首页 | 本学科首页   官方微博 | 高级检索  
     

混沌神经网络综合法在边坡位移预测中的应用
引用本文:张卓,练继建. 混沌神经网络综合法在边坡位移预测中的应用[J]. 哈尔滨工业大学学报, 2009, 41(4): 210-211,246
作者姓名:张卓  练继建
作者单位:张卓,ZHANG Zhuo(天津大学,建筑工程学院,天津,300072;重庆交通大学,土木建筑学院,重庆,400074);练继建,LIAN Ji-jian(天津大学,建筑工程学院,天津,300072)  
摘    要:根据混沌理论具有分析非线性动态系统的混沌特性和人工神经网络具有考虑多因素影响的特点,本文提出了混沌神经网络综合预测模型.该方法首先利用非线性科学和理论分析滑坡位移时间序列的动态特性,然后将重构相空间计算的最小嵌入维数作为输入神经元的数目引入到人工神经网络预测模型中.分析算例预测结果表明,混沌神经网络综合预测模型计算精度较高.

关 键 词:混沌  相空间重构  神经网络  预测

Slope displacement forecast using the combination of chaos and neural network
ZHANG Zhuo,LIAN Ji-jian. Slope displacement forecast using the combination of chaos and neural network[J]. Journal of Harbin Institute of Technology, 2009, 41(4): 210-211,246
Authors:ZHANG Zhuo  LIAN Ji-jian
Affiliation:1(1.School of Civil Engineering,Tianjin University,Tianjin 300072,China;2.School of Civil Engineering and Architecture,Chongqing Jiaotong University,Chongqing 400074,China)
Abstract:A forecast model with the combination of chaos and neural network is put forward according to the characteristics that chaos theory can analyze the chaos trait of nonlinear dynamic system and the artificial neural network can consider the effects of multiplicate factors.First of all,the method analyzes the dynamic characteristics of landslide displacement time series using the nonlinear science and theory,and then brings the least embedment dimension calculated by phase space reconstruction as the number of neural input into the artificial neural network model.The forecast results of an analysis example reveal the precise calculation of the proposed forecast model.
Keywords:chaos  phase space reconstruction  neural network  forecast
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号