TY - GEN
T1 - A heteroscedastic Gaussian process approach for SHM-based modelling and forecasting of high-speed rail track slab deformation
AU - Wang, Q. A.
AU - Ni, Y. Q.
AU - Zhang, C.
PY - 2019
Y1 - 2019
N2 - Uncertainty complicates structural health monitoring (SHM) data modelling and forecasting for high-speed rail (HSR) track slab deformation. Standard Gaussian process (GP) assumes a uniform noise throughout the input space. However, this assumption can be unrealistic for HSR SHM data modelling because of its unique heteroscedastic uncertainty induced by dynamic train loading, electromagnetic interference, large temperature variation and daily maintenance of railway track infrastructure. This study firstly develops a novel online SHM system enabled by fiber Bragg grating (FBG) technology to eliminate electromagnetic interference for continuous and long-term monitoring of track slab deformation, with the capacity of temperature self-compensation. To deal with different sources of uncertainty, a heteroscedastic GP approach, Variational Heteroscedastic Gaussian Process (VHGP), is explored for data modelling, estimation of the monitoring data uncertainty level and data forecasting. Results demonstrate that the VHGP framework yields more robust regression results and the estimated confidence level can better depict the heteroscedastic variances of the noise in HSR data. Higher accuracy for both regression and forecasting is gained through VHGP and the position with maximum noise can be forecasted more accurately.
AB - Uncertainty complicates structural health monitoring (SHM) data modelling and forecasting for high-speed rail (HSR) track slab deformation. Standard Gaussian process (GP) assumes a uniform noise throughout the input space. However, this assumption can be unrealistic for HSR SHM data modelling because of its unique heteroscedastic uncertainty induced by dynamic train loading, electromagnetic interference, large temperature variation and daily maintenance of railway track infrastructure. This study firstly develops a novel online SHM system enabled by fiber Bragg grating (FBG) technology to eliminate electromagnetic interference for continuous and long-term monitoring of track slab deformation, with the capacity of temperature self-compensation. To deal with different sources of uncertainty, a heteroscedastic GP approach, Variational Heteroscedastic Gaussian Process (VHGP), is explored for data modelling, estimation of the monitoring data uncertainty level and data forecasting. Results demonstrate that the VHGP framework yields more robust regression results and the estimated confidence level can better depict the heteroscedastic variances of the noise in HSR data. Higher accuracy for both regression and forecasting is gained through VHGP and the position with maximum noise can be forecasted more accurately.
UR - http://www.scopus.com/inward/record.url?scp=85091458433&partnerID=8YFLogxK
M3 - Conference article published in proceeding or book
AN - SCOPUS:85091458433
T3 - 9th International Conference on Structural Health Monitoring of Intelligent Infrastructure: Transferring Research into Practice, SHMII 2019 - Conference Proceedings
SP - 454
EP - 459
BT - 9th International Conference on Structural Health Monitoring of Intelligent Infrastructure
A2 - Chen, Genda
A2 - Alampalli, Sreenivas
PB - International Society for Structural Health Monitoring of Intelligent Infrastructure, ISHMII
T2 - 9th International Conference on Structural Health Monitoring of Intelligent Infrastructure: Transferring Research into Practice, SHMII 2019
Y2 - 4 August 2019 through 7 August 2019
ER -