This paper proposes a Deep Learning Enhanced Principal Component Analysis (PCA) approach for outlier detection to assess the structural condition of bridges. We employ partially explainable autoencoder architecture to replicate and enhance the data compression and reconstruction ability of PCA. The particularity of the method lies in the addition of residual connections to account for nonlinearities. We apply the proposed method to monitoring data obtained from two bridges under real operation conditions and compare the results before and after adding the residual connections. Results show that the addition of residual connections enhances the outlier detection ability of the network, allowing to detect lighter damages.

One of the aims of applying sustainable development to bridge infrastructure was to provide bridge owners with strengthening solutions that could lead to increased service life for existing structures. In the case of steel bridges, the assessment of the remaining service life is most often linked to the determination of structural deterioration caused by corrosion and fatigue. Damage caused by fatigue is very difficult to assess before crack initiation and is more likely to occur in older structures, where the phenomenon was not taken into account in designs before 1970. In addition, old steel materials display more brittle behavior. To meet these challenges, a preventive methodology for fatigue strengthening of steel structures was developed. The method begins with scheduling a fatigue design analysis of the existing construction to determine the most fatigue damage exposed construction elements of the bridge. The remaining fatigue life of these elements can be increased with a strengthening solution based on the use of adhesively bonded ultra-high modulus (UHM) carbon fiber–reinforced polymer (CFRP) plates, which were applied to a steel surface before failure indicators such as cracks arise. This article presents the development process of this preventive method and a demonstrative application to an existing bridge (Jarama Bridge). Strain measurement was carried out to verify the theoretical expectations of the reinforcement. Different parameters were studied, including the influence of low traffic volumes during the reinforcement application. The results proved the efficiency of this system for the structure under study.

This work provides an unsupervised learning approach based on a single-valued performance indicator to monitor the global behavior of critical components in a viaduct, such as bearings. We propose an outlier detection method for longitudinal displacements to assess the behavior of a singular asymmetric prestressed concrete structure with a 120 m high central pier acting as a fixed point. We first show that the available long-term horizontal displacement measurements recorded during the undamaged state exhibit strong correlations at the different locations of the bearings. Thus, we combine measurements from four sensors to design a robust performance indicator that is only weakly affected by temperature variations after the application of principal component analysis. We validate the method and show its efficiency against false positives and negatives using several metrics: accuracy, precision, recall, and F1 score. Due to its unsupervised learning scope, the proposed technique is intended to serve as a real-time supervision tool that complements maintenance inspections. It aims to provide support for the prioritization and postponement of maintenance actions in bridge management.

This article deals with the comparative analysis of current cable force monitoring techniques. In addition, the experience of three cable stress monitoring techniques during the construction phase is included: (a) the installation of load cells on the active anchorages of the cables, (b) the installation of unidirectional strain gauges, and (c) the evaluation of stresses in cables applying the vibrating wire technique by means of the installation of accelerometers. The main advantages and disadvantages of each technique analysed are highlighted in the Construction Process context of the Tajo Viaduct, one of the most singular viaducts recently built in Spain.