Using Bayesian networks for the assessment of underwater scour for road and railway bridges

Abstract

Flood-induced scour is among the most common external causes of bridge failures worldwide. In the United States, scour is the cause of 22 bridges fails every year, whereas in the UK, it contributed significantly to the 138 collapses of bridges in the last century. Scour assessments are currently based on visual inspections, which are time-consuming and expensive. Nowadays, sensor and communication technologies offer the possibility to assess in real time the scour depth at critical bridge locations; yet, monitoring an entire infrastructure network is not economically feasible. A way to overcome this limitation is to instal scour monitoring systems at critical bridge locations, and then extend the piece of information gained to the other assets exploiting the correlations present in the system. In this article, we propose a scour hazard model for road and railway bridge scour management that utilises information from a limited number of scour monitoring systems to achieve a more confined estimate of the scour risk for a bridge network. A Bayesian network is used to describe the conditional dependencies among the involved random variables and to update the scour depth distribution using data from monitoring of scour and river flow characteristics. This study constitutes the first application of Bayesian networks to bridge scour risk assessment. The proposed probabilistic framework is applied to a case study consisting of several road bridges in Scotland. The bridges cross the same river, and only one of them is instrumented with a scour monitoring system. It is demonstrated how the Bayesian network approach allows to significantly reduce the uncertainty in the scour depth at unmonitored bridges.

Invited perspectives: Challenges and future directions in improving bridge flood resilience

“…Moreover, SHM improves the knowledge of the current state of the asset and provides bridge managers with useful information for prioritizing retrofit and risk reduction interventions. It can also be useful for bridge state assessment before, during, or after extreme events (Maroni, 2020b). Obtaining information regarding the integrity of the structure in near real time has positive effects for the rapid response to these events and the recovery, starting from the rescue operations.…”

“…One way to overcome the cost limitation is to install monitoring systems only at critical locations, by extending the information gained at these locations to the other assets through the use of Bayesian networks (BNs) (see e.g. Maroni et al, 2020b). These probabilistic tools provide a graphical representation of the various variables involved in a problem (e.g.…”

“…nodes). Maroni et al (2020b) developed a BN-based framework for evaluating the scour risk for three bridges crossing the river Nith in Scotland, exploiting data from scour probes installed at a bridge (Fig. 4a) and gauging stations.…”

Research on Intelligent Monitoring Technology of Municipal Road and Bridge Engineering Construction and Quality

“…Literature [15] used the transfer function method to evaluate the road concavity height and rotational stiffness by vehicle tire axial acceleration index and verified the feasibility of the method through simulation numerical measurement. Literature [16] developed a framework to quantify the risk of flood impacts on roads and bridges, which was optimized and refined based on real cases. Literature [17] integrated the motion weight quantification technique and interferometric radar detector into a bridge quality monitoring system, which can realize the monitoring of bridge weight loading, and the monitoring system shows the characteristics of high efficiency, stability, and accuracy in practical applications.…”

The Artificial Intelligence of Things Sensing System of Real-Time Bridge Scour Monitoring for Early Warning during Floods

“…In the present study, a monitoring system that consists of a combination of IoT and AI is developed and utilized to obtain real-time measurements in the scour processes at the bridge pier. In recent years, with the rise of deep learning (DL) technology, especially in image recognition and classification applications, scientific fields have made impressive breakthroughs [ 42 , 43 , 44 , 45 , 46 , 47 ]. The significant difference between convolutional neural networks of deep learning and conventional machine learning (ML) methods is that the traditional ML methods rely on humans to design and select the image features for classification where the corresponding results are deeply affected.…”