电子学报 ›› 2012, Vol. 40 ›› Issue (9): 1909-1912.DOI: 10.3969/j.issn.0372-2112.2012.09.034

• 科研通信 • 上一篇    

一种最小长度约束的EMD包络拟合方法

朱伟芳, 赵鹤鸣, 陈小平   

  1. 苏州大学电子信息学院, 江苏苏州 215006
  • 收稿日期:2011-08-05 修回日期:2012-05-17 出版日期:2012-09-25
    • 作者简介:
    • 朱伟芳 女,1977年10月出生于浙江省湖州市.讲师、博士研究生,主要研究领域为自适应信号分析方法、生物医学信号处理. E-mail:wfzhu@suda.edu.cn 赵鹤鸣 男,1957年8月出生于江苏省无锡市.教授、博士生导师,苏州大学电子信息学院院长,主要研究领域为语音信号处理、神经网络理论与应用.
    • 基金资助:
    • 国家自然科学基金 (No.61005047); 江苏省自然科学基金 (No.BK2010214)

A Least-Length Constrained Envelope Approach for EMD

ZHU Wei-fang, ZHAO He-ming, CHEN Xiao-ping   

  1. School of Electronics and Information Engineering, Soochow University, Suzhou, Jiangsu 215006, China
  • Received:2011-08-05 Revised:2012-05-17 Online:2012-09-25 Published:2012-09-25
    • Supported by:
    • National Natural Science Foundation of China (No.61005047); Natural Science Foundation of Jiangsu Province,  China (No.BK2010214)

摘要: 经典经验模态分解(Empirical Mode Decomposition,EMD)采用三次样条插值方法进行包络拟和,存在较严重的"过冲"现象。在研究该问题已有方法基础上,提出了一种基于最小长度约束的包络拟合方法,以包络曲线长度最小为目标函数,采用Lagrange求极小值法优化极值点处的导数值,然后采用分段三次Hermite函数插值方法进行包络拟合,得到平滑包络线.实验表明该方法能有效地克服三次样条插值法的"过冲"现象和分段抛物线插值法的人为弯折现象,能拟合出更平滑的包络线,使得EMD分解更准确,有效改善模态混淆问题.

关键词: 经验模态分解, 包络拟合, 最优化方法, 模态混淆

Abstract: In classic EMD,the envelopes fitted by cubic spline interpolation may often occur overshoots.In this paper,a new envelope fitting method based on the least-length constrained interpolation is proposed.Taking the length of the fitted envelope as the target function,Lagrange optimization method is used to optimize the derivatives of the interpolation nodes.With the optimized derivatives,piecewise Hermite interpolation method is used to fit the more smooth envelopes.The result of experiments proves that the new method can solve the overshoots caused by cubic spline interpolation and the artificial bends caused by piecewise parabola interpolation effectively and let the results of EMD more accurate.This method can overcome mode mixing well,which is one of the major drawbacks of the original EMD.

Key words: empirical mode decomposition, envelope fitting, optimization method, mode mixing

中图分类号: