地震作用下高层建筑结构的分散神经网络振动控制研究

Decentralized neural networks vibration control of tall buildings under earthquakes

针对地震作用下高层建筑振动神经网络控制问题,将神经网络理论与分散控制理论相结合,提出分散神经网络振动控制方案,并应用于高层结构地震反应振动控制中。利用多层前馈神经网络建立结构模型,预测结构的振动响应。基于NARMA-L2的神经自校正控制系统设计BP神经网络控制器,研究分散神经网络振动控制效果,并与神经网络集中控制进行比较。对某20层Benchmark结构模型进行数值模拟分析,结果表明,本文提出的分散神经网络振动控制方法简化了神经网络的结构,可有效控制结构振动和消除时滞;同时,相对于集中控制的单一失效,本文方法的可靠性更强且可以保证振动控制系统的实时响应。

Vibration control of tall buildings under earthquakes based on the neural networks is studied.By combining the neural network theory and the decentralized control strategy,an algorithm named Decentralized Neural Networks Control(DNNC)is been presented for the seismic response control of tall buildings.The structural model is built by using multilayer feedforward neural network to predict the structural vibration response.The BP neural network controller is designed on the basis of Nonlinear Auto-Regressive Moving Average(NARMA)mode to study the effectiveness of the DNNC which is then compared with that of Centralized Neural Networks Control(CNNC).The performance of control strategies of a typical 20-floor seismically excited building is analyzed the performance of the control strategies.The results indicate that the DNNC strategy could simplify the structure of the neural networks and effectively mitigate structural seismic response and eliminate the time delay of the control system.It is also more reliable in ensuring the real-time response of vibration control system.