基于BP神经网络的轮带系统的变结构控制  

Variable Structure Control of Belt Drive Systems via BP Neural Network Methods

作　　者：程翔[1] 张伟[1] 

机构地区：[1]福州大学机械工程及自动化学院,福建福州350108

出　　处：《机械制造与自动化》2015年第5期176-179,共4页Machine Building & Automation

基　　金：福州大学科研启动基金资助项目(826230);福州大学科技发展基金资助项目(826807)

摘　　要：采用变结构离散指数趋近律设计出有效的控制律,通过控制张紧臂的状态,从而抑制轮带的横向振动。运用BP神经网络自适应调整控制律的参数,抑制了系统抖振问题。仿真结果表明,基于BP神经网络离散指数趋近律的滑模控制律有效抑制了轮带的横向振动和系统在滑模面的抖振。in order to control the state of the tension arm, a discrete index reaching law of the variable structure is used to design an effective sliding mode control law. As a result, the transverse vibration of the belt is restrained. By using BP neural network methods, the chattering of the variable structure is controlled. Simulation results show that the chattering and the transverse vibration of the belt are well suppressed by the sliding mode control law.

关 键 词：轴向运动弦线 变结构控制 离散指数趋近律 BP神经网络 

分 类 号：O321[理学—一般力学与力学基础]