摘要
从利用高阶累积量对加性高斯有色噪声中非高斯过程辨识的基本理论出发 ,对近年来基于高阶统计量方法辨识非高斯、非最小相位 ARMA模型的算法进行了分析和综述 ,阐明了借助高阶统计量方法可以克服传统的基于2阶统计量方法在解决此类问题中的缺陷 ,有效地解决非高斯。
This paper begins with the theory of identification of non Gaussian process in additive colored Gaussian noise, then analyses and reviews the cumulant methods to identify non Gaussian and non minimum phase ARMA model, which have been developed during recent years. By means of higher order cumulants, the identification of non Gaussian process and non minimum phase system are effective , which can overcome drawbacks of all the traditional methods based on second order statistics in this area.
出处
《上海大学学报（自然科学版）》
CAS
CSCD
2001年第5期438-441,453,共5页
Journal of Shanghai University:Natural Science Edition
