Author(s)

Yongjun Zhang ¹, Qiangqiang Ma ¹, Tianhui Ma ², Jun Peng ³, Shengrong Xie ⁴

Affiliation(s)

¹ College of Science, Qingdao University of Technology, Qingdao, 266033, China
² State Key Laboratory of Coastal and Offshore Engineering, Dalian University of Technology, Dalian, 116024, China
³ Sinosteel Maanshan General Institute of Mining Research Co, Ltd, Maanshan, 243000, China
⁴ School of Energy and Mining Engineering, China University of Mining & Technology-Beijing, Beijing, 100083, China

Corresponding Author

Qiangqiang Ma

ABSTRACT

In order to meet the growing demand for underground space for economic development and infrastructure needs, there are more and more underground space constructions represented by subways in various regions. Most of the subway tunnel projects cross the fault fracture zone with low quality, and the terrain conditions are extremely complex. In response to the special geological surface settlement problem of Qingdao Metro, this article takes the construction stage of the Chaobuling platform of Metro Line 4 as an example. Based on on-site monitoring and measurement data, combined with the initial weights of the BP neural network modified by the finite element analysis software MIDAS, displacement inversion analysis is carried out on the surface settlement data of the large cross-section tunnel. The model fitting results are checked using the post check difference test method, A BP neural network model with good fitting and generalization ability was obtained. This model optimizes the shortcomings of the BP neural network model, such as slow convergence speed and easy trapping in local minima, while also avoiding the drawbacks of large errors, inaccurate accuracy, and ground reliability in numerical simulation. The application of this method is suitable for solving large-scale and complex nonlinear tunnel engineering problems. Its stability and applicability are good, and its accuracy is greatly improved compared to traditional simulation methods, which has a guiding role for corresponding engineering.

KEYWORDS

Surface subsidence, BP neural network, Midas, genetic algorithm, subway tunnel

CITE THIS PAPER

Yongjun Zhang, Qiangqiang Ma, Tianhui Ma, Jun Peng, Shengrong Xie, Analysis of Surface Settlement in Large Section Tunnel Based on Improved BP Neural Network. Journal of Civil Engineering and Urban Planning (2023) Vol. 5: 1-11. DOI: http://dx.doi.org/10.23977/jceup.2023.050501.

REFERENCES

[1] Yin Yueping, Zhang Zuochen, Zhang Kaijun. Research on the current situation and prevention measures of ground settlement in China. Journal of Geological Hazards and Environment Preservation, 2005 (02): 1-8.
[2] Wu Bo. Study on Surface Settlement during Urban Metro Tunnel Construction under Complex Conditions. Master’s thesis, Southwest Jiaotong University, 2003.
[3] Z F Hu, Z Q Yue, J Zhou, L G Tham. Design and construction of a deep excavation in soft soils adjacent to the Shanghai Metro tunnels. Canadian Geotechnical Journal, 2003, 40 (5).
[4] Liu Guo B, Jiang Rebecca J, Ng Charles W. W, Hong Y. Deformation characteristics of a 38m deep excavation in soft clay. Canadian Geotechnical Journal, 2011, 48 (12).
[5] Jiang Xinliang, Zhao Zhimin, Li Yuan. Analysis and calculation of the settlement trough curve caused by tunnel excavation. Rock and Soil Mechanics, 2004 (10): 1542-1544. DOI:10.16285/j.rsm.2004.10.006.
[6] Song Guang, Song Erxiang. Selection of soil constitutive models in numerical simulation of foundation pit excavation. Engineering Mechanics, 2014, 31 (05): 86-94.
[7] Li Hongxia, Zhao Xinhua, Chi Haiyan, Zhang Jianjun. Ground settlement prediction and analysis based on an improved BP neural network model. Journal of Tianjin University, 2009, 42 (01): 60-64.
[8] Wang Suihui, Pan Guorong. Application of artificial neural network in predicting surface deformation of tunnel. Journal of Tongji University (Natural Science Edition), 2001 (10): 1147-1151.
[9] Su Daozhen, Luo Jianjun. Deformation test and prediction of surrounding rock in a large-section weak stratum tunnel. Chinese Journal of Rock Mechanics: and Engineering, 2016, 35 (S2): 4029-4039. DOI: 10. 13722/ j. cnki. jrme. 2015. 1600.
[10] Sun Jun, Yuan Jinrong. Shield construction disturbance and stratum movement and their intelligent neural network prediction. Chinese Journal of Rock Mechanics and Engineering, 2001 (03): 261-267.
[11] Li Yuansong, Li Xinping, Zhang Chengliang. Prediction method of tunnel surrounding rock displacement based on BP neural network. Chinese Journal of Rock Mechanics and Engineering, 2006 (S1): 2969-2973.
[12] Hou Shaokang, Liu Yaoru, Zhang Kai. TBM excavation parameter prediction based on IPSO-BP hybrid model. Chinese Journal of Rock Mechanics and Engineering, 2020, 39 (08):1648-1657. DOI:10.13722/j.cnki.jrme.2019.1084.
[13] Yi Xiaoming, Chen Weizhong, Li Shucai, Dai Yonghao. Application of BP neural network in displacement back analysis of bifurcated tunnel. Chinese Journal of Rock Mechanics and Engineering, 2006 (S2): 3927-3932. 

Sponsors, Associates, and Links

---

• Journal of Sustainable Development and Green Buildings
  
  
• Landscape and Urban Horticulture
  
  
• Bridge and Structural Engineering
  
  
• Soil Mechanics and Geotechnical Engineering
  
  
• Journal of Municipal Engineering
  
  
• Heating, Ventilation and Air Conditioning
  
  
• Indoor Air Quality and Climate
  
  
• Computer Aided Architecture Design