基于量子遗传算法的非线性系统辨识  

Identification of Nonlinear System Based on Quantum Genetic Algorithm

作　　者：张海丽[1] 张宏立[1] 

机构地区：[1]新疆大学电气工程学院,新疆乌鲁木齐830047

出　　处：《计算机仿真》2014年第3期359-362,共4页Computer Simulation

基　　金：自治区研究生科研创新项目资助(XJGRI2013033)

摘　　要：研究非线性系统的辨识问题,一直是现代辨识领域中的一个主要课题。针对非线性系统中Hammerstein模型,由于传统辨识方法对Hammerstein模型中非线性部分具有不易辨识的缺陷,提出了群集智能算法中的量子遗传算法对非线性系统进行辨识的方法。将参数辨识问题转化为参数空间上的函数优化问题,利用量子遗传算法获得优化问题的解。通过MATLAB仿真,并与遗传算法比较,结果表明,量子遗传算法不仅提高了辨识的寻优速度,而且获得了更精确的辨识效果,从而验证了该改进方法的有效性和可行性,为非线性系统辨识开拓了一种新方法。Nonlinear system identification is an main topic in modem identification fields. A new method of the Quantum Genetic Algorithm（QGA） for nonlinear system identification was presented in the paper. We changed the parameter identification problem into the function optimization problem on the parameter space, and the QGA was a- dopted to solve optimization problem. The MATLAB simulation software was used to carry out experiments. The re- suits were compared with the Quantum Genetic Algorithm, which shows that using the QGA can improve the speed and obtain better recognition results.

关 键 词：非线性系统模型 参数辨识 量子遗传算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]