Enhancing Smart Urban Mobility through Digital Twin-driven Autonomous Transportation and Predictive Maintenance

Abstract

The research formulates a digital twin-focused autonomous transport system with a double functionality of predictive maintenance and traffic control. Through a simulation-based approach, real-time traffic flow data and vehicle health data were consolidated into a digital twin platform for autonomous transport in a Lagos urban transport model. Artificial intelligence software, including anomaly detection, predictive repair, and reinforcement learning, as well as adaptive traffic management, was incorporated into the digital twin platform. Results indicate that the framework achieved a 27% decline in vehicle downtime, an 18% increase in component lifespan, and a 22% decline in maintenance expenditures. Concomitantly, traffic optimization results achieved a 31% decline in congestion and a 24% average improvement in travel time in the simulated urban corridors. The results support the capacity of digital twin technology to achieve real-time decision-making, increase operating reliability, and facilitate sustainable mobility in future urban environments. The study emphasizes the potential of digital twins as a new technology for future autonomous transportation systems.