摘要
给出了一种将Hopfield神经网络运用于线性系统辨识问题的方法。通过测量输入、状态变量和状态变量的微分,构造Hopfield网络神经元之间的权重和各神经元的偏流。网络神经元的状态将收敛到被辨识系统的参数的值。使用Hopfield神经网络辨识舰炮液压伺服系统的三阶模型,仿真结果表明用这种系统辨识方法辨识时变和时不变系统是可行的。
A method was presented to apply a Hopfield network to the problem of linear system identification.By measuring inputs,state variables,and time derivatives of state variables,the weights and biases of Hopfield network were constructed.The states of the neurons of this network will converge to the values of the system parameters,which are to be identified.The Hopfield network was used to identify the three-order model of the hydraulic servo system for ship-gun,simulation results show the feasibility of using this system to identify the time-varying and time-invariant system.
出处
《机床与液压》
北大核心
2005年第7期136-138,130,共4页
Machine Tool & Hydraulics
关键词
系统辨识
神经网络
计算机仿真
舰载火炮
System identification
Neural network
Computer simulation
Warship-guns
