不确定非线性系统神经网络自适应控制

针对一类不确定非线性系统,利用神经网络可逼近任意非线性函数的能力,以及误差滤波理论,提出了一种基于径向基神经网络的自适应控制器设计方案,以使非线性系统在存在不确定项或受到未知干扰时,其输出为期望输出.根据Lyapunov理论,给出了系统稳定的充分条件,并进行了详细证明.该设计方法能够保证跟踪误差收敛,从而进一步说明该控制器的有效性.最后,用Sumulink对设计方案进行仿真,仿真结果表明了其实用性.

Neural Network Adaptive Control for Uncertain Nonliear Systems

Based on the capability of neural networks to approach any nonlinear function,combined with Error Filtering theory,for a class of uncertain nonlinear system,a radial basis function based neural network adaptive control scheme is proposed.The control purpose is that the output of nonlinear system is the desired output when the nonlinear system has uncertain factor or disturbance.A sufficient condition for the stability of the nonliear system is given,which had been proven by Lyapunov theory.This scheme guarantees the convergence to the tracking error.It indicates that the controller is effectual.The result of simulink shows the practicability of the controller.