Home Skip to main content

Cell-Phone Data Collection Can Help Rail Inspectors Focus Efforts

Posted: Aug 1, 2019

MPC researchers at North Dakota State University developed and evaluated an automated symptom screening system for railroad tracks and equipment. The system located and characterized possible track surface abnormalities by analyzing the inertial dynamics of a hi-rail vehicle or in-service rail vehicles using a smartphone data logging application. The research relied on signal processing, data processing, modeling, and signal classification techniques. The method developed in this research will not rely on adapting sensor configurations, and will require only a data upload capability. The new smart-phone based sensors will compress and upload their geo-tagged inertial data periodically to a centralized processor. Remote algorithms will combine and process the data from multiple train traversals to identify abnormal symptoms and identify their locations.

A three-smartphone-based data collection system will significantly improve the location estimation to within 5 meters with a single traversal. With two traversals, the estimation can be improved to within 3 meters. The approach would free up track time and capacity previously reserved for manual inspections as well as improve safety for railroad workers.

Pan Lu, Ph.D.
North Dakota State University

Intelligent Transportation Systems Approach to Railroad Infrastructure Performance Evaluation: Track Surface Abnormality Identification with Smartphone-Based App

NDSU Dept 2880P.O. Box 6050Fargo, ND 58108-6050