Automated monitoring system for insulated joints: Preliminary results using axle box acceleration measurements
More Info
expand_more
Abstract
This paper presents preliminary results towards an automated monitoring system for quality assessment of insulated joints based on axle box acceleration (ABA) measurements. Longitudinal and vertical ABA signals from all the wheels of the measuring train (trailing and leading wheels, right and left rails), GPS and train speed are processed to first determine the location of an insulated joint, and then to extract from the ABA signals those characteristics that better represent the quality of the insulated joint. We compare the responses of different insulated joints in a good state or with visible surface degradation. Different indicators are used to classify the joint condition, being the most relevant the maximum ABA response, and some wavelet frequency bands. Track inspections were performed to collect validation data in different insulated joints of the Dutch railway network. The preliminary results show a good agreement in terms of both detection and quality assessment