A centralized railway infrastructure monitoring framework (RIMF) can enable predictive maintenance, improve operation efficiency, and enhance the understanding of supply chain complexity as well as offer opportunities for redundancy, enhance supply chain resilience, and improve the safety and protection of assets.
ATGMS-based Railway Infrastructure Monitoring Framework
RIMF Highlights
Intelligent rail track data collecting unit including LiDAR, environmental sensors
Data reduction and data selection techniques for onboard live processing
5G and edge computing for real time data communication
Intelligent Sensing, Integrated Solution
A live centralized railway safety and security infrastructure monitoring framework composed of a national data network, database, and secure web-based access portal that integrates continuous data collection from on-board rail track measuring units - A Real-time Live ATGMS. The micrometer-level track measurement accuracy provided by our high-frequency, high-definition LiDAR-based ATGMS allows RIMF to predict the condition trend, improve railway network security, promote a resilient infrastructure, and enable predictive maintenance.
The solution is: affordablefor any size of operator in any country; portableto be installed on any train configuration; expandableup to high-speed trains on account of our high LiDAR scanning rate; and scalable to any level of the transportation system.
Features and Value Proposition
Cost Effective
The high frequency, high definition LiDAR based ATGMS is affordable for any operators to install on any in-service trains. The regular and repeated inspection data can cover every portion of the nationwide railway up to sub-millimetre detail. The current and historical data will provide a foundation of predicting condition. Real-time data communication will give the warning signal for critical accidents.
Predictive Maintenance
This autonomous drive-by track monitoring method provides faster, cheaper, and reliable data. Every in-service rail vehicle with data collection units would be part of the data network informing on track conditions. The data could be collected on a daily and even hourly basis to enable predictive maintenance at the railway network-level, which will improve rail system robustness, data transparency, and overall security.
Real time processing on continuous live data
Live data collected from different cars and areas of the train: data collection units will automatically and autonomously measure track geometry from an in-service loaded vehicle at track speed, and a database and network that can run software and integrates a data fusion mechanism and algorithm to produce readable data in different formats: live map, analysis reports, alert, warning messages, and suggestion tips.
