基于RBF神经网络的结构动力响应预测
|
摘要
介绍了径向基函数(RBF)神经网络学习速度快,动态仿真性强,具有较强的输入输出映射功能和全局最优逼近的结构特点.针对快速预测结构动力响应有助于克服结构振动控制中时滞效应的特点及BP网络存在的问题,应用RBF网络对结构的位移、加速度进行了预测,并采用BP网络作对比研究.仿真结果表明RBF神经网络训练速度快,精度高,可及时为主动控制建筑结构响应提供较为准确的优化性能指标,从而为实现在线实时控制结构响应提供优良的保证.
Constitutive features of radial basis function(RBF),such as fast neural network learning,strong dynamic simulation ability,good input/output mapping function,and global optimal approaching,were introduced.Taking into consideration of the feature that fast prediction of structural dynamic response is useful for overcoming the time-lag effect in structural vibration control,and aiming at the existing problems in BP network,the RBF network was employed to predict the displacement and acceleration of the construction.The RBF network was also used to conduct comparison investigation.Simulation result showed that there were fast training and high accuracy with RBF neural network,so that it could provide more accurate optimal performance indexes for timely active control of structural response of the buildings and good guarantee for implementing on-line real-time control of structural response.
Constitutive features of radial basis function(RBF),such as fast neural network learning,strong dynamic simulation ability,good input/output mapping function,and global optimal approaching,were introduced.Taking into consideration of the feature that fast prediction of structural dynamic response is useful for overcoming the time-lag effect in structural vibration control,and aiming at the existing problems in BP network,the RBF network was employed to predict the displacement and acceleration of the construction.The RBF network was also used to conduct comparison investigation.Simulation result showed that there were fast training and high accuracy with RBF neural network,so that it could provide more accurate optimal performance indexes for timely active control of structural response of the buildings and good guarantee for implementing on-line real-time control of structural response.
引文
[1]HE YU’AO,HU XIANZHONG,ZHAN SHENG.Predictingseismic response of structures by artificial neural network[J].Transactions of Tianjin University,1996,2(2):36-39.
[2]欧进萍.结构振动控制主动、半主动和智能控制[M].北京:科学出版社,2003.
[3]从爽.神经网络、模糊系统及其在运动控制中的应用[M].合肥:中国科学技术大学出版社,2001.
[4]闻新,周露,李翔,等.MATLAB神经网络仿真与应用[M].北京:科学出版社,2003.
[5]沈谦,王涛.结构优化的RBF神经网络学习算法[J].微电子学与计算机,2000,4:14-18.
[6]李庆丰,彭刚,李黎.人工神经网络对结构动力响应的预测[J].三峡大学学报:自然科学版,2003,25(3):215-217.
[7]杜永峰,李慧,赵国藩.地震作用下结构振动最优控制的一种一般算法[J].大连理工大学学报,2004,44(6):864-869.
[8]杜永峰,白莉,夏亚峰,等.小震下隔震结构的随机响应及失效概率分析[J].兰州理工大学学报,2004,30(6):101-105.
[9]徐建功,王肇民,何玉敖.基于预测控制的结构振动半主动控制研究[J].世界地震工程,2003,19(2):126-131.
[10]阎石,林皋,黎海林.人工神经网络在结构振动控制中应用[J].大连理工大学学报,2000,40(5):589-592.
[11]翟东武,朱②.基于神经网络的结构振动响应预测控制[J].清华大学学报:自然科学版.2000,40(S1):61-65.
[12]吴建军,何玉敖.结构振动控制中神经网络应用的新进展[J].世界地震工程,2000,1(16):10-19.
[13]张顺宝.基于神经网络的结构振动最优控制[J].工程力学(增刊),2000:436-440.
[2]欧进萍.结构振动控制主动、半主动和智能控制[M].北京:科学出版社,2003.
[3]从爽.神经网络、模糊系统及其在运动控制中的应用[M].合肥:中国科学技术大学出版社,2001.
[4]闻新,周露,李翔,等.MATLAB神经网络仿真与应用[M].北京:科学出版社,2003.
[5]沈谦,王涛.结构优化的RBF神经网络学习算法[J].微电子学与计算机,2000,4:14-18.
[6]李庆丰,彭刚,李黎.人工神经网络对结构动力响应的预测[J].三峡大学学报:自然科学版,2003,25(3):215-217.
[7]杜永峰,李慧,赵国藩.地震作用下结构振动最优控制的一种一般算法[J].大连理工大学学报,2004,44(6):864-869.
[8]杜永峰,白莉,夏亚峰,等.小震下隔震结构的随机响应及失效概率分析[J].兰州理工大学学报,2004,30(6):101-105.
[9]徐建功,王肇民,何玉敖.基于预测控制的结构振动半主动控制研究[J].世界地震工程,2003,19(2):126-131.
[10]阎石,林皋,黎海林.人工神经网络在结构振动控制中应用[J].大连理工大学学报,2000,40(5):589-592.
[11]翟东武,朱②.基于神经网络的结构振动响应预测控制[J].清华大学学报:自然科学版.2000,40(S1):61-65.
[12]吴建军,何玉敖.结构振动控制中神经网络应用的新进展[J].世界地震工程,2000,1(16):10-19.
[13]张顺宝.基于神经网络的结构振动最优控制[J].工程力学(增刊),2000:436-440.
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