Smart Structures and Systems

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Railway sleeper crack recognition based on edge detection and CNN

  • Wang, Gang (College of Mechanical & Electrical Engineering, Wenzhou University) ;
  • Xiang, Jiawei (College of Mechanical & Electrical Engineering, Wenzhou University)
  • Received : 2021.01.24
  • Accepted : 2021.08.28
  • Published : 2021.12.25
⟨ Previous Next ⟩

Abstract

Cracks in railway sleeper are an inevitable condition and has a significant influence on the safety of railway system. Although the technology of railway sleeper condition monitoring using machine learning (ML) models has been widely applied, the crack recognition accuracy is still in need of improvement. In this paper, a two-stage method using edge detection and convolutional neural network (CNN) is proposed to reduce the burden of computing for detecting cracks in railway sleepers with high accuracy. In the first stage, the edge detection is carried out by using the 3×3 neighborhood range algorithm to find out the possible crack areas, and a series of mathematical morphology operations are further used to eliminate the influence of noise targets to the edge detection results. In the second stage, a CNN model is employed to classify the results of edge detection. Through the analysis of abundant images of sleepers with cracks, it is proved that the cracks detected by the neighborhood range algorithm are superior to those detected by Sobel and Canny algorithms, which can be classified by proposed CNN model with high accuracy.

Keywords

Acknowledgement

This work is supported by the NSFC (No. U1909217), the ZJNSF (No. LD21E050001), the Zhejiang Zhejiang Special Support Program for High-level Personnel Recruitment of China (No. 2018R52034) and the Wenzhou Major Science and Technology Innovation Project of China (No. ZG2020051).

References

  1. Ada, M., Sevim, B., Yuzer, N. and Ayvaz, Y. (2018), "Assessment of damages on a RC building after a big fire", Adv. Concr. Constr., Int. J., 6(2), 177-197. https://doi.org/10.12989/acc.2018.6.2.177
  2. Beura, S., Majhi, B. and Dash, R. (2015), "Mammogram classification using two dimensional discrete wavelet transform and gray-level co-occurrence matrix for detection of breast cancer", Neurocomputing, 154, 1-14. https://doi.org/10.1016/j.neucom.2014.12.032
  3. Canny, J. (1987), "A computational approach to edge detection", IEEE. T Pattern. Anal., 8, 679-698. 10.1109/TPAMI.1986.4767851
  4. Celik, O., Terrell, T., Gul, M. and Catbas, F.N. (2018), "Sensor clustering technique for practical structural monitoring and maintenance", Struct. Monit. Maint., Int. J., 5(2), 273-295. https://doi.org/10.12989/smm.2018.5.2.273
  5. Chen, S.C. and Chiu, C.C. (2019), "Texture construction edge detection algorithm", Appl. Sci-Basel, 9(5), 897. https://doi.org/10.3390/app9050897
  6. Do, N.T., Mei, Q. and Gul, M. (2019), "Damage assessment of shear-type structures under varying mass effects", Struct. Monit. Maint., Int. J., 6(3), 237-254. https://doi.org/10.12989/smm.2019.6.3.237
  7. Figueira, D., Sousa, C. and Serra Neves, A. (2018), "Winkler spring behavior in FE analyses of dowel action in statically loaded RC cracks", Comput. Concrete, Int. J., 21(5), 593-605. https://doi.org/10.12989/cac.2018.21.5.593
  8. Franca, A.S. and Vassallo, R.F. (2020), "A method of classifying railway sleepers and surface defects in real environment", IEEE Sens. J., 21(10), 11301-11309. https://doi.org/10.1109/JSEN.2020.3026173
  9. Friedl, M.A. and Brodley, C.E. (1997), "Decision tree classification of land cover from remotely sensed data", Remote Sens. Environ., 61, 399-409. https://doi.org/10.1016/S0034-4257(97)00049-7
  10. Gao, W., Zhang, X., Yang, L. and Liu, H. (2010), "An improved sobel edge detection", Proceedings of the 3rd International Conference on Computer Science and Information, Technology, 5, 67-71. https://doi.org/10.1109/ICCSIT.2010.5563693
  11. Gao, Y., Liu, X.Y. and Xiang, J.W. (2020), "FEM simulation-based generative adversarial networks to detect bearing faults", IEEE T. Ind. Inform., 16(7), 4961-4971. https://doi.org/10.1109/TII.2020.2968370
  12. Gao, Y., Liu, X.Y., Huang, H.Z. and Xiang, J.W. (2021), "A hybrid of finite element simulation and generative adversarial networks to classify faults in rotor-bearing systems", ISA Transact., 108, 356-366. https://doi.org/10.1016/j.isatra.2020.08.012
  13. Goel, N., Kaur, H. and Saxena, J. (2020), "Modified decision based unsymmetric adaptive neighborhood trimmed mean filter for removal of very high density salt and pepper noise", Multimed.Tools Appl., 79(27), 19739-19768. https://doi.org/10.1007/s11042-020-08687-y
  14. Gonzalez, R.C., Woods, R.E. and Eddins, S.L. (2004), Digital Image Processing Using Matlab, Gatesmark Publishing, New York, USA.
  15. Haeri, H., Sarfarazi, V., Zhu, Z. and Moradizadeh, M. (2018), "The effect of ball size on the hollow center cracked disc (HCCD) in Brazilian test", Comput. Concrete, Int. J., 22(4), 373-381. https://doi.org/10.12989/cac.2018.22.4.373
  16. Han, D., Liu, Q. and Fan, W. (2018), "A new image classification method using CNN transfer learning and web data augmentation", Expert. Syst. Appl., 95, 43-56. https://doi.org/10.1016/j.eswa.2017.11.028
  17. Hsu, C., Lu, C. and Pei, S. (2012), "Image feature extraction in encrypted domain with privacy-preserving SIFT", IEEE T. Image Process., 21, 4593-4607. https://doi.org/10.1109/TIP.2012.2204272
  18. Isik, E., Aydin, M.C. and Buyuksarac, A. (2020), "24 January 2020 Sivrice (Elazig) earthquake damages and determination of earthquake parameters in the region", Earthq. Struct., Int. J., 19(2), 145-156. https://doi.org/10.12989/eas.2020.19.2.145
  19. Janeliukstis, R., Rucevskis, S. and Kaewunruen, S. (2019a), "Mode shape curvature squares method for crack detection in railway prestressed concrete sleepers", Eng. Fail. Anal., 105, 386-401. https://doi.org/10.1016/j.engfailanal.2019.07.020
  20. Janeliukstisa, R., Clarkb, A., Papaeliasc, M. and Kaewunruen, S. (2019b), "Flexural cracking-induced acoustic emission peak frequency shift in railway prestressed concrete sleepers", Eng. Struct, 178, 493-505. https://doi.org/10.1016/j.engstruct.2018.10.058
  21. Jiang, Z. and Xiang, J. (2020), "Method using XFEM and SVR to predict the fatigue life of plate-like structures", Struct. Eng. Mech., Int. J., 73(4), 455-462. https://doi.org/10.12989/sem.2020.73.4.455
  22. Kingma, D.P. and Ba, J. (2014), "Adam: A method for stochastic optimization", arXiv preprint arXiv:1412.6980.
  23. Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012), "ImageNet classification with deep convolutional neural networks", Proceedings of the 26th Annual Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA.
  24. Leaman, F., Herz, A., Brinnel, V., Baltes, R. and Clausen, E. (2020), "Analysis of acoustic emission signals during fatigue testing of a M36 bolt using the Hilbert-Huang spectrum", Struct. Monit. Maint., Int. J., 7(1), 13-25. https://doi.org/10.12989/smm.2020.7.1.013
  25. Lecun, Y. and Bengio, Y. (1995), "Convolutional networks for images, speech, and time series", (Arbib, M.A. Eds.), In: The Handbook of Brain Theory and Neural Networks, MIT Press, Cambridge, USA.
  26. Liu, H., Ding, Y.L., Zhao, H.W., Wang, M.Y. and Geng, F.F. (2020), "Deep learning-based recovery method for missing structural temperature data using LSTM network", Struct. Monit. Maint., Int. J., 7(2), 109-124. https://doi.org/10.12989/smm.2020.7.2.109
  27. Mizuno, K., Terachi, Y., Takagi, K., Izumi, S., Kawaguchi, H. and Yoshimoto, M. (2012), "Architectural study of HOG feature extraction processor for real-time object detection", 2012 IEEE Workshop on Signal Processing Systems, Quebec City, QC, Canada, October, pp. 197-202. https://doi.org/10.1109/SiPS.2012.57
  28. Perez, L. and Wang, J. (2017), "The effectiveness of data augmentation in image classification using deep learning", arXiv preprint arXiv:1712.04621.
  29. Prasath, V.S., Thanh, D.N.H. and Hung, N.Q. (2020), "Multiscale gradient maps augmented Fisher information-based image edge detection", IEEE Access, 8, 141104-141110. https://doi.org/10.1109/ACCESS.2020.3013888
  30. Seif, A., Salut, M.M. and Marsono, M.N. (2010), "A hardware architecture of prewitt edge detection", Proceedings of 2010 IEEE Conference on Sustainable Utilization and Development in Engineering and Technology, Kuala Lumpur, Malaysia, November, pp. 99-101.
  31. Sengsri, P., Ngamkhanong, C., Melo, A.L.O.D., Papaelias, M. and Kaewunruen, S. (2020), "Damage detection in fiber-reinforced foamed urethane composite railway bearers using acoustic emissions", Infrastruct., 5(6), 50. https://doi.org/10.3390/infrastructures5060050
  32. Shemirani, A.B., Sarfarazi, V., Haeri, H. and Marji, M.F. (2018), "A discrete element simulation of a punch-through shear test to investigate the confining pressure effects on the shear behaviour of concrete cracks", Comput. Concrete, Int. J., 21(2), 189-197. https://doi.org/10.12989/cac.2018.21.2.189
  33. Shih, F.Y. (2010), Image processing and mathematical morphology, Archives of Dermatology.
  34. Shorten, C. and Khoshgoftaar, T.M. (2019), "A survey on image data augmentation for deep learning", J. Big Data, 6(1), 1-48. https://doi.org/10.1186/s40537-019-0197-0
  35. Siddhartha, S., Yu, C., Qing, H., Reza, M. and Zhiguo, L. (2018), "Data-driven optimization of railway maintenance for track geometry", Transp. Res. Part C: Emerg. Technol, 90, 34-58. https://doi.org/10.1016/j.trc.2018.02.019
  36. Simonyan, K. and Zisserman, A. (2014), "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv:1409.1556.
  37. Song, W., Xiang, J. and Zhong, Y. (2017), "Mechanical parameters detection in stepped shafts using the FEM based IET", Smart Struct. Syst., Int. J., 20(4), 473-481. https://doi.org/10.12989/sss.2017.20.4.473
  38. Suykens, J.A.K. and Vandewalle, J. (1999), "Least squares support vector machine classifiers", Neural Process. Lett., 9, 293-300. https://doi.org/10.1023/A:1018628609742
  39. Sysyn, M., Nabochenko, O., Kovalchuk, V., Gruen, D. and Pentsak, A. (2019), "Improvement of inspection system for common crossings by track side monitoring and prognostics", Struct. Monit. Maint., Int. J., 6(3), 219-235. https://doi.org/10.12989/smm.2019.6.3.219
  40. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V. and Rabinovich, A. (2014), "Going deeper with convolutions", Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, pp. 1-9.
  41. Torre, V. and Poggio, T.A. (1986), "On edge detection", IEEE T. Pattern. Anal., 8, 147-163. https://doi.org/10.1109/TPAMI.1986.4767769
  42. Viswanath, K., Mukherjee, J. and Biswas, P.K. (2011), "Image filtering in the block DCT domain using symmetric convolution", J. Vis. Commun. Image R., 22, 141-152. https://doi.org/10.1016/j.jvcir.2010.11.005
  43. Wang, S. and Xiang, J. (2019), "A minimum entropy deconvolution-enhanced convolutional neural networks for fault diagnosis of axial piston pumps", Soft Comput., 24, 1-15. https://doi.org/10.1007/s00500-019-04076-2
  44. Yella, S., Dougherty, M. and Gupta, N.K. (2009), "Condition monitoring of wooden railway sleepers", Transp. Res. Part C: Emerg. Technol., 17, 38-55. https://doi.org/10.1016/j.trc.2008.06.002
  45. Xia, B., Cao, J., Zhang, X. and Peng, Y. (2020), "Automatic concrete sleeper crack detection using a one-stage detector", Int. J. Intell. Robot. Appl., 4(3), 319-327. https://doi.org/10.1007/s41315-020-00141-4
  46. Xiang, J., Chen, X. and Yang, L. (2009), "Crack identification in short shafts using wavelet-based element and neural networks", Struct. Eng. Mech., Int. J., 33(5), 543-560. https://doi.org/10.12989/sem.2009.33.5.543
  47. Xiang, J., Jiang, Z., Wang, Y. and Chen, X. (2011), "Study on damage detection software of beam-like structures", Struct. Eng. Mech., Int. J., 39(1), 77-91. https://doi.org/10.12989/sem.2011.39.1.077
  48. Xiang, J., Matsumoto, T., Long, J., Wang, Y. and Jiang, Z. (2012), "A simple method to detect cracks in beam-like structures", Smart Struct. Syst., Int. J., 9(4), 335-353. https://doi.org/10.12989/sss.2012.9.4.335
  49. Xiang, J., Nackenhorst, U., Wang, Y., Jiang, Y., Gao, H. and He, Y. (2014), "A new method to detect cracks in plate-like structures with though-thickness cracks", Smart Struct. Syst., 14(3), 397-418. https://doi.org/10.12989/sss.2014.14.3.397
  50. Xie, X., Xie, G. and Xu, X. (2018), "High precision image segmentation algorithm using SLIC and neighborhood rough set", Multimed.Tools Appl., 77(24), 31525-31543. https://doi.org/10.1007/s11042-018-6150-y
  51. Yang, Z., Chen, X., Tian, S. and He, Z. (2012), "Multiple damages detection in beam based approximate waveform capacity dimension", Struct. Eng. Mech., Int. J., 41(5), 663. https://doi.org/10.12989/sem.2012.41.5.663
  52. Yang, Z.B., Yu, J.T., Tian, S.H., Chen, X.F. and Xu, G.J. (2018), "A damage localization method based on the singular value decomposition (SVD) for plates", Smart Struct. Syst., Int. J., 22(5), 621-630. https://doi.org/10.12989/sss.2018.22.5.621
  53. Yin, H., Gong, Y. and Qiu, G. (2020), "Fast and efficient implementation of image filtering using a side window convolutional neural network", Signal Process., 176, 107717. https://doi.org/10.1016/j.sigpro.2020.107717
  54. Zaharah, A.B., Aaqib, S., Irina, S. and Andre, G.D. (2019), "Predictive maintenance using tree-based classification techniques: A case of railway switches", Transp. Res. Part C: Emerg. Technol., 101, 35-54. https://doi.org/10.1016/j.trc.2019.02.001
  55. Zeng, Z., Shuaibu, A.A., Liu, F., Ye, M. and Wang, W. (2020), "Experimental study on the vibration reduction characteristics of the ballasted track with rubber composite sleepers", Constr. Building Mater., 262, 120766. https://doi.org/10.1016/j.conbuildmat.2020.120766
  56. Zhong, Y. and Xiang, J. (2019), "Impact location on a stiffened composite panel using improved linear array", Smart Struct. Syst., Int. J., 24(2), 173-182. https://doi.org/10.12989/sss.2019.24.2.173