Application of Genetic Optimization of Neural Network Method in the Stability Analysis of Open Pit Slope
Genetic algorithms and neural networks are combined to establish hybrid GA-BP algorithm in order to solve the problems in network training by pure BP algorithm, such as slow constringency, lack of theoretical guidance in network architecture design, as well as easy to fall into local minimum during the learning process. With the advantages of global optimization ability of genetic algorithm and the rapid constringency of the BP fast local searching algorithm, the comprehensive algorithm shows the ability of nonlinear approach of multilayer feed forward network, improves the performance of BP, and provides an efficient and practical method of slope stability analysis. The results show that the method can effectively and accurately predict the slope landslide and provide an available method for further evaluation of the slope stability.
open pit mine slope stability genetic algorithm neural network
Fang-wei HE Ming ZHU Tie-liang LIU Lian-hai WANG
College of Resource and Environment, Mining & Safety Technology Key Lab of Hebei Province,Hebei Poly Tangshan Sanyou Mine Corporation, Tangshan 063101, China
国际会议
The Third International Conference on Modelling and Simulation(第三届国际建模、计算、仿真、优化及其应用学术会议 ICMS 2010)
无锡
英文
248-252
2010-06-04（万方平台首次上网日期，不代表论文的发表时间）