Mathematic model modeling method for EMD (Empirical Mode Decomposition) illusive component recognition

Abstract

The invention discloses a mathematic model for EMD (Empirical Mode Decomposition) illusive component recognition based on K-L divergence and SVM and a modeling method thereof. The method comprises the steps of performing EMD decomposition on the most ordinary diphonia signals to obtain a limited number of IMF (Intrinsic Mode Function) components to serve as an SVM training sample set, utilizing a frequency spectrum ratio method to calibrate all the IMF components as true components or illusive components, calculating out K-L divergence values between the IMF components and an original signal, inputting the K-L divergence values as unique characteristics for describing the IMF components into SVM, and training out a classifier mathematic model capable of recognizing the EMD illusive components. A classifier can solve the problem of difficultly recognizing the illusive components after EMD decomposition of regular signals of three-tone signals, four-tone signals, even multiple-tone signals and the like; to signals containing mode mixing phenomena, the classifier mathematic model still has stronger robustness on recognizing the EMS illusive components. The modeling method disclosed by the invention is applied to the technical field of utilizing empirical mode decomposition to perform signal analysis.

Description

technical field [0001] The invention relates to a mathematical model modeling method for EMD false component identification, which is applied to the technical field of signal analysis by using empirical mode decomposition. Background technique [0002] The Empirical Mode Decomposition (EMD) method is an adaptive time-frequency analysis method based on the local time characteristics of data proposed by Chinese-American N.E.Huang et al. in 1998. It can decompose complex signals into finite intrinsic mode function components, referred to as IMF (Intrinsic Mode Function) components, and is widely used in nonlinear and non-stationary time series processing. [0003] On the one hand, the ideal EMD application condition is the Nyquist frequency greater than 4 times the sampling frequency, and the minimum requirement for the application of EMD should be the Nyquist frequency greater than 2 times the sampling frequency; on the other hand, the generation of each IMF component in the E...

AI Technical Summary

Problems solved by technology

[0004] The literature "Huang Dishan. The method of removing false modal components in empirical mode decomposition [J]. Vibration, Testing and Diagnosis, 2011, 31(3): 381-384." Completeness, energy principle and the nature of false modal components, the false components are judged by judging the increase or decrease of energy after the addition of the first-order IMF component and the higher-order IMF component, but this method is only applicable to specific regular signals; literature " Lin Li. Improved EMD Algorithm Based on Correlation Coefficient [J] Computer and Digital Engineering. 2008,36(12):28-29,38 "Peng Z K, Tse P W, Chu F L.A comparisonstudy of improved Hilbert-Huang transform and wavelet transform: Application to fault diagnosis for rolling bearing [J]. Mechanical Systems and Signal Processing, 2005(19): 974-988." (abbreviation: correlation coefficient method) uses the correlation coefficient between the IMF component and the original signal to remove The idea of ​​noise denoising is used to distinguish EMD false components, and the threshold is set to 1 / 10 of the maximum correlation coefficient. If it is less than the threshold, it is judged as a false component. However, for mechanical vibration signals with more frequency components, Sometimes the difference in the correlation coefficient corresponding to the real component and the false component is not obvious, which is easy to cause misjudgment; the literature "Han Zhonghe, Zhu Xiaoxun, Li Wenhua. Research on the false component identification method of K-L divergence [J]. Chinese Journal of Electrical Engineering. 2012, 32(11):112-117." and the literature "Song Na, Shi Yu, Zhou Keyin, Application of Genetic Algorithm in EMD False Component Identification" (both methods are referred to as: KL divergence method) both propose to calculate the IMF component The K-L divergence value (relative entropy) between the original signal and the K-L divergence value of all IMF components is normalized. When the normalized divergence value is greater than a given threshold, it is judged as a false component. For the determination of the threshold in this method, the author still gives it based on experience, and it is not universal

Images