基于SaS过程的分数低阶时频自回归滑动平均模型参数估计及时频分布  

Parameter Estimation and Time-frequency Distribution of Fractional Lower Order Time-frequency Auto-regressive Moving Average Model Algorithm Based on SaS Process

作　　者：龙俊波[1] 汪海滨[2] 

机构地区：[1]九江学院电子工程学院,九江332005 [2]九江学院信息科学与技术学院,九江332005

出　　处：《电子与信息学报》2016年第7期1710-1716,共7页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(61261046;61362038);江西省自然科学基金(20142BAB207006);江西省教育厅科技基金(GJJ14738;GJJ14739)~~

摘　　要：针对SaS过程下时频自回归滑动平均(TFARMA)模型分析方法的退化,该文用分数低阶共变取代二阶相关提出了分数低阶时频自回归滑动平均(FLO-TFARMA)模型的概念,并推导了模型参数的求解方法。在此基础上,给出了FLO-TFARMA模型时频谱估计算法,和已有的TFARMA模型时频谱算法进行了详细的比较。计算机仿真结果表明,在SaS过程环境下,所提出的FLO-TFARMA时频谱明显优于TFARMA时频谱,尤其是当参数a较小时,FLO-TFARMA时频谱优势更明显。The performances of Time-Frequency Auto-Regressive Moving Average（TFARMA） model method degenerate under SaS distribution environment. Hence, Fractional Lower Order Time-Frequency AutoRegressive Moving Average（FLO-TFARMA） model algorithm based on fractional lower order covariant is proposed, the parameters estimation of FLO-TFARMA model is introduced, time-frequency distribution based on FLO-TFARMA model is given, FLO-TFARMA model algorithm are compared with the existing TFARMA algorithm in detail. The simulation results show that FLO-TFARMA model method have better performance than TFARMA model method under SaS distribution environment, and the time-frequency spectrum of FLOTFARMA method is more obvious when the parameter a is smaller.

关 键 词：信号处理 a稳定分布 非平稳信号 时频分布 自回归滑动平均 尤拉沃克方程 

分 类 号：TN911.7[电子电信—通信与信息系统]