基于小波网络的非线性系统辨识研究

小波网络为非线性系统辨识研究提供了一种有效的方法,但目前用于小波网络学习的进化算法易陷入局部极小等缺陷.结合生物免疫系统的概念和理论,在非线性系统辨识中引入基于免疫算法的小波网络.该算法中抗体通过浓度相互作用的机制来促进或抑制抗体的生成,借此保持抗体的多样性,并产生了高亲和力的抗体对种群进行不断的更新,提高了算法的全局搜索能力和收敛速度.最后,把基于免疫算法的小波网络用于一个非线性系统辨识的标准实例中,仿真结果验证了该算法的有效性.

Research on Nonlinear System Identification based on Wavelet Networks

Wavelet networks provide solid foundation for nonlinear system identification.As the evolutionary algorithms for wavelet networks often settle in local minimum of the error,an immune algorithm(IA) learning algorithm of wavelet networks based on the biological immune system is set up for nonlinear system identification.The IA uses the interaction mechanism based on density of antibodies to keep the diversity of antibodies,and improve the global search ability and convergence speed.Finally,the IA based wavelet networks is applied to nonlinear system identification,and the results show that the Immune Algorithm can greatly improve the convergence and achieve higher accuracy.