Damage Identification in Warren Truss Bridges by Two Different Time–Frequency Algorithms

Abstract

Recently, a number of authors have been focusing on drive-by monitoring methods, exploiting sensors mounted on the vehicle rather than on the bridge to be monitored, with clear advantages in terms of cost and flexibility. This work aims at further exploring the feasibility and effectiveness of novel tools for indirect health monitoring of railway structures, by introducing a higher level of accuracy in damage modelling, achieve more close-to-reality results. A numerical study is carried out by means of a FE 3D model of a short span Warren truss bridge, simulating the dynamic interaction of the bridge/track/train structure. Two kinds of defects are simulated, the first one affecting the connection between the lower chord and the side diagonal member, the second one involving the joint between the cross-girder and the lower chord. Accelerations gathered from the train bogie in different working conditions and for different intensities of the damage level are analyzed through two time-frequency algorithms, namely Continuous Wavelet and Huang-Hilbert transforms, to evaluate their robustness to disturbing factors. Compared to previous studies, a complete 3D model of the rail vehicle, together with a 3D structural scheme of the bridge in place of the 2D equivalent scheme widely adopted in the literature, allow a more detailed and realistic representation of the effects of the bridge damage on the vehicle dynamics. Good numerical results are obtained from both the two algorithms in the case of the time-invariant track profile, whereas the Continuous Wavelet Transform is found to be more robust when a deterioration of track irregularity is simulated.