Application of Machine Learning Techniques Toward Time- Based Change in Track Condition Using an Onboard Sensor in Revenue-Service Rolling Stock

Principal Investigator/Researcher

Dr. Farrokh Jazizadeh, Virginia Tech
Start: September 1, 2019
End: August 31, 2020

Project Description

Condition monitoring of rail infrastructure is an important task to ensure safety and ride quality. The increasing travel demands of the rail network due to higher miles traveled requires regular monitoring of the infrastructure and efficient processing of the data for timely decision-making. Despite the regular data collection on different parameters such as acceleration and track geometry, the data processing is commonly performed to document the track performance and maintenance without further knowledge discovery to realize all the potential from historical data. Motivated by the wealth of historical track data in practice, this paper investigates the feasibility of using onboard data that is repeatedly collected over a period of time on a segment of the track to potentially identify changes to the track. The proposed approach has been envisioned to learn from repeated historical time-series data to identify both the location and timing of unexpected changes to the track system. To account for stochastic nature of the collected data, associated with the temporal mismatch between the time-series across different inspection runs, we propose a framework by adopting the concept of Matrix Profile without relying on time series synchronization. The approach divides the entire data into smaller track segments, performs extensive similarity search of time-series signatures, and associate locations with higher dissimilarity to changes of the track either due to maintenance or a potential defect. To demonstrate the efficacy and potential of the method, evaluation on both synthetic data and the field geometry data from a revenue- service Class I railroad has been conducted. The findings provide promising results in predicting the location of track changes with a reasonably high degree of certainty, with automated offline analysis.

Implementation of Research Outcomes

The research heavily relies on filed data. The implementation of the research outcome will be continually occurring throughout the course of the project.

Implementation of Research Outcomes

Flow Diagram for Track Change Identification Machine Learning Strategy from Repeatedly Collected Data

Impacts/Benefits of Implementation

This project is expected to have a major impact on the diagnosis and prognosis of track maintenance. It is also expected to have a major impact on condition-based maintenance of the track, which in turn will have a significant effect on improving safety and reducing maintenance of the way costs.

Web Links