Transport accounts for nearly 25% of total greenhouse gas emissions in Europe and is the main cause of urban air pollution. Therefore, decarbonizing urban transport and increasing the use of public transport are strategic priorities.
Existing infrastructure, however, requires enhancements. The integration of reliable models of Urban Traction Electrification Systems (UTES) and Public Transport Vehicles (PTVs) would allow network optimization, detection of criticalities, and preventive interventions following a predictive maintenance approach.
Key quantities to monitor in near real-time include vehicle positions, electrical demand, currents, voltages, and substation contributions. To overcome current model limitations, a Digital Twin (DT) is proposed: a digital replica of the physical system for optimization and problem prediction using AI, machine learning, and big data.
Objectives: identify barriers and DT strategies for UTES, develop a low-cost smart meter, design a multilayer open-source DT prototype, and apply it to DC integration and Predictive Maintenance.
External support will be provided by two companies for all the activities of the project: Infra.To and GTT.
Contributing scientific sectors
