Predictive Modeling of Rail Track Geometry Defects Toward Improved Safety and Maintenance

September 22, 2016

About the Seminar

Track geometry defects have been identified as a major cause of train derailments. To maintain railroad safety, the Federal Railroad Administration has set track safety standards that require defects to be corrected or protected within a prescribed time limit. In current practice, track geometry cars classify the defects into two severity groups: yellow tags and red tags. 

Although a large volume of measurement data is currently being collected, track deterioration is a complex stochastic process whose many factors may not be captured by the data. This presentation outlined research focused on developing probabilistic models that account for the stochastic nature of track geometry deterioration. The new predictive model for track geometry defects will make reliable predictions on when a yellow tag defect will turn into red tag. In addition to improving safety, this model could enable more efficient planning for track maintenance.

Webcast

About the Speaker

Hadi Meidani is an assistant professor in the Department of Civil and Environmental Engineering at the University of Illinois at Urbana-Champaign. Prior to joining UIUC, he served as a postdoctoral research associate in the Department of Aerospace and Mechanical Engineering at USC and in the Scientific Computing and Imaging Institute at the University of Utah. His research interests are uncertainty quantification, Bayesian statistics, and surrogate-based modeling for civil engineering structures and systems.