AIoT-informed digital twin communication for bridge maintenance

Abstract

Digital twin (DT) has been moving progressively from concept to practice for bridge operation and maintenance (O&M), but its issues of data synchronization and fault tolerance remain problematic. This paper investigates the time delay of bridge DT services according to communication and computation complexity, revealing the distinct impact of their sequence, and proposes an AIoT-informed DT communication framework to solve the above issues. The information hierarchy and two-way communication can be leveraged to minimize communication complexity in the framework. Meanwhile, the data flow and resilience of the proposed framework are demonstrated using a Petri net. Moreover, the framework is developed into a prototypical DT through cross-platform integration and validated with different cases. The results demonstrate that compared with other existing bridge DTs, the proposed framework has high efficiency, low-latency, and excellent fault tolerance, which can contribute to the efficiency and safety of bridge O&M, especially under communication-constraint circumstances. The framework is also promising for federated learning to protect the AI-model privacy of different stakeholders and has the potential to support agent-based intelligent bridge management in the future with little human intervention.