Indirect measurement of bridge surface roughness using vibration responses of a two-axle moving vehicle based on physics-constrained generative adversarial network

Abstract

This study addresses the challenge of indirectly measuring bridge surface roughness through the vibration responses of a moving vehicle, which is crucial for pavement maintenance and bridge safety assessment. A physics-constrained generative adversarial network (PC-GAN) was proposed for the probabilistic estimation of surface roughness. The method consists of two steps: initially, a GAN informed by physics-based knowledge extracts combined information of bridge vibration deflection and surface roughness from vehicle accelerations. Subsequently, a feed-forward network isolates the bridge surface roughness from the combined data. Numerical examples validate the PC-GAN method, demonstrating sustained high accuracy under challenging conditions, including ISO 8608 level C road roughness, vehicle speeds up to 8 m s^-1, 10 % deviation in vehicle parameters, 10 % environmental noise, and 10 % vehicle damping ratio. Laboratory tests further confirmed the method's efficacy, with the successful detection of artificial barriers on the bridge surface and a mean relative error of 3.33 % in height estimation. The PC-GAN method is demonstrated to be a robust tool for estimating bridge surface roughness under various numerical and laboratory conditions. These findings provide valuable insights for the rapid inspection of bridge pavement conditions using vibration responses from moving test vehicles.