基于混合进化策略的非线性系统辨识

Nonlinear System Identification Based on Hybrid Evolution Strategy

进化策略是一类适用于非线性、不可微和多峰值复杂函数的优化方法。提出了基于混合进化策略的非线性系统辨识方法。方法的基本思想是将非线性系统辨识问题转化为参数空间上的函数优化问题,然后应用一种新的混合进化策略对整个参数空间进行搜索以获得系统参数的最优估计。仿真结果显示了该方法的有效性。

Evolution strategies are a c lass of optimization methods which are applicable to functions that are nonlinea r,nondifferentiable and multimodal.A nonlinear system identification method ba sed on hybrid evolution strategy is proposed.The basic idea of the method is th at the problems of nonlinear system identification are cast as function optimiz ation over parameter space,and then a new hybrid evolution strategy is applied to search the parameter space in order to find the optimal estimation of the sys tem parameters.Simulation results show the feasibility of the method.