Long-Term Deflection Prediction from Computer Vision-Measured Data History for High-Speed Railway Bridges

Management of the vertical long-term deflection of a high-speed railway bridge is a crucial factor to guarantee traffic safety and passenger comfort. Therefore, there have been efforts to predict the vertical deflection of a railway bridge based on physics-based models representing various influential factors to vertical deflection such as concrete creep and shrinkage. However, it is not an easy task because the vertical deflection of a railway bridge generally involves several sources of uncertainty. This paper proposes a probabilistic method that employs a Gaussian process to construct a model to predict the vertical deflection of a railway bridge based on actual vision-based measurement and temperature. To deal with the sources of uncertainty which may cause prediction errors, a Gaussian process is modeled with multiple kernels and hyperparameters. Once the hyperparameters are identified through the Gaussian process regression using training data, the proposed method provides a 95% prediction interval as well as a predictive mean about the vertical deflection of the bridge. The proposed method is applied to an arch bridge under operation for high-speed trains in South Korea. The analysis results obtained from the proposed method show good agreement with the actual measurement data on the vertical deflection of the example bridge, and the prediction results can be utilized for decision-making on railway bridge maintenance.

[1]  Amir F. Atiya,et al.  Comprehensive Review of Neural Network-Based Prediction Intervals and New Advances , 2011, IEEE Transactions on Neural Networks.

[2]  Manfred Borovcnik,et al.  A Probabilistic Perspective , 1991 .

[3]  Hugh Alan Bruck,et al.  Digital image correlation using Newton-Raphson method of partial differential correction , 1989 .

[4]  Lars Landberg,et al.  Short-term prediction of local wind conditions , 1994 .

[5]  J. Wesley Hines,et al.  Prediction interval estimation techniques for empirical modeling strategies and their applications to signal validation tasks , 2003 .

[6]  Maria Q. Feng,et al.  A Vision-Based Sensor for Noncontact Structural Displacement Measurement , 2015, Sensors.

[7]  Maria Q. Feng,et al.  Nontarget Vision Sensor for Remote Measurement of Bridge Dynamic Response , 2015 .

[8]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[9]  R. Muirhead.  Aspects of Multivariate Statistical Theory , 1982, Wiley Series in Probability and Statistics.

[10]  Enrico Primo Tomasini,et al.  Laser Doppler Vibrometry: Development of advanced solutions answering to technology's needs , 2006 .

[11]  Bojan Likar,et al.  Predictive control of a gas-liquid separation plant based on a Gaussian process model , 2007, Comput. Chem. Eng..

[12]  Charles W. Therrien,et al.  Probability and Random Processes for Electrical and Computer Engineers , 2011 .

[13]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[14]  Fernando di Sciascio,et al.  Biomass estimation in batch biotechnological processes by Bayesian Gaussian process regression , 2008, Comput. Chem. Eng..

[15]  Janina Decker,et al.  Design Of Concrete Structures , 2016 .

[16]  Aiqun Li,et al.  Deflection Reliability Analysis of PSC Box-Girder Bridge under High-Speed Railway Loads , 2012 .

[17]  Nam-Sik Kim,et al.  Deflection estimation of a full scale prestressed concrete girder using long-gauge fiber optic sensors , 2008 .

[18]  Sung-Han Sim,et al.  Extension of indirect displacement estimation method using acceleration and strain to various types of beam structures , 2014 .

[19]  Gareth James,et al.  Variance and Bias for General Loss Functions , 2003, Machine Learning.

[20]  Hyun-Moo Hur,et al.  Evaluation of Traffic Safety and Passenger Comfort of KTX considering Vertical Deformation of Steel-Composite Arch Bridge due to Temperature Change , 2018 .

[21]  Mingchu Li,et al.  Bridge Displacement Monitoring Method Based on Laser Projection-Sensing Technology , 2015, Sensors.

[22]  Rui Calçada,et al.  Non-contact measurement of the dynamic displacement of railway bridges using an advanced video-based system , 2014 .

[23]  Nam-Sik Kim,et al.  Numerical model validation for a prestressed concrete girder bridge by using image signals , 2013 .

[24]  Sami F. Masri,et al.  A vision-based approach for the direct measurement of displacements in vibrating systems , 2003 .

[25]  Sung-Han Sim,et al.  Computer Vision-Based Structural Displacement Measurement Robust to Light-Induced Image Degradation for In-Service Bridges , 2017, Sensors.

[26]  Miguel A. Vicente,et al.  A Novel Laser and Video-Based Displacement Transducer to Monitor Bridge Deflections , 2018, Sensors.

[27]  Alex B. McBratney,et al.  Spatial prediction of soil properties from landform attributes derived from a digital elevation model , 1994 .

[28]  Dan M. Frangopol,et al.  Time-Dependent Reliability of PSC Box-Girder Bridge Considering Creep, Shrinkage, and Corrosion , 2011 .

[29]  Raffaele Zinno,et al.  Monitoring of Bridges by a Laser Pointer: Dynamic Measurement of Support Rotations and Elastic Line Displacements: Methodology and First Test , 2018, Sensors.

[30]  Athanasios Sfetsos,et al.  A novel approach for the forecasting of mean hourly wind speed time series , 2002 .

[31]  Maria Q. Feng,et al.  Vision-Based Displacement Sensor for Monitoring Dynamic Response Using Robust Object Search Algorithm , 2010, IEEE Sensors Journal.

[32]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[33]  Bijaya K. Panigrahi,et al.  Prediction Interval Estimation of Electricity Prices Using PSO-Tuned Support Vector Machines , 2015, IEEE Transactions on Industrial Informatics.

[34]  Carlo Cappello,et al.  A Viscoelastic Model for the Long‐Term Deflection of Segmental Prestressed Box Girders , 2018, Comput. Aided Civ. Infrastructure Eng..

[35]  Qiang Yu,et al.  Excessive Long-Time Deflections of Prestressed Box Girders. II: Numerical Analysis and Lessons Learned , 2012 .

[36]  Bo Chen,et al.  Study on Finite Element Model Updating in Highway Bridge Static Loading Test Using Spatially-Distributed Optical Fiber Sensors , 2017, Sensors.

[37]  David Barber,et al.  Bayesian reasoning and machine learning , 2012 .

[38]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[39]  Alessandro Cabboi,et al.  Vibration-based structural health monitoring of stay cables by microwave remote sensing , 2015 .

[40]  Nam-Sik Kim,et al.  Dynamic characteristics of suspension bridge hanger cables using digital image processing , 2013 .

[41]  S. Parivallal,et al.  Long-Term Prestress Loss and Camber of Box-Girder Bridge , 2014, ACI Structural Journal.

[42]  Y. J. Kim,et al.  Time-dependent and residual behavior of pultruded GFRP beams subjected to sustained intensities and cold temperature , 2012 .

[43]  Jus Kocijan,et al.  Evolving Gaussian process models for prediction of ozone concentration in the air , 2013, Simul. Model. Pract. Theory.