基于径向基函数神经网络滑模控制的运动控制系统

Radial Basis Function Neural Network Sliding Mode Control for Motion Control System

针对运动控制系统的非线性动态摩擦力,为提高系统的位置跟踪精度,利用一种径向基函数(RBF)神经网络滑模控制方法。采用一种具有指数形式的非线性摩擦力,利用径向基函数神经网络在线估计系统的不确定动力学,利用李亚普诺夫稳定性理论推导出网络权值的在线自适应律。仿真结果表明了该控制策略的有效性。

A radial basis function （RBF） neural network sliding mode method was used to compensate nonlinear dynamic friction that existed in motion control system and to improve the system position tracking performance. A kind of exponential type friction was adopted, and a radial basis function neural work estimator was proposed to estimate the uncertain system dynamics on-line, the parameter on-line adaptive laws were derived in the sense of Lyapunov stability theorem. Simulation results show the validity of proposed RBF neural network sliding mode control method.