This digital twin framework uses artificial intelligence to manage real-life data, offering an intelligent and integrated bridge management system to monitor activity before it happens. A digital twin is a virtual representation of a real bridge, continually updated with real-time and historical data to represent the past and present, and capable of simulating possible futures. Bridges are essential transportation infrastructure and require periodic inspections to ensure safety and reliability. These inspections are typically done manually, but these procedures can be challenging and require working in unsafe conditions. Moreover, the reliability of the collected data depends on human judgment and experience. In the United States alone, 10 percent of the 600,000 bridges are structurally deficient. In the face of aging and deterioration, bridge maintenance and life-cycle management require accurate performance data and efficient evaluation technology. A workflow that integrates weigh stations, automated sensors on bridges, and structural health monitoring via the data-rich environment of a digital twin would circumvent the difficulties of manual inspection and provide predictive knowledge of the state of bridges, possibly preventing serious or catastrophic collapses.
Researchers at the University of Florida have developed a digital twin bridge that incorporates sensing technologies such as structural health monitoring and weigh-in-motion into an intelligent system that can monitor activity on the bridge in real-time. By unlocking data-driven management of bridges, it offers a dynamic model capable of detecting events that may damage the bridge before they happen.
Enables real-time monitoring and efficient decision-making related to the maintenance, operation, and management of bridges
This bridge digital twin virtually encodes the specifications of each element of the physical structure, along with functionality and performance data. Its utility comes from the fact that it is a high-fidelity representation of the physical bridge that, unlike the physical bridge, can interact with other software and integrate additional data. Since the presence of overweighted semi-trailer trucks is one of the biggest risk factors for bridges, integration with traffic data can be especially beneficial, particularly if weigh-in-motion systems are included. Weigh-in-motion systems contain sensors embedded under the surface of the road that can flag overweighted vehicles in real-time. The digital twin developed here is capable of combining with the weigh-in-motion sensors to update weight information in real-time and predict when heavy vehicles should be delayed in crossing the bridge to reduce damage. The demonstrated sensor integration provides the additional benefit of reducing the need for in-person bridge inspection.