基于Simulink的结构动力响应预测仿真
|
摘要
基于Matlab/Simulink下神经网络工具箱功能进行在地震作用下的结构振动响应预测仿真。利用RBF神经网络对实时地震数据进行动力响应预测,能有效的解决在振动控制中所存在的时滞效应以及测量系统的噪声干扰等问题。通过对计算模型顶层以及标准层的结构动力响应预测结果以及实际结构动力响应结果的对照,证实了使用Simulink下的神经网络功能进行结构响应预测的准确性,并为后续仿真阶段对响应数据采用序列最优控制法进行计算,获得系统控制力奠定基础。
The prediction simulation of seismic response for the structure based on the neural network toolbox function of Matlab/Simulink.Utilizing the RBF neural network to precede the dynamic response prediction upon the real time seismic data could solve the problem,such as,time lag which exists in the vibration controlling and the noise disturbing of the measure system,effectively.By compared with dynamic response prediction data and actual system vibration response data for the top floor and one of the normal floors of the structure verify the possibility,which verify the neural network function of the Simulink to predict the dynamic response of the controlled system.This verification also lay the foundation for the further real time structure control research,that utilize the sequential optimal control method calculating the predicted dynamic response data to achieve the final controlling force of the controlled system.
The prediction simulation of seismic response for the structure based on the neural network toolbox function of Matlab/Simulink.Utilizing the RBF neural network to precede the dynamic response prediction upon the real time seismic data could solve the problem,such as,time lag which exists in the vibration controlling and the noise disturbing of the measure system,effectively.By compared with dynamic response prediction data and actual system vibration response data for the top floor and one of the normal floors of the structure verify the possibility,which verify the neural network function of the Simulink to predict the dynamic response of the controlled system.This verification also lay the foundation for the further real time structure control research,that utilize the sequential optimal control method calculating the predicted dynamic response data to achieve the final controlling force of the controlled system.
引文
[1]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,2001:80-85.
[2]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.
[3]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.
[4]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.
[5]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.
[6]杜永峰,郭剑虹.基于RBF神经网络的结构动力响应预测[J].兰州理工大学学报,2006(2)
[2]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.
[3]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.
[4]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.
[5]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.
[6]杜永峰,郭剑虹.基于RBF神经网络的结构动力响应预测[J].兰州理工大学学报,2006(2)
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