DOI QR코드

DOI QR Code

A long-term tunnel settlement prediction model based on BO-GPBE with SHM data

  • Yang Ding (Department of Civil Engineering, Hangzhou City University) ;
  • Yu-Jun Wei (Department of Civil Engineering, Zhejiang University) ;
  • Pei-Sen Xi (Zhejiang Engineering Research Center of Smart Rail Transportation, Power China Huadong Engineering Corporation Limited) ;
  • Peng-Peng Ang (Zhejiang Engineering Research Center of Smart Rail Transportation, Power China Huadong Engineering Corporation Limited) ;
  • Zhen Han (Nanjing Metro Operation Co., Ltd.)
  • 투고 : 2023.07.29
  • 심사 : 2023.12.01
  • 발행 : 2024.01.25

초록

The new metro crossing the existing metro will cause the settlement or floating of the existing structures, which will have safety problems for the operation of the existing metro and the construction of the new metro. Therefore, it is necessary to monitor and predict the settlement of the existing metro caused by the construction of the new metro in real time. Considering the complexity and uncertainty of metro settlement, a Gaussian Prior Bayesian Emulator (GPBE) probability prediction model based on Bayesian optimization (BO) is proposed, that is, BO-GPBE. Firstly, the settlement monitoring data are analyzed to get the influence of the new metro on the settlement of the existing metro. Then, five different acquisition functions, that is, expected improvement (EI), expected improvement per second (EIPS), expected improvement per second plus (EIPSP), lower confidence bound (LCB), probability of improvement (PI) are selected to construct BO model, and then BO-GPBE model is established. Finally, three years settlement monitoring data were collected by structural health monitoring (SHM) system installed on Nanjing Metro Line 10 are employed to demonstrate the effectiveness of BO-GPBE for forecasting the settlement.

키워드

과제정보

This paper was supported by the Ministry of education of Humanities and Social Science project (No. 23YJCZH037), the Foundation of the State Key Laboratory of Mountain Bridge and Tunnel Engineering (No. SKLBT2210), China, the Educational Science Planning Project of Zhejiang Province (No. 2023SCG222), and the Scientific Research Project of Zhejiang Provincial Department of Education (No. Y202248682).

참고문헌

  1. Brochu, E., Cora, V.M. and De Freitas, N. (2010), "A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning", Comput. Sci., 1012.2599. 
  2. Bull, A.D. (2011), "Convergence rates of efficient global optimization algorithms", Mach. Learn., 12(10), arXiv: 1101.3501. 
  3. Bullock, Z., Karimi, Z., Dashti, S., Porter, K., Liel, A.B. and Franke, K.W. (2019), "A physics-informed semi-empirical probabilistic model for the settlement of shallow-founded structures on liquefiable ground", Geotechnique, 69(5), 406-419. https://doi.org/10.1680/jgeot.17.P.174 
  4. Chen, Z. and Sun, H. (2021), "Sparse representation for damage identification of structural systems", Struct. Health Monit., 20(4), 1644-1656. https://doi.org/10.1177/1475921720926970 
  5. Deng, H.S., Fu, H.L., Yue, S., Huang, Z. and Zhao, Y.Y. (2022), "Ground loss model for analyzing shield tunneling-induced surface settlement along curve sections", Tunn. Underg. Space Technol., 119, 104250. https://doi.org/10.1016/j.tust.2021.104250 
  6. Ding, Y., Ye, X.W. and Guo, Y. (2023a), "Wind load assessment with the JPDF of wind speed and direction based on SHM data", Structures, 47(1), 2074-2080. https://doi.org/10.1016/j.istruc.2022.12.028 
  7. Ding, Y., Ye, X.W. and Guo, Y. (2023b), "Data set from wind, temperature, humidity and cable acceleration monitoring of the Jiashao bridge", J. Civil Struct. Health Monit., 13(2-3), 579-589. https://doi.org/10.1007/s13349-022-00662-5 
  8. Ding, Y., Ye, X.W. and Guo, Y. (2023c), "Copula-based JPDF of wind speed, wind direction, wind angle, and temperature with SHM data", Probab. Eng. Mech., 73, 103483. https://doi.org/10.1016/j.probengmech.2023.103483 
  9. Ding, Y., Ye, X.W., Guo, Y., Zhang, R. and Ma, Z. (2023d), "Probabilistic method for wind speed prediction and statistics distribution inference based on SHM data-driven", Probab. Eng. Mech., 73, 103475. https://doi.org/10.1016/j.probengmech.2023.103475 
  10. Ding, Y., Ye, X.W. and Guo, Y. (2023e), "A multistep direct and indirect strategy for predicting wind direction based on the EMD-LSTM model", Struct. Control Health Monit., 4950487. https://doi.org/10.1155/2023/4950487 
  11. Ding, Y., Ye, X.W., Su, Y.H. and Zheng, X.L. (2023f), "A framework of cable wire failure mode deduction based on Bayesian network", Structures, 57, 104996. https://doi.org/10.1016/j.istruc.2023.104996 
  12. Ding, Y., Hang, D., Wei, Y.J., Zhang, X.L., Ma, S.Y., Liu, Z.X., Zhou, S.X. and Han, Z. (2023g), "Settlement prediction of existing metro induced by new metro construction with machine learning based on SHM data: a comparative study", J. Civil Struct. Health Monit., 13(6-7), 1447-1457. https://doi.org/10.1007/s13349-023-00714-4 
  13. Ding, Y., Ye, X.W., Ding, Z., Wei, G., Cui, Y.L., Han, Z. and Jin, T. (2023h), "Short-term tunnel-settlement prediction based on Bayesian wavelet: a probability analysis method", J. Zhejiang Univ.-SCI A, 24(11), 960-977. https://doi.org/10.1631/jzus.A2200599 
  14. Fang, K., Yang, Z., Jiang, Y., Sun, Z. and Wang, Z. (2020), "Surface subsidence characteristics of fully overlapping tunnels constructed using tunnel boring machine in a clay stratum", Comput. Geotech., 125, 103679. https://doi.org/10.1016/j.compgeo.2020.103679 
  15. Gelbart, M.A., Snoek, J. and Adams, R.P. (2014), "Bayesian optimization with unknown constraints", Mach. Learn., arXiv: 1403.5607. 
  16. Gong, W., Luo, Z., Juang, C.H., Huang, H., Zhang, J. and Wang, L. (2014), "Optimization of site exploration program for improved prediction of tunneling-induced ground settlement in clays", Comput. Geotech., 56, 69-79. https://doi.org/10.1016/j.compgeo.2013.10.008 
  17. Han, Q., Ni, P.H., Du, X.L., Zhou, H. and Cheng, X. (2022), "Computationally efficient Bayesian inference for probabilistic model updating with polynomial chaos and Gibbs sampling", Struct. Control Health Monit., 29(6), e2936. https://doi.org/10.1002/stc.2936 
  18. Huang, H., Jia, R., Shi, X., Liang, J. and Dang, J. (2021), "Feature selection and hyper parameters optimization for short-term wind power forecast", Appl. Intell., 51(10), 6752-6770. https://doi.org/10.1007/s10489-021-02191-y 
  19. Jones, D.R., Schonlau, M. and Welch, W.J. (1998), "Efficient global optimization of expensive black-box functions", J. Global Optim., 13(4), 455-492. https://doi.org/10.1023/A:1008306431147 
  20. Li, B. and Wang, Z.Z. (2019), "Numerical study on the response of ground movements to construction activities of a metro station using the pile-beam-arch method", Tunn. Underg. Space Technol., 88, 209-220. https://doi.org/10.1016/j.tust.2019.03.014 
  21. Li, W., Feng, W. and Yuan, H.Z. (2020), "Multimode traffic travel behavior characteristics analysis and congestion governance research", J. Adv. Transp., 5, 1-8. https://doi.org/10.1155/2020/6678158 
  22. Liu, T., Wei, H., Liu, S. and Zhang, K. (2020a), "Industrial time series forecasting based on improved Gaussian process regression", Soft Comput., 24(20), 15853-15869. https://doi.org/10.1007/s00500-020-04916-6 
  23. Liu, B., Zhang, D.W., Yang, C. and Zhang, Q.B. (2020b), "Long-term performance of metro tunnels induced by adjacent large deep excavation and protective measures in Nanjing silty clay", Tunn. Underg. Space Technol., 95, 103147. https://doi.org/10.1016/j.tust.2019.103147 
  24. Luat, N.V., Nguyen, V.Q., Lee, S., Woo, S. and Lee, K. (2020), "An evolutionary hybrid optimization of MARS model in predicting settlement of shallow foundations on sandy soils", Geomech. Eng., Int. J., 21(6), 583-598. https://doi.org/10.12989/gae.2020.21.6.583 
  25. Madra, A., Causse, P., Trochu, F., Adrien, J., Maire, E. and Breitkopf, P. (2019), "Stochastic characterization of textile reinforcements in composites based on X-ray microtomographic scans", Compos. Struct., 224, 111031. https://doi.org/10.1016/j.compstruct.2019.111031 
  26. Miliziano, S. and de Lillis, A. (2019), "Predicted and observed settlements induced by the mechanized tunnel excavation of metro line C near S. Giovanni station in Rome", Tunn. Underg. Space Technol., 86, 236-246. https://doi.org/10.1016/j.tust.2019.01.022 
  27. Moaveni, B. and Najafi, S. (2017), "Metro traffic modeling and regulation in loop lines using a robust model predictive controller to improve passenger satisfaction", IEEE Transact. Control Syst. Technol., 26(5), 1541-1551. https://doi.org/10.1109/tcst.2017.2735945 
  28. Mu, B., Xie, X., Li, X., Li, J., Shao, C. and Zhao, J. (2021), "Monitoring, modelling and prediction of segmental lining deformation and ground settlement of an EPB tunnel in different soils", Tunn. Underg. Space Technol., 113, 103870. https://doi.org/10.1016/j.tust.2021.103870 
  29. Ni, Y.Q., Wang, Y.W. and Zhang, C. (2020), "A Bayesian approach for condition assessment and damage alarm of bridge expansion joints using long-term structural health monitoring data", Eng. Struct., 212, 110520. https://doi.org/10.1016/j.engstruct.2020.110520 
  30. Ni, P.H., Li, Q., Han, Q., Xu, K. and Du, X.L. (2023), "Substructure approach for Bayesian probabilistic model updating using response reconstruction technique", Mech. Syst. Signal Proc., 183, 109624. https://doi.org/10.1016/j.ymssp.2022.109624 
  31. Qiu, J., Qin, Y., Feng, Z., Wang, L. and Wang, K. (2020), "Safety risks and protection measures for city wall during construction and operation of Xi'an Metro", J. Perform. Constr. Fac., 34(2), 04020003. https://doi.org/10.1061/(ASCE)CF.1943-5509.0001374 
  32. Qu, K., Xu, Y.Y. and Huang, J.X. (2023), "Numerical simulation of hydrodynamic characteristics of submerged floating tunnels under the action of focused waves", J. Changsha Univ. Sci. Techn. (Natural Science), (04):127-141. [In Chinese] https://doi.org/10.19951/j.cnki.1672-9331.20220425001 
  33. Shi, S., Zhao, R., Li, S., Xie, X., Li, L., Zhou, Z. and Liu, H. (2019), "Intelligent prediction of surrounding rock deformation of shallow buried highway tunnel and its engineering application", Tunn. Underg. Space Technol., 90, 1-11. https://doi.org/10.1016/j.tust.2019.04.013 
  34. Snoek, J., Larochelle, H. and Adams, R.P. (2012), "Practical bayesian optimization of machine learning algorithms", Mach. Learn., arXiv:1206.2944. 
  35. Tan, L.S., Ong, V.M., Nott, D.J. and Jasra, A. (2016), "Variational inference for sparse spectrum Gaussian process regression", Statis. Comput., 26(6), 1243-1261. https://doi.org/10.1007/s11222-015-9600-7 
  36. Tu, H., Zhou, H., Qiao, C. and Gao, Y. (2020), "Excavation and kinematic analysis of a shallow large-span tunnel in an up-soft/low-hard rock stratum", Tunn. Underg. Space Technol., 97, 103245. https://doi.org/10.1016/j.tust.2019.10324 
  37. Vereecken, E., Botte, W., Lombaert, G. and Caspeele, R. (2020), "Bayesian decision analysis for the optimization of inspection and repair of spatially degrading concrete structures", Eng. Struct., 220, 111028. https://doi.org/10.1016/j.engstruct.2020.111028 
  38. Wan, H.P. and Ni, Y.Q. (2018), "Bayesian modeling approach for forecast of structural stress response using structural health monitoring data", J. Struct. Eng., 144(9), 04018130. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002085 
  39. Wan, H.P. and Ni, Y.Q. (2019), "Bayesian multi-task learning methodology for reconstruction of structural health monitoring data", Struct. Health Monit., 18(4), 1282-1309. https://doi.org/10.1177/1475921718794953 
  40. Wang, F., Gou, B. and Qin, Y. (2013), "Modeling tunneling-induced ground surface settlement development using a wavelet smooth relevance vector machine", Compu. Geotech., 54, 125-132. https://doi.org/10.1016/j.compgeo.2013.07.004 
  41. Wang, Z.L., Ogawa, T. and Adachi, Y. (2019), "Influence of algorithm parameters of Bayesian optimization, genetic algorithm, and particle swarm optimization on their optimization performance", Adv. Theory Simulat., 2(10), 1900110. https://doi.org/10.1002/adts.201900110 
  42. Ye, X.W., Ding, Y. and Wan, H.P. (2019), "Machine learning approaches for wind speed forecasting using long-term monitoring data: a comparative study", Smart Struct. Syst., Int. J., 24(6), 733-744. https://doi.org/10.12989/sss.2019.24.6.733 
  43. Ye, X.W., Ding, Y. and Wan, H.P. (2020), "Statistical evaluation of wind properties based on long-term monitoring data", J. Civ. Struct. Health Monit., 10(5), 987-1000. https://doi.org/10.1007/s13349-020-00430-3 
  44. Ye, X.W., Ding, Y. and Wan, H.P. (2021), "Probabilistic forecast of wind speed based on Bayesian emulator using monitoring data", Struct. Control Health Monit., 28(1), e2650. https://doi.org/10.1002/stc.2650 
  45. Zhang, S., Shang, C., Wang, C., Song, R. and Wang, X. (2019), "Real-time safety risk identification model during metro construction adjacent to buildings", J. Construt. Eng. Manag., 145(6), 04019034. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001657 
  46. Zhang, K., Lyu, H.M., Shen, S.L., Zhou, A. and Yin, Z.Y. (2020a), "Evolutionary hybrid neural network approach to predict shield tunneling-induced ground settlements", Tunn. Underg. Space Technol., 16, 103594. https://doi.org/10.1016/j.tust.2020.103594 
  47. Zhang, P., Wu, H.N., Chen, R.P. and Chan, T.H. (2020b), "Hybrid meta-heuristic and machine learning algorithms for tunneling-induced settlement prediction: A comparative study", Tunn. Underg. Space Technol., 99, 103383. https://doi.org/10.1016/j.tust.2020.103383 
  48. Zhang, W., Zhao, M., Du, X., Gao, Z. and Ni, P. (2023), "Probabilistic machine learning approach for structural reliability analysis", Probab. Eng. Mech., 74, 103502. https://doi.org/10.1016/j.probengmech.2023.103502