层叠P阶多项式主成分分析在轴承故障诊断中的应用

PDF(1823 KB)

振动与冲击 ›› 2019, Vol. 38 ›› Issue (2) : 25-32.

论文

牟亮 ,王凯 ,李彦，於辉

作者信息 +

Bearing fault diagnosis based on the stacked P-order polynomial principal component analysis

MOU Liang,WANG Kai,LI Yan,YU Hui

Author information +

文章历史 +

摘要

针对传统滚动轴承故障特征提取及识别高度依赖先验知识及专家经验，导致其故障诊断的人工成本高及分类精度不够高的问题，提出一种层叠P阶多项式主成分分析方法实现滚动轴承故障的精确诊断。首先，提出一种可适用于处理线性不可分数据的P阶多项式主成分分析法从滚动轴承的振动信号中自动学习去相关的低维特征；其次，构建了层叠P阶多项式主成分分析网络，从去相关的低维特征中进一步增强学习更具可分辨性的特征，并通过反向优化过程，确保学习的特征不失真；最后，采用K最近邻分类器对学习到的特征矢量进行分类，实现故障模式的辨识。通过滚动轴承故障数据库上的诊断实验验证了提出方法的可靠性和有效性。

Abstract

The traditional rolling bearing fault feature extraction and recognition highly rely on priori knowledges and expert experiences,resulting in its high labor cost and not enough accurate classification.A method of stacked P-order polynomial principal component analysis(SPPCA) was proposed to realize the accurate diagnosis of rolling bearing faults.First,a P-order polynomial principal component analysis(PPCA),which is applicable to deal with linear inseparable data,was presented to automatically learn the uncorrelated low-dimensional features from the vibration signals of rolling bearings.Next,a SPPCA network was built to further learn more discriminative features，using the back-forward optimization to ensure that learnt features are not distorted.Then,a K nearest neighbor classifier was used to classify the learnt feature vectors to identify the fault model.The experimental results on the database of rolling bearings faults verified the reliability and validity of the proposed method.

导出引用

牟亮,王凯,李彦，於辉. 层叠P阶多项式主成分分析在轴承故障诊断中的应用[J]. 振动与冲击, 2019, 38(2): 25-32

MOU Liang,WANG Kai,LI Yan,YU Hui. Bearing fault diagnosis based on the stacked P-order polynomial principal component analysis[J]. Journal of Vibration and Shock, 2019, 38(2): 25-32

参考文献

[1] 丁康,孔正国.振动调幅调频信号的调制边频带分析及其调解方法[J].振动与冲击,2005,24(6):9-12.
DING Kang, KONG Zhengguo. Analysis and demodulation method of side band of vibration amplitude modulation and frequency modulation signal[J]. Journal of vibration and shock, 2005,24(6):9-12.
[2] 向丹,葛爽.一种基于小波包样本熵和流形学习的故障特征提取模型[J].振动与冲击,2013,9(11):1—5.
XIANG Dan,GE Shuang. A model of fault feature extraction based on wavelet packet sample entropy and manifold learning[J]. Journal of vibration and shock,2013,9(11):1—5.
[3] 王志刚,李友荣,吕勇.基于谐波小波变换的共振解调法[J].振动与冲击, 2006,25(4):159—161.
WANG Zhigang, LI Yourong, LV Yong. Resonance Demodulation Method Based on Harmonic Wavelet Transform [J]. Journal of vibration and shock, 2006, 25(4):159—161.
[4] LEI Yaguo, FENG Jia, LIN Jing et al. An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data[J]. IEEE Transactions on industrial electron,2016, 63(5):3137-3147.
[5] AMAR M, I GONDAL, C WILSON. Vibration spectrum imaging: A novel bearing fault classification approach[J]. IEEE Transactions on industrial electron, 2015,62(1):494–502.
[6] ZHANG L, XIONG G, Liu H, et al. Bearing fault diagnosis using multi-scale entropy and adaptive neuro-fuzzy inference[J]. Expert Systems with Applications, 2010, 37(8): 6077-6085.
[7] ZHEN J, Cheng Junshen, Yu Yang. A rolling bearing fault diagnosis approach based on LCD and fuzzy entropy[J]. Mechanism and Machine Theory, 2013,70:441-453.
[8] I. T. JOLLIFFE. Principal Component Analysis[M]. Kent: Sprin-ger, 2012:204-205.
[9] L. I. KUNCHEVA, W. J. FAITHFULL. PCA feature extraction for change detection in multidimensional unlabeled data[J]. IEEE Transactions on neural networks and learning systems, 2014.25(1):69-80.
[10] MPS Chawla. PCA and ICA processing methods for removal of artifacts and noise in electro-car diagram: A survey and comparison[J]. Applied Soft Computing, 2011,11(2):2216-2226.
[11] BERTSEKAS D P. Constrained optimization and Lagrange multiplier methods[M]. Manhattan:Academic press, 2014:160-175.
[12] VINCENT P, LAROCHELLE H, LAJOIE I, et al. Stacked denoising auto encoders: Learning useful representations in a deep network [J]. Journal of Machine Learning Research, 2010,11(1): 3371-3408.
[13] LOU X, K. A. LOPARO. Bearing fault diagnosis based on wavelet transform and fuzzy inference[J]. Mechanical Systems and Signal Processing, 2014,18(5):1077–1095.
[14] NASIBOVE E, KANDEMIR-CAVAS C. Efficiency analysis of KNN and minimum distance-based classifiers in enzyme family prediction[J]. Computational biology and chemistry, 2009, 33(6):461-464.
[15] 雷亚国，贾峰，周昕，等.基于深度学习理论的机械装备大数据健康监测方法[J].机械工程学报,2015,11(51):49
LEI Yaguo, JIA Feng, ZHOU Xin, et al. A Deep Learning-based Method for Machinery Health Monitoring with Big Data[J]. Journal of mechanical engineering, 2015,11(51):49
[16] Dawn E, Holmes Lakhmi C, Jain. Innovations in Machine
Learning[M]. New York:Springer Press, 2002.
[17] LI W, ZHANG S, HE g. Semi-supervised distance-preserving self-organizing map for machine-defect detection and classification[J]. IEEE Transactions on Instrumentation and Measurement, 2013,62(5):869-879.
[18] ZHANG X, YI Liang, J. Zhou. A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM[J]. Measurement, 2015,69(1):164-179.
[19] 李锋，赵洁，王家序，等.判别式正交线性局部切空间排列故障辨识[J].计算机集成制造系统,2014,1(20):173-180.
LI Feng, ZHAO Jie, WANG Jiaxu, et al. Fault identification for discriminant orthogonal linear local tangent space alignment[J]. Computer Integrated Manufacturing Systems,2014,1(20):173-180.李锋，王家序，汤宝平，等.有监督不相关局部Fisher判别分析故障诊断[J]. 振动工程学报.2015.8(28):657-664.
[20] LI Feng, WANNG Jiaxu, TANG Baoping, et al. Supervised uncorrelated local Fisher discriminant analysis fault diagnosis[J]. Journal of vibration engineering, 2015.8(28):657-664.