【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。更多还原

【Abstract】 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.更多还原