Abstract：Rolling bearing fault signals appear mostly in the form of modulation, and are vulnerable to influenced by other big energy source signals，causing the great limitation of traditional method on information extraction. According to these characteristics, the intrinsic time scale decomposition (ITD) and independent component analysis (ICA) of signal analysis method was proposed. Firstly, the signal was decomposed into several proper rotation components and a trend component by the ITD method. Then they were destructed as the input matrix of ICA based on mutual correlation criterion. Using FastICA algorithm to solve mixed, so as to realize the separation of the fault signal and the noise signal. This method is applied to the fault diagnosis of rolling bearing. The analysis of the field data results show that this method is effective and feasible, and also has certain engineering application value.
柏 林1，陆 超1，赵 鑫2. 基于ITD与ICA的滚动轴承故障特征提取方法[J]. 振动与冲击, 2015, 34(14): 153-156.
BO Lin1，LU Chao1，ZHAO Xin2. A method in fault diagnosis of rolling bearing based on ITD and ICA. JOURNAL OF VIBRATION AND SHOCK, 2015, 34(14): 153-156.
[1] 翁乐明. 独立分量分析若干问题的研究[D]. 上海：上海交通大学, 2009.
[2] Wang Z Y.Chen J, Dong G M, et al．Constrained independent component analysis and its application to machine fault diagnosis[J].Mechanical Systems and Signal Processing, 2011,25(7) : 2501-2512.
[3] 张俊红,李林洁,马文朋,等.EMD-ICA联合降噪在滚动轴承中的应用[J].中国机械工程,2013,24(11):1468-1472.
ZHANG jun-hong, LI lin-jie, MA Wen-peng, et al. Application of EMD-ICA to fault diagnosis of rolling bearing[J]. China Mechanical Engineering,2013, 24(11): 1468-1472.
[4] Frei M G ,Osorio I. Intrinsic time-scale decomposition: time-frequency-energy analysis and real-time filtering of non-stationary signals[J]. Proceedings of the Royal Society of London A, 2006, 2078 (463): 321-342.
[5] 杨敏军, 邱玲. 一种直扩信号的检测方法[J]. 计算机仿真,2007, 24(9): 322-324.
YANG Min-jun ,QIU Ling. A method of DS signal
detection [J]. Computer Simulation, 2007, 24(9): 322-324.
[6] 金艳, 姬红兵, 罗军辉. 一种基于循环统计量的直扩信号检测与参数估计方法[J]. 电子学报, 2006, 34(4): 634-637.
JIN Yan, JI Hong-bing, Luo Jun-hui. A cyclic-cumulant based method for DS-SS signal detection and parameter estimation[J]. Acta Electronica Sinica, 2006, 34(4): 634- 637.
[7] 胥永刚，陆明，谢志聪. 基于固有时间尺度分解的能量算子解调法及故障诊断应用[J].海军工程大学学报，2013, 25(1):27-31.
XUYong-gang, LU Ming, XIE Zhi-cong. Teager energy operator demodulation method based on ITD and its applications in fault diagnosis [J]. Jouranal of Naval University of Engineering, 2013, 25(1):27-31.
[8] 安学利,蒋东翔,刘超,等.基于固有时间尺度分解的风电机组轴承故障特征提取[J].电力系统自动化,2012,36(5)：41- 44.
AN Xue-li, JIANG Dong-xiang, LIU Chao, et al. Bering fault feature extraction of wind turbine based on intrinsic time-scale decomposition [J]. Automation of Electric Power System, 2012,36(5)：41-44.
[9] Han Jing-tao, jiao Si-hai, Jiang Zheng-yi. The de-noising algorithm based on intrinsic time-scale decomposition [J]. Advanced materials Research, 2011, 422:347-352.
[10] 邵晨曦,王剑,范金峰，等. 一种自适应的EMD端点延拓方法[J]. 电子学报,2007, 35(10):1994-1948.
SHAO Chen-xi, WANG Jian, FAN Jin-feng, et al. A self-adaptive method dealing with the method issue of EMD[J].Acta Electronica Sinica,2007, 35(10): 1994-1948.
[11] Xu J, Zhang J S, Huang Y. The analysis of servo loading effect in high-speed railway [C]. ICRE 2010-International Conference on Railway Engineering,2010: 350-355．
[12] Peng Z K, Perter W T,Chu F L. A Comparison study of improved hilbert-huang transform and wavelet transform: application to fault diagnosis for rolling bearing [J]. Mechanical Systems and Signal Processing, 2005,19(5): 974-988.
[13] Bearing data center website.Case Western Res Unive- rsity,http://www.eecs.cwru.edu/laboratoryerve/ bearing.
