参数不确定柔性机械手的神经滑模控制  

Neural Sliding Mode Control for Flexible Manipulators with Uncertain Parameters

作　　者：张袅娜[1] 

机构地区：[1]长春工业大学自动化系,长春130012

出　　处：《机械工程学报》2011年第1期31-35,42,共6页Journal of Mechanical Engineering

基　　金：国家自然科学基金资助项目(60474016)

摘　　要：通过重新定义系统的输出,将具有不确定性参数的柔性机械手系统分成输入输出子系统与零动态子系统。对输入输出子系统提出神经滑模控制策略,通过满足滑模可达条件对径向基函数(Radial basis function,RBF)神经网络的权值进行在线修正,以逼近系统的非奇异终端滑模控制输入,该方法可有效消除抖振;重新定义的系统输出中的系数,通过将零动态子系统在稳定工作点附近的近似线性化来选取。仿真试验结果表明,该方法实现了柔性机械手点到点的准确控制,消除了柔性机械手末端的弹性振动。The system is decomposed into the input-output subsystem and the zero dynamics subsystem for flexible manipulators with uncertain parameters through the output of manipulators system is redefined.The neural sliding mode control strategy is proposed for the input-output subsystem.The weights of the radial basis function（RBF） neural network is adjusted online to meet sliding mode arrived conditions.It can guarantee the output of the network to close approach insingular non-singular terminal sliding mode control input of the system and avoid chattering phenomenon.The zero dynamics subsystem is approximation approximately linearizred at nearby the equilibrium point to select the design control parameters.Computer Ssimulation and experiment results demonstrate that the controller design method presented herefulfills the accurate control from point to point and vibration damping can be accomplished.control of the flexible manipultor,and the elastic vibration at the end of flexible manipulator is eliminated.

关 键 词：柔性机械手 非奇异终端滑模 神经网络 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]