气动肌肉的最小二乘支持向量机迟滞模型

谢胜龙; 任国营; 谢胜龙; 张文欣; 鲁玉军; 张为民; 朱俊江; 林立; 任国营

doi:10.3969/j.issn.1000-1158.2020.04.009

PDF(1445 KB)

计量学报 ›› 2020, Vol. 41 ›› Issue (4) : 441-447. DOI: 10.3969/j.issn.1000-1158.2020.04.009

力学计量

气动肌肉的最小二乘支持向量机迟滞模型

谢胜龙^1,2,3,4, 张文欣², 鲁玉军⁴, 张为民², 朱俊江¹, 林立⁵, 任国营³

作者信息 +

The Hysteresis Modeling of Pneumatic Muscle Based on Least Squares Support Vector Machine Approach

XIE Sheng-long^1,2,3,4, ZHANG Wen-xin², LU Yu-jun⁴, ZHANG Wei-min², ZHU Jun-jiang¹, LIN Li⁵, REN Guo-yin³

Author information +

文章历史 +

摘要

针对传统迟滞模型存在的待辨识参数多、参数辨识过程复杂和辨识精度低等问题,采用最小二乘支持向量机对气动肌肉的位移/气压迟滞开展建模研究。通过非线性映射将原始数据空间映射到高维空间,将原系统的非线性问题变成高维空间中的线性问题,借助于最小二乘法求解该线性方程组,从而提高其求解速度及收敛精度。在气动肌肉迟滞特性实验的基础上,采用所建数学模型,与经典的PI模型进行对比。结果表明,采用最小二乘支持向量机建立的数学模型具有更高的建模精度,均方差和平均误差相比PI模型分别减小了99.21%和99.1%,该方法可为后续气动肌肉的迟滞补偿控制提供有效的手段。

Abstract

The traditional hysteresis modeling methods have series problems such as many parameters to be identified, complex parameter identification process and low identification accuracy, thus the least squares support vector machine (LS-SVM) approach is proposed to characterize the hysteresis phenomenon of pneumatic muscle(PM). The method maps the original data space to the high-dimensional space by non-linear mapping, thus the non-linear problem of the original system is transformed into a linear problem in the high-dimensional space, the least square method is used to solve the system of linear equations, which improves the speed of solution and convergence accuracy. Based on the experiments, the mathematical model of displacement/pressure hysteresis on PM was established by using LS-SVM method, the calculation results showed that the mathematical model established by LS-SVM has higher modeling accuracy and various error indices such as mean variance and mean error are significantly reduced, which reduce 99.21% and 99.1% respectively compared with the classical PI model. The method providing an effective means for subsequent hysteresis compensation control of PM.

导出引用

谢胜龙, 张文欣, 鲁玉军, 张为民, 朱俊江, 林立, 任国营. 气动肌肉的最小二乘支持向量机迟滞模型[J]. 计量学报. 2020, 41(4): 441-447 https://doi.org/10.3969/j.issn.1000-1158.2020.04.009

XIE Sheng-long, ZHANG Wen-xin, LU Yu-jun, ZHANG Wei-min, ZHU Jun-jiang, LIN Li, REN Guo-yin. The Hysteresis Modeling of Pneumatic Muscle Based on Least Squares Support Vector Machine Approach[J]. Acta Metrologica Sinica. 2020, 41(4): 441-447 https://doi.org/10.3969/j.issn.1000-1158.2020.04.009

中图分类号： TP931

参考文献

1 李铁风, 李国瑞, 梁艺鸣, 等. 软体机器人结构机理与驱动材料研究综述［J］. 力学学报, 2016, 48 (4): 756-766. LiT F, LiG R, LiangY M, et al. Review of materials and structures in soft robotics［J］. Chinese Journal of Theoretical and Applied Mechanics, 2016, 48 (4): 756-766.
2 王田苗, 郝雨飞, 杨兴帮, 等. 软体机器人: 结构、驱动、传感与控制［J］. 机械工程学报, 2017, 53 (13): 1-13. WangT M, HaoY F, YangX B, et al. Soft robotics: structure, actuation, sensing and control［J］. Journal of Mechanical Engineering, 2017, 53 (13): 1-13.
3 范伟, 林瑜阳, 李钟慎. 基于BP神经网络的压电陶瓷蠕变预测［J］. 计量学报, 2017, 38 (4): 429-434. FanW, LinY Y, LiZ S. Prediction of the creep of piezoelectric ceramic based on BP neural network optimized by genetic algorithm［J］. Acta Metrologica Sinica, 2017, 38 (4): 429-434.
4 谢胜龙, 刘海涛, 梅江平. 气动人工肌肉迟滞-蠕变特性研究现状与进展［J］. 系统仿真学报, 2018, 30 (3): 809-823. XieS L, LiuH T, MeiJ P. Achievements and developments of hysteresis and creep of pneumatic artificial muscles［J］. Journal of System Simulation, 2018, 30 (3): 809-823.
5 姜宁, 姚恩涛, 邹华章, 等. 基于智能气缸的功能可配置机械手的设计［J］. 计量学报, 2018, 39 (2): 173-177. JiangN, YaoE T, ZhouH Z, et al. A excogitation of function configurable manipulator based on the intelligent cylinder［J］. Acta Metrologica Sinica, 2018, 39 (2): 173-177.
6 Vo-MinhT, TjahjowidodoT, RamonH, et al. A new approach to modeling hysteresis in a pneumatic artificial muscle using the Maxwell-Slip model［J］. IEEE/ASME Transactions on Mechatronics, 2011, 16 (1): 177-186.
7 于海涛, 郭伟, 谭宏伟, 等. 基于气动肌腱驱动的拮抗式仿生关节设计与控制［J］. 机械工程学报, 2012, 48 (17): 1-9. YuH T, GuoW, TanH W, et al. Design and control on antagonistic bionic joint driven by pneumatic muscles actuators［J］. Journal of Mechanical Engineering, 2012, 48 (17): 1-9.
8 ZhaoJ, ZhongJ, FanJ. Position control of a pneumatic muscle actuator using RBF neural network tuned PID controller［J］. Mathematical Problems in Engineering, 2015,2015: Article ID 810231.
9 ZhongJ, FanJ, ZhuY, et al. One nonlinear PID control to improve the control performance of a manipulator actuated by a pneumatic muscle actuator［J］. Advances in Mechanical Engineering, 2014, 501 (8): 802-824.
10 AschemannH, SchindeleD. Comparison of model-based approaches to the compensation of hysteresis in the force characteristic of pneumatic muscles［J］. IEEE Transactions on Industrial Electronics, 2014, 61 (7): 3620-3629.
11 LinC J, LinC R, YuS K, et al. Hysteresis modeling and tracking control for a dual pneumatic artificial muscle system using Prandtl-Ishlinskii model［J］. Mechatronics, 2015, 28: 35-45.
12 谢胜龙, 梅江平, 刘海涛. McKibben型气动人工肌肉研究进展与趋势［J］. 计算机集成制造系统, 2018, 24 (5): 1065-1081. XieS L, MeiJ P, LiuH T. Achievements and trends of research on McKibben pneumatic artificial muscles［J］. Computer Integrated Manufacturing Systems, 2018, 24 (5): 1065-1081.
13 WongP K, XuQ S, VongC M, et al. Rate-dependent hysteresis modeling and control of a piezostage using online support vector machine and relevance vector ma-chine［J］. IEEE Transactions on Industrial Electronics, 2012, 59 (4): 1988-2001.
14 朱江淼,闫迪,高源,等. 基于改进EEMD和LSSVM的单频周跳探测与修复方法［J］. 计量学报, 2019, 40(3): 491-497. ZhuJ M,YanD,GaoY,et al. The Method for Single-frequency Cycle-slip Detection and Reparation Based on Modified EEMD and LSSVM［J］. Acta Metrologica Sinica, 2019, 40(3): 491-497.
15 张启忠,席旭刚,罗志增. 基于多源生物信号的下肢步态相识别［J］. 计量学报, 2018, 39(6): 895-901. ZhangQ Z,XiX G,LuoZ Z. Gait phase recognition based on multi-source biological signals［J］. Acta Metrologica Sinica, 2018, 39(6): 895-901.
16 XuQ S, WongP K. Hysteresis modeling and compensation of a piezostage using least squares support vector machines［J］. Mechatronics, 2011, 21 (7): 1239-1251.
17 朱大业, 丁晓红, 王神龙, 等. 基于支持向量机模型的复杂非线性系统试验不确定度评定方法［J］. 机械工程学报, 2018, 54 (8): 177-184. ZhuD Y, DingX H, WangS L, et al. Uncertainty evaluation method of complex nonlinear system test based on support vector machine model［J］. Journal of Mechanical Engineering, 2018, 54 (8): 177-184.
18 SuykensJ A K, VandewalleJ. Least squares support vector machine classifiers［J］. Neural Processing Letters,1999,9:293-300.
19 XuJ H, XiaoM B, DingY. Modeling and Compensation of Hysteresis for Pneumatic Artificial Muscles based on Gaussian Mixture Models［J］. Sci China Tech Sci, 2019, 62(7): 1094-1102.
20 张桂林, 张承进, 李康. 基于PI 迟滞模型的压电驱动器自适应辨识与逆控制［J］. 纳米技术与精密工程, 2013,11 (1): 85-89. ZhangG L, ZhangC J, LiK. Adaptive Identification and Inverse Control of Piezoelectric Actuators Based on PI Hysteresis Model［J］. Nanotechnology and Precision Engineering, 2013, 11 (1): 85-89.
21 XieS L, MeiJ P, LiuH T, et al. Hysteresis modeling and trajectory tracking control of the pneumatic muscle actuator using modified Prandtl-Shlinskii model［J］. Mechanism and Machine Theory, 2018, 120: 213-224.