Smart Structures and Systems

  • 제33권3호
  • /
  • Pages.189-199
  • /
  • 2024
  • /
  • 1738-1584(pISSN)
  • /
  • 1738-1991(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Operational performance evaluation of bridges using autoencoder neural network and clustering

  • Huachen Jiang (Shanghai Key Laboratory of Engineering Structure Safety, SRIBS) ;
  • Liyu Xie (Department of Disaster Mitigation for Structures, Tongji University) ;
  • Da Fang (Southeast University, Key Laboratory of Concrete and Prestressed Concrete Structure of Ministry of Education) ;
  • Chunfeng Wan (Southeast University, Key Laboratory of Concrete and Prestressed Concrete Structure of Ministry of Education) ;
  • Shuai Gao (Southeast University, Key Laboratory of Concrete and Prestressed Concrete Structure of Ministry of Education) ;
  • Kang Yang (School of Railway Transportation, Shanghai Institute of Technology) ;
  • Youliang Ding (Southeast University, Key Laboratory of Concrete and Prestressed Concrete Structure of Ministry of Education) ;
  • Songtao Xue (Department of Disaster Mitigation for Structures, Tongji University)
  • 투고 : 2021.12.29
  • 심사 : 2024.01.25
  • 발행 : 2024.03.25
⟨ 이전 논문 다음 논문 ⟩

초록

To properly extract the strain components under varying operational conditions is very important in bridge health monitoring. The abnormal sensor readings can be correctly identified and the expected operational performance of the bridge can be better understood if each strain components can be accurately quantified. In this study, strain components under varying load conditions, i.e., temperature variation and live-load variation are evaluated based on field strain measurements collected from a real concrete box-girder bridge. Temperature-induced strain is mainly regarded as the trend variation along with the ambient temperature, thus a smoothing technique based on the wavelet packet decomposition method is proposed to estimate the temperature-induced strain. However, how to effectively extract the vehicle-induced strain is always troublesome because conventional threshold setting-based methods cease to function: if the threshold is set too large, the minor response will be ignored, and if too small, noise will be introduced. Therefore, an autoencoder framework is proposed to evaluate the vehicle-induced strain. After the elimination of temperature and vehicle-induced strain, the left of which, defined as the model error, is used to assess the operational performance of the bridge. As empirical techniques fail to detect the degraded state of the structure, a clustering technique based on Gaussian Mixture Model is employed to identify the damage occurrence and the validity is verified in a simulation study.

키워드

과제정보

This work is supported by the National Key Research and Development Program of China (2021YFE0112200), Shanghai Municipal Transportation Commission (JT2023-KY-003), Key Research Support Project of SRIBS (KY10000038.20230065), the Japan Society for Promotion of Science (Kakenhi No. 18K04438), the Tohoku Institute of Technology research Grant, and the Housing & UrbanRural Construction Commission of Shanghai Municipality (2023-002-029).

참고문헌

  1. Amezquita-Sanchez, J.P. and Adeli, H. (2016), "Signal processing techniques for vibration-based health monitoring of smart structures", Arch. Computat. Methods Eng., 23(1), 1-15. https://doi.org/10.1007/s11831-014-9135-7
  2. Bao, Y., Chen, Z., Wei, S., Xu, Y., Tang, Z. and Li, H. (2019), "The state of the art of data science and engineering in structural health monitoring", Engineering, 5, 234-242. https://doi.org/10.1016/j.eng.2018.11.027
  3. Bengio, Y., Lamblin, P., Popovici, D. and Larochelle, H. (2007), "Greedy layer-wise training of deep networks", Adv. Neural Inform. Process. Syst., 19, 153. https://www.iro.umontreal.ca/~lisa/pointeurs/BengioNips2006All.pdf
  4. Cardini, A.J. and DeWolf, J.T. (2009), "Long-term structural health monitoring of a multi-girder steel composite bridge using strain data", Struct. Health Monitor., 8(1), 47-58. https://doi.org/10.1177/1475921708094789
  5. Chen, Z.C., Li, H. and Bao, Y.Q. (2019), "Analyzing and modeling inter-sensor relationships for strain monitoring data and missing data imputation: a copula and functional data-analytic approach", Struct. Health Monitor., 18(4), 1168-1188. https://doi.org/10.1177/1475921718788703
  6. Costa, B.J.A. and Figueiras, J.A. (2012), "Evaluation of a strain monitoring system for existing steel railway bridges", J. Constr. Steel Res., 72, 179-191. https://doi.org/10.1016/j.jcsr.2011.12.006
  7. Cross, E.J., Koo, K.Y., Brownjohn, J.M.W. and Worden, K. (2013), "Long-term monitoring and data analysis of the Tamar Bridge", Mech. Syst. Signal Process., 35(1-2), 16-34. https://doi.org/10.1016/j.ymssp.2012.08.026
  8. Ding, Y.L., Wang, G.X., Hong, Y., Song, Y.S., Wu, L.Y. and Yue, Q. (2017), "Detection and localization of degraded truss members in a steel arch bridge based on correlation between strain and temperature", J. Perform. Constr Facil., 31(5), 04017082. https://doi.org/10.1061/(ASCE)CF.1943-5509.0001075
  9. Ding, Y., Yang, K., Jiang, H., Wang, M. and Wan, C. (2022), "Data abnormal detection using bidirectional long-short neural network combined with artificial experience", Smart Struct. Syst., Int. J., 29(1), 117-127. https://doi.org/ 10.12989/sss.2022.29.1.117
  10. Doebling, S.W., Farrar, C.R. and Prime, M.B. (1998), "A summary review of vibration-based damage identification methods", Shock Vib. Digest, 30(2), 91-105. https://doi.org/10.1177/058310249803000201
  11. 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
  12. Farrar, C.R., Cornwell, P.J., Doebling, S.W. and Prime, M.B. (2000), "Structural health monitoring studies of the alamosa canyon and I-40 Bridges", Los Alamos National Lab., NM, USA.
  13. Huang, H.B., Yi, T.H., Li, H.N. and Liu, H. (2018), "New representative temperature for performance alarming of bridge expansion joints through temperature-displacement relationship", J. Bridge Eng., 23(7), 04018043. https://ascelibrary.org/doi/10.1061/%28ASCE%29BE.1943-5592.0001258
  14. Huang, H.B., Yi, T.H., Li, H.N. and Liu, H. (2020), "Strain-based performance warning method for bridge main girders under variable operating conditions", J. Bridge Eng., 25(4), 04020013. https://ascelibrary.org/doi/10.1061/%28ASCE%29BE.1943-5592.0001538
  15. Jiang, H., Wan, C., Yang, K., Ding, Y. and Xue, S. (2021), "Modeling relationships for field strain data under thermal effects using functional data analysis", Measurement, 177, 109279. https://doi.org/10.1016/j.measurement.2021.109279
  16. Kim, S.W., Yun, D.W., Park, D.U., Chang, S.J. and Park, J.B. (2021), "Estimation of live load distribution factor for a PSC I girder bridge in an ambient vibration test", Appl. Sci., 11(22), 11010. https://doi.org/10.3390/app112211010
  17. Kingma, D.P. and Welling, M. (2014), "Auto-encoding variational bayes", Proceedings of the 2nd International Conference on Learning Representations. https://arxiv.org/abs/1312.6114v10
  18. Ko, J.M. and Ni, Y.Q. (2005), "Technology developments in structural health monitoring of large-scale bridges", Eng. Struct., 27(12), 1715-1725. https://doi.org/10.1016/j.engstruct.2005.02.021
  19. Kuok, S.C. and Yuen, K.V. (2016), "Investigation of modal identification and modal identifiability of a cable-stayed bridge with Bayesian framework", Smart Struct. Syst., Int. J., 17(3), 445-470. https://doi.org/10.12989/sss.2016.17.3.445
  20. Li, H., Li, S., Ou, J. and Li, H. (2010), "Modal identification of bridges under varying environmental conditions: Temperature and wind effects", Struct. Control Health Monitor., 17(5), 495-512. https://doi.org/10.1002/stc.319
  21. Mallat, S.G. (1989), "A theory for multiresolution signal decomposition: the wavelet representation", IEEE Transact. Pattern Anal. Mach. Intell., 11(7), 674-693. https://doi.org/10.1109/34.192463
  22. Nagarajaiah, S. and Yang, Y.C. (2017), "Modeling and harnessing sparse and low-rank data structure: a new paradigm for structural dynamics, identification, damage detection, and health monitoring", Struct. Control Health Monitor., 24(1), e1851. https://doi.org/10.1002/stc.1851
  23. Ni, Y.Q., Xia, H.W., Wong, K.Y. and Ko, J.M. (2012), "In-service condition assessment of bridge deck using long-term monitoring data of strain response", J. Bridge Eng., 17(6), 876-885. https://doi.org/10.1061/(ASCE)BE.1943-5592.0000321
  24. Noel, A.B., Abdaoui, A., Elfouly, T., Ahmed, M.H., Badawy, A. and Shehata, M.S. (2017), "Structural health monitoring using wireless sensor networks: a comprehensive survey", IEEE Commun. Surveys Tutorials, 19(3), 1403-1423. https://doi.org/10.1109/COMST.2017.2691551
  25. Peng, Z., Li, J. and Hao, H. (2022), "Long-term condition monitoring of cables for in-service cable-stayed bridges using matched vehicle-induced cable tension ratios", Smart Struct. Syst., Int. J., 29(1), 167-179. https://doi.org/10.12989/sss.2022.29.1.167
  26. Petersen, O.W., Oiseth, O., Nord, T.S. and Lourens, E. (2018), "Estimation of the full-field dynamic response of a floating bridge using Kalman-type filtering algorithms", Mech. Syst. Signal Process., 107, 12-28. https://doi.org/10.1016/j.ymssp.2018.01.022
  27. Shajihan, S.A.V., Wang, S., Zhai, G. and Spencer Jr, B.F. (2022), "CNN based data anomaly detection using multi-channel imagery for structural health monitoring", Smart Struct. Syst., Int. J., 29(1), 181-193. https://doi.org/ 10.12989/sss.2022.29.1.181
  28. Sohn, H. (2007), "Effects of environmental and operational variability on structural health monitoring", Philosoph. Transact. Royal Soc. A-Mathe. Phys. Eng. Sci, 365(1851), 539-560. https://doi.org/10.1098/rsta.2006.1935
  29. Taysi, N and Abid, S. (2015), "Temperature distributions and variations in concrete box-girder bridges: experimental and Finite Element Parametric Studies", Adv. Struct. Eng., 18(4), 469-486. https://doi.org/10.1260/1369-4332.18.4.469
  30. Wan, H.P. and Ni, Y.Q. (2018), "Bayesian modeling approach for forecast of structural stress response using structural health monitoring data", J. Struct. Eng., 144(9), 04018130. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002085
  31. Wang, G.X., Ding, Y.L., Sun, P., Wu, L.L. and Yue, Q. (2015), "Assessing static performance of the dashengguan yangtze bridge by monitoring the correlation between temperature Field and Its Static Strains", Mathe. Probl. Eng., 2015, 946907. https://doi.org/10.1155/2015/946907
  32. Wang, H., Zhu, Q., Zou, Z., Xing, C., Feng, D. and Tao, T. (2020), "Temperature distribution analysis of steel box-girder based on long-term monitoring data", Smart Struct. Syst., Int. J., 25(5), 593-604. https://doi.org/ 10.12989/sss.2020.25.5.593
  33. Xia, Y., Chen, B., Weng, S., Ni, Y.Q. and Xu, Y.L. (2012), "Temperature effect on vibration properties of civil structures: A literature review and case studies", J. Civil Struct. Health Monitor., 2(1), 29-46. https://doi.org/10.1007/s13349-011-0015-7
  34. Xia, Q., Cheng, Y., Zhang, J. and Zhu, F. (2017), "In-service condition assessment of a long-span suspension bridge using temperature-induced strain data", J. Bridge Eng., 22(3), 04016124. https://doi.org/10.1061/(ASCE)BE.1943-5592.0001003
  35. Yan, A.M., Kerschen, G., DoBoe, P. and Golinval, G. (2005a), "Structural damage diagnosis under varying environmental conditions - Part I: A linear analysis", Mech. Syst. Signal Process., 19(4), 847-864. https://doi.org/10.1016/j.ymssp.2004.12.002
  36. Yan, A.M., Kerschen, G., DoBoe, P. and Golinval, G. (2005b), "Structural damage diagnosis under varying environmental conditions - Part II: local PCA for non-linear cases", Mech. Syst. Signal Process, 19(4), 865-880. https://doi.org/10.1016/j.ymssp.2004.12.003
  37. Yang, K., Ding, Y., Sun, P., Zhao, H. and Geng, F. (2019), "Modeling of temperature time-lag effect for concrete box-girder bridges", Appl. Sci., 9(16), 3225. https://doi.org/10.3390/app9163255
  38. Yarnold, M.T. and Moon, F.L. (2015), "Temperature-based structural health monitoring baseline for long-span bridges", Eng. Struct., 86, 157-167. https://doi.org/10.1016/j.engstruct.2014.12.042
  39. Zapico-Valle, J.L., Garcia-Diegues, M. and Alonso-Camblor, R. (2013), "Nonlinear modal identification of a steel frame", Eng. Struct., 56, 246-259. https://doi.org/10.1016/j.engstruct.2013.04.026
  40. Zhang, Y.L., Kurata, M. and Lynch, J.P. (2017), "Long-term modal analysis of wireless structural monitoring data from a suspension bridge under varying environmental and operational conditions: system design and automated modal analysis", J. Eng. Mech., 143(4), 04016124. https://ascelibrary.org/doi/10.1061/%28ASCE%29EM.1943-7889.0001198
  41. Zhao, H., Ding, Y., Li, A., Ren, Z. and Yang, K. (2020), "Live-load strain evaluation of the prestressed concrete box-girder bridge using deep learning and clustering", Struct. Health Monitor., 19(4), 1051-1063. https://doi.org/10.1177/1475921719875630