基于RBF神经网络的非线性系统对象辨识

Object Identification of Non-linear System Based on RBF Netual Network

被控对象数学模型的精确建立是控制理论研究和发展的重要基础,但在实际工况中的控制系统多为复杂的非线性系统,因此高精度的非线性系统辨识技术显得至关重要。RBF神经网络具有对任意非线性函数逼近的能力,于是设计将RBF神经网络技术运用到系统辨识中,并通过Matlab仿真基于RBF神经网络对给定复杂非线性系统的辨识。仿真结果表明在对于复杂非线性系统的辨识上,基于RBF神经网络的系统辨识法是准确可行的。

The establishment of accurate mathematical model of the controlled object is an important basis for the research and development of control theory,however,most of the control systems in actual working conditions are complex non-linear systems,therefore,high-precision non-linear system identification technology is very important.The RBF neural network has the ability to approximate non-linear functions,so the RBF neural network is designed to be used in system identification,and the given complex non-linear system is identified based on the neural network through Matlab simulation.Simulation results show that system identification based on RBF neural network is accurate and feasible for the identification of complex non-linear system.