不确定关节机器人模型的神经网络补偿自适应控制

钟斌

doi:10.13433/j.cnki.1003-8728.2017.0308

不确定关节机器人模型的神经网络补偿自适应控制

doi: 10.13433/j.cnki.1003-8728.2017.0308

钟斌

1.
中国人民武装警察部队工程大学装备工程学院, 西安 710086

基金项目:

国家自然科学基金项目（51005246）资助

详细信息

作者简介:
钟斌(1975-),副教授,博士,研究方向为机电系统智能控制及其自动化、军事装备理论及其应用等,zhongbinchina@163.com

计量
- 文章访问数: 232
- HTML全文浏览量: 34
- PDF下载量: 17
- 被引次数: 0
出版历程
- 收稿日期: 2015-08-28
- 刊出日期: 2017-03-05

Adaptively Controlling Neural Network Compensation with Uncertain Joint Robot Model

Zhong Bin

1.
Equipment Engineering College, Engineering University of Chinese Armed Police Force, Xi'an 710086, China

摘要

摘要: 为了达到关节机器人轨迹跟踪控制的目的，针对由于机器人结构参数、作业环境干扰及结构共振模式等不确定性因素造成的机器人不确定性动力学模型，将该模型分解为名义模型和建模误差两部分，其中的建模误差采用RBF神经网络进行补偿和估计，得到其估计信息。RBF神经网络的权值通过Lyapunov稳定性分析和自适应算法进行调节。机器人的神经网络补偿自适应控制解决了机器人这类不确定模型的轨迹跟踪控制问题。对3关节机器人实验验证结果表明，3关节均在约4 s时跟踪期望轨迹，并且跟踪误差渐近趋近于0，并且RBF神经网络能很好地逼近由不确定性因素引起的建模部分。
- 关节机器人 /
- 不确定模型 /
- RBF神经网络 /
- 自适应权值调整
Abstract: In order to achieve the trajectory tracking control of a joint robot, because an uncertain joint robot's structural parameters cause a dynamic model's modeling errors and interfere with the working environment and the uncertain joint robot's resonant mode, the joint robot's dynamic model was divided into nominal model and error model. The error model was compensated by the RBF neural network, thus obtaining its estimation information. The neural network's output weights were adjusted adaptively according to the Lyapunov stability theory. The joint robot's adaptive neural network controller was used to solve the problems for the uncertain joint robot's dynamic system. Besides, the controller can gradually and stably track the desired trajectory though defining the Lyapunov function, being used to control a three-joint robot's torque. All the three joints can track the desired trajectory in 4 s. Tracking errors can gradually approach 0. Simulation and experimental results show that the RBF neural network can favorably approach modeling errors caused by uncertainties.
- uncertain joint robot /
- modeling error /
- RBF neural network /
- output weight

HTML全文

参考文献(15)

[1]	宁学涛,潘玉田,杨亚威,等.基于运动学和动力学的关节空间轨迹规划[J].计算机仿真,2015,32(2):409-413 Ning X T, Pan Y T, Yang Y W, et al. Joint space trajectory planning of python-based delta robot[J]. Computer Simulation, 2015,32(2):409-413(in Chinese)
[2]	雷霆,张国良,羊帆,等.基于观测器的空间机器人神经自适应鲁棒控制[J].计算机仿真,2015,32(3):370-374 Lei T, Zhang G L, Yang F, et al. Neural network adaptive robust control of space robot based on observer[J]. Computer Simulation, 2015,32(3):370-374(in Chinese)
[3]	Li Z J, Zhang Y N, Yang Y P. Support vector machine optimal control for mobile wheeled inverted pendulums with unmodelled dynamics[J]. Neurocomputing, 2011,73(13-15):2773-2782
[4]	印峰,王耀南,夏汉民.多个关节机器人逆运动学问题的实时求解[J].中国机械工程,2010,21(10):1143-1148 Yin F, Wang Y N, Xia H M. Real-time solution of inverse kinematics problem of multi-joint robots[J]. China Mechanical Engineering, 2010,21(10):1143-1148(in Chinese)
[5]	李雪琴,殷国富,刘爽,等.基于雅可比矩阵分析法的多关节机器人机构设计技术研究[J].四川大学学报(工程科学版),2011,43(S1):252-256 Li X Q, Yin G F, Liu S, et al. Research on the mechanism design of multi-joint robot by the analysis of Jacobian matrix[J]. Journal of Sichuan University (Engineering Science Edition), 2011,43(S1):252-256(in Chinese)
[6]	田慧慧,苏玉鑫.机器人系统输出反馈重复学习轨迹跟踪控制[J].控制与决策,2012,27(11):1756-1760 Tian H H, Su Y X. Global asymptotic stable repetitive output feedback tracking control of robot manipulators[J]. Control and Decision, 2012,27(11):1756-1760(in Chinese)
[7]	Banerjee A, Bhattacharya B, Mallik A K. Large deflection of cantilever beams with geometric non-linearity:analytical and numerical approaches[J]. International Journal of Non-Linear Mechanics, 2008,43(5):366-376
[8]	胡盛斌,陆敏恂.多个关节机器人反馈线性化双模糊滑模控制[J].机械科学与技术,2013,32(1):105-110,115 Hu S B, Lu M X. Feedback linearization double fuzzy sliding mode control for multi-links robot[J]. Mechanical Science and Technology for Aerospace Engineering, 2013,32(10):105-110,115(in Chinese)
[9]	Islam S, Liu P X. Robust adaptive fuzzy output feedback control system for robot manipulators[J]. IEEE/ASME Transactions on Mechatronics, 2011,16(2):288-296
[10]	罗召成,朱世强,王会方.机器人自适应PID饱和输出反馈控制[J].传感器与微系统,2012,31(3):66-70 Luo S C, Zhu S Q, Wang H F. Adaptive PID saturate output feedback control of robot manipulators[J]. Transducer and Microsystem Technologies, 2012,31(3):66-70(in Chinese)
[11]	许可诚,顾寄南,王富良.换刀机械手控制系统的设计与研究[J].机械设计与制造,2011,(8):158-160 Xu K C, Gu J N, Wang F L. Design and research of control system for tool changing manipulator[J]. Machinery Design & Manufacture, 2011,(8):158-160(in Chinese)
[12]	王凤利,冯亚磊,董吉顺,等.基于Kane方法的关节机器人举升机构的动力学分析[J].组合机床与自动化加工技术,2011,(1):30-32 Wang F L, Feng Y L, Dong J S, et al. Dynamics analysis of clean room robot's lifting mechanism based on Kane method[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2011,(1):30-32(in Chinese)
[13]	Delavari H, Ghaderi R, Ranjbar A, et al. Fuzzy fractional order sliding mode controller for nonlinear systems[J]. Communications in Nonlinear Science and Numerical Simulation, 2010,15(4):963-978
[14]	Oda M. Space robot experiments on NASDA'S ETS-VⅡ satellite-preliminary overview of the experiment results[C]//IEEE International Conference on Robotics and Automation, Piscataway, NJ, USA:IEEE, 1999:1390-1395
[15]	Harmon F G, Frank A A, Joshi S S. The control of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle using a CMAC neural network[J]. Neural Networks, 2005,18(5-6):772-780