Virtual Axle Detector based on Analysis of Bridge Acceleration Measurements by Fully Convolutional Network

We recorded the measurement data used in the present study on a single-span steel trough railway bridge located on a long-distance traffic line in Germany. The bridge is 18.4 m long in total with a free span of 16.4 m. A total of  10 seismic uniaxial accelerometers of the type PCB-39B04 (PCB Synotech) with a sensitivity of 1000 mV/g (±10\%), a broadband resolution of 0.000003 gRMS, a measurement range of ±5 gpk and a frequency range of 0.06 to 450 Hz (±5\%) were installed.  The measurements are triggered via the rising slope of the wheel load measuring point G1, the measurements from the ring buffer are stored from ten seconds before the trigger together with the 50 seconds long measurement after the triggering. The recorded signals thus all have a length of 60 seconds. All sensor signals were recorded with a sampling frequency of fs = 600 Hz using the catmanAP software and the CX22 data recorder connected to an MX1601B universal amplifier and an MX1616B strain gauge amplifier (all products are from HBK).