Title :
Signal feature extraction base on fractal dimensions of time-frequency domain
Author :
Yu, Yuan ; Jingshan, Shang ; Baoliang, Li ; Shixuan, Yao
Author_Institution :
Sch. of Mech. Eng., Dalian JiaoTong Univ., Dalian, China
Abstract :
In this paper, vibration signal multifractal method was researched, multifractal on time-frenquency domain was an energy fractal and the signal feature extraction was based on the analysis of its energy ditributing. The method analysed signal on time-frequency domain to characterize the distributing of its frequency or energy, and the signal´s feature was extracted by fractal dimension. After the signal was changed to time-frequency domain by Hilbert-Huang transform, general dimension Dq would be calculated from the signal in time-frequency domain by least square method. In the end, examples of emulator and practical application proved that this integrated method was feasible.
Keywords :
Hilbert transforms; feature extraction; signal processing; time-frequency analysis; Hilbert-Huang transform; energy distributing analysis; signal feature extraction; time-frequency domain; vibration signal multifractal method; Data envelopment analysis; Failure analysis; Feature extraction; Fluctuations; Fractals; Signal analysis; Spectral analysis; Time domain analysis; Time frequency analysis; Vibration measurement; Hilbert-Huang transform; general dimension; multifractal;
Conference_Titel :
Nature & Biologically Inspired Computing, 2009. NaBIC 2009. World Congress on
Conference_Location :
Coimbatore
Print_ISBN :
978-1-4244-5053-4
DOI :
10.1109/NABIC.2009.5393887