柔性结构神经网络分布式振动控制
|
摘要
提出采用分布式控制解决柔性结构振动问题,并且控制形式简单,便于控制力的实施。结合神经网络可以解决常规分布式控制难于解决的非线型耦合问题。神经网络采用非线性自回归移动平均移动方法,提高了神经网络的运算速度快。最后,在不同作动力情况下,将集中式神经网络控制和分布式神经网络分别采用相同的最大作动力对作动器/结构耦合系统进行控制。结果表明,分布式神经网络控制在采用较小的控制力情况下,取得了更好的控制效果。
In this paper,the vibration problem of flexible construction structure suppressed by using this distributed control method.And this control mode is easy to load the control force, especially for a large-scale structure.Combined with NN,this method can solve nonlinear coupled problems,which cannot be solved by normal distributed control.NN used in this paper adopts Nonlinear Autoregressive-Moving Average(NARMA)method,which can train the NN quickly。Then,under different maximum active forces,the centralized NN and the distributed NN control methods are used to control actuator/coupled structure system,respectively.The simulations show that distributed NN control obtains better control effect while uses less control force.
In this paper,the vibration problem of flexible construction structure suppressed by using this distributed control method.And this control mode is easy to load the control force, especially for a large-scale structure.Combined with NN,this method can solve nonlinear coupled problems,which cannot be solved by normal distributed control.NN used in this paper adopts Nonlinear Autoregressive-Moving Average(NARMA)method,which can train the NN quickly。Then,under different maximum active forces,the centralized NN and the distributed NN control methods are used to control actuator/coupled structure system,respectively.The simulations show that distributed NN control obtains better control effect while uses less control force.
引文
[1]吴建军，何玉傲．结构振动控制中神经网络应用的新进展．世界地震工程．2000，16(1)11：10-19．
[2]G.W.Housner,L.A.Bergman.et al.Structure Control:Past,Present,and Future.Journal of Engineering Mechanics,ASCE,1997 123(9):897-971.
[3]李东旭．大型挠性结构分散化振动控制—理论与方法．长沙：国防科技大学出版社2002．
[4]胡跃明，周其节．分布参数变结构控制系统．北京：国防工业出版社，1996．
[5]Jamshid Ghaboussi,Abodolreza Joghataie.Active Control of Structure Using Neural Networks.Journal of Engineering Mechanics,ASCE,1995 121(4):555-567.
[6]Shih-Lin Hung,C.Y.Kao,J.C.Lee.Active Pulse Structure Control Using Artificial Neural Networks.Journal of Engineering Mechanics,ASCE,2000 126(8):839-849.
[7]飞思科技产品研发中心．MATLAB6．5辅助神经网络分析与设计．北京：电子工业出版社2003．
[8]Khaldoon Bani-Hani,Jamshid Ghaboussi.Nonlinear Structural Control Using Neural Networks.Journal of Engineering Mechanics,ASCE,1998 124(3):319-327.
[2]G.W.Housner,L.A.Bergman.et al.Structure Control:Past,Present,and Future.Journal of Engineering Mechanics,ASCE,1997 123(9):897-971.
[3]李东旭．大型挠性结构分散化振动控制—理论与方法．长沙：国防科技大学出版社2002．
[4]胡跃明，周其节．分布参数变结构控制系统．北京：国防工业出版社，1996．
[5]Jamshid Ghaboussi,Abodolreza Joghataie.Active Control of Structure Using Neural Networks.Journal of Engineering Mechanics,ASCE,1995 121(4):555-567.
[6]Shih-Lin Hung,C.Y.Kao,J.C.Lee.Active Pulse Structure Control Using Artificial Neural Networks.Journal of Engineering Mechanics,ASCE,2000 126(8):839-849.
[7]飞思科技产品研发中心．MATLAB6．5辅助神经网络分析与设计．北京：电子工业出版社2003．
[8]Khaldoon Bani-Hani,Jamshid Ghaboussi.Nonlinear Structural Control Using Neural Networks.Journal of Engineering Mechanics,ASCE,1998 124(3):319-327.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心