Given the problem of fault samples is difficult to get and the demand of the real-time online diagnosis in the gear fault diagnosis. A novel Incremental Semi-supervised Variable Predictive Mode based Class Discriminate (ISVPMCD) gear fault on-line detection method is put forward in this paper. Firstly, the VPMCD approach was used to establish initial prediction model for a small number of labeled samples; secondly, the criterion of VPMCD was used to provide initial pseudo labels for unlabeled samples; thirdly, the pseudo labeled samples were screened by cross-correlation rule; fairly, the pseudo labeled samples and labeled samples as the training samples are to update the initial prediction model, so that the global information of the whole sample set could be considered, and which can effectively solve the problem of fault diagnosis of small sample. In addition, the method does not need to establish discriminant model in the process of real-time updating new samples, which shortens the time of classification and offers a new way for real-time online diagnosis. The analysis results of the UCI standard data and the experimental data of gear show that the ISVPMCD pattern recognition method suitable for small samples can identify the gear working state and fault type much more quickly and accurately.
Key words
Incremental Semi-supervised Variable Predictive Mode based Class Discriminate /
Incremental；Semi-supervised /
Gear fault diagnosis
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1] Bai S H. Semi-supervised learning of language model using unsupervised topic model[C].IEEE International Conference on Acoustics, Speech and Signal Processing-Proceedings, 2010:5386-5389.
[2] Mehdizadeh M, MacNish C. Semi-supervised neighborhood preserving discriminant embedding: a semi-supervised subspace learning algorithm [J].Computer Science, 2011, 6494:199-212.
[3] Xiaobin He, Yupu Yang, Yahong Yang. Fault diagnosis based on variable –weighted kernel Fisher discriminant analysis [J]. Chemometrics and Intelligent Laboratory System, 2008, 93(1):27-33.
[4] M.Saimurugan,K.I.Ramachandran,V.Sugumaran,et al.Multi component fault diagnosis of rotational mechanical system based on decision tree and support vector machine[J].Expert Systems with Applications,2011,38(4):3819-3826.
[5] Zengbing Xu,Jiangping Xuan,Tielin Shi,et al.A novel fault diagnosis method of bearing based on improved fussy ARTMAP and modified distance discriminant technique[J].Expert Systems with Applications.2009,36(9):11801-11807.
[6] Wang C C, Yuan K, Shen P C, et al., Applications of fault diagnosis in rotating machinery by using time series analysis with neural network[J]. Expert Systems with Applications, 2010, 37(2): 1696-1702.
[7] Sheng-wei Fei, Xiao-bin Zhang. Fault diagnosis of power transformer based on support vector machine with genetic algorithm [J]. Expert Systems with Applications, 2009, 36(8): 11352-11357.
[8] Rao Raghuraj,Samavedham Lakshminarayanan.Variable predictive models-A new multivariate classification approach for pattern recognition applications [J]. Pattern Recognition, 2009, 42(1):7-16.
[9] Peng Z, Chu F, He Y. Vibration signal analysis and feature extraction based on reassigned wavelet scalogram[J]. Journal of Sound and Vibration, 2002, 253(5):1087-1100.
[10] Cheng J S,Yu D J,Yang Y. Energy operator demodulating approach based on EMD and its application in mechanical fault diagnosis［J］.Chinese Journal of Mechanical Engineering, 2004,40( 8):115-118.
[11] Yaguo Lei,Zhengjia He,Yanyang Zi.Application of the EEMD method to rotor fault diagnosis of rotating machinery [J]. Mechanical Systems and Signal Processing.2009, 23:1327-1338.
[12] 程军圣,郑近德,杨宇.一种新的非平稳信号分析方法——局部特征尺度分解[J].振动工程学报.2012, 25(2):215-220.
Cheng Junsheng, Zheng Jinde, Yang Yu. A nonstationary signal analysis approach——the local characteristic-scale decomposition method[J].Journal of Vibration Engineering, 2012, 25(2): 215-22.
[13] Frank A, Asuncion A. UCI machine learning repository [Online], available: http://archive.ics.uci.edu/ml, May 3, 2010
{{custom_fnGroup.title_en}}
Footnotes
{{custom_fn.content}}
PDF(1211 KB)
