Application of BP Neural Network to Risk Analysis of Deep Foundation Pit

Lu De Zou; Dong Wei Cao

doi:10.4028/www.scientific.net/AMM.556-562.5989

Paper Titles

Optimizing Container Reshuffle Operations in Container Yards Based on Dynamic Programming
p.5972

Based on the Research of WSN in Information Security Technology
p.5976

Time Series Forecast of Foundation Pit Deformation Based on BP Neural Network
p.5979

The Application of Neural Network Technology in the Fundus Angiography Image Segmentation
p.5984

Application of BP Neural Network to Risk Analysis of Deep Foundation Pit
p.5989

Study on Monitoring and Safety Early Warning Technology of Bridge Health Based on Internet of Things Technology
p.5994

Design of Firewall Security Control Program
p.5999

Design and Implementation of User Model Based on Light Blog
p.6003

A Cloud Platform for Clinical Information Exchange Based on Web Services
p.6007

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 556-562Application of BP Neural Network to Risk Analysis...

Application of BP Neural Network to Risk Analysis of Deep Foundation Pit

Abstract:

there are many uncertainty factors in the design process of the deep foundation pit engineering, such as the soil parameters, loading, which make the calculated displacement, settlement and safety factor have randomness and uncertainty. This paper combines uniform design (UD) with BP neural network. The UD structures random samples. Then, BP neural network trains random samples and the corresponding lateral displacement, settlement of ground and safety factors to get response relationship respectively. On this basis, the probability density distribution of each response parameter is obtained by predicting a large number of samples obtained by the Monte Carlo simulation. And then the Breadth Border Method, Narrow Bounds Method and PNET method are used to calculate system failure probability of foundation pit. The instance analysis shows that the method has high computing efficiency and the result is reasonable. It provides an effective way for the reliability analysis of the foundation pit engineering.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 556-562)

Pages:

5989-5993

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.556-562.5989

Citation:

Cite this paper

Online since:

May 2014

Authors:

Lu De Zou*, Dong Wei Cao

Keywords:

BP Neural Network (BPNN), Deep Foundation Pit Engineering, Monte Carlo Simulation, Risk, Uniform Test

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] ZHAO Hong-bo. Application of SVM on reliability analysis of underground engineering[J]. Rock and Soil Mechanics. 2009: 30(2)526~530.

Google Scholar

[2] ZHU Jian-feng. An optimization method of reliability analysis of foundation pit reinforced with soil nailing [J]. Rock and Soil Mechanics. 2010: 31(7)2336~2341.

Google Scholar

[3] PENG Hai-ming, CHANG Wei-hua, PENG Xiao-yang. Application of Rosenblueth method to reliability analysis of deep excavation against heave stability[J]. Rock and Soil Mechanics, 2005, 26(7): 1132－1135.

Google Scholar

[4] LUO Xiao-hui, CHAO Ze-dong, XIAO Jian. Stability Analysis of Reinforced Soil Nail Based Upon Monte-Carlo Method[J]. J. of HUST. 2006, 23(1), 31-39.

Google Scholar

[5] YAO Hai-hui, CHEN Xiao-xia, ZHAO Qing. Reliability analysis of foundation pit on overall and slip based on the practical analysis method[J]. YELLOW RIVER. 2011, 33(5), 122-124.

Google Scholar

[6] TANG Hua, SHI Gui-cai, GE Xiu-ru. Application of Uniform Design to Displacement Back Analysis in Underground Engineering[J]. Chinese Journal of Rock Mechanics and Engineering. 2006, 25(10), 2017-(2022).

Google Scholar

[7] SONG Zhi-gang, Song Jie. Reliability Analysis of Compartment Fire by Improved Response Surface Method[A]. Proceedings of the eleventh international symposium on structural engineering, 2010, volume II: 1271-1276.

Google Scholar