Machine Learning and Railway Track Deterioration Part 1: Degree of Railroad Ballast Fouling Using Gaussian Process Regression

This project aims to investigate the intensity of ballast fouling on a railroad using track geometry data and data from ground penetrating radar generated from an 1820ft railway line. The data from the railway line was segmented, and each segment comprised mostly geometric data and one variable of both ballast properties and environmental data. The Gaussian process regression model used in this paper shows a significant relationship between the predictor and response variables. In addition, the model generated a feature importance plot to ascertain the contribution of each variable to ballast fouling on the rail line. The performance metrics generated from the model and the surface response show that Gaussian process regression can be used to gain insight into the nature of fouling on a railway track.

Language

• English

Project

• Status: Active
• Funding: $50000
• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Performing Organizations:

  University of Maryland, College Park

  Department of Civil and Environmental Engineering
  College Park, MD  United States  20742
• Principal Investigators:

  Attoh-Okine, Nii

• Start Date: 20231001
• Expected Completion Date: 0
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Ballast (Railroads); Deterioration; Ground penetrating radar; Railroad tracks; Regression analysis
• Subject Areas: Maintenance and Preservation; Railroads;

Filing Info

• Accession Number: 01931533
• Record Type: Research project
• Source Agency: Research and Education in Promoting Safety (REPS) University Transportation Center
• Files: UTC, RIP
• Created Date: Sep 20 2024 9:14PM