Fault recognition method for speed-up and speed-down process of rotating machinery based on independent component analysis and Factorial Hidden Markov Model

Abstract The behavior characteristics of the speed-up and speed-down process of rotating machinery possess the distinct diagnostic value. The abundant information, non-stationarity, poor repeatability and reproducibility in this process lead to the necessity to find the corresponding method of feature extraction and fault recognition. In this paper, combining independent component analysis (ICA) and Factorial Hidden Markov Model (FHMM), a new method of the fault recognition named ICA–FHMM is proposed. In the proposed method, ICA is used for the redundancy reduction and feature extraction of the multi-channel detection, and FHMM as a classifier to recognize the faults of the speed-up and speed-down process in rotating machinery. This method is compared with another recognition method named ICA–HMM, in which ICA is similarly used for the feature extraction, however Hidden Markov Model (HMM) as a classifier. Experimental results show that the proposed method is very effective, and the ICA–FHMM recognition method is superior to the ICA–HMM recognition method.

[1]  Manabu Kotani,et al.  Application of independent component analysis to feature extraction of speech , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[2]  S. Poyhonen,et al.  INDEPENDENT COMPONENT ANALYSIS OF VIBRATIONS FOR FAULT DIAGNOSIS OF AN INDUCTION MOTOR , 2003 .

[3]  M. Ingleby,et al.  Classification of vibration signatures of turbogenerators , 1989 .

[4]  Li Zhi.  Application of Wavelet Transform and FHMM in Fault Diagnosis of Speed-up and Speed-down Process of Rotating Machinery , 2003 .

[5]  Amrane Houacine,et al.  Compound PCA-ICA neural network model for enhancement and feature extraction of multi-frequency polarimetric SAR imagery , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[6]  Erkki Oja,et al.  Applications of neural blind separation to signal and image processing , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  Ding Qi.  Research on Fault Diagnosis Methods for Rotating Machines Based on Factorial Hidden Markov Model , 2003 .

[8]  Robert P. W. Duin,et al.  Blind separation of rotating machine sources: bilinear forms and convolutive mixtures , 2002, Neurocomputing.

[9]  T J Sejnowski,et al.  Learning the higher-order structure of a natural sound. , 1996, Network.

[10]  Wu Zhao-tong.  ICA Based Neural Networks for Pattern Recognition of Mechanical Faults , 2003 .

[11]  Aapo Hyvärinen,et al.  Survey on Independent Component Analysis , 1999 .

[12]  Beth Logan,et al.  Factorial Hidden Markov Models for Speech Recognition: Preliminary Experiments , 1997 .

[13]  Michael I. Jordan,et al.  Factorial Hidden Markov Models , 1995, Machine Learning.

[14]  J. Cardoso,et al.  Blind beamforming for non-gaussian signals , 1993 .

[15]  M. Ingleby,et al.  Automatic taxonomy and modal analysis for vibration diagnosis , 1991 .

[16]  Robert P. W. Duin,et al.  Robust machine fault detection with independent component analysis and support vector data description , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[17]  Ho-Young Jung,et al.  Speech feature extraction using independent component analysis , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[18]  Yang Shi-xi,et al.  Extracting invariable fault features of rotating machines with multi-ICA networks , 2003 .

[19]  Tzyy-Ping Jung,et al.  Independent Component Analysis of Electroencephalographic Data , 1995, NIPS.

[20]  Aapo Hyvärinen,et al.  Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces , 2000, Neural Computation.

[21]  Beth Logan,et al.  Factorial HMMs for acoustic modeling , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[22]  R. Moddemeijer.  On estimation of entropy and mutual information of continuous distributions , 1989 .

[23]  Alexander Ypma,et al.  Learning methods for machine vibration analysis and health monitoring , 2001 .