Development of relationships and trending methodologies for railroad track component and geometry data

The safe and efficient movement of trains requires periodic inspection of the geometry of the track system and health of its components. Railroads have used laser-based track geometry testing to comply with regulatory requirements and internal business practices for over 30 years. More recently, these systems have been supplemented by new technologies capable of inspecting many other attributes of the track including subgrade condition, track component health, and ballast profile. Computational advances including machine vision and artificial intelligence, and the application of big data, have drastically increased the value that can be derived from the ever-growing track health dataset. In this thesis, I present a method to manage the flow of data in a railroad, starting from field data collection to multi-year capital plans. In my case study, geometry and track component data were collected over a 115-mile (185 km) heavy haul Class I railroad subdivision in the US and were analyzed for correlations. One of the primary challenges to using track-related data collected from multiple inspection systems on different days is aligning datasets. In this research, datasets are aligned using fixed assets (switches and crossings). After aligning the datasets, fixed windows and aggregation functions are used to analyze the data. Correlation matrices and scatter plots of static data from both technologies showed little correlation between the two datasets. This suggests that railroads should consider the use of both technologies to comply with federal regulations, monitor the condition of their components and infrastructure, and ensure the safe movement of trains. Additionally, a trending framework is developed that is suitable for both geometry and component data, providing useful information to develop comprehensive maintenance plans to facilitate reliable and efficient passenger and freight movement.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Civil Engineering

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2023

Author dc:creator

• Morgado Bilheri T Carvalho, Arthur

Contributors dc:contributor

• Edwards, John Riley

• Railway
• Track
• Geometry
• Degradation

Statement dc:rights

• Copyright 2023 Arthur Morgado Bilheri T Carvalho

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/122064

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F122064