Vehicle-as-a-Sensor Approach for Urban Track Anomaly Detection

Area of Science:

• Engineering
• Transportation Science
• Smart City Infrastructure

Background:

• Urban tram infrastructure requires continuous monitoring for safety and efficiency.
• Traditional methods using specialized diagnostic trains are often costly and inefficient.
• Integrating condition monitoring into existing public transport offers a novel approach.

Purpose of the Study:

• To present a Vibration-based Track Anomaly Detection (VTAD) system for real-time monitoring of urban tram infrastructure.
• To utilize public transport vehicles as distributed mobile sensor platforms.
• To establish a cost-effective and scalable predictive maintenance solution.

Main Methods:

• Integration of low-cost micro-electro-mechanical system (MEMS) accelerometers, Global Positioning System (GPS) modules, and ESP32 microcontrollers.
• Wireless data transmission using Message Queuing Telemetry Transport (MQTT) for continuous condition monitoring.
• Application of a ±6σ statistical threshold to vertical vibration signals for anomaly detection.

Main Results:

• Field tests demonstrated reliable detection and location of track anomalies with meter-level accuracy.
• The system successfully converted public transport vehicles into effective mobile sensor platforms.
• Validation through repeated measurements confirmed the system's reliability.

Conclusions:

• The VTAD system provides a validated, cost-effective, and scalable predictive maintenance solution for tram infrastructure.
• The system enables integration into intelligent transportation systems and smart city infrastructure.
• This approach eliminates the need for dedicated diagnostic trains, optimizing resource allocation.