Sensors That Improve Rail Transport Safety

Fraunhofer Institute

Fraunhofer Institute researchers are developing a human-machine communication system, comprised of a cloud-supported, wireless network of sensors, that will make it possible to detect damage to rail vehicles before an accident occurs. The new system will also alert engineers when trains need service.

“We want to root out any damage early on and move away from maintenance at set intervals in favor of condition-based maintenance,” says Fraunhofer researcher Michael Niedermayer. As part of the system, every axle and undercarriage on a train is equipped with small radio sensors that collect data on the condition of wearing parts. The data is then transferred to an online maintenance cloud for measurement and analysis.

“Here we have sensor nodes that can capture even the slightest variations in vibration,” Niedermayer says. “We call this in-depth diagnosis.” The method allows repairs to be made before anything breaks and causes significant damage.

The goal is to provide train engineers with all relevant data, diagnostic technicians with detailed measurement data, and designers with measurement statistics covering wear to all parts, enabling them to improve the technical design of the next product generation. Furthermore, “since the system is intended to work without batteries, the algorithms mustn’t drain unnecessary energy by using up excessive computing power,” Niedermayer says. Article

DCL: This article discusses what is in fact a real-time event processing system. Unfortunately the researchers talk about “data” coming from sensors. This means they are probably re-inventing and implementing special versions of general event processing technology. They may well have been able to utilize event processing products already on the market.