The Surface Subsidence Prediction of Shield Construction Based on the Fuzzy Neural Network

Conference paper


There are many factors that influence the surface subsidence caused by shield construction, which make it difficult to predict the subsidence using the mechanical models. The fuzzy neural network proves to be good at dealing with nonlinear and fuzzy problems and can well establish the nonlinear relationship between influence factors and surface subsidence. In order to improve predicting the tunneling-induced surface settlement, the fuzzy neural network is adopted. The model gives a consideration to the tunneling boring machine (TBM) geometric size, stratum mechanical properties and construction parameters. Compared with the predicted results of BP neural network in Nanchang subway, Adaptive Network-based Fuzzy Inference System (ANFIS) has a higher accuracy in the prediction. The model of ANFIS can be applied to the similar projects to guide the construction of tunnel and guarantee the safety of surface constructions.


Upper-soft lower-hard stratum Prediction of surface subsidence Tunneling-induced subsidence ANFIS 


  1. 1.
    Qin, B., Mao, Y.: Application of adaptive network-based fuzzy inference system for load forecasting. Comput. Inf. 25(2–3), 194–196 (2009)Google Scholar
  2. 2.
    Zhang, M.X., Zhou, H., Tu, M.: Prediction of surface settlement of shield tunneling based on fuzzy neural network. In: The Second National Conference on Geotechnical Engineering, Wuhan, China, pp. 290–295 (2006)Google Scholar
  3. 3.
    Liu, H.B., Wang, L.G., Zhang, L.H., Dai, B.B., Jing, Y.B.: Prediction of tunneling-induced surface settlement based on artificial neural network technology. Min. Res. Dev. 27(2), 26–29 (2007)Google Scholar
  4. 4.
    Zhou, C.Z., Yang, J.S., Mou, Y.T., Wang, S.Y.: Prediction of tunneling-induced surface settlement in upper-soft lower-hard stratum in Nanchang. J. Disaster Prev. Mitig. Eng. 35(8), 556–562 (2015)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of Geotechnical EngineeringTongji UniversityShanghaiChina
  2. 2.Key Laboratory of Geotechnical and Underground Engineering of the Ministry of EducationTongji UniversityShanghaiChina

Personalised recommendations