AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (22.2 MB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access

Intelligent recognition of voids behind tunnel linings using deep learning and percussion sound

Xiaolei Zhang1Xin Lin1Wei Zhang2Yong Feng3 ( )Wei Lan4Yuewu Da2Kan Hu2
Key Laboratory of Geotechnical and Underground Engineering of the Ministry of Education, Department of Geotechnical Engineering, Tongji University, Shanghai 200092, China
Wuxi Water Group Co., Ltd., Wuxi 214031, China
Urban Mobility Institute, Tongji University, Shanghai 201804, China
Shanghai Shenyuan Geotechnical Engineering Co., Ltd., Shanghai 200040, China
Show Author Information

Abstract

Voids behind tunnel linings are critical factors affecting tunnels’ safety and durability. For automatic, rapid, and accurate detection of void defects behind tunnel linings, this paper proposes an intelligent recognition method of void detection based on deep learning (DL) and percussion method. Extensive indoor percussion experiments were first conducted to obtain a total of 77,925 percussion signals. Afterward, the mel-frequency cepstrum coefficients (MFCCs) are utilized for signal feature extraction, based on which a convolutional neural network (CNN) is developed for automatic void defect diagnosis. The void automated diagnosis tests are subsequently performed, and the impact of three key factors on the recognition results is investigated. The results show that the proposed CNN can accurately identify voids ranging from 0.10 to 0.30 m, with an average accuracy of 94.96% and an F1 score of 72.29%. The exploration of the slab thickness indicates that the proposed method is capable of detecting voids with an average accuracy of 94.37% and an F1 score of 74.55%, with the slab thicknesses ranging from 0.10 to 0.30 m. Furthermore, the boundary effects of concrete slabs are analyzed. Finally, an on-site validation is carried out, and the good agreements between the developed method and ultrasonic detection method indicate that the CNN-aided percussion method is feasible in practical tunnel lining void inspection tasks.

References

[1]

W. Broere. Urban underground space: Solving the problems of today’s cities. Tunnell Undergr Space Technol, 2016, 55: 245–248.

[2]
J. F. Wang, H. W. Huang, X. Y. Xie, et al. Risk assessment of voids behind the lining of mountain tunnels. In: Proceedings of GeoFlorida 2010: Advances in Analysis, Modeling & Design, Orlando, Florida, USA, 2010: pp 2319–2328.
[3]

Y. Zhao, P. F. Li. A statistical analysis of China’s traffic tunnel development data. Engineering, 2018, 4: 3–5.

[4]

Y. Feng, X. L. Zhang, S. J. Feng, et al. Improved SOLOv2 detection method for shield tunnel lining water leakages. J Intell Constr, 2023, 1: 9180004.

[5]

S. J. Feng, Y. Feng, X. L. Zhang, et al. Deep learning with visual explanations for leakage defect segmentation of metro shield tunnel. Tunnell Undergr Space Technol, 2023, 136: 105107.

[6]

N. Zhang, X. J. Zhu, Y. F. Ren. Analysis and study on crack characteristics of highway tunnel lining. Civil Eng J, 2019, 5: 1119–1123.

[7]

H. Zi, Z. D. Ding, X. F. Ji, et al. Effect of voids on the seismic vulnerability of mountain tunnels. Soil Dyn Earthq Eng, 2021, 148: 106833.

[8]

C. Leung, M. A. Meguid. An experimental study of the effect of local contact loss on the earth pressure distribution on existing tunnel linings. Tunnell Undergr Space Technol, 2011, 26: 139–145.

[9]

W. B. Yang, G. Y. Ma, J. L. Tu, et al. Effects of voids on the dynamic response of tunnels under train-induced vibration loads. Int J Phys Modell Geotech, 2023, 23: 77–91.

[10]

X. L. Wu, X. H. Bao, J. Shen, et al. Evaluation of void defects behind tunnel lining through GPR forward simulation. Sensors, 2022, 22: 9702.

[11]

C. Maierhofer. Nondestructive evaluation of concrete infrastructure with ground penetrating radar. J Mater Civil Eng, 2003, 15: 287–297.

[12]
D. G. Pollock, K. J. Dupuis, B. Lacour, et al. Detection of Voids in Prestressed Concrete Bridges using Thermal Imaging and Ground-Penetrating Radar. Washington (USA): Washington State Transportation Center, 2008.
[13]

N. J. Cassidy, R. Eddies, S. Dods. Void detection beneath reinforced concrete sections: The practical application of ground-penetrating radar and ultrasonic techniques. J Appl Geophys, 2011, 74: 263–276.

[14]
K. Virupakshappa, E. Oruklu. Multi-class classification of defect types in ultrasonic NDT signals with convolutional neural networks. In: Proceedings of 2019 IEEE International Ultrasonics Symposium (IUS), Glasgow, UK, 2019: pp 1647–1650.
[15]

S. C. Guo, Q. L. Dai, X. Sun, et al. Ultrasonic scattering measurement of air void size distribution in hardened concrete samples. Constr Build Mater, 2016, 113: 415–422.

[16]

S. C. Guo, Q. L. Dai, X. Sun, et al. Ultrasonic techniques for air void size distribution and property evaluation in both early-age and hardened concrete samples. Appl Sci, 2017, 7: 290.

[17]

J. K. Zhang, W. Z. Yan, D. M. Cui. Concrete condition assessment using impact–echo method and extreme learning machines. Sensors, 2016, 16: 447.

[18]

T. Watanabe, T. Morita, C. Hashimoto, et al. Detecting voids in reinforced concrete slab by SIBIE. Constr Build Mater, 2004, 18: 225–231.

[19]

P. L. Yeh, P. L. Liu. Application of the wavelet transform and the enhanced Fourier spectrum in the impact echo test. NDT E Int, 2008, 41: 382–394.

[20]

F. Yao, G. Y. Chen, J. H. Su. Experimental research and numerical simulation on grouting quality of shield tunnel based on impact echo method. Shock Vib, 2016, 2016: 1025276.

[21]

G. Zhang, R. S. Harichandran, P. Ramuhalli. Application of noise cancelling and damage detection algorithms in NDE of concrete bridge decks using impact signals. J Nondestruct Eval, 2011, 30: 259–272.

[22]
O. Abraham, J. S. Popovics. Impact–echo techniques for evaluation of concrete structures. In: Non-Destructive Evaluation of Reinforced Concrete Structures: Non-Destructive Testing Methods. C. Maierhofer, H. W. Reinhardt, G. Dobmann, Eds. Cambridge (USA): Woodhead Publishing, 2010: pp 466–489.
[23]
J. Y. L. Kasahara, H. Fujii, A. Yamashita, et al. Fuzzy clustering of spatially relevant acoustic data for defect detection. IEEE Rob Autom Lett, 2018, 3: 2616–2623.
[24]

H. X. Tang, S. G. Long, T. Li. Quantitative evaluation of tunnel lining voids by acoustic spectrum analysis. Constr Build Mater, 2019, 228: 116762.

[25]

D. D. Chen, V. Montano, L. S. Huo, et al. Detection of subsurface voids in concrete-filled steel tubular (CFST) structure using percussion approach. Constr Build Mater, 2020, 262: 119761.

[26]
T. Barbu. Comparing various voice recognition techniques. In: Proceedings of the 5th Conference on Speech Technology and Human–Computer Dialogue, Constanta, Romania, 2009: pp 1–6.
[27]

S. Yella, N. K. Gupta, M. S. Dougherty. Comparison of pattern recognition techniques for the classification of impact acoustic emissions. Transp Res Part C: Emerg Technol, 2007, 15: 345–360.

[28]

C. Yuan, J. C. Zhang, L. Chen, et al. Timber moisture detection using wavelet packet decomposition and convolutional neural network. Smart Mater Struct, 2021, 30: 035022.

[29]

O. Chia Ai, M. Hariharan, S. Yaacob, et al. Classification of speech dysfluencies with MFCC and LPCC features. Expert Syst Appl, 2012, 39: 2157–2165.

[30]

Y. Lecun, L. Bottou, Y. Bengio, et al. Gradient-based learning applied to document recognition. Proc IEEE, 1998, 86: 2278–2324.

[31]

A. Krizhevsky, I. Sutskever, G. E. Hinton. ImageNet classification with deep convolutional neural networks. Commun ACM, 2017, 60: 84–90.

[32]
O. Ronneberger, P. Fischer, T. Brox. U-Net: Convolutional networks for biomedical image segmentation. In: Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 2015: pp 234–241.
[33]

L. Chen, H. B. Xiong, X. H. Sang, et al. An innovative deep neural network-based approach for internal cavity detection of timber columns using percussion sound. Struct Health Monit, 2022, 21: 1251–1265.

[34]

Q. Z. Kong, K. Y. Ji, J. X. Gu, et al. A CNN-integrated percussion method for detection of FRP-concrete interfacial damage with FEM reconstruction. Struct Health Monit, 2023, 22: 216–231.

[35]
X. Li, S. Chen, X. L. Hu, et al. Understanding the disharmony between dropout and batch normalization by variance shift. In: Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, New York, USA, 2019: pp 2677–2685.
[36]
K. R. Chapagain, W. Bjerke, S. Wagle. Ultrasonic measurements of grouted tendon ducts in the concrete structure using Elop Insight Scanner. In: Proceedings of the International Symposium on Nondestructive Testing in Civil Engineering, Zurich, Switzerland, 2022.
Journal of Intelligent Construction
Pages 9180029-9180029
Cite this article:
Zhang X, Lin X, Zhang W, et al. Intelligent recognition of voids behind tunnel linings using deep learning and percussion sound. Journal of Intelligent Construction, 2023, 1(4): 9180029. https://doi.org/10.26599/JIC.2023.9180029

3395

Views

313

Downloads

3

Crossref

Altmetrics

Received: 24 September 2023
Revised: 02 November 2023
Accepted: 09 November 2023
Published: 27 December 2023
© The Author(s) 2023. Published by Tsinghua University Press.

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Return