论文部分内容阅读
使用小波神经网络分别逼近对象模型和逆模型,并对原非线性系统及其逆模型组成的伪线性系统采用内模控制理论,基于逆系统方法进行控制。当系统的建模误差满足线性增长条件时,分析了小波神经网络内模控制系统的鲁棒性和稳定性,当系统的建模误差不满足线性增长条件时,应用波波夫超稳定性理论分析了系统的鲁棒性。仿真结果表明小波神经网络内模控制系统是处理非线性问题比较有效的方法之一。
The wavelet neural network is used to approximate the object model and the inverse model respectively. The internal model control theory and the inverse system method are used to control the pseudo-linear system composed of the original nonlinear system and its inverse model. When the modeling error of the system satisfies the condition of linear growth, the robustness and stability of the internal model control system of the wavelet neural network are analyzed. When the modeling error of the system does not satisfy the linear growth condition, the application of the Popov super-stability theory The robustness of the system is analyzed. Simulation results show that the wavelet neural network model control system is one of the most effective methods to deal with nonlinear problems.