01373755

Component

North American railroads have been experiencing traffic demand growth and increasing capacity constraints. Effective capacity management is thus crucial to a railroad company’s success, and the first step in capacity management is to measure and monitor capacity and congestion. This research established a development process for constructing parametric capacity models for single and double-track railroads with simulation results using regression and neural network (NN) techniques. Both regression and NN techniques were applied to the development of parametric models for typical Midwestern, North American, single-track and double-track mainline subdivision. The developed regression model performs better in single-track capacity estimation, whereas NN outperforms the regression model on double-track capacity. Using this capacity evaluation tool can determine the efficiency of current operations and an objective basis to assess the need for capital expansion projects.

This paper was sponsored by TRB committee AR040(1) Rail Capacity

01362476

12-1288

English

22p

2012

Transportation Research Board 91st Annual Meeting

Digital/other

Figures; References; Tables

Double track; Neural networks; Parametric analysis; Railroad transportation; Regression analysis; Simulation; Single track

Rail line capacity

North America

Operations and Traffic Management; Planning and Forecasting; Railroads; I72: Traffic and Transport Planning

Transportation Research Board Annual Meeting 2012 Paper #12-1288

TRIS, TRB

Feb 8 2012 5:01PM