An integrated robotic system for automatic detection and characterisation of rolling contact fatigue cracks in rails using an alternating current field measurement sensor

This paper considers the development of an integrated robotic system which may be used to automatically locate and then systematically scan rolling contact fatigue cracks on rails to provide more detailed information on the cracks' sub-surface size. The system consists of a mechanised trolley, a robot, a commercially available AMIGO alternating current field measurement (ACFM) system and a laser distance sensor. The dynamic results, when the trolley moves at a controlled speed to detect defects, and the static results, when the defect location has been determined and the robot arm is used to characterise (size) the defect, are both considered. During field trials it was found that in the detection test most of the artificial cracks were detected automatically by employing a novel combined threshold and signature match (CTSM) method. The results of the characterisation test also suggest that the system can automatically take reliable constant lift-off ACFM measurements over the cracks at close to optimum range for characterisation where the relative angle offset between the ACFM sensor and the crack is bounded to be within 5 degrees.