基于 HNN 的弹性连杆机构主动控制系统的参数估计  

Parameter Estimation for the Active Control System of Flexible Linkage Mechanisms Based on Hopfield Neural Networks

作　　者：宋轶民[1] 马文贵[1] 张策[1] 

机构地区：[1]天津大学

出　　处：《机械科学与技术》1998年第5期782-784,788,共4页Mechanical Science and Technology for Aerospace Engineering

基　　金：国家自然科学基金;天津市自然科学基金

摘　　要：基于Ｈｏｐｆｉｅｌｄ神经网络的优化计算原理，对弹性连杆机构主动控制系统进行了参数估计。首先将ＫＥＤ模型转化为状态空间模型，根据系统输出观测出状态变量，最终采用连续型ＨＮＮ实现了该线性时变系统的参数估计。仿真结果证明了这种方法的有效性。Based on the optimization computing theory of Hopfield Neural Networks(HNN), a parameter estimation method is developed in this paper for the active control system of flexible linkage mechanisms. The state space model of the controlled system is derived firstly; then the state variables are observed by using the outputs of the system; finally, the parameters of the linear time varying system are estimated by means of continuous HNN. Simulation results prove the validity of the proposed method.

关 键 词：弹性 连杆机构 神经网络 参数估计 主动控制 

分 类 号：TH112.5[机械工程—机械设计及理论]