柔性铰接板振动视觉测量与小波神经网络控制  

Vibration vision measurement and wavelet neural network control of flexible hinged plate

作　　者：邱志成[1] 刘一鸿 李旻[1] QIU Zhicheng;LIU Yihong;LI Min(School of Mechanical and Automotive Engineering,South China University of Technology,Guangzhou 510641,China)

机构地区：[1]华南理工大学机械与汽车工程学院,广东广州510641

出　　处：《光学精密工程》2024年第7期998-1010,共13页Optics and Precision Engineering

基　　金：国家自然科学基金资助项目(No.52175093);广东省自然科学基金资助项目(No.2019A1515011901)。

摘　　要：为了解决航天器上用于供能的太阳帆板类柔性薄板结构的振动问题,针对一种移动柔性铰接板系统构建了双目视觉系统的振动测控实验平台,采用双目立体视觉方法来检测振动,并设计了自回归小波神经网络控制器(Self-Recurrent Wavelet Neural Network Controller,SRWNNC)来抑制振动。对双目视觉系统进行了标定,基于视差原理和图像处理算法,通过解算标志点的三维坐标来获取振动信号。建立了系统的有限元模型,并通过辨识得到校正后的系统模型参数。基于辨识得到的模型在仿真环境中训练SRWNNC,用于实验系统的振动主动控制。分别针对移动柔性铰接板系统固定基座和平移轨迹运动两种情况,进行了双目视觉振动检测和振动控制仿真和实验研究。仿真和实验结果表明,双目视觉传感器对振动信号的检测精度小于0.1 mm,SRWNNC也展现出比大增益PD控制器更好的抑振效果,验证了双目视觉振动检测和SRWNNC抑制振动的准确性和有效性。To address the vibration challenges in flexible thin plate structures like solar panels on spacecraft,this study investigates a translational flexible hinged plate system.A binocular vision-based measurement and control experimental platform is developed.This platform employs the binocular stereo vision technique for vibration detection,and introduces a self-recurrent wavelet neural network controller(SRWNNC)to mitigate vibration.The system's binocular vision is precisely calibrated.Utilizing the principles of disparity and advanced image processing algorithms,it calculates the three-dimensional coordinates of specific markers to capture vibration signals.A finite element model of the system is constructed,facilitating the identification of system model parameters.Following this,the SRWNNC is trained within a simulation environment using the identified model parameters,aiming for effective vibration control in the experimental system.Experiments and simulations are conducted on the system,focusing on both fixed base and translational trajectory movements,to evaluate the effectiveness of binocular vision in vibration detection and the SRWNNC in active vibration suppression.The findings confirm that the binocular vision sensor achieves a high accuracy less than 0.1 mm in detecting vibrations,and the SRWNNC outperforms traditional large gain PD controllers in damping vibrations,thus validating the efficiency and accuracy of the proposed vibration detection and suppression methods.

关 键 词：双目视觉 移动柔性铰接板 自回归小波神经网络 振动抑制 

分 类 号：TP212.6[自动化与计算机技术—检测技术与自动化装置]