High-speed railway has achieved remarkable development in China, and safety monitoring of high-speed railway is becoming an important research. Fiber bragg grating (FBG) sensing technology is applied for monitoring and early warning system of high-speed railway track condition in this paper. The sensor network is built by putting FBG sensors on the high-speed rail tracks, which is necessary for real-time online monitoring of railway track temperature, displacement and strain. These different variables are collected, processed and analyzed by FBG demodulator. In addition, the railway track temperature prediction model are established based on relevance vector regression algorithm, which further improves the prediction accuracy and generalization performance. The system has been applied in the real-time online monitoring and early warning system of Guangzhou-Shenzhen-Hong Kong high-speed railway track condition. The system is running in good condition and playing an important role in early warning.
[1]
Huazhong Yang,et al.
Blind Drift Calibration of Sensor Networks Using Sparse Bayesian Learning
,
2016,
IEEE Sensors Journal.
[2]
George Eastman House,et al.
Sparse Bayesian Learning and the Relevan e Ve tor Ma hine
,
2001
.
[3]
Jie Liu,et al.
Displacement monitor with FBG deforming ring and its application in high speed railway
,
2012,
Other Conferences.
[4]
Li Liu,et al.
Nonlinear Hydrological Time Series Forecasting Based on the Relevance Vector Regression
,
2006,
ICONIP.