Robust correlation mapping of train-induced stresses for high-speed railway bridge using convolutional denoising autoencoder

Abstract

Train-induced stresses in different monitoring points not only reflects local mechanical characteristics of the structural components but also has inherent spatiotemporal correlations in the high-speed railway bridges. Mapping correlations among the stress responses can assist recognizing train-induced stress pattern and lay foundation for structural health diagnosis. However, correlation mapping and feature extraction of structural responses rely heavily on the data integrity, the pre-constructed model may be out of action due to data acquisition/transmission error, sensor faults, etc., commonly exists in the structural health monitoring system. Considering the characteristics of various incomplete train-induced stresses, this study presents a robust correlation mapping of incomplete data to complete data using one-dimensional convolutional denoising autoencoder. Stacked convolutional layers are employed as encoder to extract robust spatiotemporal feature of incomplete stresses, and transposed convolutional layers served as decoder to reconstruct denoised and complete stresses. In the training strategy, various incomplete data conditions, where stress data are lost continuously or discretely with different missing rates, are considered as training samples, making the established correlation mapping robust, accurate, and adaptive. The application on a high-speed railway truss bridge demonstrates that the proposed method can robustly reconstruct the complete stress data under different data loss conditions. The method can also be employed to assess the importance of any sensor combinations to the monitoring item, which shed light on the maintenance of sensor network.

Keywords

Train-induced stress high-speed railway bridge convolutional denoising autoencoder spatiotemporal correlation robust data mining

Get full access to this article

View all access options for this article.

References

Xia

Zhang

Guo

. Analysis of resonance mechanism and conditions of train-bridge system. J Sound Vibr 2006; 297: 810–822. DOI: 10.1016/j.jsv.2006.04.022.

Xia

De Roeck

. Dynamic response of a train-bridge system under collision loads and running safety evaluation of high-speed trains. Comput Struct 2014; 140: 23–38. DOI: 10.1016/j.compstruc.2014.04.010.

Moreu

, et al. Dynamic assessment of timber railroad bridges using displacements. J Bridge Eng 2015; 20: 12. DOI: 10.1061/(asce)be.1943-5592.0000726.

Ticona Melo

Bittencourt

Ribeiro

, et al. Dynamic response of a railway bridge to heavy axle-load trains considering vehicle-bridge interaction. Int J Struct Stab Dyn 2018; 18: 27. DOI: 10.1142/s0219455418500104.

Wang

Zhu

, et al. Identification of moving train loads on railway bridge based on strain monitoring. Smart Struct Syst 2019; 23: 263–278. DOI: 10.12989/sss.2019.23.3.263.

Azim

. A data-driven damage assessment tool for truss-type railroad bridges using train induced strain time-history response. Aust J Struct Eng 2021; 22: 16. DOI: 10.1080/13287982.2021.1908710.

Moreu

Kim

Spencer

. Railroad bridge monitoring using wireless smart sensors. Struct Control Health Monit 2017; 24: 17. DOI: 10.1002/stc.1863.

Xia

Soliman

, et al. Bridge stress calculation based on the dynamic response of coupled train-bridge system. Eng Struct 2015; 99: 334–345. DOI: 10.1016/j.engstruct.2015.04.014.

Fugate

Sohn

Farrar

. Vibration-based damage detection using statistical process control. Mech Syst Signal Proc 2001; 15: 707–721. DOI: 10.1006/mssp.2000.1323.

10.

Omenzetter

Brownjohn

JMW

. Application of time series analysis for bridge monitoring. Smart Mater Struct 2006; 15: 129–138. DOI: 10.1088/0964-1726/15/1/041.

11.

Gul

Necati Catbas

. Statistical pattern recognition for Structural Health Monitoring using time series modeling: theory and experimental verifications. Mech Syst Signal Proc 2009; 23: 2192–2204. DOI: 10.1016/j.ymssp.2009.02.013.

12.

Gul

Catbas

. Structural health monitoring and damage assessment using a novel time series analysis methodology with sensor clustering. J Sound Vibr 2011; 330: 1196–1210. DOI: 10.1016/j.jsv.2010.09.024.

13.

Yao

Pakzad

. Autoregressive statistical pattern recognition algorithms for damage detection in civil structures. Mech Syst Signal Proc 2012; 31: 355–368. DOI: 10.1016/j.ymssp.2012.02.014.

14.

Worden

Cross

. On switching response surface models, with applications to the structural health monitoring of bridges. Mech Syst Signal Proc 2018; 98: 139–156. DOI: 10.1016/j.ymssp.2017.04.022.

15.

Wan

. Bayesian modeling approach for forecast of structural stress response using structural health monitoring data. J Struct Eng 2018; 144: 12. DOI: 10.1061/(asce)st.1943-541x.0002085.

16.

Wan

H-P

Y-Q

. Bayesian multi-task learning methodology for reconstruction of structural health monitoring data. Struct Health Monit 2019; 18: 1282–1309. DOI: 10.1177/1475921718794953.

17.

Jin

Yun

. A review on deep learning-based structural health monitoring of civil infrastructures. Smart Struct Syst 2019; 24: 567–585. DOI: 10.12989/sss.2019.24.5.567.

18.

Glisic

Kim

, et al. Convolutional neural network-based data recovery method for structural health monitoring. Struct Health Monit 2020: 18. DOI: 10.1177/1475921719897571.

19.

Zhang

Miyamori

Mikami

, et al. Vibration-based structural state identification by a 1-dimensional convolutional neural network. Comput-Aided Civil Infrastruct Eng 2019; 34: 822–839. DOI: 10.1111/mice.12447.

20.

Glisic

Kim

, et al. Convolutional neural network-based data recovery method for structural health monitoring. Struct Health Monit 2020: 18. DOI: 10.1177/1475921719897571.

21.

Zhao

Ding

, et al. Digital modeling on the nonlinear mapping between multi-source monitoring data of in-service bridges. Struct Control Health Monit 2020: 17. DOI: 10.1002/stc.2618.

22.

Zhang

Noori

. Deep learning for data anomaly detection and data compression of a long-span suspension bridge. Comput-Aided Civil Infrastruct Eng 2020; 35: 685–700. DOI: 10.1111/mice.12528.

23.

Wang

Cha

Y-J

. Unsupervised deep learning approach using a deep auto-encoder with an one-class support vector machine to detect structural damage. Struct Health Monit 2020: 20. DOI: 10.1177/1475921720934051.

24.

Jiang

Han

, et al. Structural dynamic response reconstruction and virtual sensing using a sequence to sequence modeling with attention mechanism. Autom Constr 2021; 131: 17. DOI: 10.1016/j.autcon.2021.103895.

25.

Fan

Hao

, et al. Data driven structural dynamic response reconstruction using segment based generative adversarial networks. Eng Struct 2021; 234: 17. DOI: 10.1016/j.engstruct.2021.111970.

26.

Lei

Sun

Xia

. Lost data reconstruction for structural health monitoring using deep convolutional generative adversarial networks. Struct Health Monit 2021; 20: 2069–2087. DOI: 10.1177/1475921720959226.

27.

Zhu

Song

, et al. Review and big data perspectives on robust data mining approaches for industrial process modeling with outliers and missing data. Annu Rev Control 2018; 46: 107–133. DOI: 10.1016/j.arcontrol.2018.09.003.

28.

Vincent

Larochelle

Bengio

, et al. Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on Machine learning, Helsinki, Finland, 5–9 July 2008, pp. 1096–1103.

29.

Bengio

Yao

Alain

, et al. Generalized Denoising Auto-Encoders as Generative Models. arXiv preprint arXiv:13056663[cs.LG], Nov. 2013.

30.

Gondara

Wang

. MIDA: Multiple Imputation Using Denoising Autoencoders. arXiv preprint arXiv:170502737[cs.LG], Feb. 2017.

31.

Zhang

Ren

, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, USA, 27–30 June 2016, pp. 770–778.