首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于改进神经网络的边坡岩体弹性力学参数识别方法
引用本文:李守巨,刘迎曦,刘玉晶.基于改进神经网络的边坡岩体弹性力学参数识别方法[J].湖南科技大学学报(自然科学版),2002,17(1):58-61.
作者姓名:李守巨  刘迎曦  刘玉晶
作者单位:1. 大连理工大学,工业装备结构分析国家重点实验室,辽宁,大连,116024
2. 吉林工学院,基础科学系,吉林,长春,130012
基金项目:国家自然科学基金资助项目 (编号 :1 0 0 72 0 1 4 ),工业装备结构分析国家重点实验室开放基金资助项目 (编号 :GZ990 8)
摘    要:基于人工神经网络的 BP算法 ,建立了根据边坡开挖后岩体位移观测数据识别岩体弹性力学参数的数值方法 .在网络训练过程中采用改进的 BP算法 ,通过对学习算子的优化搜索 ,大大提高了网络的收敛速度 ,解决了 BP算法迭代过程中目标函数振荡问题 .通过算例表明 ,提出的改进的 BP算法有助于提高岩土材料参数识别收敛速度和识别精度 .图5 ,表 3,参 15

关 键 词:神经网络  参数识别  学习算子  优化  边坡岩体
文章编号:1000-9930(2002)01-0058-04
修稿时间:2001年5月8日

Identification algorithm of elastic parameters of rock body in slope based on improved BP neural networks
LI Shou ju ,LIU Ying xi ,LIU Yu jing.Identification algorithm of elastic parameters of rock body in slope based on improved BP neural networks[J].Journal of Hunan University of Science & Technology(Natural Science Editon),2002,17(1):58-61.
Authors:LI Shou ju  LIU Ying xi  LIU Yu jing
Institution:LI Shou ju 1,LIU Ying xi 1,LIU Yu jing 2
Abstract:Based on the artificial neural networks(ANN) and according to measured displacements after the rock slope excavation, the identification algorithm of rock slope elastic parameters was set up.The improved BP algorithm of neural networks was applied during the neural networks training process. By application of optimized learning operator, the convergence speed of the objective function has been fasted and the oscillation problem of objective function has also been solved during the iteration. The numerical computation results show that the convergence speed and the identification precision have been improved by making use of improved BP neural networks algorithm proposed in this paper.5figs.,3tabs.,15refs.
Keywords:neural networks  parameters identification  learning operator  optimization  rock slope
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