基于HHT和AR模型的数据预测方法研究  

The Data Prediction Methods Based on Hilbert-Huang Transform and AR Mode

作　　者：王秋生[1] 崔勇[1] 袁海文[1] 

机构地区：[1]北京航空航天大学自动化科学与电气工程学院,北京100083

出　　处：《电子测量与仪器学报》2008年第S2期8-12,共5页Journal of Electronic Measurement and Instrumentation

基　　金：国家自然科学基金资助项目(编号:60504023)

摘　　要：希尔伯特-变换黄是分析非平稳信号的有效方法,已在信号分析与处理领域得到了广泛应用。希尔伯特-黄变换以经验模态分解为基础,能够将非平稳信号分解成为若干个固有模态分量和一个残余分量。本文提出的基于经验模态分解的数据预测方法,是利用经验模态分解得到的残余分量、并结合AR模型的算法优势,实现对非平稳数据的有效预测。本文利用三种不同的典型数据进行仿真验证,实验结果验证了所提出预测方法的有效性,并给出了影响预测性能的主要因素。Hilbert-Huang Transform is one of the effective methods to analysis non-stationary signal. It has been widely used in signal analysis and processing domain. Hilbert-Huang Transform is based on Empirical Mode Decomposition. It can decompose one signal into several intrinsic mode functions and one residue component. The data predictive algorithm based on empirical mode decomposition is proposed in this paper. It uses AR mode to analysis residue component to implement data prediction. Three types of data are used in simulation to verify the presented algorithm. The results validate the effectiveness of the algorithm and the influencing factors are analyzed for predictive effectiveness.

关 键 词：希尔伯特-黄变换 AR模型 数据预测 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]