基于自适应概率主成分分析的滚动轴承故障特征增强方法

胡爱军,南 冰

振动与冲击 ›› 2017, Vol. 36 ›› Issue (19) : 145-150.

PDF(860 KB)
PDF(860 KB)
振动与冲击 ›› 2017, Vol. 36 ›› Issue (19) : 145-150.
论文

基于自适应概率主成分分析的滚动轴承故障特征增强方法

  • 胡爱军,南 冰
作者信息 +

Fault feature enhancement method for rolling bearing based on adaptive probabilistic principal component analysis

  • HU Aijun, NAN Bing
Author information +
文章历史 +

摘要

针对实际工程中滚动轴承微弱故障信号特征难以提取的问题,提出了一种新的自适应概率主成分分析(adaptive probabilistic principal component analysis, APPCA)的轴承故障特征增强方法。概率主成分分析(probabilistic principal component analysis, PPCA) 能够提取信号的主要故障特征,去除背景噪声干扰,但结果易受到主成分数与原始变量维数选择的影响。为了自适应实现最佳分析结果,利用粒子群算法多参数寻优特性,根据最大峭度准则确定影响PPCA的最佳影响参数组合。原信号通过APPCA方法处理后,背景噪声得到有效抑制,故障特征得到增强,最后通过包络分析识别故障特征。仿真和实验结果证明了该方法的有效性。

Abstract

Aiming at the difficulty of extracting weak fault signal feature of rolling element bearings in practical engineering, a new method named adaptive probabilistic principal component analysis (APPCA) is proposed to enhance feature of bearing fault. PPCA is able to extract main fault feature and remove background noise interference, but easily affected by the number of principal components and the dimension of original variables. in order to adaptively achieve the best analysis result, the particle swarm optimization algorithm with multi-parameter optimization characteristic is applied to search for the optimal combination of influencing parameters of PPCA based on the maximum kurtosis criterion. After the original signal is processed by the APPCA method, the background noise is effectively suppressed, and the fault feature is enhanced, finally, the signal envelope spectrum is analyzed to identify fault feature. The simulation and experiment results show the effectiveness of this method.

关键词

滚动轴承 / 概率主成分分析 / 故障诊断

Key words

 rolling bearing / probabilistic principal component analysis / fault diagnosis

引用本文

导出引用
胡爱军,南 冰. 基于自适应概率主成分分析的滚动轴承故障特征增强方法[J]. 振动与冲击, 2017, 36(19): 145-150
HU Aijun, NAN Bing. Fault feature enhancement method for rolling bearing based on adaptive probabilistic principal component analysis[J]. Journal of Vibration and Shock, 2017, 36(19): 145-150

参考文献

[1] 胡爱军, 马万里, 唐贵基. 基于集成经验模态分解和峭度准则的滚动轴承故障特征提取方法[J]. 中国电机工程学报, 2012, 32(11):106-111.
HU Aijun, MA Wanli, TANG Guiji. Rolling bearing fault feature extraction method based on ensemble empirical mode decomposition and kurtosis criterion[J]. Proceedings of the CSEE, 2012, 32(11):106-111.
[2] 唐贵基, 王晓龙. 最大相关峭度解卷积结合1.5维谱的滚动轴承早期故障特征提取方法[J]. 振动与冲击, 2015(12):79-84.
TANG Guiji, WANG Xiaolong. Feature extraction for rolling bearing incipient fault based on maximum correlated kurtosis deconvolution and 1.5 dimension spectrum[J]. Journal of Vibration and Shock, 2015(12):79-84.
[3] 孙伟, 熊邦书, 黄建萍,等. 小波包降噪与LMD相结合的滚动轴承故障诊断方法[J]. 振动与冲击, 2012, 31(18):153-156.
SUN Wei, XIONG Bangshu, HUANG Jianping, et al. Fault diagnosis of a rolling bearing using Wavelet packet de-noising and LMD[J]. Journal of Vibration and Shock, 2012, 31(18):153-156.
[4] 邓飞跃, 唐贵基, 何玉灵. 基于倒谱预白化和形态学自互补Top-Hat 变换的滚动轴承故障特征提取[J]. 振动与冲击, 2015(15):77-81.
DENG Feiyue, TANG Guiji, HE Yuling. Fault feature extraction for rolling element bearings based on cepstrum pre-whitening and morphology self-complementary top-hat transformation[J]. Journal of Vibration and Shock, 2015(15):77-81.
[5] 唐贵基, 王晓龙. 基于EEMD降噪和1.5维能量谱的滚动轴承故障诊断研究[J]. 振动与冲击, 2014(1):6-10.
TANG Guiji, WANG Xiaolong. Fault diagnosis for roller bearings based on EEMD de-noising and 1.5 dimensional energy spectrum[J]. Journal of Vibration and Shock, 2014(1):6-10.
[6] 彭畅, 柏林, 谢小亮. 基于EEMD、度量因子和快速峭度图的滚动轴承故障诊断方法[J]. 振动与冲击, 2012(20):143-146.
PENG Chang, BO Lin, XIE Xiaoliang. Fault diagnosis method of rolling element bearings based on EEMD, measure-factor and fast kurtogram[J]. Journal of Vibration and Shock, 2012(20):143-146.
[7] Tipping M E, Bishop C M. Probabilistic Principal Component Analysis[J]. Journal of the Royal Statistical Society, 1999, 61(3):611–622.
[8] Bishop C M, Tipping M E. A Hierarchical Latent Variable Model for Data Visualization[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1998, 20(3):281-293.
[9] 陆超, 陈捷, 洪荣晶. 采用概率主成分分析的回转支承寿命状态识别[J]. 西安交通大学学报, 2015, 49(10):90-96.
LU Chao, CHEN Jie, HONG Rongjing. Recognition of life state for slewing bearings using probabilistic principal component analysis[J]. Journal of Xi’an Jiaotong University, 2015, 49(10):90-96.
[10] Xiang J, Zhong Y, Gao H. Rolling element bearing fault detection using PPCA and spectral kurtosis[J]. Measurement, 2015, 75:180-191.
[11] Bellas A, Bouveyron C, Cottrell M, et al. Model-based clustering of high-dimensional data streams with online mixture of probabilistic PCA[J]. Advances in Data Analysis & Classification, 2013, 7(3):281-300.
[12] Zuccolotto P. Principal component analysis with interval imputed missing values[J]. Asta Advances in Statistical Analysis, 2012, 96(1):1-23.
[13] Kennedy J, Eberhart R. Particle swarm optimization[A].  Proceeding of IEEE International Conference on Neural Networks[C]. Perth, Australia, 1995:1942-1948.
[14] 沈伋, 韩丽川, 沈益斌. 基于粒子群算法的飞机总体参数优化[J]. 航空学报, 2008, 29(6):1538-1541.
SHEN Ji, HAN Lichuan, SHEN Yibin. Optimization of airplane primary parameters based on particle swarm algorithm[J]. Acta Aeronautica ET Astronautica Sinica, 2008, 29(6):1538-1541.
[15] 唐贵基, 王晓龙. 最大相关峭度解卷积结合稀疏编码收缩的齿轮微弱故障特征提取[J]. 振动工程学报, 2015, 28(3):478-486.
TANG Guiji, WANG Xiaolong. Weak feature extraction of gear fault based on maximum correlated kurtosis deconvolution and sparse code shrinkage[J], Journal of Vibration Engineering, 2015, 28(3):478-486.
[16] 王宏超, 陈进, 董广明. 基于最小熵解卷积与稀疏分解的滚动轴承微弱故障特征提取[J]. 机械工程学报, 2013, 49(1):88-94.
WANG Hongchao, CHEN Jin, DONG Guangming. Fault diagnosis method for rolling bearing’s weak fault based on minimum entropy deconvolution and sparse decomposition[J]. Journal of Mechanical Engineering, 2013, 49(1):88-94.

PDF(860 KB)

Accesses

Citation

Detail

段落导航
相关文章

/