基于神经网络的磁流变阻尼器逆控制研究

作者：徐健忠，王洪飞 日期：2009-04-21/span> 浏览：3806 查看PDF文档

基于神经网络的磁流变阻尼器逆控制研究

徐健忠，王洪飞
（杭州电子科技大学 机械工程学院，浙江 杭州 310018）

摘要：为了解决阻尼器的非线性问题，设计了一种纯剪切型磁流变阻尼器，并针对其非线性特性，提出了利用径向基函数（RBF）神经网络的非线性映射能力，以建立磁流变阻尼器的逆模型。由已训练的磁流变（MR）阻尼器的逆向神经网络模型和MR阻尼器组成的控制单元，在给定所需控制力的情况下，使MR阻尼器产生相应的阻尼力，实现了MR阻尼器提供连续可调输出力的目的，也使得纯剪切型MR阻尼器在一些需要精确控制的场合能够方便使用。仿真结果表明，神经网络逆控制的方法是有效的、可行的。
关键词：磁流变阻尼器；逆模型；径向基函数神经网络；仿真
中图分类号：TP273文献标识码：A文章编号：1001-4551(2009)03-0087-03

Inverse control of MR damper based on neural network technology
XU Jian-zhong, WANG Hong-fei
(College of Mechanical Engineering, Hangzhou Dianzi University, Hangzhou 310018, China)
Abstract: In order to solve the nonlinear problem of lampers, a pure-shear magneto-rtheological(MR) damper was designed. In view of its non-linear characteristics, it was proposed to make use of the radial basis function(RBF) neural networks non-linear mapping capabilities and establish MR dampers inverse model to solve its problem of non-linear. At the condition of given control force, the control unit composed of having been trained inverse neural networks model of MR damper and MR damper, could make MR damper conduce corresponding damping force. It was achieved the MR dampers to provide adjustable power output for the purpose of making pure-shear MR dampers in the need for precise control of a lot of occasions. The simulation results show that neural network inverse control method is effective and feasible.
Key words: magneto-rtheological(MR) damper; inverse model; radial basis-function(RBF) neural networks; simulation
参考文献(References):
［1］关新春，李金海，欧进萍.足尺磁流变液耗能器的性能与试验研究［J］.工程力学，2005,22(6):207-211.
［2］SPENCER J B F, DYKE S J, SAINM K, et al. Phenomenological model for magnetorheological dampers［J］. Joumal of Engineering Mechanics, ASCE,1997,123(3):230-238.
［3］吴剑，王洪飞.基于ANSYS的磁流变阻尼器磁路优化设计[J].机电工程，2008，25（2）：74-76.
［4］关新春，欧进萍.磁流变耗能器的阻尼力模型及其参数确定［J］.振动与冲击,2000,20(1):5-8.
［5］ANTSAKLIS P J. Neural networks in control system: special section on neural networks for systems and control［J］. IEEE Control Systems Magazine,1990,4(3):3-5.
［6］何玉彬，李新忠.神经网络控制技术及其应用[M].北京：科学出版社,2000.