Deep convolutional neural network for multi-level non-invasive tunnel lining assessment

doi:10.1007/s11709-021-0800-2

Front. Struct. Civ. Eng.

2022, Vol. 16

Issue (2) : 214-223 https://doi.org/10.1007/s11709-021-0800-2

RESEARCH ARTICLE

Deep convolutional neural network for multi-level non-invasive tunnel lining assessment

Bernardino CHIAIA, Giulia MARASCO(

), Salvatore AIELLO

Department of Structural, Geotechnical and Building Engineering, Polytechnic University of Turin, Torino 10129, Italy

Download: PDF(4269 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

In recent years, great attention has focused on the development of automated procedures for infrastructures control. Many efforts have aimed at greater speed and reliability compared to traditional methods of assessing structural conditions. The paper proposes a multi-level strategy, designed and implemented on the basis of periodic structural monitoring oriented to a cost- and time-efficient tunnel control plan. Such strategy leverages the high capacity of convolutional neural networks to identify and classify potential critical situations. In a supervised learning framework, Ground Penetrating Radar (GPR) profiles and the revealed structural phenomena have been used as input and output to train and test such networks. Image-based analysis and integrative investigations involving video-endoscopy, core drilling, jacking and pull-out testing have been exploited to define the structural conditions linked to GPR profiles and to create the database. The degree of detail and accuracy achieved in identifying a structural condition is high. As a result, this strategy appears of value to infrastructure managers who need to reduce the amount and invasiveness of testing, and thus also to reduce the time and costs associated with inspections made by highly specialized technicians.

Keywords concrete structure GPR damage classification convolutional neural network transfer learning

Corresponding Author(s): Giulia MARASCO

About author:

Mingsheng Sun and Mingxiao Yang contributed equally to this work.

Just Accepted Date: 21 January 2022 Online First Date: 28 March 2022 Issue Date: 20 April 2022

Cite this article:

Bernardino CHIAIA,Giulia MARASCO,Salvatore AIELLO. Deep convolutional neural network for multi-level non-invasive tunnel lining assessment[J]. Front. Struct. Civ. Eng., 2022, 16(2): 214-223.

URL:

https://academic.hep.com.cn/fsce/EN/10.1007/s11709-021-0800-2
https://academic.hep.com.cn/fsce/EN/Y2022/V16/I2/214

Tab.1 Hyperparameters

Tab.2 Technical characteristics of GPR with dual frequency antenna

Tab.3 Technical characteristics of GPR with high-frequency antenna

Fig.1 2-lane tunnel (3 profiles) and 3-lane tunnel (5 profiles).

Fig.2 Presence of voids and anomalies.

Fig.3 Flowchart: Multi-level damage classification approach.

Tab.4 Confusion matrix Level 1

Tab.5 Confusion matrix Level 6

Fig.4 Training progress-loss/accuracy vs number of iterations.

Tab.6 Confusion matrix Level 2a

Tab.7 Confusion matrix Level 2b

Tab.8 Confusion matrix Level 3

Tab.9 Confusion matrix Level 4

Tab.10 Confusion matrix Level 5

Fig.5 Level 1. Error percentages as function of number of sample and training percentages.

Fig.6 Level 5. Error percentages as function of number of sample and training percentages.

1	A Showkati, H Salari-rad, M Hazrati Aghchai. Predicting long-term stability of tunnels considering rock mass weathering and deterioration of primary support. Tunnelling and Underground Space Technology, 2021, 107 : 103670 https://doi.org/10.1016/j.tust.2020.103670
2	F Ye, N Qin, X Liang, A Ouyang, Z Qin, E Su. Analyses of the defects in highway tunnels in China. Tunnelling and Underground Space Technology, 2021, 107 : 103658 https://doi.org/10.1016/j.tust.2020.103658
3	K H Kim, N H Park, H J Kim, J H Shin. Modelling of hydraulic deterioration of geotextile filter in tunnel drainage system. Geotextiles and Geomembranes, 2020, 48( 2): 210–219 https://doi.org/10.1016/j.geotexmem.2019.11.008
4	C Gao, Z Zhou, W Yang, C Lin, L Li, J Wang. Model test and numerical simulation research of water leakage in operating tunnels passing through intersecting faults. Tunnelling and Underground Space Technology, 2019, 94 : 103134 https://doi.org/10.1016/j.tust.2019.103134
5	L Xiong, D Zhang, Y Zhang. Water leakage image recognition of shield tunnel via learning deep feature representation. Journal of Visual Communication and Image Representation, 2020, 71 : 102708 https://doi.org/10.1016/j.jvcir.2019.102708
6	Z Xuefu, Z Yaonan. Study on a new-styled measure for treating water leakage of the permafrost tunnels. Tunnelling and Underground Space Technology, 2006, 21( 6): 656–667 https://doi.org/10.1016/j.tust.2005.11.006
7	Working Group on Maintenance ITA, of Underground Structures Repair. Report on the damaging effects of water on tunnels during their working life. Tunnelling and Underground Space Technology, 1991, 6( 1): 11–76 https://doi.org/10.1016/0886-7798(91)90005-O
8	Y Luo, J Chen. Research status and progress of tunnel frost damage. Journal of Traffic and Transportation Engineering (English Edition), 2019, 6( 3): 297–309 https://doi.org/10.1016/j.jtte.2018.09.007
9	W L Wang, T T Wang, J J Su, C H Lin, C R Seng, T H Huang. Assessment of damage in mountain tunnels due to the Taiwan (China) Chi-Chi Earthquake. Tunnelling and Underground Space Technology, 2001, 16( 3): 133–150 https://doi.org/10.1016/S0886-7798(01)00047-5
10	M Lei, L Liu, C Shi, Y Tan, Y Lin, W Wang. A novel tunnel-lining crack recognition system based on digital image technology. Tunnelling and Underground Space Technology, 2021, 108 : 103724 https://doi.org/10.1016/j.tust.2020.103724
11	B Kim, S Cho. Automated vision-based detection of cracks on concrete surfaces using a deep learning technique. Sensors (Switzerland), 2018, 18( 10): 3452 https://doi.org/10.3390/s18103452
12	J Zhu, J Song. An intelligent classification model for surface defects on cement concrete bridges. Applied Sciences (Basel, Switzerland), 2020, 10( 3): 972 https://doi.org/10.3390/app10030972
13	C Feng, H Zhang, S Wang, Y Li, H Wang, F Yan. Structural damage detection using deep convolutional neural network and transfer learning. KSCE Journal of Civil Engineering, 2019, 23( 10): 4493–4502 https://doi.org/10.1007/s12205-019-0437-z
14	Q Song, Y Wu, X Xin, L Yang, M Yang, H Chen, C Liu, M Hu, X Chai, J Li. Real-time tunnel crack analysis system via deep learning. IEEE Access : Practical Innovations, Open Solutions, 2019, 7 : 64186–64197 https://doi.org/10.1109/ACCESS.2019.2916330
15	Patterson B, Leone G, Pantoja M, Behrouzi A. Deep learning for automated image classification of seismic damage to built infrastructure. In: 11th US National Conference on Earthquake Engineering, Integrating Science, Engineering & Policy. 2018, 10: 6561–6571
16	Y J Cha, W Choi, G Suh, S Mahmoudkhani, O Büyüköztürk. Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types. Computer-Aided Civil and Infrastructure Engineering, 2018, 33( 9): 731–747 https://doi.org/10.1111/mice.12334
17	K Deisseroth, V Gradinaru. Advances in neurotechniques: Methods that reveal the structure and function of the brain. Science, 2014, 345( 6197): 698–698
18	A M Alani, F Tosti. GPR applications in structural detailing of a major tunnel using different frequency antenna systems. Construction & Building Materials, 2018, 158 : 1111–1122 https://doi.org/10.1016/j.conbuildmat.2017.09.100
19	D Feng, X Wang, B Zhang. Specific evaluation of tunnel lining multi-defects by all-refined GPR simulation method using hybrid algorithm of FETD and FDTD. Construction & Building Materials, 2018, 185 : 220–229 https://doi.org/10.1016/j.conbuildmat.2018.07.039
20	T Dawood, Z Zhu, T Zayed. Deterioration mapping in subway infrastructure using sensory data of GPR. Tunnelling and Underground Space Technology, 2020, 103 : 103487 https://doi.org/10.1016/j.tust.2020.103487
21	W Al-Nuaimy, Y Huang, M Nakhkash, M T C Fang, V T Nguyen, A Eriksen. Automatic detection of buried utilities and solid objects with GPR using neural networks and pattern recognition. Journal of Applied Geophysics, 2000, 43( 2-4): 157–165 https://doi.org/10.1016/S0926-9851(99)00055-5
22	P Nakkiran. More data can hurt for linear regression: Sample-wise double descent. 2019, arXiv: 1912.07242
23	P Nakkiran, G Kaplun, Y Bansal, T Yang, B Barak, I Sutskever. Deep double descent: Where bigger models and more data hurt. Journal of Statistical Mechanics: Theory and Experiment, 2021, 2021( 12): 124003
24	W Rawat, Z Wang. Deep convolutional neural networks for image classification: A comprehensive review. Neural Computation, 2017, 29( 9): 2352–2449 https://doi.org/10.1162/neco_a_00990
25	O Russakovsky, J Deng, H Su, J Krause, S Satheesh, S Ma, L Fei-Fei. Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 2015, 115( 3): 211–252
26	J Markoff. For Web Images, Creating New Technology to Seek and Find. New York Times, 2012
27	G ParkinsonC Ékes. Ground penetrating radar evaluation of concrete tunnel linings. In: 12th International Conference on Ground Penetrating Radar. Birmingham: University of Birmingham, 2008
28	G Grandjean, J C Gourry, A Bitri. Evaluation of GPR techniques for civil-engineering applications: Study on a test site. Journal of Applied Geophysics, 2000, 45( 3): 141–156 https://doi.org/10.1016/S0926-9851(00)00021-5
29	G Kilic, L Eren. Neural network based inspection of voids and karst conduits in hydro–electric power station tunnels using GPR. Journal of Applied Geophysics, 2018, 151 : 194–204 https://doi.org/10.1016/j.jappgeo.2018.02.026
30	C TrelaT KindM Schubert. Detection of air voids in concrete by radar in transmission mode. In: 8th International Workshop on Advanced Ground Penetrating Radar (IWAGPR). Florence: IEEE, 2015
31	S W JawM Hashim. Accuracy of data acquisition approaches with ground penetrating radar for subsurface utility mapping. In: 2011 IEEE International RF & Microwave Conference. Seremban: IEEE, 2011
32	W Shao, A Bouzerdoum, S L Phung, L Su, B Indraratna, C Rujikiatkamjorn. Automatic classification of ground-penetrating-radar signals for railway-ballast assessment. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49( 10): 3961–3972 https://doi.org/10.1109/TGRS.2011.2128328
33	P A Torrione, K D Morton, R Sakaguchi, L M Collins. Histograms of oriented gradients for landmine detection in ground-penetrating radar data. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52( 3): 1539–1550 https://doi.org/10.1109/TGRS.2013.2252016
34	A G Davis, M K Lim, C G Petersen. Rapid and economical evaluation of concrete tunnel linings with impulse response and impulse radar non-destructive methods. NDT & E International, 2005, 38( 3): 181–186 https://doi.org/10.1016/j.ndteint.2004.03.011
35	E Cardarelli, C Marrone, L Orlando. Evaluation of tunnel stability using integrated geophysical methods. Journal of Applied Geophysics, 2003, 52( 2−3): 93–102 https://doi.org/10.1016/S0926-9851(02)00242-2
36	H JoY H NaJ B Song. Data augmentation using synthesized images for object detection. In: 17th International Conference on Control, Automation and Systems (ICCAS). Jeju: IEEE, 2017
37	Z Zhong, L Zheng, G Kang, S Li, Y Yang. Random erasing data augmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34( 7): 13001–13008 https://doi.org/10.1609/aaai.v34i07.7000
38	Z Hussain, F Gimenez, D Yi, D Rubin. Differential data augmentation techniques for medical imaging classification tasks. AMIA annual symposium proceedings, 2017, 2017 : 979–984
39	K HeX ZhangS RenJ Sun. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV: IEEE, 2016
40	C Anitescu, E Atroshchenko, N Alajlan, T Rabczuk. Artificial neural network methods for the solution of second order boundary value problems. Computers, Materials & Continua, 2019, 59( 1): 345–359 https://doi.org/10.32604/cmc.2019.06641
41	H Guo, X Zhuang, T Rabczuk. A deep collocation method for the bending analysis of Kirchhoff plate. Computers, Materials & Continua, 2019, 59( 2): 433–456 https://doi.org/10.32604/cmc.2019.06660
42	A Ventura. Extraction of frequent semantic relationships between objects in segmented images. Dissertation for the Doctoral Degree. Turin: Polytechnic University of Turin, 2020 (In Italian)
43	R LongadgeS Dongre. Class imbalance problem in data mining review. 2013, arXiv:1305.1707
44	J D Rodriguez, A Perez, J A Lozano. Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32( 3): 569–575 https://doi.org/10.1109/TPAMI.2009.187
45	P RefaeilzadehL TangH Liu. Cross-Validation. In: Encyclopedia of Database Systems. New York: Springer, 2016
46	G JamesD WittenT HastieR Tibshirani. An Introduction to Statistical Learning: With Applications in R. New York: Springer, 2013

[1]	Pierclaudio SAVINO, Francesco TONDOLO. Automated classification of civil structure defects based on convolutional neural network[J]. Front. Struct. Civ. Eng., 2021, 15(2): 305-317.
[2]	Pengfei HE, Yang SHEN, Yun GU, Pangyong SHEN. 3D fracture modelling and limit state analysis of prestressed composite concrete pipes[J]. Front. Struct. Civ. Eng., 2019, 13(1): 165-175.
[3]	Bj?rn SCHüTTE,Viktor SIGRIST. Shear assessment of compression flanges of structural concrete T-beams[J]. Front. Struct. Civ. Eng., 2014, 8(4): 354-361.
[4]	Pijush Samui, Jagan J. Determination of effective stress parameter of unsaturated soils: A Gaussian process regression approach[J]. Front Struc Civil Eng, 2013, 7(2): 133-136.

Viewed

Full text

Abstract

Cited

Shared

Discussed