Data Acquisition and Processing Methods for Rail Wear Measurement Based on Structured Light
Download citation file:
- Ris (Zotero)
- Reference Manager
The rail wear measurement has its importance on the maintenance of railways, and data acquisition and processing are crucial tasks for rail wear measurement. Rail wear directly influences wheel-rail contact and life of rail tracks, so accurate and effective measurement of rail wear is a continuous demand. In this paper, a structured light data acquisition system is developed, and a data processing method for the alignment of point clouds from structured light scanning and CAD model of the rail is proposed for rail wear measurement. For the alignment of the structured light data and CAD model, random points sampling from CAD models is conducted to generate enough points for point clouds registration. In the coarse registration, the curvature of the rail profile is utilized for the point feature histograms(PFH) generation. In the fine registration, the points on different surfaces of the rail are employed by the ICP algorithm. To find more effective registration means, the analysis from software Geomagic Qualify is compared. It reveals that the surfaces on the rail with less or without wear are more suitable for fine registration.