The use of onboard sensors and wayside detectors to continuously assess the mechanical condition of railcars, detecting developing faults such as bearing degradation, wheel flat spots, and brake issues before they cause failures. Car health data is integrated with maintenance planning systems to enable predictive maintenance. It reduces bad-order rates and unplanned service interruptions.
The network of trackside sensing systems that monitor trains as they pass, including hot box detectors, dragging equipment detectors, wheel impact load detectors, and machine vision systems. Data from wayside detectors is transmitted in real time to dispatching centers and maintenance systems. Wayside detection is a foundational layer of railroad safety and car health monitoring.
The integrated use of telecommunications and informatics to remotely monitor and transmit data from railcars and locomotives, including GPS location, temperature, shock events, door open/close status, and mechanical sensor readings. Telematics devices enable proactive management of car condition and cargo integrity without physical inspection. They are increasingly standard on tank cars, refrigerator cars, and high-value equipment.
A general term for any wayside device that monitors passing trains for mechanical defects including hot bearings, dragging equipment, shifted loads, broken wheels, and wheel impact loads. Modern defect detectors transmit data in real time to dispatching centers and maintenance databases. A network of detectors provides continuous surveillance of the entire train as it moves through the system.
A railcar that has been removed from service because it has a mechanical defect, damage, or other condition that makes it unsafe or unsuitable to move loaded. Bad-ordered cars are set out at a repair facility until they are inspected and restored to serviceable condition. The term is used as both a noun and a verb in railroad operations.
The use of machine learning models, historical performance data, real-time train location, and network condition information to generate more accurate arrival time predictions for railcars and intermodal shipments. Predictive ETA models outperform schedule-based estimates by accounting for actual network conditions and train plan changes. Improved ETA accuracy enables better inventory management and customer service.