Computers and Concrete

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Deep learning of sweep signal for damage detection on the surface of concrete

  • Gao Shanga (Department of Civil Engineering, School of Transportation Science and Engineering, Beihang University) ;
  • Jun Chen (Department of Civil Engineering, School of Transportation Science and Engineering, Beihang University)
  • Received : 2023.02.13
  • Accepted : 2023.06.23
  • Published : 2023.11.25
⟨ Previous Next ⟩

Abstract

Nondestructive evaluation (NDE) is an important task of civil engineering structure monitoring and inspection, but minor damage such as small cracks in local structure is difficult to observe. If cracks continued expansion may cause partial or even overall damage to the structure. Therefore, monitoring and detecting the structure in the early stage of crack propagation is important. The crack detection technology based on machine vision has been widely studied, but there are still some problems such as bad recognition effect for small cracks. In this paper, we proposed a deep learning method based on sweep signals to evaluate concrete surface crack with a width less than 1 mm. Two convolutional neural networks (CNNs) are used to analyze the one-dimensional (1D) frequency sweep signal and the two-dimensional (2D) time-frequency image, respectively, and the probability value of average damage (ADPV) is proposed to evaluate the minor damage of structural. Finally, we use the standard deviation of energy ratio change (ERVSD) and infrared thermography (IRT) to compare with ADPV to verify the effectiveness of the method proposed in this paper. The experiment results show that the method proposed in this paper can effectively predict whether the concrete surface is damaged and the severity of damage.

Keywords

Acknowledgement

The research described in this paper was financially supported by the National Natural Science Foundation of China (Grant No. 51978027).

References

  1. Bang, H., Min, J. and Jeon, H. (2021), "Deep learning-based concrete surface damage monitoring method using structured lights and depth camera", Sensors, 21(8), 2759. https://doi.org/10.3390/s21082759.
  2. Bhowmick, S., Nagarajaiah, S. and Veeraraghavan, A. (2020), "Vision and deep learning-based algorithms to detect and quantify cracks on concrete surfaces from UAV videos", Sensors, 20(21), 6299. https://doi.org/10.3390/s20216299.
  3. Bouvrie, J. (2006), Notes on Convolutional Neural Networks, Massachusetts Institute of Technology, Cambridge, MA, USA.
  4. Carrion, A., Genoves, V., Gosalbez, J., Miralles, R. and Paya, J. (2017), "Ultrasonic signal modality: A novel approach for concrete damage evaluation", Cement Concrete Res., 101, 25-32. https://doi.org/10.1016/j.cemconres.2017.08.011.
  5. Cha, Y.J., Choi, W. and Buyukozturk, O. (2017), "Deep learning-based crack damage detection using convolutional neural networks", Comput. Aid. Civil Infrastr. Eng., 32(5), 361-378. https://doi.org/10.1111/mice.12263.
  6. Cha, Y.J., Choi, W., Suh, G., Mahmoudkhani, S. and Buyukozturk, O. (2018). "Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types", Comput. Aid. Civil Infrastr. Eng., 33(9), 731-747. https://doi.org/10.1111/mice.12334.
  7. Chang, P.C., Flatau, A. and Liu, S.C. (2003), "Health monitoring of civil infrastructure", Struct. Heal. Monit., 2(3), 257-267. https://doi.org/10.1177/1475921703036169.
  8. Chen, J.H., Su, M.C., Cao, R., Hsu, S.C. and Lu, J.C. (2017), "A self organizing map optimization based image recognition and processing model for bridge crack inspection", Autom. Constr., 73, 58-66. https://doi.org/10.1016/j.autcon.2016.08.033.
  9. Chen, R., Huang, X., Yang, L., Xu, X., Zhang, X. and Zhang, Y. (2019), "Intelligent fault diagnosis method of planetary gearboxes based on convolution neural network and discrete wavelet transform", Comput. Ind., 106, 48-59. https://doi.org/10.1016/j.compind.2018.11.003.
  10. Cheng, C.C., Cheng. T.M. and Chiang, C.H. (2008), "Defect detection of concrete structures using both infrared thermography and elastic waves", Autom. Constr., 18(1), 87-92. https://doi.org/10.1016/j.autcon.2008.05.004.
  11. Choi, W. and Cha, Y.J. (2019) "SDDNet: Real-time crack segmentation", IEEE Trans. Ind. Electron., 67, 8016-8025. https://doi.org/10.1109/TIE.2019.2945265.
  12. Daubechies, I. (1990), "The wavelet transform, time-frequency localization and signal analysis", IEEE Trans. Inf. Theory, 36(5), 961-1005. https://doi.org/10.1109/18.57199.
  13. Dung, C.V. (2019), "Autonomous concrete crack detection using deep fully convolutional neural network", Autom. Constr., 99, 52-58. https://doi.org/10.1016/j.autcon.2018.11.028.
  14. Haile, M.A., Zhu, E., Hsu, C. and Bradley, N. (2020), "Deep machine learning for detection of acoustic wave reflections", Struct. Heal. Monit., 19(5), 1340-1350. https://doi.org/10.1177/1475921719881642.
  15. Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R.R. (2012), "Improving neural networks by preventing co-adaptation of feature detectors", arXiv preprint arXiv:1207.0580.
  16. Ioffe, S. and Szegedy, C. (2015), "Batch normalization: Accelerating deep network training by reducing internal covariate shift", Proceedings of the 32nd International Conference on Machine Learning, Lille, France, July.
  17. Jang, K., Kim, N. and An, Y.K. (2019), "Deep learning-based autonomous concrete crack evaluation through hybrid image scanning", Struct. Heal. Monit., 18(5-6), 1722-1737. https://doi.org/10.1177/1475921718821719.
  18. Kang, D. and Cha, Y.J. (2018). "Autonomous UAVs for structural health monitoring using deep learning and an ultrasonic beacon system with geo-tagging", Comput. Aid. Civil Infrastr. Eng., 33(10), 885-902. https://doi.org/10.1111/mice.12375.
  19. Kang, D., Benipal, S.S., Gopal, D.L. and Cha, Y.J. (2020). "Hybrid pixel-level concrete crack segmentation and quantification across complex backgrounds using deep learning", Autom. Constr., 118, 103291. https://doi.org/10.1016/j.autcon.2020.103291.
  20. Kang, D.H. and Cha, Y.J. (2022). "Efficient attention-based deep encoder and decoder for automatic crack segmentation", Struct. Heal. Monit., 21(5), 2190-2205. https://doi.org/10.1177/14759217211053776.
  21. Kingma, D.P. and Ba, J. (2014), "Adam: A method for stochastic optimization", arXiv preprint arXiv:1412.6980.
  22. Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2017), "ImageNet classification with deep convolutional neural networks", Commun. ACM., 60(6), 84-90. https://doi.org/10.1145/3065386.
  23. Lei, D., Yang, L., Xu, W., Zhang, P. and Huang, Z. (2017), "Experimental study on alarming of concrete micro-crack initiation based on wavelet packet analysis", Constr. Build. Mater., 149, 716-723. https://doi.org/10.1016/j.conbuildmat.2017.05.159.
  24. Lin, T.Y., Goyal, P., Girshick, R., He, K. and Dollar, P. (2017), "Focal loss for dense object detection", Proceedings of the IEEE International Conference on Computer Vision, Cambridge, MA, USA, June.
  25. Long, J., Shelhamer, E. and Darrell, T. (2015), "Fully convolutional networks for semantic segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Juan, PR, USA, June.
  26. Miao, R., Gao, Y., Ge, L., Jiang, Z. and Zhang, J. (2019), "Online defect recognition of narrow overlap weld based on two-stage recognition model combining continuous wavelet transform and convolutional neural network", Comput. Ind., 112, 103115. https://doi.org/10.1016/j.compind.2019.07.005.
  27. Murphy, K.P. (2012), "Machine learning: A probabilistic perspective", MIT Press, Cambridge, MA, USA.
  28. Nair, V. and Hinton, G.E. (2010), "Rectified linear units improve Restricted Boltzmann machines", Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel, June.
  29. Park, J. (2018), "Identification of damage in beam structures using flexural wave propagation characteristics", J. Sound Vib., 318(4-5), 820-829. https://doi.org/10.1016/j.jsv.2008.05.008.
  30. Park, S.E., Eem, S.H. and Jeon, H. (2020), "Concrete crack detection and quantification using deep learning and structured light", Constr. Build. Mater., 252, 119096. https://doi.org/10.1016/j.conbuildmat.2020.119096.
  31. Puri, N., Valero, E., Turkan, Y. and Bosche, F. (2018), "Assessment of compliance of dimensional tolerances in concrete slabs using TLS data and the 2D continuous wavelet transform", Autom. Constr., 94, 62-72. https://doi.org/10.1016/j.autcon.2018.06.004.
  32. Sercu, T. and Goel, V. (2016), "Advances in very deep convolutional neural networks for LVCSR", arXiv preprint arXiv:1604.01792.
  33. Xu, G., Liu, M., Jiang, Z., Soffker, D. and Shen, W. (2019), "Bearing fault diagnosis method based on deep convolutional neural network and random forest ensemble learning", Sensors, 19(5), 1088. https://doi.org/10.3390/s19051088.
  34. Yang, C. and Chen, J. (2019), "Fully noncontact nonlinear ultrasonic characterization of thermal damage in concrete and correlation with microscopic evidence of material cracking", Cement Concrete Res., 123, 105797. https://doi.org/10.1016/j.cemconres.2019.105797.
  35. Yang, Q., Shi, W., Chen, J. and Lin, W. (2020), "Deep convolution neural network-based transfer learning method for civil infrastructure crack detection", Autom. Constr., 116, 103199. https://doi.org/10.1016/j.autcon.2020.103199.
  36. Yu, L., He, S., Liu, X., Jiang, S. and Xiang, S. (2022), "Intelligent crack detection and quantification in the concrete bridge: A deep learning-assisted image processing approach", Adv. Civil Eng., 2022, 1-15. https://doi.org/10.1155/2022/1813821.
  37. Zeiler, M.D. and Fergus, R. (2013), "Stochastic pooling for regularization of deep convolutional neural networks", arXiv preprint arXiv:1301.3557.
  38. Zhao, B., Lei, D., Fu, J., Yang, L. and Xu, W. (2019), "Experimental study on micro-damage identification in reinforced concrete beam with wavelet packet and DIC method", Constr. Build. Mater., 210, 338-346. https://doi.org/10.1016/j.conbuildmat.2019.03.175.