移动荷载下基于RBF神经网络的地基土参数识别
|
摘要
研究了移动荷载作用下径向基神经网络在地基土的参数识别中的应用。针对径向基神经网络的不足,采用压缩映射递阶遗传算法来确定网络参数(连接权、隐节点中心和宽度),改进算法的收敛性。基于频率响应,采用主元分析方法,有效减少了网络的输入节点。结果表明该方法是可行的。
This paper investigated a new estimation method of soil properties under moving load by using radial basis function(RBF) neural network.A contractive mapping and hierarchical genetic algorithm for RBF neural network was proposed to train network parameters such as connection weights,centres and widths.In addition,the improving algorithm converged faster and could avoid falling into local minima.This research used the frequency response data as input to RBF neural network.By applying a principal component analysis(PCA),the number of input nodes was reduced largely.This method was proved to be practical in estimating the parameters.
This paper investigated a new estimation method of soil properties under moving load by using radial basis function(RBF) neural network.A contractive mapping and hierarchical genetic algorithm for RBF neural network was proposed to train network parameters such as connection weights,centres and widths.In addition,the improving algorithm converged faster and could avoid falling into local minima.This research used the frequency response data as input to RBF neural network.By applying a principal component analysis(PCA),the number of input nodes was reduced largely.This method was proved to be practical in estimating the parameters.
引文
[1]Kazuhiro Yamamoto,Shinichi Isayama,Yasutoshi Kitamura.A Simple Estimation Method of Soil Properties Using NeuralNetwork for Prediction of Ground Vibration[A].Environmental Vibration:Prediction,Monitoring and Evalution[C].Hangzhou:The Auspices of Natural Science Foundation of China,2003.458~465.
[2]Siddharthan R,Norris G M,Epps J A.Use of FWD Data for Pavement Material Characterization and Performance[J].Jour-nal of Transportation Engineering,1991,117:660~678.
[3]Luco J E,Wong H L.Identifination of Soil Properties from Foundation Impedance Function[J].Journal of Geotechnical Engi-neering,1992,118:780~795.
[4]Zang C,Imregun M.Structural Damage Delection Using Artificial Neural Networks and Measured RFF Data Reduced viaPrincipal Component Projection[J].Journal of Sound and Vibration,2001,242(5):813~827.
[5]Okumura Y,Kuno K.Prediction of Railway Noise and Vibration Levels by Neural Networks(in Japanese)[J].The Journal ofthe Acoustical Society of Japan,1993,59:563~567.
[6]谢伟平,王国波,于艳丽.移动荷载作用下双层Euler梁模型土动力响应分析[J].地震工程与工程振动,2004,24(1):82~86.
[7]孙文爽,陈兰祥.多元统计分析[M].北京:高等教育出版社,1994.
[8]郑丕谔,马艳华.RBF神经网络的递阶遗传训练新方法[J].控制与决策,2000,15(2):165~168.
[9]邹承明,钟珞,涂建维.神经网络与压缩映射遗传算法耦合技术研究[J].武汉理工大学学报,2003,25(1):40~42.
[2]Siddharthan R,Norris G M,Epps J A.Use of FWD Data for Pavement Material Characterization and Performance[J].Jour-nal of Transportation Engineering,1991,117:660~678.
[3]Luco J E,Wong H L.Identifination of Soil Properties from Foundation Impedance Function[J].Journal of Geotechnical Engi-neering,1992,118:780~795.
[4]Zang C,Imregun M.Structural Damage Delection Using Artificial Neural Networks and Measured RFF Data Reduced viaPrincipal Component Projection[J].Journal of Sound and Vibration,2001,242(5):813~827.
[5]Okumura Y,Kuno K.Prediction of Railway Noise and Vibration Levels by Neural Networks(in Japanese)[J].The Journal ofthe Acoustical Society of Japan,1993,59:563~567.
[6]谢伟平,王国波,于艳丽.移动荷载作用下双层Euler梁模型土动力响应分析[J].地震工程与工程振动,2004,24(1):82~86.
[7]孙文爽,陈兰祥.多元统计分析[M].北京:高等教育出版社,1994.
[8]郑丕谔,马艳华.RBF神经网络的递阶遗传训练新方法[J].控制与决策,2000,15(2):165~168.
[9]邹承明,钟珞,涂建维.神经网络与压缩映射遗传算法耦合技术研究[J].武汉理工大学学报,2003,25(1):40~42.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心