基于自适应RBF神经网络算法的建筑结构递阶分散控制研究

Hierarchical decentralized control of building structure based on adaptive RBF neural network algorithm

针对建筑结构振动控制的递阶分散控制问题进行研究。首先,通过设置全局控制器消除子系统间的关联耦合;在此基础上,结合Lyapunov稳定性理论和RBF神经网络理论设计了仅依赖于子系统位移和速度响应反馈信息的自适应控制律,并利用差分进化(DE)算法对自适应RBF神经网络局部子控制器相关参数进行优化,建立了适用于建筑结构振动控制的自适应RBF神经网络递阶分散控制(ARBFHDC)算法。对ASCE 9层Benchmark模型进行递阶分散控制设计、优化及仿真分析。结果表明,不同地震激励下,基于ARBFHDC算法设计的递阶分散控制较传统集中控制而言有更好的控制效果,且能保障各子系统作动器处于最大功效工作状态。

The hierarchical decentralized control problem of building structure vibration control is studied in this paper. Firstly, The associated coupling between subsystems is eliminated by setting the global controller. Secondly, Lyapunov stability theory and RBF neural network theory are employed to design the adaptive control law which depends only on the displacement and the velocity response of relevant subsystem, and the parameters of adaptive RBF neural network local sub-controller is optimized through using the differential evolution （DE） algorithm. And then, the adaptive RBF neural network hierarchical decentralized control （ARBFHDC） algorithm is established for the building structure vibration control. The ASCE 9-story Benchmark building is selected as a numerical example to evaluate the control performances of the hierarchical decentralized control. Numerical simulation results indicate that the ARBFHDC algorithm is suitable for hierarchical decentralized control strategy under different seismic performance when comparing with traditional centralized control operating at maximum efficiency. excitations, it can perform up to a superior control , and can guarantee the actuators of each subsystem are