EDGE EMPOWERED DIGITAL TWIN ARCHITECTURE FOR REAL-TIME STRUCTURAL HEALTH MONITORING OF SMART BRIDGES

By

Nidhi Mishra ,

Nidhi Mishra

Assistant Professor, Kalinga University , Naya Raipur, Chhattisgarh , India

View authors publications

Search this author on:

PubMed | Google Scholar

Aakansha Soy

Aakansha Soy

Assistant Professor, Kalinga University , Naya Raipur, Chhattisgarh , India

View authors publications

Search this author on:

PubMed | Google Scholar

Abstract

Urban infrastructure, especially smart bridges, is growing rapidly, requiring effective solutions to ensure structural integrity. Conventional Structural Health Monitoring (SHM) systems have limitations in scalability, speed, and accuracy. This paper presents a new edge-enabled digital twin platform for real-time SHM of smart bridges, combining IoT, cloud computing, and edge computing. The architecture offers a high-performance, decentralized scheme of continuous monitoring to facilitate real-time detection and forecasting of structural failure by integrating the sensors on the bridges and the edge devices. The fundamental approach uses an Autoencoder-based anomaly detection, in which Autoencoders are trained to learn to recreate sensor information, and learn to behave normally by modeling the structural behavior of the bridge. In the case of real-time monitoring, the differences between the real sensor values and the reconstructed data are compared, and anomalies are noted, which are indicators of structural problems. This architecture minimizes latency by often processing data at the edge and by improving decision-making by initiating maintenance actions based on identified anomalies. The digital twin model captures the actual behavior of a bridge, providing extensive information on the current condition of the infrastructure. The suggested system is tested in terms of five major performance indicators, namely accuracy, processing time, energy consumption, scalability, and false alarm rate. Indications show that the system delivers better results than traditional SHM systems across a range of key features, including much higher anomaly detection accuracy, shorter processing time, and more efficient energy use. The system can be scaled, and additional bridges with a significantly reduced false alarm rate can be supported, therefore reducing unnecessary maintenance intervention. In general, the edge-enabled digital twin architecture can provide a promising solution to real-time SHM to enhance the safety and efficiency of smart bridges. The next research will involve integrating AI-based predictive analytics into the digital twin system to increase further the capacity of the system to indicate structural failures prior to it happening.

References

Citation

Copyright

Article metrics