摘要
以带有有色噪声的CARMA模型为例,分析了在干扰项参数辨识当中,误差较大的原因以及影响辨识误差的因素,并利用二次辨识的思想提出了一种提高辨识精度的方法.通过此方法并结合一个具体实例,给出了Matlab仿真辨识的结果.仿真结果表明,经过二次辨识的参数更接近真实值.
The paper uses CARMA model as an example, and analyses the reason of error of noise disturbance parameter identification and the factor that influences identification error. Then introduce a method to improve the precision of identification based on the idea of twice identification. Besides, the paper makes use of the method in an example and gives Matlab emulation identification results. The results display that the parameters are more close to real value after twice identification.
出处
《昆明理工大学学报（理工版）》
北大核心
2009年第6期49-52,共4页
Journal of Kunming University of Science and Technology(Natural Science Edition)
关键词
参数估计
最小二乘
二次辨识
parameter identification
least - squares
twice identification
