Railroad Infrastructure Health Assessment Using Multiway Data Factorization - A Case for Railroad Track Geometry Data

Start: June 2017, End: September 2018

Principal Investigator/Researcher

Professor Ni Attoh-Okine and Offei Adarkwa, University of Delaware

Project Description

Large amounts of railroad track geometry data are generated by both passenger and freight railroad systems in the U.S. and results from the analysis of this data could serve as the basis for proactive maintenance to improve safety and system performance. Different methods have been used to analyze track geometry data but this work focuses on how multiway data analysis can be used to generate insights from this data. The results obtained from this analysis are compared to the 2 dimensional approach for analyzing the same data in order to showcase the main advantages associated with using multidimensional data analysis techniques in the management of railroads.

Implementation of Research Outcomes

This report shows the potential benefits of using a multiway data modeling approach to analyze railroad infrastructure data collected over time. The multiway decomposition approach revealed Surface and Gage measurements as being the most dominant variables responsible for almost half of the variation in the data set. This research thus allows for a new approach to track geometry analysis modeling which will be implemented as part of ongoing UTC program activity.

Impacts/Benefits of Implementation

This approach has not been implemented to date in the form of a maintenance planning model but it offers significant potential in improved track geometry maintenance modeling, planning and implementation.