基于RBF神经网络手术机器人从手控制系统研究

详细信息    查看全文 | 推荐本文 |

英文篇名：Research on Slave-hand Control System of Surgical Robot Based on RBF Neural Network 作者：张禹 ; 杨铭 英文作者：ZHANG Yu;YANG Ming;Institute of Mechanical Engineering,Shenyang University of Technology; 关键词：手术机器人 ; RBF神经网络 ; 模型分块逼近 ; 自适应控制 英文关键词：Surgical robot;;RBF neural network;;Model block approximation;;Adaptive control 中文刊名：JCYY 英文刊名：Machine Tool & Hydraulics 机构：沈阳工业大学机械工程学院; 出版日期：2019-05-15 出版单位：机床与液压 年：2019 期：v.47;No.483 基金：沈阳市机器人及智能制造装备重点实验室建设(F13-297-1-00) 语种：中文; 页：JCYY201909013 页数：5 CN：09 ISSN：44-1259/TH 分类号：70-74

摘要

以手术机器人的从手为研究对象,使用径向基函数(RBF)神经网络对手术机器人从手进行基于模型分块逼近的自适应控制。针对手术机器人从手动力学模型建模不准确的问题,采用RBF神经网络分别对从手动力学模型中的3个系数矩阵分块逼近,计算出从手的精确动力学模型,同时动态调整控制律实现对系统的稳定自适应控制。在系统稳定性分析的基础上,进行了仿真实验。实验结果表明:该控制算法改进了系统控制性能,具有精度高、稳定性好、鲁棒性强的特点。
        Taking surgical robot slave-hand as research object, adaptive control based on block approximation was completed to the surgical robot slave-hand based on radial basis function(RBF) neural network. Aiming at the inaccurate modeling for the surgical robot slave-hand, RBF neural network was used to segment the three coefficients matrixes from the slave-hand mechanics model respectively, and the actual dynamics model of the slave-hand was obtained. At the same time,control law was adjusted dynamically to achieve stable and adaptive control of the system. Based on the stability analysis of the algorithm, the simulation experiment was completed. Experimental results show that the proposed control algorithm improves the system control performance and has the characteristics of high precision, good stability and strong robustness.

引文

[1] DEACON G,HARWOOD A,HOLDBACK J,et al.The Pathfinder Image-guided Surgical Robot[J].Journal of Engineering in Medicine,2010,224(5):691-713.
    [2] MITSUISHI M,IIZUKA Y,WATANABE H,et al.Remote Operation of a Micsurgical System[C]//Proceedings of the IEEE International Conference on Robotics and Automation.Piscataway NJ USA:IEEE,1998:1013-1019.
    [3] 陈志煌,陈力.闭链双臂空间机器人抓持载荷基于径向基函数神经网络的补偿控制[J].机械工程学报,2011,47(7):38-44.CHEN Z H,CHEN L.Compensation Control for Grasped Object of Dual-arm Space Robot with Closed-chain Based on Radial Basis Function Neural Network[J].Journal of Mechanical Engineering,2011,47(7):38-44.
    [4] 俞建成,李强,张艾群,等.水下机器人的神经网络自适应控制[J].控制理论与应用,2008,25(1):9-13.YU J C,LI Q,ZHANG A Q,et al.Neural Network Adaptive Control for Underwater Vehicles[J].Control Theory and Application,2008,25(1):9-13.
    [5] 彭济根,倪元华,乔红.柔性关节机操手的神经网络控制[J].自动化学报,2007,33(2):175-180.PENG J G,NI Y H,QIAO H.Neural Network Control of Flexible-joint Robot Manipulators[J].ACTA Automatica Sinica,2007,33(2):175-180.
    [6] WAI R J.Tracking Control Based on Neural Network Strategy for Robot Manipulator[J].Neurocomputing,2003,51:425-445.
    [7] CRAIG J J.机器人学导论[M].北京:机械工业出版社,2006.
    [8] 刘金琨.机器人控制系统的设计与MATLAB仿真[M].北京:清华大学出版社,2008.
    [9] 任斌,程良伦.李雅普诺夫稳定性理论中V函数的构造研究[J].自动化与仪器仪表,2009(2):8-10.REN B,CHENG L L.The Structure of V Function in Lyapunov’s Stableness Theory[J].Automation & Instrumentation,2009(2):8-10.
    [10] 姚世锋,薛德庆,张彦斌,等.LabVIEW与Matlab的混合编程[J].兵工自动化,2005(6):111-112.YAO S F,XUE D Q,ZHANG Y B,et al.Method of Hybird Programming with LabVIEW and Matlab[J].Ordnance Industry Automation,2005(6):111-112.
    [11] 裴锋,杨万生.LabVIEW与MATLAB混合编程[J].电子技术应用,2004,30(3):4-6.