Detection of Range-Based Rail Gage and Missing Rail Fasteners

Abstract

Defects in railroad tracks are responsible for several incidents every year. Rail gage is one of the most important measurements for track maintenance because deviations in gage indicate where potential defects may exist. In addition, missing rail fasteners can be considered a critical defect that should be detected and repaired because missing fasteners are a common cause of gage misalignment issues. An improvement or enhancement to the currently available automatic inspection system specifically devised to estimate rail gage and detect missing rail fasteners is presented. A three-dimensional (3-D) imaging sensor, which produces high-resolution two-dimensional images and 3-D profiles, is used to capture the data. Then a range-based approach is used to inspect the railroad track. The 3-D structure of the rail components (rail heads and rail fasteners) is relied on instead of a vision-based approach, which suffers from illumination changes. The system is evaluated with data recorded from real scenarios in two cities (Metro Madrid in Spain and the London Underground) with different nominal gage values and fastening elements. The system is described, and results are presented, evaluated, and discussed.