转子-轴承系统混沌运动的神经网络反馈控制方法

PDF(1934 KB)

振动与冲击 ›› 2012, Vol. 31 ›› Issue (11) : 145-148.

论文

转子-轴承系统混沌运动的神经网络反馈控制方法

张顺浩1, 郑铁生2

作者信息 +

Feedback control for chaotic motion of nonlinear dynamical system by intelligent neural network

Jang Sun-Ho1, Zheng Tie-sheng2

Author information +

文章历史 +

摘要

用神经网络技术对刚性Jeffcott转子-轴承系统进行混沌滞延反馈控制研究。研究结果表明，当转子-轴承系统进入混沌状态后，引入时间滞延反馈控制信号，可以消除转子-轴承系统的混沌振动，使嵌入在混沌吸引子中的不稳定周期轨道回到稳定周期轨道上。采用间接误差计算的BP神经网络学习方法和自适应学习率BP算法结合而形成的改进型BP神经网络方法，可以快速搜寻到次优化的滞延反馈控制强度，从而即时有效地消除转子-轴承系统的混沌振动。一旦混沌振动回归稳态周期振动，则反馈控制信号自动消失。该方法为控制转子-轴承系统的振动状态提供了理论依据，特别是对工程实际转子系统有实用价值。

Abstract

In this paper, the control of chaotic vibration using neural network for a rigid Jeffcott rotor system supported on short journal bearings is presented. Results of the research demonstrate that feedback control signal is applied to rotor-bearing system, an unstable periodic orbit embedded in the chaotic attractor is attracted to stable periodic orbit. From learning of the neural network, the delay feedback control gain is automatically traced. Numerical simulations show that in short time, a chaotic vibration has be stabilized effectively and then the feedback signal has automatically vanished. This method offer theoretical basis for control of chaotic vibration of rotor bearing system, especially for the rotor system used in engineering practice.

导出引用

张顺浩; 郑铁生. 转子-轴承系统混沌运动的神经网络反馈控制方法[J]. 振动与冲击, 2012, 31(11): 145-148

Jang Sun-Ho; Zheng Tie-sheng. Feedback control for chaotic motion of nonlinear dynamical system by intelligent neural network[J]. Journal of Vibration and Shock, 2012, 31(11): 145-148