Affiliation:
1. Xi’an Research Institution of High-Technology
Abstract
The nonlinear blind source separation is a practical and effective method in processing mechanical vibration signal, but it has the limitation which learning rate is fixed. It will take a long time for iterative parameters to get convergence. In this paper, a variable rate nonlinear BSS is proposed. The learning rate of the algorithm is adjusted based on iterative error in the different stopping iterating time and inverse proportion. The proposed algorithm increasing the efficiency of the nonlinear BSS and de-noising the vibration signals. Experiment on gears shows that the signal gained by the method more impersonality represents the gear condition
Publisher
Trans Tech Publications, Ltd.
Reference9 articles.
1. A. Hyvarinen, J. Karhunaen, Erkki Oja, Independent Component Analysis, Wiley, New York, (2001).
2. J. Fortuna, D. Capson, ICA for position and pose measurement from images with occlusion, in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, (ICASSP '02), vol. 4, 2002, pp.3604-3607.
3. A. Cichocki, Blind signal processing methods for analyzing multichannel brain signals, International Journal of Bioelectromagnitis . 6 (1) (2004) 22-27.
4. U. Madhow, Blind adaptive interference suppression for direct-sequence CDMA, Proceedings of the IEEE 86 (10) (1998) 2049-206.
5. E. Oja, K. Kiviluoto, S. Malaroiu, Independent component analysis for financial time series, in: Adaptive Systems for Signal Processing, Communications, and Control Symposium 2000, AS-SPCC, The IEEE 2000, Lake Louise, Alta, 2000, pp.111-116.