Smart Structures and Systems

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Convolutional neural network-based damage detection method for building structures

  • Oh, Byung Kwan (Department of Architectural Engineering, Kyungil University) ;
  • Glisic, Branko (Department of Civil and Environmental Engineering, Princeton University) ;
  • Park, Hyo Seon (Department of Architectural Engineering, Yonsei University)
  • Received : 2019.05.17
  • Accepted : 2021.04.13
  • Published : 2021.06.25
⟨ Previous Next ⟩

Abstract

This study presents a damage detection method based on modal responses for building structures using convolutional neural networks (CNNs). The modal responses used in the method are obtained from the dynamic responses, which are measured in a building structure under ambient excitations; these are then transformed to a modal participation ratio (MPR) value for a measuring point and mode. As modal responses vary after damages in the structures, the MPR for a specific location and mode also changes. Thus, in this study, MPR variations, which can be obtained by comparing the MPRs of damaged and healthy structures, are utilized for damage detection without the need for identification of modal parameters. Since MPRs are derived for the number of measuring points (N) in the structure as well as the same number of modes (N), the MPRs and MPR variations can be arranged as an N × N matrix. This low-dimensional MPR variations set is used as the input map of the presented CNN architecture and information about damage locations and severities of the target structure is set as the output of the CNN. The presented CNN is trained for establishing the relationship between MPR variations and damage information and utilized to estimate the damage. The presented damage detection method is applied to numerical examples for two multiple degrees of freedoms and a three-dimensional ASCE benchmark numerical model. Training datasets created from damage scenarios assuming changes in the stiffness are used to train the CNN and the performance of this CNN is verified. Finally, this study examines how variations in the operator size and number of layers in the CNN architecture affect the damage detection performance of CNNs.

Keywords

Acknowledgement

This work was supported by a National Research Foundation of Korea (NRF) grant funded by the Korea government (Ministry of Science, ICT & Future Planning, MSIP) (NRF-2021R1A2C33008989 and No. 2018R1A5A1025137).

References

  1. Abdeljaber, O., Avci, O., Kiranyaz, S., Gabbouj, M. and Inman, D.J. (2017), "Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks", J. Sound Vib., 388, 154-170. https://doi.org/10.1016/j.jsv.2016.10.043
  2. Abdeljaber, O., Avci, O., Kiranyaz, M.S., Boashash, B., Sodano, H. and Inman, D.J. (2018), "1-D CNNS for structural damage detection: Verification on a structural health monitoring benchmark data", Neurocomputing, 275, 1308-1317. https://doi.org/10.1016/j.neucom.2017.09.069
  3. Chen, F. and Jahanshahi, M.R. (2018), "NB-CNN: Deep learning-based crack detection using convolutional neural network and Naive Bayes data fusion", IEEE Trans Ind. Electron., 65(5), 4392-4400. https://doi.org/10.1109/TIE.2017.2764844
  4. Chen, J. and Loh, C. (2018), "Two-stage damage detection algorithms of structure using modal parameters identified from recursive subspace identification", Earthq. Eng. Struct. D., 47(3), 573-593. https://doi.org/10.1002/eqe.2980
  5. Chen, C., Jiang, F., Yang, C., Rho, S., Shen, W., Liu, S. and Liu, Z. (2018), "Hyperspectral classification based on spectral-spatial convolutional neural networks", Eng. Appl. Artif. Intell., 68, 165-171. https://doi.org/10.1016/j.engappai.2017.10.015
  6. Chopra, A.K. (2001), Dynamics of Structures - Theory and Applications to Earthquake Engineering, Pearson, Englewood Cliffs, NJ, USA.
  7. Esfandiari, A. (2017), "An innovative sensitivity-based method for structural model updating using incomplete modal data", Struct. Control Hlth., 24(4), e1905. https://doi.org/10.1002/stc.1905
  8. Glisic, B. and Inaudi, D. (2012), "Development of method for inservice crack detection based on distributed fiber optic sensors", Struct. Health Monit., 11(2), 161-171. https://doi.org/10.1177/1475921711414233
  9. Glisic, B., Inaudi, D., Lau, J.M. and Fong, C.C. (2013), "Ten-year monitoring of high-rise building columns using long-gauge fiber optic sensors", Smart Mater. Struct., 22(5), 055030. https://doi.org/10.1088/0964-1726/22/5/055030
  10. Guo, Y.L., Kwon, D.K. and Kareem, A. (2016), "Near-real-time hybrid system identification framework for civil structures with application to Burj Khalifa", J. Struct. Eng., 142(2), 04015132. https://doi.org/10.1061/(ASCE)ST.1943-541X.0001402
  11. Hsu, T.Y., Liao, W.I. and Hsiao, S.Y. (2017), "Damage detection for beam structures based on local flexibility method and macro-strain measurement", Smart Struct. Syst., Int. J., 19(4), 393-402. https://doi.org/10.12989/sss.2017.19.4.393
  12. Johnson, E.A., Lam, H.F., Katafygiotis, L.S. and Beck, J.L. (2004), "Phase I IASC-ASCE structural health monitoring benchmark problem using simulated data", J. Eng. Mech., 130(1), 3-15. https://doi.org/10.1061/(ASCE)0733-9399(2004)130:1(3)
  13. Kaveh, A. and Maniat, M. (2015), "Damage detection based on MCSS and PSO using modal data", Smart Struct. Syst., Int. J., 15(5), 1253-1270. https://doi.org/10.12989/sss.2015.15.5.1253
  14. Lecun, Y., Bengio, Y. and Hinton, G. (2015), "Deep learning", Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
  15. Li, J. and Hao, H. (2014), "Substructure damage identification based on wavelet-domain response reconstruction", Struct. Health Monitor., 13(4), 389-405. https://doi.org/10.1177/1475921714532991
  16. Li, P., Zhu, H., Luo, H. and Weng, S. (2015), "Structural damage identification based on genetically trained ANNs in beams", Smart Struct. Syst., Int. J., 15(1), 227-244. http://dx.doi.org/10.12989/sss.2015.15.1.227
  17. Li, Z., Park, H.S. and Adeli, H. (2017), "New method for modal identification of super high-rise building structures using discretized synchrosqueezed wavelet and Hilbert transforms", Des. Tall Spec., 26(3), 273-289. https://doi.org/10.1002/tal.1312
  18. Liang, Y., Li, D., Song, G. and Zhan, C. (2017), "Damage detection of shear buildings through structural mass-stiffness distribution", Smart Struct. Syst., Int. J., 19(1), 11-20. http://dx.doi.org/10.12989/sss.2017.19.1.011
  19. Liang, Y., Feng, Q., Li, H. and Jiang, J. (2019), "Damage detection of shear buildings frequency-change-ratio and model updating algorithm", Smart Struct. Syst., Int. J., 23(2), 107-122. http://dx.doi.org/10.12989/sss.2019.23.2.107
  20. Lin, Y.Z., Nie, Z.H. and Ma, H.W. (2017), "Structural damage detection with automatic feature-extraction through deep learning", Comput.-Aided Civil Inf., 32(12), 1025-1046. https://doi.org/10.1111/mice.12313
  21. Machavaram, R. and Shankar, K. (2013), "Joint damage identification using improved radial basis function networks in frequency and time domain", Appl. Soft Comput., 13(7), 3366-3379. https://doi.org/10.1016/j.asoc.2013.02.004.
  22. Oh, B.K., Hwang, J.W., Kim, Y., Cho, T. and Park, H.S. (2015), "Vision-based system identification method for building structures using a motion capture system", J. Sound Vib., 356, 72-85. https://doi.org/10.1016/j.jsv.2015.07.011
  23. Oh, B.K., Kim, D. and Park, H.S. (2017), "Modal response-based visual system identification and model updating methods for building structures", Comput.-Aided Civil Inf., 32(1), 34-56. https://doi.org/10.1111/mice.12229
  24. Oppenheim, A.V. and Schafer, R.W. (2011), Discrete-Time Signal Processing, Pearson, Upper Saddle River, NJ, US.
  25. Pacific Earthquake Engineering Research Center (PEER) (2006), OpenSees: Open System for Earthquake Engineering Simulation, University of California, CA, USA.
  26. Padil, K.H., Bakhary, N. and Hao, H. (2017), "The use of a non-probabilistic artificial neural network to consider uncertainties in vibration-based-damage detection", Mech. Syst. Signal Pr., 83, 194-209. https://doi.org/10.1016/j.ymssp.2016.06.007
  27. Park, H.S. and Oh, B.K. (2018a), "Real-time structural health monitoring of a supertall building under construction based on visual modal identification strategy", Automat. Constr., 85, 273-289. https://doi.org/10.1016/j.autcon.2017.10.025
  28. Park, H.S. and Oh, B.K. (2018b), "Damage detection of building structures under ambient excitation through the analysis of the relationship between the modal participation ratio and story stiffness", J. Sound Vib., 418, 122-143. https://doi.org/10.1016/j.jsv.2017.12.036
  29. Park, S.W., Park, H.S., Kim, J.H. and Adeli, H. (2015), "3d displacement measurement model for health monitoring of structures using a motion capture system", Measurement, 59, 352-362. https://doi.org/10.1016/j.measurement.2014.09.063
  30. Park, H.S., Kim, D., Lim, S.A. and Oh, B.K. (2017), "Dynamic torsional response measurement model using motion capture system", Smart Struct. Syst., Int. J., 19(6), 679-694. http://dx.doi.org/10.12989/sss.2017.19.6.679
  31. Park, S., Jeong, H., Min, H., Lee, H. and Lee, S. (2018), "Wavelet-like convolutional neural network structure for time-series data classification", Smart Struct. Syst., Int. J., 22(2), 175-183. http://dx.doi.org/10.12989/sss.2018.22.2.175
  32. Sarlo, R., Tarazaga, P.A. and Kasarda, M.E. (2018), "High resolution operational modal analysis on a five-story smart building under wind and human induced excitation", Eng. Struct., 176, 279-292. https://doi.org/10.1016/j.engstruct.2018.08.060
  33. Sigurdardottir, D.H. and Glisic, B. (2015), "On-Site Validation of Fiber-Optic Methods for Structural Health Monitoring: Streicker Bridge", J. Civil Struct. Health Monitor., 5(4), 529-549. https://doi.org/10.1007/s13349-015-0123-x
  34. Sigurdardottir, D.H. and Glisic, B. (2014), "Detecting minute damage in beam-like structures using the neutral axis location", Smart Mater. Struct., 23(12), 125042. https://doi:10.1088/0964-1726/23/12/125042
  35. Sotoudehnia, E., Shahabian, F. and Sani, A.A. (2019), "An iterative method for damage identification of skeletal structures utilizing biconjugate gradient method and reduction of search space", Smart Struct. Syst., Int. J., 23(1), 45-60. http://dx.doi.org/10.12989/sss.2019.23.1.045
  36. Sun, S.B., He, Y.Y., Zhou, S.D. and Yue, Z.J. (2017), "A data-driven response virtual sensor technique with partial vibration measurements using convolutional neural network", Sensors, 17(12), 2888. https://doi.org/10.3390/s17122888
  37. Wu, W.H., Chen, C.C., Jhou, J.W. and Lai, G. (2018), "A rapidly convergent empirical mode decomposition method for analyzing the environmental temperature effects on stay cable force", Comput.-Aided Civil Inf., 33(8), 672-690. https://doi.org/10.1111/mice.12355
  38. Xiong, H., Cao, J., Zhang, F., Ou, X. and Chen, C. (2019), "Investigation of the SHM-oriented model and dynamic characteristics of a super-tall building", Smart Struct. Syst., Int. J., 23(3), 295-306. http://dx.doi.org/10.12989/sss.2019.23.3.295
  39. Xu, B., Song, G. and Masri, S.F. (2011), "Damage detection for a frame structure model using vibration displacement measurement", Struct. Health Monitor., 11(3), 281-292. http://doi.org/10.1177/1475921711430437
  40. Xu, Y., Bao, Y., Chen, J., Zuo, W. and Li, H. (2018), "Surface fatigue crack identification in steel box girder of bridges by a deep fusion convolutional neural network based on consumer-grade camera images", Struct. Health Monitor., 18(3), 653-674. https://doi.org/10.1177/1475921718764873
  41. Yin, T., Jiang, Q. and Yuen, K. (2017), "Vibration-based damage detection for structural connections using incomplete modal data by Bayesian approach and model reduction technique", Eng. Struct., 132, 260-277. https://doi.org/10.1016/j.engstruct.2016.11.035
  42. Zhang, C.D. and Xu, Y.L. (2016), "Structural damage identification via multi-type sensors and response reconstruction", Struct. Health Monitir., 15(6), 715-729. https://doi.org/10.1177/1475921716659787
  43. Zhang, F.L., Xiong, H.B., Shi, W.X. and Ou, X. (2016), "Structural health monitoring of Shanghai Tower during different stages using a Bayesian approach", Struct. Control Hlth., 23(11), 1366-1384. https://doi.org/10.1002/stc.1840
  44. Zhu, Y.C., Xie, Y.L. and Au, S.K. (2018), "Operational modal analysis of an eight-storey building with asynchronous data incorporating multiple setups", Eng. Struct., 165, 50-62. https://doi.org/10.1016/j.engstruct.2018.03.011