No abstract

Reinforced concrete bridge decks deteriorate over time primarily due to increasing traffic loads, severe environmental conditions, especially in North America, and deferred maintenance. Condition monitoring of those structures in a timely manner is of a great importance for making informed decisions regarding maintenance, rehabilitation and replacement strategies to preserve their value, maintain their levels of service and safeguard against catastrophic failures. The objective of this paper is to introduce a comprehensive review of the current state of the art on condition monitoring of reinforced concrete bridge decks. Deterioration progression of bridge decks including different types of defects (i.e., cracks, corrosion, delamination, spalling, honeycomb and voids), their associated causes and effects are introduced. Commonly used non-invasive and non-destructive evaluation methods, including digital imaging, ground-penetrating radar, infrared thermography, half-cell potential, electrical resistivity, chain drag & hammer sounding, ultrasonic surface wave, ultrasonic pulse echo and impact echo, are presented with their capabilities and limitations. A bibliometric analysis was conducted to investigate the current trend in condition monitoring. The review also examines the frequency of methods used in condition monitoring and provide a classification of recent studies according to study type (e.g., field or laboratory experiment), joint use (i.e., whether study applied method as a stand-alone or hybridized it with another method) and performance (i.e., whether study investigated performance indicators of the applied methods or not). The key stages in monitoring condition states of bridge decks considering risks are discussed. Current practices, challenges and future perspectives are also highlighted.

Bridge decks’ maintenance funding requirements are influenced by bridge decks' current and predicted future conditions. Additionally, the serviceability of bridges may be negatively impacted by the degradation of bridge decks. Bridge inspections require considerable effort, time, cost, and resources; besides, such inspections may introduce hazards and safety concerns. This paper introduces a data-driven hybrid feature selection framework for predicting bridge deck deterioration conditions and applying it to a bridge deck in Iowa State, USA. Firstly, the Boruta algorithm, stepwise regression, and multi-layer perceptron are employed to find the best subset of features that contribute to bridge deck deterioration. Then, four classification models were developed using the best feature subset of features, namely k-nearest neighbours, random forest, artificial neural networks, and deep neural networks. The hyperparameters of the models were optimized to get their best performance. The developed models showed comparable performance, and the random forest model outperformed the other models in prediction accuracy with fewer misclassifications. The developed models are thought to reduce field inspections and give insights into the most influential factors in bridge deck deterioration conditions.

No abstract

No abstract