经验模式分解回顾与展望

摘要/Abstract

摘要：

经验模式分解EMD打破了Fourier变换、小波分解等传统数据分析方法需要预先设定基函数的局限，是一种完全由数据驱动的自适应非线性非平稳时变信号分解方法，可以将数据从高频到低频分解成具有物理意义的少数几个固有模态函数分量和一个余量。首先介绍了原始EMD方法的原理和算法；接着，总结归纳了EMD当前的研究现状，分析了EMD存在的端点效应、模态混叠、运行速度问题及其在二维情况下的问题并对国内外学者解决这些问题的方法进行了概述和比较；最后结合EMD研究存在的难题指出了EMD进一步研究与应用的发展方向。

关键词: 经验模式分解, 固有模态函数, HilbertHuang变换

Abstract:

Empirical Mode Decomposition (EMD) is a totally datadriven and selfadaptive decomposition algorithm that is used to analyze nonlinear, nonstationary and timevarying signal, it breaks out the limitation of needing of presetting basis function for traditional data analysis method like Fourier transformation and wavelet decomposition, and it can decompose a signal into a few intrinsic mode function components with physical meaning and a residue from highfrequency to lowfrequency. Firstly, the principle and algorithm of the original EMD method are introduced. Secondly, we present an overview of the current development of EMD and analyze EMD's existing end effects, mode mixing, running speed problems and the problems that appeared when the original data are twodimensional and compared researchers' solutions to these problems. Finally, combined with its problems, several directions of further research and application are pointed out.

Key words: empirical mode decomposition(EMD);intrinsic mode function (IMF);HilbertHuang transform

毛玉龙，范虹. 经验模式分解回顾与展望[J]. J4, 2014, 36(01): 155-162.

MAO Yulong,FAN Hong. Review and prospects of empirical mode decomposition [J]. J4, 2014, 36(01): 155-162.

参考文献［55］

［1］	Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and nonstationary time series analysis［J］. Proceeding of the Royal Society of London A, 1998, 454(1971):903995.
［2］	Lei Y G, He Z J, Zi Y Y. Application of the EEMD method to rotor fault diagnosis of rotating machinery［J］. Mechanical Systems and Signal Processing, 2009, 23(4):13271338.
［3］	Parey A, Rachori R B. Variable cosine windowing of intrinsic mode functions:Application to gear fault diagnosis［J］. Measurement, 2012, 45(3):415426.
［4］	Li H L, Kwong S, Yang L, et al. Hilberthuang transform for analysis of heart rate variability in cardiac health［J］. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2011, 8(6):15571567.
［5］	Wang T, Zhang M C, Yu Q H, et al. Comparing the applications of EMD and EEMD on timefrequency analysis of seismic signal［J］. Journal of Applied Geophysics, 2012, 83:2934.
［6］	Liu H, Chen C, Tian H Q. A hybrid model for wind speed prediction using empirical mode decomposition and artificial neural networks［J］. Renewable Energy, 2012, 48:545556.
［7］	Bamhart B L, Eichinger W E. Empirical mode decomposition applied to solar irradiance, global temperature, sunspot number, and CO2 concentration data［J］. Journal of Atmospheric and SolarTerrestrial Physics, 2011, 73(13):17711779.
［8］	Zhang Y, Xie Z H. Ensemble empirical mode decomposition of impactecho data for testing concrete structures［J］. NDT & E International, 2012, 51:7484.
［9］	Wang Gang, Leng Shuang. The denoising method of CT image based on empirical mode decomposition［J］. Technology Innovation and Application, 2012, 11(22):16.(in Chinese)
［10］	Wang Jianguo, Wang Xiaotong, Xu Xiaogang, et al. Image enhancement method based on empirical mode decomposition［J］. Electronics Optics & Control, 2010, 17(2):1820.(in Chinese)
［11］	Wan Jian, Ren Longtao, Zhao Chunhui. Simulation research of applying twodimensional empirical mode decomposition on image feature extraction［J］. Journal of System Simulation, 2009, 21(3):799801.(in Chinese)
［12］	Zhang Jun, Li Ming, Lu Yuming, et al. Fatigue fracture image segmentation based on BEMD［J］. Failure Analysis and Prevention, 2011, 6(2):7074.(in Chinese)
［13］	Yeh M H. The complex bidimensional empirical mode decomposition［J］. Signal Processing, 2012, 92(2):523541.
［14］	Tian Y, Zhao K, Xu Y P, et al. An image compression method based on the multiresolution characteristics of BEMD［J］. Computers and Mathematics with Applications, 2011, 61(8):21422147.
［15］	Qi K Y, He Z J, Zi Y Y. Cosine windowbased boundary processing method for EMD and its application in rubbing fault diagnosis［J］. Mechanical Systems and Signal Processing, 2007, 21(5):27502760.
［16］	Zhao J P, Huang D J. Mirror extending and circular spline function for empirical mode decomposition method［J］. Journal of Zhejiang University:SCIENCE, 2001, 2(3):247252.
［17］	Rilling G, Flandrin P, Goncalves P. On empirical mode decomposition and its algorithms［C］∥Proc of IEEEEURASIP Workshop on Nonlinear Signal and Image Processing, 2003:811.
［18］	Huang Daji, Zhao Jinping, Su Jilan. The end issue of HilbertHuang transform［J］. Acta Oceanologica Sinica, 2003, 25(1):114.(in Chinese)
［19］	Shao Chenxi, Wang Jian, Fan Jinfeng, et al. A selfadaptive method dealing with the end issue of EMD［J］. Acta Electronica Sinica, 2007, 35(10):19441948.(in Chinese)
［20］	Liu Huiting, Zhang Min, Cheng Jiaxing. Dealing with the end issue of EMD based on polynomial fitting algorithm［J］. Computer Engineering and Application, 2004, 40(16):8485.(in Chinese)
［21］	Cheng Junsheng, Yu Dejie, Yang Yu. Discussion of end effects of HilbertHuang transform［J］. Journal of Vibration and Shock, 2005, 24(6):4047.(in Chinese)
［22］	Dou Dongyang, Zhao Yingkai. Method of improving ending effect of HilbertHuang transform using auto regressive integrated moving average model［J］. Journal of Vibration, Measurement & Diagnosis, 2010, 30(3):249253.(in Chinese)
［23］	Wu Q, Sherman D R. Boundary extension and stop criteria for empirical mode decomposition［J］. Advances in Adaptive Data Analysis, 2010, 2(2):157169.
［24］	Deng Y J, Wang W, Qian C C, et al. Boundaryprocessingtechnique in EMD method and Hilbert transform［J］. Chinese Science Bulletin, 2001, 46(1):954960.
［25］	Lee C Y, Lee Y C. BPNN based processing for end effects of HHT［J］. World Academy of Science, Engineering and Technology, 2010, 72(50):9597.
［26］	Cheng J H, Yu D J, Yang Y. Application of support vector regression machines to the processing of end effects of HilbertHuang［J］. Mechanical Systems and Signal Processing, 2007, 21(3):11971211.
［27］	He Z, Shen Y, Wang Q. Boundary extension for HilbertHuang transform inspired by gray prediction model［J］. Signal Processing, 2012, 92(3):685697.
［28］	Lin D C, Guo Z L, An F, et al. Elimination of end effects in empirical mode decomposition by mirror image coupled with support vector regression［J］. Mechanical Systems and Signal Processing, 2012, 31:1328.
［29］	Zhang Fan, Liao Xingquan. An improved method for elimination of HHT end effects［EB/OL］. ［20100524］. http://www.paper.edu.cn/index.php/default/download/downPaper/201005583.(in Chinese)
［30］	Li Zaiwei, Lian Songliang. Analysis of track irregularity signal by improved HilbertHuang transform［J］. Journal of Shenzhen University(Science and Engineering), 2012, 29(3):270275.(in Chinese)
［31］	Wu Z H,Huang N E.A study of the characteristics of white noise using the empirical mode decomposition method［J］. Proceeding of the Royal Society of London A, 2004, 460:15971611.
［32］	Wu Z H, Huang N E. Ensemble empirical mode decomposition:A noise assisted data analysis method［J］. Advances in Adaptive Data Analysis, 2009, 1(1):141.
［33］	Lei Y G, He Z J, Zi Y Y. EEMD method and WNN for fault diagnosis of locomotive roller bearings［J］. Expert Systems with Applications, 2011, 38(6):73347341.
［34］	Zhang J, Yan R Q, Gao R X. Performance enhancement of ensemble empirical mode decomposition［J］. Mechanical Systems and Signal Processing, 2010, 24(7):20142123.
［35］	Torres M E, Colominas M A, Schlotthauer G. A complete ensemble empirical mode decomposition with adaptive noise［C］∥Proc of IEEE International Conference on Acoustics, Speech and Signal Processing, 2011:41444147.
［36］	Guo W, Tse P W. Enhancing the ability of ensemble empirical mode decomposition in machine fault diagnosis［C］∥Proc of Prognostics and Health Management Conference, 2010:17.
［37］	Zhao Jinping. Study on the effects of abnormal events to empirical mode decomposition method and the removal method for abnormal signal［J］. Journal of Ocean University of Qingdao, 2001, 31(6):805814.(in Chinese)
［38］	Li H L, Yang L H, Huang D R. The study of the intermittency test filtering character of HilbertHuang transform［J］. Mathematics and Computers in Simulation, 2005, 70(1):2232.
［39］	Song Lixin,Wang Qi,Wang Yujing,et al.Empirical mode decomposition method with intermittency test and separation［J］. Journal of Harbin Engineering University, 2007, 28(2):178182.(in Chinese)
［40］	Gao Y C, Ge G T, Sheng Z Y, et al. Analysis and solution to the mode mixing phenomenon in EMD［C］∥Proc of Congress on Image and Signal Processing, 2008:223227.
［41］	Qin Pinle, Lin Yan, Chen Ming. Empirical mode decomposition method based on wavelet with translation invariance algorithm［J］. Chinese Journal of Scientific Instrument, 2008, 29(12):26372641.(in Chinese)
［42］	Deering R, Kaiser J F. The use of a masking signal to improve empirical mode decomposition［C］∥Proc of IEEE International Conference on Acoustics, Speech and Signal Processing IV, 2005:485488.
［43］	Tang B P, Dong S J, Song T. Method for eliminating mode mixing of empirical mode decomposition based on the revised blind source separation［J］. Signal Processing, 2012, 92(1):248258.
［44］	Yang Yanli, Deng Jiahao, Wu Caipeng. Analysis of mode mixing phenomenon in the empirical mode decomposition method［C］∥Proc of the 2nd International Symposium on Science and Engineering, 2009:553556.
［45］	Yu Dejie, Cheng Junsheng, Yang Yu. Mechanical failure diagnosis of HilbertHuang transform method［M］. Beijing:Science Press, 2006.(in Chinese)
［46］	Damerval C, Meignen S, Perrier V. A fast algorithm for bidimensional EMD［J］. IEEE Signal Processing Letters, 2005, 12(10):701704.
［47］	Nunes J C, Guyot S, Delechelle E. Texture analysis based on local analysis of the bidimensional empirical mode decomposition［J］. Machine Vision and Applications, 2005, 16(3):177188.
［48］	Xu Y, Liu B, Liu J, et al. Twodimensional empirical mode decomposition by finite elements［J］. Proceedings of the Royal Society, Part A, 2006, 462(2074):30813096.
［49］	Bhuiyan S M A, Adhami R R, Khan J F. Fast and adaptive bidimensional empirical mode decomposition using orderstatistics filter based envelope estimation［J］. EURASIP Journal on Advances in Signal Processing, 2008:118.
［50］	Xu G L, Wang X T, Xu X G. Improved bidimensional EMD and Hilbert spectrum for the analysis of textures［J］. Pattern Recognition, 2009, 42(5):718734.
［51］	Huang N E, Wu M C, Long S R, et al. A confidence limit for the empirical mode decomposition and Hilbert spectral analysis［J］. Proceedings of the Royal Society, Part A, 2003, 459(2037):23172345.
［52］	Rrilling G, Flandrin P, Goncalves P. Empirical mode decomposition as a filter bank［J］. IEEE Signal Processing Letters, 2004, 11(2):112114.
［53］	Xu Guanlei, Wang Xiaotong, Xu Xiaogang, et al. The conditions and criterion of using EMD from multicomponent to single component［J］. Progress in Natural Science, 2006, 16(10):13561360.(in Chinese)
［54］	Liang Lingfei, Ping Ziliang. Medical image enhancement based on window empirical mode decomposition algorithm［J］. Journal of Optoelectronics·Laser, 2010, 21(9):14211425.(in Chinese)
［55］	Zheng Qin. Research on algorithms of medical image fusion based on EMD［D］. Hangzhou:Zhejiang University of Technology, 2011.(in Chinese)
	附中文参考文献：
［9］	王刚, 冷爽. 基于经验模态分解的CT图像去噪方法［J］. 科技创新与应用, 2012, 11(22):16.
［10］	王建国, 王孝通, 徐晓刚，等. 基于经验模式分解的图像增强研究［J］. 电光与控制, 2010, 17(2):1820.
［11］	万建, 任龙涛, 赵春晖. 二维EMD应用在图像边缘特征提取中的仿真研究［J］. 系统仿真学报, 2009, 21(3):799801.
［12］	张俊, 黎明, 鲁宇明，等. 基于BEMD的疲劳断口图像分割［J］. 失效分析与预防, 2011, 6(2):7074.
［18］	黄大吉, 赵进平, 苏纪兰. 希尔伯特黄变换的端点延拓［J］. 海洋学报, 2003, 25(1):114.
［19］	邵晨曦, 王剑, 范金锋，等. 一种自适应的EMD端点延拓方法［J］. 电子学报, 2007, 35(10):19441948.
［20］	刘慧婷, 张旻, 程家兴. 基于多项式拟合算法的EMD端点问题的处理［J］. 计算机工程与应用, 2004, 40(16):8485.
［21］	程军圣, 于德介, 杨宇. HilbertHuang变换端点效应问题的讨论［J］. 振动与冲击, 2005, 24(6):4047.
［22］	窦东阳, 赵英凯. 利用ARIMA改进HHT端点效应的方法［J］. 振动、测试与诊断, 2010, 30(3):249253.
［29］	张帆, 廖星权. 一种改善的HHT端点效应抑制方法［EB/OL］. ［20100524］.http://www.paper.edu.cn/ index.php/default/download/downPaper/201005583.
［30］	李再帏, 练松良. 改进HHT方法在轨道不平顺信号分析中的应用［J］. 深圳大学学报（理工版）, 2012, 29(3):270275.
［37］	赵进平. 异常事件对EMD方法的影响及其解决方法研究［J］. 青岛海洋大学学报, 2001, 31(6):805814.
［39］	宋立新, 王祁, 王玉静，等. 具有间断事件检测和分离的经验模态分解方法［J］. 哈尔滨工程大学学报, 2007, 28(2):178182.
［41］	秦品乐, 林焰, 陈明. 基于平移不变小波阈值算法的经验模态分解方法［J］. 仪器仪表学报, 2008, 29(12):26372641.
［45］	于德介, 程军圣, 杨宇. 机械故障诊断的HilbertHuang变换方法［M］. 北京:科学出版社, 2006.
［53］	徐冠雷, 王孝通, 徐晓刚，等. 多分量到单分量可用EMD分解的条件及判据［J］. 自然科学进展, 2006, 16(10):13561360.
［54］	梁灵飞, 平子良. 基于窗口经验模式分解的医学图像增强［J］. 光电子·激光, 2010, 21(9):14211425.
［55］	郑琴. 基于EMD的医学图像融合算法研究［D］. 杭州:浙江工业大学, 2011.