MODELING CREEP BEHAVIOR OF SOFT ROCK USING AN EVOLUTIONARY NEURAL COMPUTING METHOD

摘要：

This paper presents a hybrid evolutionary neural learning algorithm to model the creep behavior of soft rock.In this method,a back-propagation neural network is trained to model the underline relationship.To improve the training efficiency,a genetic algorithm is employed to optimize the network topology and to search the global optimal initial weights for the local gradient-descent training algorithm.Application results show the flexibility and effectiveness of the present approach which provide a powerful alternative to the explicit modeling scheme characterized as costing and time-consuming work.

关键词： creep soft rock modeling genetic algorithm neural network

作者: C.X.Yang X.T.Feng B.R.Chen

作者单位: Institute of Rock and Soil Mechanics,The Chinese Academy of Sciences,Wuhan,Hubei 430071,China

会议类型: 国际会议

会议名称: 第二届国际非均质材料力学会议(The Second International Conference on Heterogeneous Material Mechanics)

会议地点: 安徽黄山

会议语种:英文

页码: 456-459

在线出版日期: 2008-06-03（万方平台首次上网日期，不代表论文的发表时间）