非高斯系统的建模方法研究

On the Modeling of Non-Gaussian Systems

近年来，高阶统计信息理论被广泛应用于非高斯系统的建模问题中．由于高阶统计信息方法特殊的信息结构，难以充分利用具体问题中的统计分布信息，从而对该方法的应用效果产生了影响．针对这一问题，本文提出一种综合应用高阶统计信息理论与非高斯系统的似然函数指标的建模方法，为在非高斯系统建模问题中充分利用问题所提供的统计信息提供了新的途径．仿真研究和实际应用取得了令人满意的效果．

Higher-order statistics methods are widely used in the modelling of non-Gaussian systems inrecent years. Due to the specific information structure in the HOS methods, the statistical distribution information of the specific problems in applications can't be fully used. This problem has limited the application ofHOS theory. To overcome this difficulty, a new method based on HOS and the maximum-likelihood index ofthe interested system is proposed in this paper. This provides a method to utilize the specific information inapplications. Satisfactory results are obtained in simulations and applications.