【摘要】 主动控制中存在时滞效应,在线实时预测结构响应,可以解决这个问题。不同的神经网络对结构响应的预测效果是不同的,针对BP网络和RBF网络的不同特点,对它们的预测效果做了对比研究。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。更多还原

【Abstract】 The time lag in active control can be solved by the real-time prediction of structural dynamic response.The response of structure is predicted with RBF neural network in this paper and it was compared with the results of BP neural network.Simulation results suggest that RBF neural network is feasible and fast in predicting structural dynamic response with great accuracy.The method can offer more accurate optimization performance indexes for the structural response,and thus it can guarantee the realization of online real-time control structural response.更多还原