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.

Structural ageing and material deterioration require infrastructure managers to continuously seek for improved solutions for bridge condition management. In the last two decades, vehicle-assisted bridge monitoring has emerged among researchers and engineers as a promising tool to support visual inspections, being a cost-efficient alternative to direct Structural Health Monitoring systems. In this work, the authors present a sparse-autoencoder-based damage detection methodology which exploits the vertical acceleration of train’s leading bogie to assess bridge health condition. The bridge under analysis in this work is a Warren truss bridge, whose FE model was designed based on the technical drawings of an actual structure, which belongs to the Italian railway line, and then validated through dynamic measurements. Raw bogie vertical accelerations are preprocessed through Continuous Wavelet Transform, allowing for the extraction of a specific frequency region of interest, governed by the modular configuration of the bridge as well as the forward speed of the convoy. Starting from the average curve of the computed wavelet coefficients, bridge health status is assessed through the use of a sparse autoencoder exploiting multiple train transits and two different damage indices. First of all the Hotelling’s statistic computed at the latent space level, and, secondly, the batch mean absolute reconstruction error. Different damage scenarios and intensities are tested in this work, considering the partial failure of stringers or cross-girder members due to corrosion, modelled as material mass loss and stiffness reduction. A large set of simulations allowed for testing the robustness of the methodology against operational variables, such as travelling speed, geometrical track irregularity evolution, and different weights of the convoy. Globally, promising damage detection performances were obtained when considering batches of 40 trains, even in presence of measurement noise and speed estimation inaccuracies.

The present study deals with the structural safety evaluation of a 50-year-old river bridge, called Baghetto Bridge, located in north Italy on the Adda River. Generally speaking, hydraulic processes are the main cause of bridge failure. Scour and hydrodynamic loads have been largely studied by the hydraulic engineering community; however, in practice, integration with structural analysis is often missing. The aim of this research is to provide a multidisciplinary procedure based on hydraulic and dynamic investigations devoted to the structural verification and monitoring of river bridges with traditional mechanical bearings. The deck–river interaction is addressed, studying the influence of debris accumulation on the bridge and performing structural verification of the bearing supports. The actions exerted on the bridge deck by the river current were estimated following the recommendations of the Italian code and making some further assumptions. In addition, dynamic investigations and FE modelling were performed. The results show (1) a relatively fast procedure that can be applied by practitioners to perform structural verification of river bridges with traditional mechanical bearings, and (2) an investigation method to evaluate temperature–frequency correlation as a reference for future inspections.

Drive-by techniques for bridge health monitoring have drawn increasing attention from researchers and practitioners, in the attempt to make bridge condition-based monitoring more cost-efficient. In this work, the authors propose a drive-by approach that takes advantage from bogie vertical accelerations to assess bridge health status. To do so, continuous wavelet transform is combined with multiple sparse autoencoders that allow for damage detection and localization across bridge span. According to authors’ best knowledge, this is the first case in which an unsupervised technique, which relies on the use of sparse autoencoders, is used to localize damages. The bridge considered in this work is a Warren steel truss bridge, whose finite element model is referred to an actual structure, belonging to the Italian railway line. To investigate damage detection and localization performances, different operational variables are accounted for: train weight, forward speed and track irregularity evolution in time. Two configurations for the virtual measuring channels were investigated: as a result, better performances were obtained by exploiting the vertical accelerations of both the bogies of the leading coach instead of using only one single acceleration signal.