一种基于神经网络的振动主动控制方法  

An Active Vibration Control Method Based on Artificial Neural Network

作　　者：袁树清[1] 赵玉成[1] 张陵[1] 许庆余[1] 

机构地区：[1]西安交通大学

出　　处：《机械科学与技术》1998年第4期585-588,共4页Mechanical Science and Technology for Aerospace Engineering

摘　　要：分析了表面贴有压电材料ＰＺＴ作为作动器的悬臂梁系统的特性，从控制角度推导出系统的传递函数，在此基础上采用神经网络对系统进行振动主动控制。分别利用线性神经网络和ＢＰ神经网络作为辨识器和控制器，同时将速度信号引入到控制器中以提高系统性能。数值仿真证明了方法的可行性。The Characteristic of cantilever beam with piezoelctric materials PZT as actuators is analyzed in this paper, and the transfer function is developed in the view of control, based upon which, neural network are employed to actively control the vibration of the system. A linear neural network are used as identifier and controller respectively,further more velocity signal is introduced to controller to improve performance of the system. The feasibility of the method is confirmed by numerical simulations 

关 键 词：人工神经网络 振动主动控制 压电材料 

分 类 号：TB123[理学—工程力学] TP18[理学—力学]