RBF网络的结构动力响应预测

Prediction of Structural Dynamic Response with RBF Neural Network

由于结构主动控制对地震反应振动控制的高效性,使主动控制在建筑结构振动控制领域中,具有广阔的应用前景,但是主动控制存在难以建立一个精确的数学模型,存在时滞效应等问题。神经网络不需要建立精确的数学模型,只是通过学习输入输出训练样本数据,就可归纳出隐含在系统输入输出中的关系;应用神经网络预测结构响应可以解决主动控制中的时滞问题,为控制决策提供依据。用RBF神经网络对结构响应进行预测,以期能为结构主动控制提供一种新的思路。

Structural active control is more efficient in the control of seismic response, which makes active control have wide application prospect in the field of structural vibration control. But it is hard to establish an accurate mathematics model for the active control which has the problem of time lag. Neural network doesn＇ t need to establish accurate mathematics model, it sums up the relation implicit in the systematic input and output through studying the input and output training sample data, By applying neural network to predict structural response, the problem of time lag in active control may be solved and the basis for controlling decision is offered. A new method for the structural active control may be offered by predicting the structural response with RBF neural network.