针对实验中采集到的滚动轴承的振动信号具有成分复杂和较强的非平稳性等特点,本文提出采用基于遗传算法优化的匹配追踪算法(GAMP)和总体平均经验模式分解(EEMD)相结合的方法,实现对滚动轴承振动信号的处理与分析。首先,利用GAMP算法将滚动轴承振动信号线性展开成能够较好的匹配该信号特征结构的一系列高斯函数,达到消除干扰噪声锁定信号的局部特征的目的;然后,针对GAMP消噪后的振动信号中可能存在的虚假频率成分或不连续的分量,利用EEMD方法来予以剔除,通过傅里叶变换将处理后的振动信号从时域转化到频域,提取出故障振动信号的故障频率;最后,采用支持向量机(SVM)对滚动轴承的正常和故障振动信号进行分类,实现了对滚动轴承的故障诊断。
Abstract
Based on genetic algorithm to optimize the matching pursuit algorithm (GAMP) and ensemble empirical mode decomposition (EEMD),a rolling bearing fault diagnosis method is proposed. It can achieve the purpose of processing and analyzing rolling bearing vibration signals which have the characteristics of complex components and strong non-stationary in the experiment. First, the rolling bearing vibration signals can be linearly expanded into a series of Gaussian functions which can better match characteristic structure of signals by GAMP algorithm. The purpose of eliminating interference noise and locking the local characteristics of the signals is achieved. Second, EEMD method is used to eliminate the false frequency components and discontinuous components that may exist in the vibration signals of GAMP. The processed vibration signals are transformed from the time domain to frequency domain by FFT, and the fault frequency of the fault vibration signals is extracted. At last, Support Vector Machine(SVM) is used to classify the normal and fault vibration signals of the rolling bearing, and the rolling bearings fault is diagnosed.
关键词
GAMP /
EEMD /
SVM /
滚动轴承 /
故障诊断
{{custom_keyword}} /
Key words
GAMP /
EEMD /
Rolling bearings /
Fault diagnosis
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 杨宇,于德介,程军圣. 基于Hilbert边际谱的滚动轴承故障诊断方法[J]. 振动与冲击,2005,24(1):70-72.
Yang Yu, Yu Deijie, Cheng Junsheng. Rolling bearing fault diagnosis method based on Hilbert marginal spectrum[J], Journal of Vibration and Shock, 2005, 24(1): 70-72.
[2] 陶少飞. 匹配追踪算法的优化及其在滚动轴承故障诊断中的应用[D].上海:上海交通大学,2012.
Tao Shaofei. Matching pursuit algorithm optimization and its application in the rolling bearing fault diagnosis[D].Shanghai, Shanghai jiaotong university, 2012.
[3] 康晨晖,催玲丽,王婧,等. 基于信号特征的复合字典多原子匹配算法研究[J]. 机械工程学报,2012,48(12):1-6.
Kang Chenhui, Cui Lingli, Wang Jing, et al. Research of composite dictionary polyatomic matching algorithm based on signal feature [J], Journal of Mechanical Engineering, 2012,48(12):1-6.
[4] Mallat S. A Wavelet Tour of Signal Processing. San Diego, CA: Academic Press, 1988.
[5] Ferreira da Silva A R. Atomic decomposition with evolutionary pursuit[J]. Digital Signal Processing, 2003, 13:317-337.
[6] Peng Z K, Tse P W, Chu F L. An Improved Hilbert-Huang Transform and Its Application in Vibration Signal Analysis[J].Journal of Sound and Vibration, 2005, 286(9):187-205.
[7] Zhang J, Yan R, Feng Z. Performance enhancement of ensemble empirical mode decomposition[J]. Mechanical Systems and Signal Processing, 2010, 24(7):2104-2123.
[8] 沈长青, 谢伟达, 朱忠奎, 等. 基于EEMD和改进的形态滤波方法的轴承故障诊断研究[J]. 振动与冲击,2013, 32(2):39-43
Shen Changqing, Xie Weida, Zhu Zhongkui, et al. Rolling element bearing fault diagnosis based on EEMD and improved morphological filtering method[J], Journal of Vibration and Shock, 2013, 32,(2): 39-43.
[9] 周智,朱永生,张优云,朱川峰,王鹏. 基于EEMD和共振解调的滚动轴承自适应故障诊断[J]. 振动与冲击,2013,32(2):76-80.
Zhou Zhi, ZhuYongsheng, Zhang Youyun, et al. Rolling bearing adaptive fault diagnosis based on EEMD and resonance demodulation[J], Journal of Vibration and Shock, 2013, 32,(2): 76-80.
[10] 于湘涛,褚福磊,郝如江. 基于柔性形态滤波和支持向量机的滚动轴承故障诊断方法[J]. 机械工程学报,2009,45(7):75-80.
YU Xiangtao, CHU Fulei, HAO Rujiang. Fault Diagnosis Approach for Rolling Bearing Based on Support Vector Machine and Soft Morphological Filters[J], journal of mechanical engineering, 2009, 45(7):75-80.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}