Intelligent Prediction of Bearing Capacity Degradation in Tunnel Linings via Pseudo-Crack Simulation and Deep Learning
Source abstract
Abstract
Cracks in tunnel linings induce bearing capacity degradation, making the rapid prediction of the damage ratio critical for structural safety assessment. However, quantifying the intrinsic mechanical performance solely from apparent surface cracks remains a challenge. To bridge this gap, this study proposes a physics-informed deep learning framework that maps visual crack features directly to the bearing capacity damage ratio. First, a high-fidelity numerical simulation system is established using the Pseudo-Crack Method implemented on the multi-scale thermodynamic platform. This approach avoids the mesh dependency of traditional fracture mechanics and is rigorously validated against existing physical model tests of lining structures in terms of crack morphology and load-displacement responses. Subsequently, a standardized synthetic dataset is constructed by distilling topological features from in-service hydraulic tunnels and applying a color-coded width visualization strategy. By conducting comparative training across eight state-of-the-art deep learning architectures, the ConvNeXtV1 model is identified as the optimal regressor, achieving a coefficient of determination of 0.89 on the test set. The proposed method effectively acts as a real-time "digital surrogate" for time-consuming non-linear finite element analysis, providing a mechanism-based, efficient solution for structural health monitoring of tunnel infrastructure.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Railway Engineering and Dynamics · Rock Mechanics and Modeling · Thermal Analysis in Power Transmission
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Engineering Research Centre of Diagnosis Technology of Hydro-Construction, Chongqing Jiaotong University, Chongqing, 400074, China.
Institute of Science and Technology, China Three Gorges Corporation, Beijing, 101149, China.
State Key Laboratory of Hydroscience and Engineering, Tsinghua University, Beijing, 100084, China.
Nanjing Hydraulic Research Institute, Nanjing, 210028, China.
References (50)
Show source-provided references
1. 1) Chen, S., Yang, Z., Liu, S., Li, L., Zheng, Y., & Yuan, Y. (2022). Numerical simulation and analysis of crack disease in tunnel lining structure. Frontiers in Materials, 9, 1007855. https://doi.org/10.3389/fmats.2022.100785510.3389/fmats.2022.1007855 ↗
2. 2) Duan, L., Feng, J., Song, J., & Yao, S. (2024). Model test study on the mechanical response of the deep buried tunnel lining. Scientific Reports, 14(1), 12863. https://doi.org/10.1038/s41598-024-63438-510.1038/s41598-024-63438-5 ↗
3. 3) Fujiyama, C., Tang, X. J., Maekawa, K., & An, X. H. (2013). Pseudo-cracking approach to fatigue life assessment of RC bridge decks in service. Journal of Advanced Concrete Technology, 11(1), 7-21. https://doi.org/10.3151/jact.11.710.3151/jact.11.7 ↗
4. 4) Gao, Y., Jiang, Y., & Li, B. (2016). Voids delineation behind tunnel lining based on the vibration intensity of microtremors. Tunnelling and Underground Space Technology, 51, 338-345. https://doi.org/10.1016/j.tust.2015.10.03210.1016/j.tust.2015.10.032 ↗
5. 5) Gong, C., Wang, Y., Peng, Y., Ding, W., Lei, M., Da, Z., & Shi, C. (2022). Three-dimensional coupled hydromechanical analysis of localized joint leakage in segmental tunnel linings. Tunnelling and Underground Space Technology, 130, 104726. https://doi.org/10.1016/j.tust.2022.10472610.1016/j.tust.2022.104726 ↗
6. 6) Gong, F., Takahashi, Y., & Maekawa, K. (2017). Strong coupling of freeze-thaw cycles and alkali silica reaction—Multi-scale poro-mechanical approach to concrete damages. Journal of Advanced Concrete Technology, 15(7), 346-367. https://doi.org/10.3151/jact.15.34610.3151/jact.15.346 ↗
7. 7) He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: IEEE International Conference on Computer Vision and Pattern Recognition. Las Vegas, Nevada 26-30 June 2016. Piscataway, New Jersey: Institute of Electrical and Electronics Engineers, 770-778. https://doi.org/10.1109/CVPR.2016.9010.1109/CVPR.2016.90 ↗
8. 8) Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., Pang, R., Adam, H., & Le, Q. (2019). Searching for MobileNetV3. In: IEEE International Conference on Computer Vision and Pattern Recognition. Long Beach, California 16-20 June 2019. Piscataway, New Jersey: Institute of Electrical and Electronics Engineers, 1314-1324. https://doi.org/10.1109/ICCV.2019.0014010.1109/ICCV.2019.00140 ↗
9. 9) Huang, G., Gong, L., Sun, X., Liang, Z., & Wang, X.-Y. (2020). Numerical investigation on flexural performance of retrofitted tunnel lining with short bolts and steel-plate. Tunnelling and Underground Space Technology, 95, 103152. https://doi.org/10.1016/j.tust.2019.10315210.1016/j.tust.2019.103152 ↗
10. 10) Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In: IEEE International Conference on Computer Vision and Pattern Recognition. Honolulu, Hawaii 21-26 July 2017. Piscataway, New Jersey: Institute of Electrical and Electronics Engineers, 2261-2269. https://doi.org/10.1109/CVPR.2017.24310.1109/CVPR.2017.243 ↗
11. 11) Huang, H., Li, Q., & Zhang, D. (2018). Deep learning based image recognition for crack and leakage defects of metro shield tunnel. Tunnelling and Underground Space Technology, 77, 166-176. https://doi.org/10.1016/j.tust.2018.04.00210.1016/j.tust.2018.04.002 ↗
12. 12) Jiang, R., Dai, F., Liu, Y., & Li, A. (2021). Fast marching method for microseismic source location in cavern-containing rockmass: Performance analysis and engineering application. Engineering, 7(7), 1023-1034. https://doi.org/10.1016/j.eng.2020.10.01910.1016/j.eng.2020.10.019 ↗
13. 13) Jin, X., Qiao, K., Bu, M., Wang, J., Wang, M., & Fang, C. (2025). Intelligent safety evaluation of tunnel lining cracks based on machine learning. Engineering Failure Analysis, 167, 109082. https://doi.org/10.1016/j.engfailanal.2024.10908210.1016/j.engfailanal.2024.109082 ↗
14. 14) Li, A., Liu, Y., Dai, F., Liu, K., & Wei, M. (2020). Continuum analysis of the structurally controlled displacements for large-scale underground caverns in bedded rock masses. Tunnelling and Underground Space Technology, 97, 103288. https://doi.org/10.1016/j.tust.2020.10328810.1016/j.tust.2020.103288 ↗
15. 15) Li, D., Xie, Q., Gong, X., Yu, Z., Xu, J., Sun, Y., & Wang, J. (2021). Automatic defect detection of metro tunnel surfaces using a vision-based inspection system. Advanced Engineering Informatics, 47, 101206. https://doi.org/10.1016/j.aei.2020.10120610.1016/j.aei.2020.101206 ↗
16. 16) Lin, Z., Feng, W., Jin, K., Chen, X., Yang, H., & Hu, Y. (2025). Evolution of cracking damage and load-bearing performance of in-service tunnel linings with cracks. Theoretical and Applied Fracture Mechanics, 138, 104897. https://doi.org/10.1016/j.tafmec.2025.10489710.1016/j.tafmec.2025.104897 ↗
17. 17) Liu, J., Wang, S., Chen, K., Wang, K., Fan, Y., & Wang, Q. (2026). Synthetic data augmentation and integrated prediction framework for low-carbon recycled concrete: Leveraging CTGAN and multiple ML models stacking. Journal of Cleaner Production, 543, 147599. https://doi.org/10.1016/j.jclepro.2026.14759910.1016/j.jclepro.2026.147599 ↗
18. 18) Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In: IEEE International Conference on Computer Vision (Virtual Conference). 20-25 June 2021. Piscataway, New Jersey: Institute of Electrical and Electronics Engineers, 9992-10002. https://doi.org/10.1109/ICCV48922.2021.0098610.1109/ICCV48922.2021.00986 ↗
19. 19) Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022). A ConvNet for the 2020s. In: IEEE Conference on Computer Vision and Pattern Recognition. New Orleans, Louisiana 19-24 June 2022. Piscataway, New Jersey: Institute of Electrical and Electronics Engineers, 11966-11976. https://doi.org/10.1109/CVPR52688.2022.0116710.1109/CVPR52688.2022.01167 ↗
20. 20) Lu, X., Liu, Y., Hou, X., Chen, C., & Gao, R. (2024). Numerical simulation of mechanical characteristics and safety performance for pre-cracked tunnel lining with the extended finite element method. Buildings, 14(1), 123. https://doi.org/10.3390/buildings1401012310.3390/buildings14010123 ↗
21. 21) Maekawa, K., Ishida, T., & Kishi, T. (2008). Multi-scale modeling of structural concrete. Boca Raton, Florida: CRC Press. https://doi.org/10.1201/978148228859910.1201/9781482288599 ↗
22. 22) Maekawa, K., Toongoenthong, K., Gebreyouhannes, E., & Kishi, T. (2006). Direct path-integral scheme for fatigue simulation of reinforced concrete in shear. Journal of Advanced Concrete Technology, 4(1), 159-177. https://doi.org/10.3151/jact.4.15910.3151/jact.4.159 ↗
23. 23) Min, B., Zhang, C., Zhu, W., Zhang, X., & Li, P. (2021). Influence of cracks at the invert on the mechanical behavior of the tunnel structures. Thin-Walled Structures, 161, 107405. https://doi.org/10.1016/j.tws.2020.10740510.1016/j.tws.2020.107405 ↗
24. 24) Min, B., Zhang, X., Zhang, C., & Zhang, X. (2024). Prediction of bearing capacity of cracked asymmetrical double-arch tunnels using the artificial neural networks. Engineering Failure Analysis, 156, 107805. https://doi.org/10.1016/j.engfailanal.2023.10780510.1016/j.engfailanal.2023.107805 ↗
25. 25) Okazaki, Y., Okazaki, S., Asamoto, S., & Chun, P. (2020). Undersampling strategy for machine-learned deterioration regression model in concrete bridges. Journal of Advanced Concrete Technology, 18(12), 753-766. https://doi.org/10.3151/jact.18.75310.3151/jact.18.753 ↗
26. 26) Pan, H., & Yin, X. (2025). Research on durability of underground lining structures using damage theory. Scientific Reports, 15(1), 18957. https://doi.org/10.1038/s41598-025-03451-410.1038/s41598-025-03451-4 ↗
27. 27) Protopapadakis, E., Voulodimos, A., Doulamis, A., Doulamis, N., & Stathaki, T. (2019). Automatic crack detection for tunnel inspection using deep learning and heuristic image post-processing. Applied Intelligence, 49(7), 2793-2806. https://doi.org/10.1007/s10489-018-01396-y10.1007/s10489-018-01396-y ↗
28. 28) Qin, D., Leichner, C., Delakis, M., Fornoni, M., Luo, S., Yang, F., Wang, W., Banbury, C., Ye, C., Akin, B., Aggarwal, V., Zhu, T., Moro, D., & Howard, A. (2025). MobileNetV4: Universal models for the mobile ecosystem. In: A. Leonardis, E. Ricci, S. Roth, O. Russakovsky, T. Sattler, & G. Varol (Eds.), 18th European Conference on Computer Vision – ECCV 2024. Milano, Italy 29 September-4 October 2024. Cham: Springer Nature Switzerland, 78-96. https://doi.org/10.1007/978-3-031-73661-2_510.1007/978-3-031-73661-2_5 ↗
29. 29) Radosavovic, I., Kosaraju, R. P., Girshick, R., He, K., & Dollar, P. (2020). Designing network design spaces. In: IEEE Conference on Computer Vision and Pattern Recognition (Virtual Conference). 13-19 June 2020. Piscataway, New Jersey: Institute of Electrical and Electronics Engineers, 10425-10433. https://doi.org/10.1109/CVPR42600.2020.0104410.1109/CVPR42600.2020.01044 ↗
30. 30) Ren, Y., Huang, J., Hong, Z., Lu, W., Yin, J., Zou, L., & Shen, X. (2020). Image-based concrete crack detection in tunnels using deep fully convolutional networks. Construction and Building Materials, 234, 117367. https://doi.org/10.1016/j.conbuildmat.2019.11736710.1016/j.conbuildmat.2019.117367 ↗
31. 31) Sirisena, G., Jayasinghe, T., Gunawardena, T., Zhang, L., Mendis, P., & Mangalathu, S. (2024). Machine learning-based framework for predicting the fire-induced spalling in concrete tunnel linings. Tunnelling and Underground Space Technology, 153, 106000. https://doi.org/10.1016/j.tust.2024.10600010.1016/j.tust.2024.106000 ↗
32. 32) Su, J., Jie, Y., Niu, X., Liu, C., & Liu, X. (2020). Mechanical behavior of tunnel lining with cracks at different positions. Symmetry, 12(2), 0194. https://doi.org/10.3390/sym1202019410.3390/sym12020194 ↗
33. 33) Tang, X. J., Fujiyama, C., Shang, F., Maekawa, K., & An, X. H. (2014). Residual fatigue life assessment of damaged RC bridge slabs based on site-inspection for cracking: A quantitative discussion. Advances in Structural Engineering, 17(4), 481-494. https://doi.org/10.1260/1369-4332.17.4.48110.1260/1369-4332.17.4.481 ↗
34. 34) Tian, L., Hu, Z., & Chen, J. (2021). Experimental and numerical research on defective shield segment under cyclic loading. Shock and Vibration, 2021(1), 8567899. https://doi.org/10.1155/2021/856789910.1155/2021/8567899 ↗
35. 35) Usman, M., & Galler, R. (2013). Long-term deterioration of lining in tunnels. International Journal of Rock Mechanics and Mining Sciences, 64, 84-89. https://doi.org/10.1016/j.ijrmms.2013.08.02810.1016/j.ijrmms.2013.08.028 ↗
36. 36) Wang, J., Mi, Z., Zhang, T., & Wang, D. (2022). Durability degradation of tunnel-lining-shotcrete exposed to nitric acid: Neutralization and nitrate ion migration. Construction and Building Materials, 336, 127554. https://doi.org/10.1016/j.conbuildmat.2022.12755410.1016/j.conbuildmat.2022.127554 ↗
37. 37) Wang, S., Chen, Y., Gong, F., Fan, Y., Huang, B.-T., & Zhang, H. (2026). Intelligent framework of temperature and humidity field coupling of early-age concrete considering hydration based on physics informed neural network. International Communications in Heat and Mass Transfer, 172, 110203. https://doi.org/10.1016/j.icheatmasstransfer.2025.11020310.1016/j.icheatmasstransfer.2025.110203 ↗
38. 38) Wang, S., Xia, P., Chen, K., Gong, F., Wang, H., Wang, Q., Zhao, Y., & Jin, W. (2023). Prediction and optimization model of sustainable concrete properties using machine learning, deep learning and swarm intelligence: A review. Journal of Building Engineering, 80, 108065. https://doi.org/10.1016/j.jobe.2023.10806510.1016/j.jobe.2023.108065 ↗
39. 39) Wang, S., Xia, P., Gong, F., Zeng, Q., Chen, K., & Zhao, Y. (2024). Multi objective optimization of recycled aggregate concrete based on explainable machine learning. Journal of Cleaner Production, 445, 141045. https://doi.org/10.1016/j.jclepro.2024.14104510.1016/j.jclepro.2024.141045 ↗
40. 40) Wang, S., Xia, P., Gong, F., Zhao, Y., & Lin, P. (2025). A Bayesian-physical informed conditional tabular generative adversarial network framework for low-carbon concrete data augmentation and hyperparameter optimization. Engineering Applications of Artificial Intelligence, 152, 110811. https://doi.org/10.1016/j.engappai.2025.11081110.1016/j.engappai.2025.110811 ↗
41. 41) Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I. S., & Xie, S. (2023). ConvNeXt V2: Co-designing and scaling ConvNets with masked autoencoders. In: IEEE Conference on Computer Vision and Pattern Recognition. Vancouver, British Columbia 18-22 June 2023. Piscataway, New Jersey: Institute of Electrical and Electronics Engineers, 16133-16142. https://doi.org/10.1109/CVPR52729.2023.0154810.1109/CVPR52729.2023.01548 ↗
42. 42) Xie, H., Wang, H., Zou, X., Chen, Y., Liu, Z., Yang, L., & Liu, K. (2025). Research on cracking mechanism and crack extension of diversion tunnel lining structure. Applied Sciences, 15(16), 9210. https://doi.org/10.3390/app1516921010.3390/app15169210 ↗
43. 43) Xu, G., He, C., Chen, Z., Liu, C., Wang, B., & Zou, Y. (2020). Mechanical behavior of secondary tunnel lining with longitudinal crack. Engineering Failure Analysis, 113, 104543. https://doi.org/10.1016/j.engfailanal.2020.10454310.1016/j.engfailanal.2020.104543 ↗
44. 44) Xu, P., Wu, Y., Huang, L., & Zhang, K. (2021). Study on the progressive deterioration of tunnel lining structures in cold regions experiencing freeze-thaw cycles. Applied Sciences, 11(13), 5903. https://doi.org/10.3390/app1113590310.3390/app11135903 ↗
45. 45) Xu, Z., Chen, J., Luo, Y., Zhu, H., Liu, W., Shi, Z., & Song, Z. (2022). Geomechanical model test for mechanical properties and cracking features of large-section tunnel lining under periodic temperature. Tunnelling and Underground Space Technology, 123, 104319. https://doi.org/10.1016/j.tust.2021.10431910.1016/j.tust.2021.104319 ↗
46. 46) Xue, Y., & Li, Y. (2018). A fast detection method via region-based fully convolutional neural networks for shield tunnel lining defects. Computer-Aided Civil and Infrastructure Engineering, 33(8), 638-654. https://doi.org/10.1111/mice.1236710.1111/mice.12367 ↗
47. 47) Yamane, T., & Chun, P. (2020). Crack detection from a concrete surface image based on semantic segmentation using deep learning. Journal of Advanced Concrete Technology, 18(9), 493-504. https://doi.org/10.3151/jact.18.49310.3151/jact.18.493 ↗
48. 48) Zhang, J., & Zhao, M. (2021). Experimental study on mechanical behavior of the skew joints of shield tunnels under large eccentric compressive loading. Tunnelling and Underground Space Technology, 111, 103876. https://doi.org/10.1016/j.tust.2021.10387610.1016/j.tust.2021.103876 ↗
49. 49) Zhang, W., Qi, J., Zhang, G., Niu, R., Zhang, C., He, L., & Lyu, J. (2022). Full-scale experimental study on failure characteristics of the key segment in shield tunnel with super-large cross-section. Tunnelling and Underground Space Technology, 129, 104671. https://doi.org/10.1016/j.tust.2022.10467110.1016/j.tust.2022.104671 ↗
50. 50) Zheng, X., Wang, W., Zhang, Y., Qi, J., & Yao, X. (2024). Macro–meso damage analysis of tunnel lining concrete under thermal–mechanical coupling based on CT images. Materials, 17(1), 253. https://doi.org/10.3390/ma1701025310.3390/ma17010253 ↗