Based on the Genetic Algorithm to Optimize the BP Neural Network in the Degree of Concrete Creep Prediction Model

Abstract:

The BP neural network model for creep degree of concrete is established,in which concrete age under load and loading time as input variables and the creep degree of concrete as output variable. In order to get best optimal weight and threshold of the BP neural network, genetic algorithms method has been used by selection, crossover and mutation operation. The BP neural network model is applied to the engineering of “515”dam.Comparison the prediction results of the BP neural network and the eight-parameters formula of concrete creep degree, the BP neural network model has high prediction accuracy. What’s more, this intelligent prediction model for creep degree of concrete has good credibility and reference value in practical engineering.

• Periodical: Applied Mechanics and Materials (Volumes 584-586)
• Pages: 1346-1350
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.584-586.1346
• Online since: July 2014
• Authors: Hui Qin Yao, Ye Long Jiang
• Keywords: Degree of Concrete Creep, Genetic Algorithm Bp Neural Network, Intelligent Prediction

References

[1] Rongyan Hui, Guoxing Huang, Ruobing Yi. The Creep of Concrete [M]. Beijing: China Electric Power Press, (1988).

[2] Chong Zhao Tang. The creep of concrete mechanics and experimental technique [M]. Beijing: Water Resources and Electric Power Press, (1982).

[3] Dachun Yang. Based on the behavior of the genetic algorithm to optimize the BP neural network identification[D]. An Shang. Anshan University of Science and Technology, (2011).

[4] Bofang Zhu. Concrete's modulus of elasticity, unit of creep and stress relaxation parameter [J]. Journal of Hydraulic Engineering, 1985(9): 54-61.