Volume 16, Issue 12 (2-2017)                   Modares Mechanical Engineering 2017, 16(12): 357-364 | Back to browse issues page

XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Hosseini Korkhili S A, Mohammad Navazi H, Momeni Massouleh S H. Combined Auto-Regressive Mirror Method for Improvement of End Effects in Empirical Mode Decomposition. Modares Mechanical Engineering 2017; 16 (12) :357-364
URL: http://mme.modares.ac.ir/article-15-6550-en.html
Abstract:   (4598 Views)
The empirical mode decomposition method is a new technique to obtain constitutive components of a signal. Applicability to all kinds of signals including non-stationary and nonlinear is a main feature of this method. So far, many researches have been done in the literature to eliminate or reduce effects of multiple sources of errors such as stop criteria, end effects and interpolation function. This article focuses on end effects error which many of previous solutions have been proposed based on symmetry or similar methods to decline it. The proposed combined method using auto-regressive (AR) models for short sections of signal edges, forecasts tails of maximum and minimum envelops. Some of first intrinsic mode functions are initially calculated as a result of AR model application. The methods based on symmetry are then used to continue sifting algorithm for remaining signal that has no enough extremums to employ AR model. Finally, by executing some examples, more accurate results obtained from proposed method are compared with those achieved from the mirror method. Noise is also added to signal time history in the last example, to simulate a more realistic situation.
Full-Text [PDF 646 kb]   (3087 Downloads)    
Article Type: Research Article | Subject: Vibration
Received: 2016/08/14 | Accepted: 2016/11/6 | Published: 2016/12/18

Add your comments about this article : Your username or Email:
CAPTCHA

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.