Shanghai Metro Line 2 as a case study, and the forecast error of this model is 17.4% less than the train′s motion model, which shows the applicability and high accuracy of this model.