Railway operators needed continuous visibility into track conditions, signaling systems, and rolling stock health across a vast network—with instant alerts for anomalies that could compromise safety or operations.

Built a real-time data ingestion pipeline for sensor telemetry from track-side devices and rolling stock.

Developed monitoring dashboards with geographic visualization of asset health and alert status.

Implemented rule-based and threshold-driven alerting with escalation workflows to maintenance teams.

Designed historical analytics for trend analysis, predictive maintenance planning, and compliance reporting.

Anomaly detection algorithms on sensor streams for early fault identification; time-series analysis for predictive maintenance scheduling.

Improved safety posture through real-time anomaly detection and rapid response alerting.

Reduced unplanned downtime with predictive maintenance insights from historical sensor data.

Centralized operations visibility across distributed rail infrastructure.

React, Node.js, MQTT/Kafka, Time-series DB, GIS mapping, Rule engine, AWS IoT, Anomaly detection algorithms.