基于径向基函数神经网络的机器人滑模控制

尽管滑模控制响应快,对系统参数和外部扰动呈不变性,但在保证系统的渐进稳定性上却存在很强的抖动缺点.因此,在一般滑模控制的基础上,引入了径向基函数神经网络(RBFNN).利用滑模控制的特点设定目标函数,将切换函数作为RBFNN的输入,滑模控制量作为其输出.利用RBF神经网络的在线学习功能,消除了控制的抖动,同时使系统具有很强的鲁棒性.对两连杆机械手进行了仿真研究,其结果表明,在存在模型误差和外部扰动的情况下,该方案既能达到高精度快速跟踪的目的,又能消除滑模控制的抖动问题.

RBFNN-based Sliding Mode Control for Robot

To the problem that the sliding mode control can assure the asymptotic stability of system,but has strong chatterings of control,the radial basis function neural network(RBFNN) is introduced to the common sliding mode control.The switching function is regarded as the input of RBFNN while the output is sliding mode controller.The object function is set by using the characteristic of sliding mode control.The system eliminates the chatterings of control and has strong robust by using the learning function of neural network.The results of simulation about a two-link robotic manipulator show that the scheme can achieve tracking effect with high precision and speediness,as well as eliminate chatterings under the condition of existing model error and external disturbance.