A Variable Rate Nonlinear Blind Source Separation
-
摘要: 基于核函数的非线性盲源分离算法在盲信号处理中有着广泛的应用,但传统的非线性盲源分离算法的学习速率是固定的。当系统的噪声和迭代误差较小而步长相对较小,则算法达到收敛的效率不高;当系统的噪声和迭代误差较大时,如果迭代步长过大则将会影响盲源分离的精度。针对这一不足,提出一种基于核函数的变速率非线性盲源分离算法,算法根据信噪比和迭代误差来调节学习速率,将该算法应用于齿轮箱故障诊断中。仿真和实验结果表明,与固定速率的非线性盲源分离算法相比,该算法具有更好的消噪和信号特征提取能力。Abstract: The nonlinear blind source separation algorithm based on kernel function has been widely applied in blind signal processing.However the learning rate of traditional kernel function method is fixed.When the system noise level and iterative error are large,it will take a long time for iterative parameters to get convergence.So it will affect the efficiency of blind source separation.In this paper,a variable rate nonlinear blind source separation algorithm based on kernel function was proposed.The learning rate of the algorithm was adjusted according to SNR and iterative error.The algorithm was applied in gear faults diagnosis.Both of the results of simulation and experiment indicate that the present algorithm has better ability of noise reduction and feature extraction than fixed rate nonlinear blind source separation.
-
Key words:
- blind source separation /
- vibration signal /
- nonlinear mixing /
- kernel function /
- fault diagnosis
-
[1] Haykin S.Unsupervised Adaptive Filtering,Vol 1:BlindSource Separation[M].New York,2000 [2] 叶红仙,杨世锡,杨将新.基于EMD～SVD～BIC的机械振动源数估计方法[J].振动、测试与诊断,2010,30(3):330～343 [3] 范涛,李志农,卢纪富等.基于变分贝斯独立分量分析的故障源盲分离[J].噪声与振动控制,2010,(1):82～85 [4] Hyvrinen A,Karhunen J,Oja E.Independent ComponentAnalysis[M].New York,2001 [5] 王法松,李宏伟,沈远彤.非线性盲源分离的原理及算法综述[J].信号处理,2005,21(3):282～287 [6] 冯健,付兴龙,刘浩达.非线性盲源分离算法综述[J].中国科技论文在线,2009,4(1):5～10 [7] 陶涛,黄高明,赵治华.后非线性混叠盲源分离算法综述[J].控制与决策,2010,25(8):1121～1128 [8] Martinez D,Bray A.Nonlinear blind source separation using ker-nels[J].IEEE Transcation on Neural Networks,2003,14(1):228～235 [9] Tan Y,Wang J.Nonlinear blind source separation using higherorder statistics and a genetic algorithm[J].IEEE Transactionson Evolutionary Computation(S1089～788X),2001,5(6):600～612 [10] Cardoso J F.Blind signal separation:Statistical principles[A].Proceedings IEEE[C],1998,86(10):2009～2025 [11] Tong L,Soon C V,Huang F Y.A new blind identification algo-rithm[A].In:International Conference on Acoustics,Speedand Signal Processing[C],1990:1784～1787 [12] Martinez D,Bray A.Nonlinear blind source separation using ker-nels[J].IEEE Transcation on Neural Networks,2003,14(1):228～235 [13] 胡晓依,何庆复,王华胜等.基于STFT的振动信号调制方法及其在轴承故障检测中的应用[J].振动与冲击,2008,27(2):82～86 [14] 丁芳,高立新,崔玲丽等.共振解调技术在设备故障诊断中的应用[J].机械设计与制造,2007,(11):178～179 -
点击查看大图
计量
- 文章访问数: 191
- HTML全文浏览量: 23
- PDF下载量: 4
- 被引次数: 0
下载:
