This study aims to develop a robust and efficient system to identify ties and ballasts in motion using a variety of non-contact sensors mounted on a robotic rail cart. The sensors include distance LiDAR sensors and inductive proximity sensors for ferrous materials to collect data while traversing railroad tracks. Many existing tie/ballast health monitoring devices cannot be mounted on Hyrail vehicles for in-motion inspection due to their inability to filter out unwanted targets (i.e., ties or ballasts). The system studied here addresses that limitation by exploring several approaches based on distance LiDAR sensors. The first approach is based on calculating the running standard deviation of the measured distance from LiDAR sensors to tie or ballast surfaces. The second approach uses machine learning (ML) methods that combine two primary algorithms (Logistic Regression and Decision Tree) and three preprocessing methods (six models in total). The results indicate that the optimal configuration for non-contact, in-motion differentiation of ties and ballasts is integrating two distance LiDAR sensors with a Decision Tree model. This configuration provides rapid, accurate, and robust tie/ballast differentiation. The study also facilitates further sensor and inspection research and development in railroad track maintenance.

This study presents a machine learning approach for estimating the presence and extent of flange-face lubrication on a rail. It offers an alternative to the current empirical and subjective methods for lubrication assessment, in which track engineers’ periodic visual inspections are used to evaluate the condition of the rail. This alternative approach uses a laser-based optical sensing system developed by the Railway Technologies Laboratory (RTL) located at Virginia Tech in Blacksburg, VA, combined with a machine learning calibration model. The optical sensing system can capture the fluorescence emitted by the grease to identify its presence, while the machine learning model classifies the extent of grease present into four thickness indices (TIs), from 0 to 3, representing heavy (3), medium (2), light (1) and low/no (0) lubrication. Both laboratory and field tests are conducted, with the results demonstrating the ability of the system to differentiate lubrication levels and measure the presence or absence of grease and TI with an accuracy of 90%.