Skip to main content
SpringerLink
Log in

Intelligent identification of mortar void in ballastless slab track using the wheelset acceleration combined with CNN-SVM

  • Original Article
  • Published:
Journal of Mechanical Science and Technology Aims and scope Submit manuscript

Abstract

Mortar void is a hidden defect in ballastless slab track difficult to be efficiently identified by traditional detection methods. This paper is dedicated to proposing a new detection method to identify the mortar void position and length using the vehicle response combined with the hybrid convolutional neural network-support vector machine (CNN-SVM) classifier. The vertical wheelset accelerations with different mortar void conditions are collected from a vehicle-track coupled dynamics simulation model. The first components decomposed from wheel-set accelerations by local mean decomposition and their envelopes are utilized as the training data due to their sensitivity to mortar void. To improve the identification precision, the scope descent method is proposed to determine the range influenced by mortar void (IMVR) and samples are labeled according to IMVR. Meanwhile, identification results are post processed based on the mortar void characteristics. The results show that over 90 % mortar void conditions with the length of 0.65 m are detected correctly and the identification has a higher precision with the mortar void length greater than 0.95 m. The proposed technology of mortar void detection using the wheelset accelerations with the hybrid CNN-SVM classifier provides reference for engineering application, which is of great significance to relieve the pressure of health monitoring of railway track.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. S. R. Matias and P. A. Ferreira, Railway slab track systems: review and research potentials, Structure and Infrastructure Engineering, 16(12) (2020) 1635–1653.

    Article  Google Scholar 

  2. Y. Zhang, X. Cai and L. Gao, Improvement on the mechanical properties of CA mortar and concrete composite specimens in high-speed railway by modification of interlayer bonding, Construction and Building Materials, 228 (2019) 1–13.

    Article  Google Scholar 

  3. Y. Shan, S. Zheng and X. Zhang, Fatigue performance of the CA mortar used in CRTS I ballastless slab track under simulated servicing condition, Materials (Basel), 11(11) (2018) 1–15.

    Article  Google Scholar 

  4. S. Zhu, Q. Fu and C. Cai, Damage evolution and dynamic response of cement asphalt mortar layer of slab track under vehicle dynamic load, Science China Technological Sciences, 57(10) (2014) 1883–1894.

    Article  Google Scholar 

  5. S. Y. Zhu and C. B. Cai, Interface damage and its effect on vibrations of slab track under temperature and vehicle dynamic loads, International Journal of Non-Linear Mechanics, 58 (2014) 222–232.

    Article  Google Scholar 

  6. Y. Li, J. Chen and J. Wang, Study on the interface damage of CRTS II slab track under temperature load, Structures, 26 (2020) 224–236.

    Article  Google Scholar 

  7. J. Ren, J. Wang and X. Li, Influence of cement asphalt mortar debonding on the damage distribution and mechanical responses of CRTS I prefabricated slab, Construction and Building Materials, 230 (2020) 116995.

    Article  Google Scholar 

  8. P. Wang, H. Xu and R. Chen, Effect of cement asphalt mortar debonding on dynamic properties of CRTS II slab ballastless track, Advances in Materials Science and Engineering, 2014 (2014) 193128.

    Article  Google Scholar 

  9. C. Yu, J. Xiang and J. Mao, Influence of slab arch imperfection of double-block ballastless track system on vibration response of high-speed train, Journal of the Brazilian Society of Mechanical Sciences and Engineering, 40(2) (2018) 109.

    Article  Google Scholar 

  10. Z. W. Li, W. F. Zhu and X. Z. Meng, Multi-layer imaging method for void defects in ballastless track using forward ray tracing with SAFT, Measurement, 173 (2021) 108532.

    Article  Google Scholar 

  11. W. F. Zhu, X. J. Chen and Z. W. Li, A SAFT method for the detection of void defect inside a ballastless track structure using ultrasonic array sensors, Sensors (Basel), 19(21) (2019) 4675–4689.

    Article  Google Scholar 

  12. X. Tian, W. Zhao and Y. Du, Detection of mortar defects in ballastless tracks of high-speed railway using transient elastic wave method, Journal of Civil Structural Health Monitoring, 8(1) (2017) 151–160.

    Article  Google Scholar 

  13. A. Che, Z. Tang and S. Feng, An elastic-wave-based full-wavefield imaging method for investigating defects in a highspeed railway under-track structure, Soil Dynamics and Earthquake Engineering, 77 (2015) 299–308.

    Article  Google Scholar 

  14. J. Xu, P. Wang and H. Liu, Identification of internal damage in ballastless tracks based on Gaussian curvature mode shapes, Journal of Vibroengineering, 18(8) (2016) 5217–5229.

    Article  Google Scholar 

  15. G. Guo, J. Wang and B. Du, Application study on fiber optic monitoring and identification of CRTS-II slab ballastless track debonding on viaduc, Applied Sciences, 11(13) (2021) 6239–6263.

    Article  Google Scholar 

  16. Q. Hu, Y. J. Shen and H. P. Zhu, A feasibility study on void detection of cement-emulsified asphalt mortar for slab track system utilizing measured vibration data, Engineering Structures, 245 (2021) 112349.

    Article  Google Scholar 

  17. M. Su, H. Xie and C. Kang, Determination of the interfacial properties of longitudinal continuous slab track via a field test and ANN-based approaches, Engineering Structures, 246 (2021) 113039.

    Article  Google Scholar 

  18. J. Ren, W. Du and W. Ye, Contact loss identification of CA mortar in prefabricated slab track based on PSO-SVM, Journal of Central South University (Science and Technology), 52(41) (2021) 4021–4031 (in Chinese).

    Google Scholar 

  19. Y. B. Yang, Z. L. Wang and B. Q. Wang, Track modulus detection by vehicle scanning method, Acta Mechanica, 231(7) (2020) 2955–2978.

    Article  MathSciNet  Google Scholar 

  20. M. Molodova, Z. Li and R. Dollevoet, Axle box acceleration: Measurement and simulation for detection of short track defects, Wear, 271(1–2) (2011) 349–356.

    Article  Google Scholar 

  21. E. Bernal, M. Spiryagin and C. Cole, Onboard condition monitoring sensors, systems and techniques for freight railway vehicles: a review, IEEE Sensors Journal, 19(1) (2019) 4–24.

    Article  Google Scholar 

  22. H. Shi, Z. Yu and H. Shi, Recognition algorithm for the disengagement of cement asphalt mortar based on dynamic responses of vehicles, Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 233(3) (2018) 270–282.

    Article  Google Scholar 

  23. J. Ren et al., Criteria for repairing damages of CA mortar for prefabricated framework-type slab track, Construction and Building Materials, 110 (2016) 300–311.

    Article  Google Scholar 

  24. A. Ganatra, Support vector machine classification methods: A review and comparison with different classifiers, Data Mining Knowledge Engineering, 3(1) (2011) 45–52.

    Google Scholar 

  25. X. X. Niu and C. Y. Suen, A novel hybrid CNN-SVM classifier for recognizing handwritten digits, Pattern Recognition, 45(4) (2012) 1318–1325.

    Article  Google Scholar 

  26. H. Wu, Q. Huang and D. Wang, A CNN-SVM combined model for pattern recognition of knee motion using mechanomyography signals, Journal of Electromyography and Kinesiology, 42 (2018) 136–142.

    Article  Google Scholar 

  27. Z. Huang, M. Sun and C. Guo, Automatic diagnosis of Alzheimer’s disease and mild cognitive impairment based on CNN + SVM networks with end-to-end training, Computational Intelligence and Neuroscience, 2021 (2021) 9121770.

    Article  Google Scholar 

  28. S. Kundu and S. Ari, P300 based character recognition using convolutional neural network and support vector machine, Biomedical Signal Processing and Control, 55 (2020) 101645.

    Article  Google Scholar 

  29. W. Da Silva Cotrim, L. Felix and V. Minim, Development of a hybrid system based on convolutional neural networks and support vector machines for recognition and tracking color changes in food during thermal processing, Chemical Engineering Science, 240 (2021) 116679.

    Article  Google Scholar 

  30. W. Feng, N. V. Halm-Lutterodt and H. Tang, Automated MRI-based deep learning model for detection of Alzheimer’s disease process, International Journal of Neural Systems, 30(6) (2020) 2050032.

    Article  Google Scholar 

  31. Z. Li, W. Gui and J. Zhu, Fault detection in flotation processes based on deep learning and support vector machine, Journal of Central South University, 26(9) (2019) 2504–2515.

    Article  Google Scholar 

  32. L. Hoang, S. H. Lee and K. R. Kwon, A 3D shape recognition method using hybrid deep learning network CNN-SVM, Electronics, 9(4) (2020) 649–662.

    Article  Google Scholar 

  33. X. Lei and J. Wang, Dynamic analysis of the train and slab track coupling system with finite elements in a moving frame of reference, Journal of Vibration and Control, 20(9) (2013) 1301–1317.

    Article  Google Scholar 

  34. S. Zhang, The Beijing-Tianjin Inter-City High-Speed Railway System Debugging Techniques, China Railway Publishing House, Beijing, China (2008) (in Chinese).

    Google Scholar 

  35. P. Xu and C. Cai, Dynamic analysis of longitudinally connected ballastless track on earth subgrade, Journal of Southwest Jiaotong University, 46(2) (2011) 189–194 (in Chinese).

    Google Scholar 

  36. H. Nan, Analysis on the Dynamic Characteristics of CRTS II Type Slab Ballastless Track on Subgrade and the Parametric study, Lanzhou Jiaotong University, Lanzhou, China (2012) (in Chinese).

    Google Scholar 

  37. Y. Wang, Z. He and Y. Zi, A comparative study on the local mean decomposition and empirical mode decomposition and their applications to rotating machinery health diagnosis, Journal of Vibration and Acoustics, 132(2) (2010) 613–624.

    Article  Google Scholar 

  38. P. Chen, H. Chen and W. Chen, Improved ensemble local mean decomposition based on cubic trigonometric cardinal spline interpolation and its application for rotating machinery fault diagnosis, Advances in Mechanical Engineering, 12(7) (2020) 1–19.

    Article  Google Scholar 

  39. J. S. Smith, The local mean decomposition and its application to EEG perception data, Journal of the Royal Society Interface, 2(5) (2005) 443–454.

    Article  Google Scholar 

  40. Y. Li, Q. Wang and T. Wang, Feature extraction of EEG signals based on local mean decomposition and fuzzy entropy, International Journal of Pattern Recognition and Artificial Intelligence, 34(12) (2020) 2058017.

    Article  Google Scholar 

  41. M. Peng, Z. Wu and Z. Zhang, From macro to micro expression recognition: deep learning on small datasets using transfer learning, 13th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2018, Xi’an, China (2018) 657–661.

  42. J. Li, Y. Liu and Q. Li, Generative adversarial network and transfer-learning-based fault detection for rotating machinery with imbalanced data condition, Measurement Science and Technology, 33(4) (2022) 045103.

    Article  Google Scholar 

  43. X. Pan, T. Phan and M. Adel, Multi-view separable pyramid network for AD prediction at MCI stage by (18)F-FDG brain PET imaging, IEEE Trans Med Imaging, 40(1) (2021) 81–92.

    Article  Google Scholar 

Download references

Acknowledgments

This work is supported by National Natural Science Foundation of China (Grant Nos.11790281, 62103037), China.

Author information

Authors and Affiliations

  1. School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, 100044, People’s Republic of China

    Xin Xin, Zunsong Ren, Yi Yin & Jinsheng Gao

Authors
  1. Xin Xin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zunsong Ren
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yi Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jinsheng Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zunsong Ren.

Additional information

Xin Xin is a Ph.D. candidate at the School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, China. Her research interests include vehicle-track coupling dynamics and structural damage identification.

Zunsong Ren is a Professor the School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, China. He received his Ph.D. in Mechanical Engineering from Southwest Jiaotong University. His research interests include vehicle-track coupling dynamics, strength and reliability of the vehicle structures, and load spectrum.

Yi Yin is an Associate Professor of the School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, China. She received her Ph.D. in Statistics from Beijing Jiaotong University. Her research interests include statistics, strength and reliability of the vehicle structures, and load spectrum.

Jinsheng Gao is a Ph.D. student at the School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, China. He received the M.S. degree in Industrial Engineering from Beijing Jiaotong University. His current research interests include operations research, intelligent heuristic and artificial intelligence.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xin, X., Ren, Z., Yin, Y. et al. Intelligent identification of mortar void in ballastless slab track using the wheelset acceleration combined with CNN-SVM. J Mech Sci Technol 36, 5845–5857 (2022). https://doi.org/10.1007/s12206-022-1103-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12206-022-1103-9

Keywords

Search

Navigation