工业机器人谐波减速器迟滞特性的神经网络建模
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Neural network modeling of hysteresis for harmonic drive in industrial robots
  • 作者:党选举 ; 王凯利 ; 姜辉 ; 伍锡如 ; 张向文
  • 英文作者:DANG Xuan-ju;WANG Kai-li;JIANG Hui;WU Xi-ru;ZHANG Xiang-wen;School of Electronic Engineering and Automation,Guilin University of Electronic Technology;National Demonstration Center for Experimental electronic circuit Education (Guilin University of Electronic Technology);
  • 关键词:谐波减速器 ; 迟滞特性 ; 径向基函数神经网络 ; 混合模型 ; 摩擦
  • 英文关键词:harmonic drive;;hysteresis;;Radial Basis Function(RBF)neural networks;;hybrid model;;friction
  • 中文刊名:GXJM
  • 英文刊名:Optics and Precision Engineering
  • 机构:桂林电子科技大学电子工程与自动化学院;电子电路国家级实验教学示范中心桂林电子科技大学;
  • 出版日期:2019-03-15
  • 出版单位:光学精密工程
  • 年:2019
  • 期:v.27
  • 基金:国家自然科学基金资助项目(No.61263013,No.61603107);; 广西自然科学基金资助项目(No.2016GXNSFDA380001,No.2015GXNSFAA139297)
  • 语种:中文;
  • 页:GXJM201903024
  • 页数:8
  • CN:03
  • ISSN:22-1198/TH
  • 分类号:189-196
摘要
谐波减速器中柔性环节与传动的非线性摩擦,导致谐波传动出现了不可避免地影响传动精度的复杂迟滞特性,为了描述谐波减速器的迟滞特性,本文构建了一个结构简洁的神经网络迟滞混合模型。该模型由类迟滞特性预处理环节和动态RBF神经网络两部分组成:对输入信号进行类迟滞预处理,处理后的信号与输入信号之间具有类迟滞特性;充分利用动态RBF神经网络实现类迟滞到谐波减速器迟滞特性的高精度映射。根据本文搭建的实验平台,在不同实验条件下获得的数据进行建模验证,在不同频率输入信号、不同负载,实现相同建模精度下,神经网络迟滞混合模型的验证精度为0.449 6(MSE),远高于经典RBF神经网络模型的3.032 1(MSE)精度,证明了所构造的神经网络迟滞混合模型的有效性和适应性。
        Nonlinear friction caused by the flexible link and the transmission process in the harmonic drive leads to complex hysteresis characteristics of harmonic transmission that inevitably affect the transmission accuracy.To describe the hysteresis characteristics of the harmonic drive,a concise neural network hysteresis hybrid model,comprising hysteresis-like characteristic preconditioning in series with a dynamic neural network,was presented in this study.It was executed in two steps:the input signal was preprocessed to produce hysteresis-like behavior;the dynamic Radial Basis Function(RBF)neural network was fully utilized to achieve high-precision approximation of hysteresis-like to hysteresis characteristics of the harmonic drive.Moreover,an experimental platform was constructed in this study,and the data obtained under different experimental conditions were modeled and verified.Both at a constant input accuracy and the accuracy with different input signals and loads,the verification accuracy obtained by the neural network hysteresis hybrid model is 0.449 6(Mean Square Error(MSE)),which is much higher than the 3.0321(MSE)accuracy of the classical neural network model.This proves the effectiveness and adaptability of the proposed neural network hysteresis hybrid model.
引文
[1]SHI Z,LI Y,LIU G.Adaptive torque estimation of robot joint with harmonic drive transmission[J].Mechanical Systems and Signal Processing.2017,96:1-15.
    [2]吴素珍,陈丹.机器人关节传动用精密减速器研究进展[J].河南科技学院学报(自然科学版),2014,42(6):58-63.WU S Z,CHEN D.Research progress on application of precision gear reducer in robot joint transmission[J].Journal of Henan Institute of Science and Technology,2014,42(6):58-63.(in Chinese)
    [3]黑沫,范世珣,廖洪波,等.精密谐波传动系统建模[J].光学精密工程,2014,22(7):1842-1849.HEI M,FAN SH X,LIAO H B,et al..Modeling of precision harmonic drive system[J].Opt.Precision Eng.,2014,22(7):1842-1849.(in Chinese)
    [4]杜志江,肖永强,董为.含有摩擦间隙迟滞的机械臂关节建模方法[J].机器人,2011,33(5):539-545.DU ZH J,XIAO Y Q,DONG W.Modeling of Robot Joints with Friction,Backlash and Hysteresis[J].Robot,2011,33(5):539-545.(in Chinese)
    [5]石照耀,徐航,韩方旭,等.精密减速器回差测量的现状与趋势[J].光学精密工程,2018,26(9):2150-2158.SHI ZH Y,XU H,HAN F X,et al..Current status and trend in precision reducer lost motion measurement[J].Opt.Precision Eng.,2018,26(9):2150-2158.(in Chinese)
    [6]赵强.具有复合材料层的谐波减速器传动精度研究[D].重庆:重庆大学,2015.ZHAO Q.Study on Transmission Accuracy of Harmonic Drive with Composite Material Layer[D].Chongqing:Chongqing University,2015.(in Chinese)
    [7]ZOU C,TAO T,JIANG G,et al..Deformation and stress analysis of short flexspline in the harmonic drive system with load[C].IEEE International Conference on Mechatronics and Automation.Takamatsu,Japan:IEEE,2013,466:676-680.
    [8]万庆祝,陆志刚,王科,等.精密谐波齿轮减速器传动误差分析[J].仪表技术与传感器,2013(5):51-54.WAN Q ZH,LU ZH G,WANG K,et al..Precision harmonic gear reducer transmission error analysis[J].Instrument Technique and Sensor,2013(5):51-54.(in Chinese)
    [9]RUDERMAN M,BERTRAM T.Modeling and observation of hysteresis lost motion in elastic robot joints[J].IFAC Proceedings Volumes,2012,45(22):13-18.
    [10]房建成,陈萌,李海涛.磁悬浮控制力矩陀螺框架系统谐波减速器的迟滞建模[J].光学精密工程,2014,22(11):2950-2958.FANG J CH,CHEN M,LI H T.Hysteresis modeling for harmonic drive in DGMSCMG gimbal system[J].Opt.Precision Eng.,2014,22(11):2950-2958.(in Chinese)
    [11]XIAO S,LI Y.Modeling and high dynamic compensating the rate-dependent hysteresis of piezoelectric actuators via a novel modified inverse preisach model[J].IEEE Transactions on Control Systems Technology,2013,21(5):1549-1557.
    [12]DANG X,TAN Y H.RBF neural networks hysteresis modelling for piezoceramic actuator using hybrid model[J].Mechanical Systems and Signal Processing,2007,21(1):430-440.
    [13]党选举,梁卫,姜辉.基于改进Preisach模型的音圈电机复杂迟滞建模[J].振动与冲击,2012,31(21):156-162.DANG X J,LIANG W,JIANG H.Complex hysteresis modeling for a voice coil motor based on improved preisach model[J].Journal of Vibration and Shock,2012,31(21):156-162.
    [14]刘金琨.智能控制[M].北京:电子工业出版社,2017.LIU J K.Intelligent control[M].Beijing:Publishing House of Electronics Industry,2017.(in Chinese)
    [15]吕勇,陈青山,刘力双,等.精密谐波齿轮输入轴扭转刚度和迟滞测试[J].合肥工业大学学报(自然科学版),2013,36(5):523-526.LV Y,CHEN Q SH,LIU L SH,et al..Test for torsional stiffness and hysteresis of input shaft of precision harmonic gear[J].Journal of Hefei U-niversity of Technology:Science and Technology,2013,36(5):523-526.(in Chinese)

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700