Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Automatic detection of railway clamps and track damages

Reference number
Coordinator Luleå tekniska universitet - Avdelningen för Drift, underhåll och akustik
Funding from Vinnova SEK 860 000
Project duration October 2016 - February 2018
Status Completed
Venture The strategic innovation programme InfraSweden2030

Purpose and goal

The purpose of the project is to create a system for automatic detection of track defects. The goal of the project was to create a data set of magnetic field measurements to investigate the possibility to detect fastener defects, defects on insulation joints and defects located on the railhead. The goal of the project was also to develop an algorithm to detect these defects. For fasteners and rail defects this was achieved.

Expected results and effects

A data set with different types of railway fasteners, joints and rail defects has been created and analysed. Measurements that have been carried out shown the possibility of detecting different types of fasteners, joints and rail head defects. A first version of an algorithm for detecting these components and their status has been developed where the focus has been on fastener anomalies. The result shows the potential for train based inspections of rail fasteners and rail defects.

Planned approach and implementation

The project was divided into the following parts. Measurement of magnetic field signatures, analysis of signals and development of algorithms for detection of track defects. Measurements were made at a specially built test track and out in the field. The field measurements provided information regarding actual defects while the test track was used to analysis different types of railway fasteners. By demodulating the measured signal in different ways different defects could be identified.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 25 November 2019

Reference number 2016-03306

Page statistics