滑移隔震半主动控制的人工神经网络方法

基于人工神经网络方法,在考虑上部结构的刚度和阻尼的条件下,通过计算基底摩擦力的大小,对滑移隔震结构的半主动控制方法进行了研究。实例计算表明,通过半主动控制的滑移隔震结构不但具有较好的隔震效果,且能有效地减小基底的最大滑移量及残余位移。通过与Bang-Bang控制和瞬时最优控制算法的对比分析表明:基于人工神经网络控制算法的控制效果优于其它控制算法,具有反馈量少、稳健性强等特点。

Semi-active Intelligent Control of Sliding Struture Based on Artifical Neural Network

Considering the stiffness and damping of super structure,this paper proposed an intelligent semi-active strategy to control the base friction force of sliding structures by artificial neural network.Numerical results show that the friction-controllable sliding structures not only behave good isolation effect,but also availably reduce the maximum slippage and residual base displacement.In order to compare the control effect of different method,this paper also used Bang-Bang control method and instantaneous optimal control method to control the sliding structures.Simulation results clearly indicate that the artificial neural network control method has some advantage comparing with other methods such as a few of quantity to be feed back,robust characteristics and so on.