FAST® Loop Comparison of Onboard Condition Monitoring Versus Wayside Detection Systems

Prior research at the University Transportation Center for Railway Safety (UTCRS) has demonstrated that onboard sensor technology can make early and accurate detections of defect initiation in railcar bearings and wheels. Hum Industrial Technology, Inc., has further developed this technology to the point of field deployment in commercial applications with multiple railcar operators. Although these field deployments have already shown the ability to detect defective wheelsets, there is a lack of head-to-head comparison data in which the same bearings and wheels are monitored using both conventional wayside sensors (Hot Bearing Detectors (HBD) and Wheel Impact Load Detectors (WILD)) and onboard monitoring (commercial units from Hum and next generation prototypes from UTCRS), at the same time on the same track. This is a crucial step in validating the current onboard technology, as well as an initial field test of newer experimental techniques. The research team proposes a large scale (40+ sensor units) test to be conducted at the MxV Rail FAST® (Facility for Accelerated Service Testing) track loop. The test will acquire data from (a) commercial Hum Boomerang wireless sensors, (b) UTCRS prototype sensors developed during the 2023-2024 funding cycle, (c) an existing HBD installed at FAST®, and (d) an existing WILD installed at FAST®. The test will include several randomly selected cars, and one car intentionally installed with a combination of healthy wheels/bearings and wheels/bearings with known early-stage defects. At the end of the test run, selected bearings and wheels will be pulled and inspected for a "ground truth" evaluation of defect severity. The outcomes of this project would include quantitative, calibrated comparisons of (a) temperature only (HBD) versus temperature and vibration (onboard) measures of bearing health and (b) wheel flat measurements from onboard accelerometers versus WILD. It will allow direct evaluation of the relative performance of onboard and wayside in early detection. The UTCRS prototype portion of the project would also demonstrate the viability of new techniques such as synchronized sampling and adaptive filter cutoffs and provide a large-scale public database for training artificial intelligence/machine learning (AI/ML) systems.

• Record URL:
  https://www.utrgv.edu/railwaysafety/_files/documents/research/mechanical/exhibit-d_utcrs_utrgv_field_test_onboard_vs_wayside_foltz_2024.pdf
• Supplemental Notes:
  • Hum Industrial Technology and MxV Rail are partners for this project.

Language

• English

Project

• Status: Active
• Funding: $254201
• Contract Numbers:

  69A3552348340

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590

  University of Texas Rio Grande Valley

  1201 W. University Dr
  Edinburg, TX  United States  78539
• Managing Organizations:

  University of Texas Rio Grande Valley

  1201 W. University Dr
  Edinburg, TX  United States  78539
• Project Managers:

  Stearns, Amy

• Performing Organizations:

  University of Texas Rio Grande Valley

  1201 W. University Dr
  Edinburg, TX  United States  78539
• Principal Investigators:

  Foltz, Heinrich

  Tarawneh, Constantine

• Start Date: 20240601
• Expected Completion Date: 20250831
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Bearings; Flaw detection; Performance tests; Rail components; Railroad safety; Wayside signals; Wireless sensors
• Subject Areas: Railroads; Safety and Human Factors;

Filing Info

• Accession Number: 01924853
• Record Type: Research project
• Source Agency: University Transportation Center for Railway Safety
• Contract Numbers: 69A3552348340
• Files: UTC, RIP
• Created Date: Jul 22 2024 8:12AM