Prediction of Cutting Deformation Based on Annealing Neural Network

Abstract:

Along with the construction of highways in our country, many highways are crossing the mountains. The excavation of those roads will form cuttings, cutting deformation monitoring and forecast provides a good guarantee for road construction safety .This paper used simulated annealing (simulated annealing, SA) algorithm combined with BP neural network algorithm, based on monitoring data, to predict the deformation of cutting and well avoid slow convergence of network training and local minimum. In the same initial conditions, the proposed algorithm based on neural network algorithm has a higher training convergence speed and better prediction accuracy than the traditional BP neural network, is an effective forecasting method.

• Periodical: Advanced Materials Research (Volumes 219-220)
• Pages: 308-311
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.219-220.308
• Online since: March 2011
• Authors: Yong Liu, Hong Ming Yu, Wen Xing Jian, Hao Tian
• Keywords: BP Neural Network (BPNN), Cutting Deformation, Prediction, Simulated Annealing (SA)

References

[1] Jiang Zongli. Introduction to Artificial Neural Networks [M]. Beijing: Higher Education Press, (2001).

[2] Song Zhiyu, Li Junjie. Based on simulated annealing neural network model of the rock slope stability evaluation method [J]. Yangtze River Scientific Research Institute, 2006, 23 (2): 43-45.

[3] Yuan Zengren served as edited. Artificial Neural Network and Its Application[M]. Beijing: Tsinghua University Press, 1999.10.