This paper illustrates the significance of the purity of cyclostationary signals and presents a new method for blind extraction of these signals. The advantage of the method can not only extract the cyclostationary signals from low order to high order in turn but also perform algorithm without knowing cyclic frequencies of the extracted signals. The effectiveness of the proposed method is finally demonstrated by computer simulations and experiments.
AntoniJ (2009) Cyclostationarity by examples. Mechanical Systems and Signal Processing23(4): 987–1036.
2.
AntoniJRandallRB (2004) Unsupervised noise cancellation for vibration signals: part I – evaluation of adaptive algorithms. Mechanical Systems and Signal Processing18(1): 89–101.
3.
AntoniJRandallRB (2002) Differential Diagnosis Of Gear And Bearing Faults. New York: American Society of Mechanical Engineers 124(2).
4.
AntoniJBonnardotFRaadAEl BadaouiM (2004) Cyclostationary modelling of rotating machine vibration signals. Mechanical Systems and Signal Processing18(6): 1285–1314.
5.
Aoufl T, Bakrim M and Aboutajdine D (2007) Blind separation of cyclo-stationary signals using generalized eigenvalue approach. In: 14th IEEE International Conference on Electronics, Circuits and Systems.
6.
BarrosAKCichockiA (2001) Extraction of specific signals with temporal structure. Neural Computation13(9): 1995–2003.
7.
BonnardotFRandallRBGuilletF (2005) Extraction of second-order cyclostationary sources – application to vibration analysis. Mechanical Systems and Signal Processing19(6): 1230–1244.
8.
BoustanyRAntoniJ (2008) Blind extraction of a cyclostationary signal using reduced-rank cyclic regression – a unifying approach. Mechanical Systems and Signal Processing22(3): 520–541.
9.
CapdessusCNandiABouguerriouN (2007) A New Source Extraction Algorithm for Cyclostationary Sources. Independent Component Analysis and Signal Separation. Heidelberg: Springer Berlin. 145–151.
10.
CapdessusCSidahmedMLacoumeJL (2000) Cyclostationary processes: application in gear faults early diagnosis. Mechanical Systems and Signal Processing14(3): 371–385.
11.
Cichocki A (2002). Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications. Chichester, New York John Wiley & Sons, Ltd. (UK).
12.
GardnerWA (1993) Cyclic Wiener filtering: theory and method. IEEE Transactions on Communications41(1): 151–151.
13.
Gardner WA (1994) Cyclostationarity in Communications and Signal Processing. New York, IEEE press.
14.
GardnerWANapolitanoAPauraL (2006) Cyclostationarity: half a century of research. Signal Processing86(4): 639–697.
15.
KoldovskýZTichavskýPOjaE (2006) Efficient variant of algorithm FastICA for independent component analysis attaining the Cramer-Rao lower bound. IEEE Transactions on Neural Networks17(5): 1265–1277.
16.
McFaddenPD (1987) A revised model for the extraction of periodic waveforms by time domain averaging. Mechanical Systems and Signal Processing1(1): 83–83.
17.
RandallRBAntoniJChobsaardS (2001) The relationship between special correlation and envelope analysis in the diagnostics of bearing faults and other cyclostationary machine signals. Mechanical Systems and Signal Processing15(5): 945–962.
18.
TichavskýPKoldovskýZOjaE (2006) Performance analysis of the FastICA algorithm and Cramér–Rao bounds for linear independent component analysis. IEEE Transactions on Signal Processing54(4): 1189–1189.
19.
Waheed K and Salam FM (2002) Blind source recovery using an adaptive generalized Gaussian score function. MWSCAS-2002. In: the 2002 45th Midwest Symposium on Circuits and Systems, 2002, Tulsa, USA.
20.
Pan YN, Chen J and Li XL (2009) Spectral entropy: a complementary index for rolling element bearing performance degradation assessment. Mechanical Engineering Science, Dalian P.R.C.
21.
ZhangZLZhangY (2006) Robust extraction of specific signals with temporal structure. Neurocomputing69(7–9): 888–893.
