The risk associated with extreme traffic loads on bridges has seldom been explored, with State-of-the-art evaluation methods being time-consuming and unsuitable for fast risk management. Traditional risk management advocates optimizing offline bridge maintenance plans. In contrast, novel approaches that can assess and manage this risk live through Intelligent Transportation Systems (ITSs) are lacking. This study addresses these gaps with a three-block framework. It utilizes Weigh-In-Motion (WIM) systems for collecting bridge-specific traffic load data, develops a probabilistic Risk Prediction Model for estimating the frequency and severity of overloading events drawing on current Structural Design Codes (SDCs), and simulates an ITS-based architecture for implementing management actions. The framework was tested on 2.5M $+$ WIM raw data records gathered from the ring road of Brescia, Italy. Results showed that bridge design loads were overcome more frequently than SDCs prescriptions, and violations of the Traffic Code mass limit significantly affected risk predictions. These findings underscore the need for increased attention when issuing permits for extremely overweighted vehicles and encourage enforcement strategies implemented by ITS-based architectures for real-time risk management.

Being a driver of failure consequences, forecasting the severity of events where design traffic load limits on bridges have been exceeded (DLEEs) is fundamental for road safety. Previous research has focused on estimating failure consequences by direct and indirect cost metrics. Only recently has research assessed severity unconventionally, in which the type of DLEEs was predicted by applying econometric models through Binomial Logistic Regression (BLR). Since machine learning models using Artificial Neural Networks (ANN) have not yet been explored, this study will enhance the literature as follows. First, two different 'severity' models were set up as a function of bridge-side, temporal-context, and traffic load hazard variables. Whilst the former relied on a BLR, the latter used an ANN. Second, the performance of these models was assessed using confusion matrixes, some performance indicators, and a cross-entropy parameter. Raw Weigh-In-Motion data on 7.4 M+ individual vehicle transits on a bridge along a primary roadway in Brescia (Italy) were processed. Although a similarly strong performance was achieved for BLR and ANN, the results indicated that ANN was able to predict severity records with a higher level of confidence than BLR on the case study dataset, with the cross-entropy of the ANN less than one third of that of the BLR. These analyses can support road authority traffic management to safeguard bridges from traffic load hazards. Finally, this study recommends future developments, such as considering the structural effects of traffic loads in the modelling, prioritizing traffic management actions among bridges at network level, and exploring the impact of ANN models in risk assessment.