Continuous Monitoring of Train Parameters Using IoT Sensor and Edge Computing

Yuliang Zhao, Xiaodong Yu, Meng Chen, Ming Zhang, Ye Chen, Xuanyu Niu, Xiaopeng Sha, Zhikun Zhan, Wen J. Li

IEEE Sensors Journal · 2020 · 40 citations · 20 references

Concepts

TL;DR

Speed and overall loading are critical for ensuring a train runs safely and stably. We develop a wireless rail monitoring system that uses IoT sensors and edge computing to deliver accurate real‑time running‑state parameters continuously. The system mounts a 50 × 50 × 17 mm MEMS sensor on the rail to capture vibration data, processes it on an edge microprocessor, uploads results via NB‑IoT, and is powered by a solar module with a cloud server for storage. Field tests on the Datong‑Qinhuangdao line showed the system is low‑cost, self‑powered, non‑track‑occupying, achieves a speed error of 0.2 km/h, perfect carriage‑count detection, and supports 24‑hour real‑time monitoring, underscoring its future potential.

Abstract

The speed and the overall loading of a train are of great importance in determining whether the entire train is running in a safe and stable manner. We present here our work in developing a wireless rail monitoring system using IoT (Internet-of-Things) sensors and edge computing to provide accurate real-time running state parameters of trains continuously over time. By placing a wireless MEMS-based sensing system (overall size of 50×50×17 mm) on a rail to collect the vibration information of the rail under excitation by the wheels of passing trains, and by using edge computing technique to analyze these captured vibration data, we calculated the state parameters of the vehicle with the microprocessor integrated with the MEMS sensors. Then, the final analysis results were uploaded to a cloud server via Narrow Band Internet-of-Things (NB-IoT) networks. The entire system consists of a solar power module, a cloud server, and an IoT sensor. Compared with traditional train state detection systems (i.e., computer vision or IR detectors) this system has the advantages of low cost, self-powering, and no line occupation. We have demonstrated that 24-hour real-time wireless monitoring without occupation of track resources is feasible using this system, which greatly improves the efficiency and quality of railway track detection. We conducted field experiments on the Datong-Qinhuangdao Railway line using our system. Experimental results showed that the absolute error in speed is 0.2 Km/h and no error in carriages quantity detection. It is expected to play a key role in the real-time monitoring of railways and trains in the future.

References

20