浏览全部资源
扫码关注微信
桂林电子科技大学 电子工程与自动化学院,广西 桂林 541004
Received:04 March 2021,
Revised:22 April 2021,
Published:15 October 2021
移动端阅览
党选举,贺思颖.采用非对称迟滞算子的工业机器人柔性关节迟滞特性建模[J].光学精密工程,2021,29(10):2412-2420.
DANG Xuan-ju,HE Si-ying.Hysteresis modeling for flexible joint of industrial robot using asymmetric hysteresis operator[J].Optics and Precision Engineering,2021,29(10):2412-2420.
党选举,贺思颖.采用非对称迟滞算子的工业机器人柔性关节迟滞特性建模[J].光学精密工程,2021,29(10):2412-2420. DOI: 10.37188/OPE.20212910.2412.
DANG Xuan-ju,HE Si-ying.Hysteresis modeling for flexible joint of industrial robot using asymmetric hysteresis operator[J].Optics and Precision Engineering,2021,29(10):2412-2420. DOI: 10.37188/OPE.20212910.2412.
针对工业机器人柔性关节所具有的多值对应及非对称特点的复杂迟滞特性对其控制精度产生不利影响的问题,在PI(Prandtl-Ishlinskii)模型框架下,提出一种针对非对称、强非线性复杂迟滞特性的神经网络建模方法。在PI模型的对称Play算子的结构基础上,将Play算子中的线性部分用非线性函数替代:将两个变化后的Sigmoid函数组合,构造一个与迟滞曲线轮廓接近的新函数,作为一个非对称非线性的迟滞算子,以此为激励函数,在PI模型框架下,构建神经网络迟滞模型,对柔性关节表现出的复杂迟滞特性进行建模。在柔性关节不同输入条件下获得的实验数据,对模型进行验证,结果表明最大预测误差能控制在1°以内,相较于PI模型,最大误差减小为其五分之一,均方根误差减小为其五分之一。所建立的神经网络迟滞模型具有较好的泛化能力,建模精度有较大提升。
To investigate the effects of complex hysteresis characteristics owing to multi value correspondence and asymmetry on the control accuracy of flexible industrial robot joints
this study proposes a neural network modeling method for complex hysteresis characteristics of asymmetry and strong nonlinearity utilizing the PI (Prandtl Ishlinskii) model framework. Based on the structure of symmetric Play operator in the PI model
the linear part of Play operator is replaced by a new operator that is a nonlinear function constructed by two modified Sigmoid functions with asymmetric nonlinear hysteresis behavior. The new operator is used as the active function that constructs the neural network hysteretic model for capturing the complex hysteresis characteristics of flexible joints. The model is verified using experimental data obtained under different input conditions of flexible joints
and the results show that the maximum prediction error can be controlled within 1°. Compared to the PI model
the maximum error and the root mean square error are reduced to one fifth. Furthermore
it can be proved that the hysteresis neural network has good generalization ability with a modeling accuracy that is greatly improved.
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 . doi: 10.3788/ope.20142211.2950 http://dx.doi.org/10.3788/ope.20142211.2950
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) . doi: 10.3788/ope.20142211.2950 http://dx.doi.org/10.3788/ope.20142211.2950
党选举 , 王凯利 , 姜辉 , 等 . 工业机器人谐波减速器迟滞特性的神经网络建模 [J]. 光学 精密工程 , 2019 , 27 ( 3 ): 694 - 701 . doi: 10.3788/OPE.20192703.0694 http://dx.doi.org/10.3788/OPE.20192703.0694
DANG X J , WANG K L , JIANG H , et al . Neural network modeling of hysteresis for harmonic drive in industrial robots [J]. Opt. Precision Eng. , 2019 , 27 ( 3 ): 694 - 701 . (in Chinese) . doi: 10.3788/OPE.20192703.0694 http://dx.doi.org/10.3788/OPE.20192703.0694
李致富 , 黄楠 , 钟云 , 等 . 压电驱动器迟滞非线性的分数阶建模及实验验证 [J]. 光学 精密工程 , 2020 , 28 ( 5 ): 1124 - 1131 .
LI ZH F , HUANG N , ZHONG Y , et al . Fractional order modeling and experimental verification of hysteresis nonlinearities in piezoelectric actuators [J]. Opt. Precision Eng. , 2020 , 28 ( 5 ): 1124 - 1131 . (in Chinese)
杨晓京 , 胡俊文 , 李庭树 . 压电微定位台的率相关动态迟滞建模及参数辨识 [J]. 光学 精密工程 , 2019 , 27 ( 3 ): 610 - 618 . doi: 10.3788/ope.20192703.0610 http://dx.doi.org/10.3788/ope.20192703.0610
YANG X J , HU J W , LI T SH . Rate-dependent dynamic hysteresis modeling of piezoelectric micro platform and its parameter identification [J]. Opt. Precision Eng. , 2019 , 27 ( 3 ): 610 - 618 . (in Chinese) . doi: 10.3788/ope.20192703.0610 http://dx.doi.org/10.3788/ope.20192703.0610
孙中梁 , 崔玉国 , 刘康 , 等 . 采用变间隔阈值PI模型的压电平台前馈控制 [J]. 压电与声光 , 2017 , 39 ( 3 ): 374 - 377 .
SUN ZH L , CUI Y G , LIU K , et al . Feedforward control of a piezoelectric stage using variable-interval threshold PI model [J]. Piezoelectrics & Acoustooptics , 2017 , 39 ( 3 ): 374 - 377 . (in Chinese)
AN D , LI H D , XU Y , et al . Compensation of hysteresis on piezoelectric actuators based on tripartite PI model [J]. Micromachines , 2018 , 9 ( 2 ): 44 . doi: 10.3390/mi9020044 http://dx.doi.org/10.3390/mi9020044
刘宽 , 赵梓舒 , 武文华 , 等 . 宏纤维复合材料MFC作动器迟滞非线性分析与补偿方法研究 [J]. 机械工程学报 , 2019 , 55 ( 14 ): 178 - 185 . doi: 10.3901/jme.2019.14.178 http://dx.doi.org/10.3901/jme.2019.14.178
LIU K , ZHAO Z SH , WU W H , et al . Hysteresis nonlinear analysis and its compensation method of MFC actuator [J]. Journal of Mechanical Engineering , 2019 , 55 ( 14 ): 178 - 185 . (in Chinese) . doi: 10.3901/jme.2019.14.178 http://dx.doi.org/10.3901/jme.2019.14.178
YEKTA P V , HONAR F J , FESHARAKI M N . Modelling of hysteresis loop and magnetic behaviour of Fe-48Ni alloys using artificial neural network coupled with genetic algorithm [J]. Computational Materials Science , 2019 , 159 : 349 - 356 . doi: 10.1016/j.commatsci.2018.12.025 http://dx.doi.org/10.1016/j.commatsci.2018.12.025
LI S , YANG X J , LI Y , et al . Research on modelling of piezoelectric micro-positioning stage based on PI hysteresis model [J]. The Journal of Engineering , 2019 , 2019( 13 ): 437 - 441 . doi: 10.1049/joe.2018.8978 http://dx.doi.org/10.1049/joe.2018.8978
蔡永根 , 崔玉国 , 赵余杰 , 等 . 采用改进PI迟滞模型的压电微夹钳前馈控制 [J]. 宁波大学学报(理工版) , 2017 , 30 ( 6 ): 53 - 58 . doi: 10.3969/j.issn.1001-5132.2017.06.010 http://dx.doi.org/10.3969/j.issn.1001-5132.2017.06.010
CAI Y G , CUI Y G , ZHAO Y J , et al . Feedforward control of a piezoelectric microgripper using improved PI hysteresis model [J]. Journal of Ningbo University (Natural Science & Engineering Edition) , 2017 , 30 ( 6 ): 53 - 58 . (in Chinese) . doi: 10.3969/j.issn.1001-5132.2017.06.010 http://dx.doi.org/10.3969/j.issn.1001-5132.2017.06.010
BHORE K , SONDKAR S . Identification of Prandtl-ishlinskii hysteresis model and its inverse for varying hysteresis nonlinearities [C]. 2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC). 34,2018 , Shah Alam, Malaysia. IEEE , 2018 : 69 - 74 . doi: 10.1109/icsgrc.2018.8657636 http://dx.doi.org/10.1109/icsgrc.2018.8657636
WANG Y F , XU R , ZHOU M L . Prandtl-ishlinskii modeling for giant magnetostrictive actuator based on internal time-delay recurrent neural network [J]. IEEE Transactions on Magnetics , 2018 , 54 ( 11 ): 1 - 4 . doi: 10.1109/tmag.2018.2827397 http://dx.doi.org/10.1109/tmag.2018.2827397
ALATAWNEH N , JANAIDEH MAL . A frequency-dependent Prandtl-ishlinskii model of hysteresis loop under rotating magnetic fields [J]. IEEE Transactions on Power Delivery , 2019 , 34 ( 6 ): 2263 - 2265 . doi: 10.1109/tpwrd.2019.2917623 http://dx.doi.org/10.1109/tpwrd.2019.2917623
范伟 , 傅雨晨 , 于欣妍 . 压电陶瓷驱动器的迟滞非线性规律 [J]. 光学 精密工程 , 2019 , 27 ( 8 ): 1793 - 1799 . doi: 10.3788/ope.20192708.1793 http://dx.doi.org/10.3788/ope.20192708.1793
FAN W , FU Y CH , YU X Y . Hysteresis nonlinear law of piezoelectric ceramic actuator [J]. Opt. Precision Eng. , 2019 , 27 ( 8 ): 1793 - 1799 . (in Chinese) . doi: 10.3788/ope.20192708.1793 http://dx.doi.org/10.3788/ope.20192708.1793
0
Views
903
下载量
2
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution