Smart Structures and Systems

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

A data fusion method for bridge displacement reconstruction based on LSTM networks

  • Duan, Da-You (School of Civil and Hydraulic Engineering, Hefei University of Technology) ;
  • Wang, Zuo-Cai (School of Civil and Hydraulic Engineering, Hefei University of Technology) ;
  • Sun, Xiao-Tong (School of Civil and Hydraulic Engineering, Hefei University of Technology) ;
  • Xin, Yu (School of Civil and Hydraulic Engineering, Hefei University of Technology)
  • Received : 2021.09.03
  • Accepted : 2021.12.15
  • Published : 2022.04.25
⟨ Previous Next ⟩

Abstract

Bridge displacement contains vital information for bridge condition and performance. Due to the limits of direct displacement measurement methods, the indirect displacement reconstruction methods based on the strain or acceleration data are also developed in engineering applications. There are still some deficiencies of the displacement reconstruction methods based on strain or acceleration in practice. This paper proposed a novel method based on long short-term memory (LSTM) networks to reconstruct the bridge dynamic displacements with the strain and acceleration data source. The LSTM networks with three hidden layers are utilized to map the relationships between the measured responses and the bridge displacement. To achieve the data fusion, the input strain and acceleration data need to be preprocessed by normalization and then the corresponding dynamic displacement responses can be reconstructed by the LSTM networks. In the numerical simulation, the errors of the displacement reconstruction are below 9% for different load cases, and the proposed method is robust when the input strain and acceleration data contains additive noise. The hyper-parameter effect is analyzed and the displacement reconstruction accuracies of different machine learning methods are compared. For experimental verification, the errors are below 6% for the simply supported beam and continuous beam cases. Both the numerical and experimental results indicate that the proposed data fusion method can accurately reconstruct the displacement.

Keywords

Acknowledgement

Financial support to complete this study was provided in part by the National Natural Science Foundation of China under grand Nos. 51922036, by the key research and development project of Anhui province under grand No. 1804a0802204, by The Fundamental Research Funds for the Central Universities under grand No. JZ2020HGPB0117, and by the Natural Science Funds for Distinguished Young Scholar of Anhui province under grand No.1708085J06. The results and opinions expressed in this paper are those of the authors only and they don't necessarily represent those of the sponsors.

References

  1. Awad, M. and Khanna, R. (2015), "Support Vector Regression", In: Efficient Learning Machines: Theories, Concepts, and Applications for Engineers and System Designers, pp. 67-80. https://doi.org/10.1007/978-1-4302-5990-9_4
  2. Candon, M.J., Esposito, M., Levinski, O., Joseph, N., Koschel, S., Carrese, R. and Marzocca, P. (2020), "On the Application of a Long-Short-Term Memory Deep Learning Architecture for Aircraft Transonic Buffet Loads Monitoring", AIAA Scitech 2020 Forum, 0702. https://doi.org/https://doi.org/10.2514/6.2020-0702
  3. Cho, S., Yun, C.-B. and Sim, S.-H. (2015), "Displacement estimation of bridge structures using data fusion of acceleration and strain measurement incorporating finite element model", Smart Struct. Syst., Int. J., 15(3-4), 645-663. https://doi.org/10.12989/sss.2015.15.3.645
  4. Chung, W., Kim, S., Kim, N.S. and Lee, H.U. (2008), "Deflection estimation of a full scale prestressed concrete girder using long-gauge fiber optic sensors", Constr. Build. Mater., 22(3), 394-401. https://doi.org/10.1016/j.conbuildmat.2006.08.007
  5. Deng, L. and Cai, C.S. (2010), "Development of dynamic impact factor for performance evaluation of existing multi-girder concrete bridges", Eng. Struct., 32(1), 21-31. https://doi.org/https://doi.org/10.1016/j.engstruct.2009.08.013
  6. Fan, G., Li, J. and Hao, H. (2019), "Lost data recovery for structural health monitoring based on convolutional neural networks", Struct. Control Health Monitor., 26(10), e2433. https://doi.org/10.1002/stc.2433
  7. Fan, G., Li, J. and Hao, H. (2020), "Dynamic response reconstruction for structural health monitoring using densely connected convolutional networks", Struct. Health Monitor., 20(4), 1373-1391. https://doi.org/10.1177/1475921720916881
  8. Fan, G., Li, J., Hao, H. and Xin, Y. (2021), "Data driven structural dynamic response reconstruction using segment based generative adversarial networks", Eng. Struct., 234, 111970. https://doi.org/10.1016/j.engstruct.2021.111970
  9. Glaser, R., Caccese, V. and Shahinpoor, M. (2012), "Shape monitoring of a beam structure from measured strain or curvature", Exp. Mech., 52(6), 591-606. https://doi.org/10.1007/s11340-011-9523-y
  10. Graves, A. (2012), Long Short-term Memory, Springer, Berlin, Heidelberg, Germany.
  11. Halil, H., Kim, D., Nam, J. and Park, K. (2016), "Accuracy and noise analyses of 3D vibration measurements using laser Doppler vibrometer", Measurement, 94, 883-892. https://doi.org/10.1016/j.measurement.2016.09.003
  12. Hester, D., Brownjohn, J., Bocian, M. and Xu, Y. (2017), "Low cost bridge load test: Calculating bridge displacement from acceleration for load assessment calculations", Eng. Struct., 143, 358-374. https://doi.org/https://doi.org/10.1016/j.engstruct.2017.04.021
  13. Hoag, A., Hoult, N.A., Take, W.A., Moreu, F., Le, H. and Tolikonda, V. (2017), "Measuring displacements of a railroad bridge using DIC and accelerometers", Smart Struct. Syst., Int. J., 19(2), 225-236. https://doi.org/10.12989/sss.2017.19.2.225
  14. Hochreiter, S. and Schmidhuber, J. (1997), "Long short-term memory", Neural Computat., 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  15. Jang, S., Jo, H., Cho, S., Mechitov, K., Rice, J.A., Sim, S.-H., Jung, H.-J., Yun, C.-B., Spencer Jr., B.F. and Agha, G. (2010), "Structural health monitoring of a cable-stayed bridge using smart sensor technology: deployment and evaluation", Smart Struct. Syst., Int. J., 6(5-6), 439-459. https://doi.org/10.12989/sss.2010.6.5_6.439
  16. Kang, L.H., Kim, D.K. and Han, J.H. (2007), "Estimation of dynamic structural displacements using fiber Bragg grating strain sensors", J. Sound Vib., 305(3), 534-542. https://doi.org/10.1016/j.jsv.2007.04.037
  17. Karim, F., Majumdar, S., Darabi, H. and Harford, S. (2019), "Multivariate LSTM-FCNs for time series classification", Neural Networks, 116, 237-245. https://doi.org/10.1016/j.neunet.2019.04.014
  18. Kim, H.I., Kang, L.H. and Han, J.H. (2011), "Shape estimation with distributed fiber Bragg grating sensors for rotating structures", Smart Mater. Struct., 20(3). https://doi.org/10.1088/0964-1726/20/3/035011
  19. Kim, K., Choi, J., Chung, J., Koo, G., Bae, I.H. and Sohn, H. (2018), "Structural displacement estimation through multi-rate fusion of accelerometer and RTK-GPS displacement and velocity measurements", Measurement, 130, 223-235. https://doi.org/10.1016/j.measurement.2018.07.090
  20. Kingma, D.P. and Ba, J. (2014), Adam: A method for stochastic optimization, arXiv preprint arXiv:14126980.
  21. Lee, H.S., Hong, Y.H. and Park, H.W. (2010), "Design of an FIR filter for the displacement reconstruction using measured acceleration in low-frequency dominant structures", Int. J. Numer. Meth. Eng., 82(4), 403-434. https://doi.org/10.1002/nme.2769
  22. Lee, J., Lee, K.C., Lee, S., Lee, Y.J. and Sim, S.H. (2019), "Long-term displacement measurement of bridges using a LiDAR system", Struct. Control Health Monitor., 26(10). https://doi.org/10.1002/stc.2428
  23. Lei, Y., Liu, C., Jiang, Y. and Mao, Y. (2013), "Substructure based structural damage detection with limited input and output measurements", Smart Struct. Syst., Int. J., 12(6), 619-640. https://doi.org/10.12989/sss.2013.12.6.619
  24. Li, S., Wang, X., Liu, H., Zhuo, Y., Su, W. and Di, H. (2020), "Dynamic deflection monitoring of high-speed railway bridges with the optimal inclinometer sensor placement", Smart Struct. Syst., Int. J., 26(5), 591-603. https://doi.org/10.12989/sss.2020.26.5.591
  25. Liu, L.J., Zhu, J.J., Su, Y. and Lei, Y. (2016), "Improved Kalman filter with unknown inputs based on data fusion of partial acceleration and displacement measurements", Smart Struct. Syst., Int. J., 17(6), 903-915. https://doi.org/10.12989/sss.2016.17.6.903
  26. Ma, Z., Chung, J., Liu, P. and Sohn, H. (2021), "Bridge displacement estimation by fusing accelerometer and strain gauge measurements", Struct. Control Health Monitor., 28(6). https://doi.org/10.1002/stc.2733
  27. Moon, H.S., Ok, S., Chun, P.J. and Lim, Y.M. (2019), "Art Artificial neural network for vertical displacement prediction of a bridge from strains (Part 1): Girder bridge under moving vehicles", Appl. Sci.-Basel, 9(14). https://doi.org/10.3390/app9142881
  28. Moreu, F., Jo, H., Li, J., Kim, R.E., Cho, S., Kimmle, A., Scola, S., Le, H., Spencer Jr., B.F. and Lafave, J.M. (2015), "Dynamic assessment of timber railroad bridges using displacements", J. Bridge Eng., 20(10). https://doi.org/10.1061/(Asce)Be.1943-5592.0000726
  29. Moschas, F. and Stiros, S. (2011), "Measurement of the dynamic displacements and of the modal frequencies of a short-span pedestrian bridge using GPS and an accelerometer", Eng. Struct., 33(1), 10-17. https://doi.org/10.1016/j.engstruct.2010.09.013
  30. Ni, Y.Q., Wang, Y.W., Liao, W.Y. and Chen, W.H. (2019), "A vision-based system for long-distance remote monitoring of dynamic displacement: experimental verification on a supertall structure", Smart Struct. Syst., Int. J., 24(6), 769-781. https://doi.org/10.12989/sss.2019.24.6.769
  31. Rapp, S., Kang, L.H., Han, J.H., Mueller, U.C. and Baier, H. (2009), "Displacement field estimation for a two-dimensional structure using fiber Bragg grating sensors", Smart Mater. Struct., 18(2). https://doi.org/10.1088/0964-1726/18/2/025006
  32. Smyth, A. and Wu, M. (2007), "Multi-rate Kalman filtering for the data fusion of displacement and acceleration response measurements in dynamic system monitoring", Mech. Syst. Signal Process., 21(2), 706-723. https://doi.org/10.1016/j.ymssp.2006.03.005
  33. Thong, Y.K., Woolfson, M.S., Crowe, J.A., Hayes-Gill, B.R. and Jones, D.A. (2004), "Numerical double integration of acceleration measurements in noise", Measurement, 36(1), 73-92. https://doi.org/10.1016/j.measurement.2004.04.005
  34. Tian, Y., Xu, Y., Zhang, D. and Li, H. (2020), "Relationship modeling between vehicle-induced girder vertical deflection and cable tension by BiLSTM using field monitoring data of a cable-stayed bridge", Struct. Control Health Monitor., e2667. https://doi.org/10.1002/stc.2667
  35. Yi, T.H., Li, H.N. and Gu, M. (2013), "Experimental assessment of high-rate GPS receivers for deformation monitoring of bridge", Measurement, 46(1), 420-432. https://doi.org/10.1016/j.measurement.2012.07.018
  36. Zheng, Z.P., Qiu, H., Wang, Z.C., Luo, S.J. and Lei, Y. (2019), "Data fusion based multi-rate Kalman filtering with unknown input for on-line estimation of dynamic displacements", Measurement, 131, 211-218. https://doi.org/10.1016/j.measurement.2018.08.057