论文部分内容阅读
研究了一类采样数据非线性系统的动态神经网络稳定自适应控制方法 .不同于静态神经网络自适应控制 ,动态神经网络自适应控制中神经网络用于逼近整个采样数据非线性系统 ,而不是动态系统中的非线性分量 .系统的控制律由神经网络系统的动态逆、自适应补偿项和神经变结构鲁棒控制项组成 .神经变结构控制用于保证系统的全局稳定性 ,并加速动态神经网络系统的逼近速度 .证明了动态神经网络自适应控制系统的稳定性 ,并得到了动态神经网络系统的学习算法 .仿真研究表明 ,基于动态神经网络的非线性系统稳定自适应控制方法较基于静态神经网络的自适应方法具有更好的性能
In this paper, we study a dynamic adaptive neural network approach to adaptive control of sampled-data nonlinear systems. Unlike static neural network adaptive control, neural networks in adaptive control of dynamic neural networks are used to approximate the entire sampled-data nonlinear system, rather than dynamic The nonlinear component of the system.The control law of the system consists of the dynamic inverse of the neural network system, the adaptive compensation term and the robust control term of the neural variable structure.The neural structure control is used to ensure the global stability of the system and accelerate the dynamic nerve The approximation speed of the network system.The stability of adaptive control system of dynamic neural network is proved and the learning algorithm of dynamic neural network system is obtained.The simulation results show that the method of steady adaptive control of nonlinear system based on dynamic neural network is more stable than that based on static Neural network adaptive method has better performance