Time Series Forecasting of Tunnel Surrounding Rock Displacement

Abstract:

In the process of tunnel construction, because the rock stress redistribute, the vault and the two groups will generate displacement constantly. This paper adopts the genetic algorithm to optimize the weight and threshold of BP neural network, taking the tunnel depth, rock types and part measured values of displacement as input parameters to construct a neural network time series prediction model of tunnel surrounding rock displacement. The method proposed in the paper has been applied in the Ma Tou Tang tunnel construction successfully, and the results show that the model can predict the displacement of the surrounding rock quickly and accurately.

• Periodical: Advanced Materials Research (Volumes 261-263)
• Pages: 1789-1793
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.261-263.1789
• Online since: May 2011
• Authors: Guang Xiang Mao, Yuan You Xia, Ling Wei Liu
• Keywords: BP Neural Network (BPNN), Genetic Algorithm (GA), Optimise, Time Series Forecast, Tunnel Surrounding Rock Displacement

References

[1] WANG Zhenlong. Time Series Analysis [M] in Chinese. Beijing. Chinese Statistics Press, 2002. 9-12

[2] CONG Shuang. Neural Network Theory and Applications Based on MATLAB Toolbox [M] in Chinese. Hefei. Science and Technology Press. 1998. Page(s): 45-46

[3] Nguyen, D.; Widrow, B. Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. Neural Networks, 1990. 1990 IJCNN International Joint Conference on Digital Object Identifier: 10.1109/IJCNN. 1990. Page(s): 21-26 vol.3

DOI: 10.1109/ijcnn.1990.137819

[4] LUO Wenhui. Application of Genetic Algorithm to Neural Network Optimization [J]. Control Engineering of China, 2003, (05)