Stress Predicting on the Surrounding Rocks of Tunnel Based on BP Neural Network

Abstract:

Surrounding rock stress is a one of significant feedback information after tunnel excavation. It is also an important factor influencing the stability of the tunnel, and the premise to determine accurately the tunnel stability. For tunnel surrounding rocks stress determined by many uncertain factors, it is difficult to accurately predict. The BP neural network model for predicting on the stress of the tunnel surrounding rock stress is created. Comparative analyze the results of the surrounding rocks stress prediction on expressway tunnel by momentum gradient algorithm, L-M algorithm and bayesian regularization algorithm. Results show that the use of bayesian regularization algorithm for neural network model has higher forecast accuracy. It can be applied in engineering practice.

• Periodical: Applied Mechanics and Materials (Volumes 170-173)
• Pages: 1638-1642
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.170-173.1638
• Online since: May 2012
• Authors: Zhi Jie Sun
• Keywords: BP Neural Network (BPNN), Predict, Stress, Surrounding Rock

References

[1] Junsheng Zhang, Ye Xue and Jinan Tao: Chinese Journal of Geotechnical Engineering. Vol. (1) (1996), pp.39-45.

[2] Shengwu Qin and Jianping Chen: Journal of jilin university (earth science edition). Vol. 38(6) (2008), pp.1005-1009.

[3] Song Ren, Diyi Jang, Zaiwen Jang and Xinrong Liu. Journal of chongqing university (natural science edition). Vol. 29(4) (2006), pp.77-79.

[4] Xin Wen and Lu Zhou: MATLAB neural network simulation and application (Science publications, Beijing 2003).

[5] Information on http://www.mathworks.cn.