Smart Structures and Systems

  • 제30권6호
  • /
  • Pages.601-612
  • /
  • 2022
  • /
  • 1738-1584(pISSN)
  • /
  • 1738-1991(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

DATCN: Deep Attention fused Temporal Convolution Network for the prediction of monitoring indicators in the tunnel

  • Bowen, Du (SKLSDE and BDBC Lab, Beihang University) ;
  • Zhixin, Zhang (SKLSDE and BDBC Lab, Beihang University) ;
  • Junchen, Ye (SKLSDE and BDBC Lab, Beihang University) ;
  • Xuyan, Tan (State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences) ;
  • Wentao, Li (SKLSDE and BDBC Lab, Beihang University) ;
  • Weizhong, Chen (State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences)
  • 투고 : 2022.03.30
  • 심사 : 2022.09.18
  • 발행 : 2022.12.25
⟨ 이전 논문 다음 논문 ⟩

초록

The prediction of structural mechanical behaviors is vital important to early perceive the abnormal conditions and avoid the occurrence of disasters. Especially for underground engineering, complex geological conditions make the structure more prone to disasters. Aiming at solving the problems existing in previous studies, such as incomplete consideration factors and can only predict the continuous performance, the deep attention fused temporal convolution network (DATCN) is proposed in this paper to predict the spatial mechanical behaviors of structure, which integrates both the temporal effect and spatial effect and realize the cross-time prediction. The temporal convolution network (TCN) and self-attention mechanism are employed to learn the temporal correlation of each monitoring point and the spatial correlation among different points, respectively. Then, the predicted result obtained from DATCN is compared with that obtained from some classical baselines, including SVR, LR, MLP, and RNNs. Also, the parameters involved in DATCN are discussed to optimize the prediction ability. The prediction result demonstrates that the proposed DATCN model outperforms the state-of-the-art baselines. The prediction accuracy of DATCN model after 24 hours reaches 90 percent. Also, the performance in last 14 hours plays a domain role to predict the short-term behaviors of the structure. As a study case, the proposed model is applied in an underwater shield tunnel to predict the stress variation of concrete segments in space.

키워드

과제정보

We thank the reviewers for their constructive comments on this research work. This work is supported by the National Key R&D Program of China No. 2018YFB2101003, the National Natural Science Foundation of China under Grant No. 51991395, U1806226, 51778033, 51822802, 71901011, U1811463, 51991391, the Science and Technology Major Project of Beijing under Grant No. Z191100002519012.

참고문헌

  1. Cao, B.T., Obel, M., Freitag, S., Mark, P. and Meschke, G. (2020), "Artificial neural network surrogate modelling for real-time predictions and control of building damage during mechanised tunnelling", Adv. Eng. Software, 149, 102869. https://doi.org/10.1016/j.advengsoft.2020.102869
  2. Carbonneau, R., Laframboise, K. and Vahidov, R. (2008), "Application of machine learning techniques for supply chain demand forecasting", Eur. J. Operat. Res., 184(3), 1140-1154. https://doi.org/10.1016/j.ejor.2006.12.004
  3. Chen, T., Yin, H., Chen, H., Wu, L., Wang, H., Zhou, X. and Li, X. (2018), "Tada: trend alignment with dualattention multi-task recurrent neural networks for sales prediction", Proceedings of 2018 IEEE International Conference on Data Mining (ICDM), Singapore, November, pp. 49-58. https://doi.org/10.1109/ICDM.2018.00020
  4. Fahimifar, A., Tehrani, F.M., Hedayat, A. and Vakilzadeh, A. (2010), "Analytical solution for the excavation of circular tunnels in a visco-elastic Burger's material under hydrostatic stress field", Tunnell. Undergr. Space Technol., 25(4), 297-304. https://doi.org/10.1016/j.tust.2010.01.002
  5. Farahani, R.V. and Penumadu, D. (2016), "Full-scale bridge damage identification using time series analysis of a dense array of geophones excited by drop weight", Struct. Control Health Monitor., 23(7), 982-997. https://doi.org/10.1002/stc.1820
  6. Hou, L. and Qu, H. (2021), "Automatic recognition system of pointer meters based on lightweight CNN and WSNs with on-sensor image processing", Measurement, 183, p. 109819. https://doi.org/10.1016/j.measurement.2021.109819
  7. Lin, S.W., Yi, T.H., Li, H.N. and Ren, L. (2017), "Damage detection in the cable structures of a bridge using the virtual distortion method", J. Bridge Eng., 22(8), 04017039. https://doi.org/10.1061/(ASCE)BE.1943-5592.0001072
  8. Mahdevari, S. and Torabi, S.R. (2012), "Prediction of tunnel convergence using artificial neural networks", Tunnell. Undergr. Space Technol., 28, 218-228. https://doi.org/10.1016/j.tust.2011.11.002
  9. Mahmoodzadeh, A., Mohammadi, M., Daraei, A., Faraj, R.H., Omer, R.M.D. and Sherwani, A.F.H. (2020), "Decision-making in tunneling using artificial intelligence tools", Tunnell. Undergr. Space Technol., 103, 103514. https://doi.org/10.1016/j.tust.2020.103514
  10. Mahmoodzadeh, A., Mohammadi, M., Ibrahim, H.H., Rashid, T.A., Aldalwie, A.H.M., Ali, H.F.H. and Daraei, A. (2021), "Tunnel geomechanical parameters prediction using Gaussian process regression", Mach. Learn. Applicat., 3, 100020. https://doi.org/10.1016/j.mlwa.2021.100020
  11. Mei, L., Mita, A. and Zhou, J. (2016), "An improved substructural damage detection approach of shear structure based on ARMAX model residual", Struct. Control Health Monitor., 23(2), 218-236. https://doi.org/10.1002/stc.1766
  12. Prakash, G., Sadhu, A., Narasimhan, S. and Brehe, J.M. (2018), "Initial service life data towards structural health monitoring of a concrete arch dam", Struct. Control Health Monitor., 25(1), e2036. https://doi.org/10.1002/stc.2036
  13. Sajedi, S.O. and Liang, X. (2020), "A data-driven framework for near real-time and robust damage diagnosis of building structures", Struct. Control Health Monitor., 27(3), e2488. https://doi.org/10.1002/stc.2488
  14. Shahrour, I., Bian, H., Xie, X. and Zhang, Z. (2020), "Smart technology applications for the optimal management of underground facilities", Undergr. Space, 6(5), 551-559. https://doi.org/10.1016/j.undsp.2020.12.002
  15. Sharifzadeh, M., Tarifard, A. and Moridi, M.A. (2013), "Time-dependent behavior of tunnel lining in weak rock mass based on displacement back analysis method", Tunnell. Undergr. Space Technol., 38, 348-356. https://doi.org/10.1016/j.tust.2013.07.014
  16. Spencer Jr, B., Ruiz-Sandoval, M.E. and Kurata, N. (2004), "Smart sensing technology: opportunities and challenges", Struct. Control Health Monitor., 11(4), 349-368. https://doi.org/10.1002/stc.48
  17. Sterpi, D. and Gioda, G. (2009), "Visco-plastic behaviour around advancing tunnels in squeezing rock", Rock Mech. Rock Eng., 42(2), 319-339. https://doi.org/10.1007/s00603-007-0137-8
  18. Tan, X., Chen, W., Wang, L., Tan, X. and Yang, J. (2020a), "Integrated approach for structural stability evaluation using real-time monitoring and statistical analysis: Underwater shield tunnel case study", J. Perform. Constr. Facil., 34(2), 04019118. https://doi.org/10.1061/(ASCE)CF.1943-5509.0001391
  19. Tan, X., Chen, W., Wu, G., Wang, L. and Yang, J. (2020b), "A structural health monitoring system for data analysis of segment joint opening in an underwater shield tunnel", Struct. Health Monitor., 19(4), 1032-1050. https://doi.org/10.1177/1475921719876045
  20. Wang, Y. and Ni, Y. (2020), "Bayesian dynamic forecasting of structural strain response using structural health monitoring data", Struct. Control Health Monitor., 27(8), e2575. https://doi.org/10.1002/stc.2575
  21. Xu, Y., Li, D., Xie, Q., Wu, Q. and Wang, J. (2021), "Automatic defect detection and segmentation of tunnel surface using modified Mask R-CNN", Measurement, 178, 109316. https://doi.org/10.1016/j.measurement.2021.109316
  22. Yu, A., Mei, W. and Han, M. (2021), "Deep learning based method of longitudinal dislocation detection for metro shield tunnel segment", Tunnell. Undergr. Space Technol., 113, 103949. https://doi.org/10.1016/j.tust.2021.103949
  23. Zheng, X., Yi, T.H., Yang, D.H. and Li, H.N. (2021), "Stiffness estimation of girder bridges using influence lines identified from vehicle-induced structural responses", J. Eng. Mech., 147(8), 04021042. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001942
  24. Zhu, H., Wang, X., Chen, X. and Zhang, L. (2020), "Similarity search and performance prediction of shield tunnels in operation through time series data mining", Automat. Constr., 114, 103178. https://doi.org/10.1016/j.autcon.2020.103178