Abstract

The paper introduces the new method to estimate vertical gauge irregularity from accelerations of the bogie using ICA (Independent Component Analysis), and examines the performance through the numerical simulation of a travelling bogie. For safety on railway systems, techniques to estimate the gauge irregularity and identify the dynamical properties of the railway vehicles are required, however they are complicated. The authors propose to apply ICA to monitor the railway system. ICA only presumes the independency of source signals, so no parameters of mixing process is required. Therefore, it is expected that ICA can identify the gauge irregularity without specifications of railway bogie. To simplify the discussion, only the vertical and pitch motions of the bogie are considered, while the dynamics of the car body is neglected. The velocities and the displacements are calculated by integrating and double integrating the measured accelerations, respectively. They are treated as parts of the observed data sets as well as the accelerations. By using ICA, the similar shape to the input irregularity is estimated, and it is shown that the ICA is effective to monitor the railway system.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call