China Safety Science Journal ›› 2018, Vol. 28 ›› Issue (8): 161-167.doi: 10.16265/j.cnki.issn1003-3033.2018.08.027

• Public Safety • Previous Articles     Next Articles

Early warning of risks in metro deep foundation pit constructionbased on T-S fuzzy neural network

WANG Qiankun1, NIAN Chunguang1, YANG Dong2, ZHANG Yufeng3   

  1. 1 School of Civil Engineering and Architecture,Wuhan University of Technology,Wuhan Hubei 430070,China;
    2 Quality and Safety Department,Wuhan Metro Group Co.,Ltd.,Wuhan Hubei 430030,China;
    3 Poly Wuhan Real Estate Development Co.,Ltd.,Wuhan Hubei 430040,China
  • Received:2018-05-10 Revised:2018-07-09 Online:2018-08-28 Published:2020-11-25

Abstract: Accurate and quick analysis of warning information is essential to guaranteeing an effective early warning of risks in metro deep foundation pits construction.To avoid the mistakes caused by single index evaluation,arbitrariness of personal decision making,and the interference of different pieces of early-warning information,this paper was aimed at building a T-S fuzzy neural network model.Firstly,the deep excavation project of Huangpuxincheng Station in Wuhan city was investigated and sources of information on risks were identified and screened from two aspects-spatial location and accident warning.Secondly,based on T-S fuzzy neural network,a multi-information fusion model was built,and a large number of samples were selected to train and test the model to improve its effectiveness and generalization.Finally,the warning information integration was made and results were discussed.The results show that the outcome of the model is consistent with the location and the type of the alert-situation,which proves the effectiveness and applicability of the fusion model in the safety precaution of deep foundation pit construction.

Key words: T-S fuzzy neural network, metro deep foundation pit, safety early warning, multi-source information identification, multi-source information fusion

CLC Number: