A Human-Centric Digital Twin Framework For Structural Health Monitoring And Green Project Management: A Case Study On The Seyed Khandan Bridge In Tehran

Despite rapid advances in structural monitoring, current approaches often lack integration between real-time analytics, environmental sustainability, and stakeholder-driven decision-making—particularly in megacity contexts. This study addresses this gap by introducing a human-centric Digital Twin (DT) framework that fuses Structural Health Monitoring (SHM) with artificial intelligence (AI), green project management principles, and sustainability metrics. The proposed framework, tested on the Seyed Khandan Bridge in Tehran, integrates a high-fidelity DT model with a hybrid CNN-LSTM architecture for dynamic anomaly detection and predictive maintenance, supported by a network of ۳۲ sensors capturing over ۳۰۰ GB of multi-modal data across ۱۲ months. Real-time synchronization between physical sensors and digital simulations, enhanced through edge computing and low-power IoT protocols, enabled high-accuracy detection of structural anomalies, with CNN-LSTM achieving a ۹۲.۴% accuracy and OC-SVM reaching ۸۷.۵% confidence in classifying thermal and load-induced stress events. Modal analysis revealed frequency shifts of up to ۰.۳ Hz under high-traffic and temperature variations, while Digital Twin simulations maintained over ۹۳% correlation with observed structural responses. Sustainability outcomes were substantial: carbon emissions dropped by ۲۲%, energy use by ۱۷%, and material consumption by ۱۸%, accompanied by a ۲۹% annual reduction in maintenance costs. These findings demonstrate that AI-enhanced DT frameworks can revolutionize infrastructure resilience and environmental performance in smart urban environments. By integrating structural intelligence with eco-conscious governance, this research establishes a scalable blueprint for resilient infrastructure management in high-risk, data-rich settings.

Keywords:

Structural Health Monitoring (SHM) , Digital Twin (DT) , Machine Learning (ML) , Deep Learning (DL) , Green Project Management , Smart Infrastructure , Seismic Resilience , Urban Sustainability , Predictive Maintenance , Seyed Khandan Bridge