基于保性能自适应RBF神经网络的MR半主动非线性鲁棒分散控制  

SEMI ACTIVE NONLINEAR ROBUST DECENTRALIZED CONTROL BASED ON GUARANTEED PERFORMANCE ADAPTIVE RBF NEURAL NETWORK

作　　者：潘兆东 谭平[2] 周福霖[2,3] PAN Zhao-dong;TAN Ping;ZHOU Fu-lin(Department Civil Engineering,Dongguan University of Technology,Dongguan 523808,China;Earthquake Engineering Research&Test Center,Guangzhou University,Guangzhou 510405,China;College of Civil Engineering,Hunan University,Changsha 410082,China)

机构地区：[1]东莞理工学院建筑工程系,东莞523808 [2]广州大学工程抗震研究中心,广州510405 [3]湖南大学土木工程学院,长沙410082

出　　处：《工程力学》2018年第10期47-55,共9页Engineering Mechanics

基　　金：科技部"十二五"支撑计划子课题(2012BAJ07B02);国家自然科学基金项目(97315301-07;51408142);教育部创新团队项目(IRT13057)

摘　　要：该文针对模型参数不确定的非线性结构半主动分散控制问题进行研究。首先,采用退化Bouc-Wen滞回模型模拟层间恢复力,并考虑模型参数(质量、刚度和阻尼)不确定及子系统间的耦合项,建立了子控制系统误差状态方程;在此基础上,设计了由保性能控制项和自适应逼近控制项构成的子控制器,其中,保性能控制项通过求解转化为线性矩阵不等式的保性能控制问题得到,逼近控制项通过RBF神经网络自适应控制律确定,同时利用Lyapunov稳定性理论对其稳定性及权值有界性进行证明;从而建立了适用于不确定结构非线性振动控制的保性能自适应RBF神经网络鲁棒分散控制(GCARBF)算法。最后,对一8层非线性结构进行MR半主动分散控制设计及0.3 g^0.8 g地震下仿真分析,结果表明了所提算法的有效性与优越性。The semi active decentralized control of nonlinear structures with uncertain parameters is studied.Firstly,the degenerated Bouc-Wen hysteretic model is utilized to simulate the restoring forces,and the error state equation of a sub-control system is established by considering the uncertainty of the model parameters(mass,stiffness and damping)and the coupling between subsystems.Secondly,a sub-controller is designed which composes of a guaranteed cost control term and an adaptive approximation control term.The guaranteed cost control term is obtained by solving the guaranteed cost control problem which is transformed into a linear matrix inequality.The approximation control term is determined by the adaptive control law of RBF neural network,and its stability and boundedness of the weights are proved by Lyapunov stability theory.And then a guaranteed cost adaptive RBF neural network robust decentralized control(GCARBF)algorithm for nonlinear vibration control of uncertain structures is established.A nonlinear 8-story building is selected as a numerical example to evaluate the control performances of the proposed algorithm.The MR semi active decentralized control design and the simulation analysis of 0.3 g^0.8 g intensity are carried out.Numerical simulation results indicate the effectiveness and superiority of the proposed algorithm.

关 键 词：MR半主动控制 鲁棒分散控制 自适应RBF神经网络控制 保性能控制 LYAPUNOV稳定性理论 线性矩阵不等式方法 

分 类 号：TU352.11[建筑科学—结构工程]