|本期目录/Table of Contents|

[1]李元松,李新平,代翼飞,等.小波神经网络在高陡边坡位移预测中的应用[J].武汉工程大学学报,2010,(09):38-42.[doi:10.3969/j.issn.16742869.2010.09.011]
　LI Yuan song,LI Xin ping,DAI Yi fei,et al.The application of wavelet neural network on displacement predicting for highsteep slope[J].Journal of Wuhan Institute of Technology,2010,(09):38-42.[doi:10.3969/j.issn.16742869.2010.09.011]
点击复制

小波神经网络在高陡边坡位移预测中的应用(/HTML)
分享到：

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
期数:
2010年09期
页码:
38-42
栏目:
机电与信息工程
出版日期:
2010-09-30

文章信息/Info

Title:
The application of wavelet neural network on displacement
predicting for highsteep slope
文章编号:
16742869(2010)09003805
作者:
李元松1; 李新平2; 代翼飞2; 田昌贵1; 陈清运1
1.武汉工程大学环境与城建学院,湖北 武汉 430074;
2.武汉理工大学土木与建筑学院,湖北 武汉 430070
Author(s):
LI Yuansong1; LI Xinping2; DAI Yifei2; TIAN Changgui1; CHEN Qingyun1
1.School of Environmental and Civil Engineering, Wuhan Institute of Technology, Wuhan 430074, China;
2.School of Civil Engineering and Architecture, Wuhan University of Technology, Wuhan 430070, China
关键词:
小波神经网络; 高陡边坡; 位移预测
Keywords:
wavelet neural network;  highsteep slope;  displacement prediction
分类号:
TU452
DOI:
10.3969/j.issn.16742869.2010.09.011
文献标志码:
A
摘要:
阐述小波神经网络模型法的基本原理与程序实施步骤,探讨了高陡边坡监测数据与小波神经网络间的联系,建立了基于小波神经元网络的高陡边坡预报模型.以工程实例为背景,对高陡边坡位移进行预测预报,并与其它方法对比分析.研究表明:小波神经网络具有较好的函数逼近能力和容错能力,经过选取恰当的网络参数,较少的级数项组成的小波神经网络就能达到良好的预测效果.
Abstract:
In this paper, the wavelet neural network is introduced based on the comment of a few methods often used to process monitoring data. Subsequently, the internal relations between monitoring data and the wavelet neural network are discussed. Finally, a displacement predicting model is set up based on wavelet neural network. With engineering practice example as background, the displacement of highsteep slope are processed and predicted by means of the wavelet BP network. The results show that the predicting value by wavelet BP network and measuring value fit very well, and these completely satisfy the requirement of engineering construction monitor and control.

参考文献/References:

［1］二滩水电开发有限公司.岩土工程安全监测手册［M］.北京:中国水利水电出版,1999.
［2］冯夏庭.智能岩石力学导论［M］.北京:科学出版社,2000.
［3］潘国荣,谷川.变形监测数据的小波神经网络预测方法［J］.大地测量与地球动力学,2007,27(4),4750.
［4］焦明连,蒋廷臣.基于小波分析的灰色预测模型在大坝安全监测中的应用［J］.大地测量与地球动力学,2009,29(2)115117.
［5］潘平.基于小波神经网络理论的边坡位移预测［J］.成都理工大学学报：自然科学版,2006,33(2):177180.
［6］Zhang Qinghua, Benveniste A. Wavelet Network［J］.IEEE Trans on Neural Network,1992,(3):889898.
［7］孙延奎.小波分析及其应用［M］.北京:机械工业出版社,2005.
［8］唐晓初.小波分析及其应用［M］.重庆:重庆大学出版社,2006.
［9］刘志刚,王晓茹,何正友,等.小波变换、神经网络和小波网络的函数逼近能力分析与比较［J］.电力系统自动化,2002,26(20):3944.
［10］王旭,王宏,王文辉.人工神经元网络原理与应用［M］.沈阳:东北大学出版社,2000.
［11］李元松,李新平,张成良.基于BP网络的隧道围岩位移预测方法［J］.岩石力学与工程学报,2006,S1:29692973.
［12］张玉祥.岩土工程时间序列预报问题初探［J］.岩石力学与工程学报,1998,17(5):552558.
［13］吕淑萍,赵咏梅.基于小波神经网络的时间序列预报方法及应用［J］.哈尔滨工程大学学报,2004,25(2):180182.

相似文献/References:

[1]吴燕玲,曾凯波,周麟,等.层次分析法在大冶高陡边坡危险性分析中的应用[J].武汉工程大学学报,2010,(01):12.
　WU Yan ling,ZENG Kai bo,ZHOU Lin,et al.Apply analytical hierarchy process to analyse the risk of high steep slope in Daye iron mine[J].Journal of Wuhan Institute of Technology,2010,(09):12.
[2]杨海燕,兰宝华.基于PSOWNN的无刷直流电机转子位置检测方法[J].武汉工程大学学报,2010,(01):93.
　YANG Hai yan,LAN Bao hua.A new position detection based on PSOwavelet neural network method for brushless DC motors[J].Journal of Wuhan Institute of Technology,2010,(09):93.
[3]鲁艳军,陈汉新,贺文杰,等.基于混合特征提取和WNN的齿轮箱故障诊断[J].武汉工程大学学报,2011,(05):82.[doi:10.3969/j.issn.16742869.2011.05.022]
　LU Yanjun,CHEN Hanxin,HE Wenjie,et al.Gearbox fault diagnosis based on hybrid feature extraction and wavelet neural network[J].Journal of Wuhan Institute of Technology,2011,(09):82.[doi:10.3969/j.issn.16742869.2011.05.022]

备注/Memo

备注/Memo:
收稿日期:20100506作者简介:李元松(1964),男,湖北应城人,博士,教授.研究方向:岩土工程数值计算、岩土工程测试和结构稳定性分析方面的教学与研究工作.
更新日期/Last Update: