基于神经网络的结构智能控制研究-结构工程专业论文.docxVIP

AbstractStructural Abstract 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 contr01．But active eontrol iS hard to establish accurate mathematics model and has the problem of time lag．Neural network need not establish accurate mathematics model，h sums up the relation implicit in the systematic input output through studying input output training sample data．Applying neural network predict structural may solve the problem of time lag in active control and 0ffer basis for controlling decision．Now,general predictiOn neural network has BP nculml network and RBF neural network mainly．BP neural network has shortcoming of slow learning speed and falling int0 the local minimum easily,and the study and remember of BP neural network is instable；compared with BP neural network．RBF neural network has fast 1earning．the strong dynamie simulation property,the better map property of input and output and垂obal optimum property．It avoid local minimum，can linearly adjustment weight value，and not back propagation t11e same time it iS realized by hardware relatively simply．It has been good choice for real—time identification and controlling for various nonlinear systems．Predicting structural dynamic respcnse quiclOy helps overcome time lag in structural contr01．The response of is predicted bv RBF neural network，and compared with the results of BP neural network．The results of simulation suggeSt that RBF neural network iS feasible and fast for prediction of structural dynamic and tlle results quite exact．ne method offer the comparatively optimization performance index for the structural response in time，thUS 0fiering the fine assurance for realizing the online real．time control structural response．To impmve further network’S performance，nalnely,the predietion of structural response based neural network has higher forecast precision for different earthquake excit