Semisupervised Distance-Preserving Self-Organizing Map for Machine-Defect Detection and Classification

Many intelligent learning methods have been successfully applied in gearbox fault diagnosis. Among them, self-organizing maps (SOMs) have been used effectively as they preserve the topological relationships of data. However, the structures of data clusters learned by SOMs may not be apparent and their shapes are often distorted. This paper presents a semisupervised diagnosis method based on a distance-preserving SOM for machine-fault detection and classification, which can also be used to visualize the SOM learning results directly. An experimental study performed on a gearbox and bearings indicated that the developed approach is effective in detecting incipient gear-pitting failure and classifying different bearing defects and levels of ball-bearing defects.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Fulei Chu,et al.  Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography , 2004 .

[3]  Teresa Orlowska-Kowalska,et al.  Neural networks application for induction motor faults diagnosis , 2003, Math. Comput. Simul..

[4]  Yang Yu,et al.  Time–energy density analysis based on wavelet transform , 2005 .

[5]  Ming Zhang,et al.  Automatic wavelet base selection and its application to contrast enhancement , 2010, Signal Process..

[6]  Jay Lee,et al.  Robust performance degradation assessment methods for enhanced rolling element bearing prognostics , 2003, Adv. Eng. Informatics.

[7]  Klaus Schulten,et al.  Self-organizing maps: stationary states, metastability and convergence rate , 1992, Biological Cybernetics.

[8]  Brij N. Singh,et al.  Optimal selection of wavelet basis function applied to ECG signal denoising , 2006, Digit. Signal Process..

[9]  Jochen Wendel,et al.  Formalizing Guidelines for Building Meaningful Self-Organizing Maps , 2010 .

[10]  Zhi-Hua Zhou,et al.  New Semi-Supervised Classification Method Based on Modified Cluster Assumption , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Shao Chao and Huang Houkuan.  A New Data Visualization Algorithm Based on ISOMAP , 2006 .

[12]  Erkki Oja,et al.  Engineering applications of the self-organizing map , 1996, Proc. IEEE.

[13]  Teuvo Kohonen,et al.  Self-Organizing Maps, Third Edition , 2001, Springer Series in Information Sciences.

[14]  F. Combet,et al.  Optimal filtering of gear signals for early damage detection based on the spectral kurtosis , 2009 .

[15]  Victor Giménez,et al.  New methods for self-organising map visual analysis , 2003, Neural Computing & Applications.

[16]  Esa Alhoniemi,et al.  SOM Toolbox for Matlab 5 , 2000 .

[17]  Klaus Schulten,et al.  Self-organizing maps: ordering, convergence properties and energy functions , 1992, Biological Cybernetics.

[18]  Robert X. Gao,et al.  Energy-Based Feature Extraction for Defect Diagnosis in Rotary Machines , 2009, IEEE Transactions on Instrumentation and Measurement.

[19]  Robert X. Gao,et al.  Hilbert–Huang Transform-Based Vibration Signal Analysis for Machine Health Monitoring , 2006, IEEE Transactions on Instrumentation and Measurement.

[20]  Robert X. Gao,et al.  PCA-based feature selection scheme for machine defect classification , 2004, IEEE Transactions on Instrumentation and Measurement.

[21]  M. Zuo,et al.  Gearbox fault detection using Hilbert and wavelet packet transform , 2006 .

[22]  Xiaojin Zhu,et al.  Can semi-supervised learning explain incorrect beliefs about categories? , 2011, Cognition.

[23]  K. Loparo,et al.  Bearing fault diagnosis based on wavelet transform and fuzzy inference , 2004 .

[24]  Robert X. Gao,et al.  Base Wavelet Selection for Bearing Vibration Signal Analysis , 2009, Int. J. Wavelets Multiresolution Inf. Process..

[25]  T Shi,et al.  Gearbox condition monitoring using self-organizing feature maps , 2004 .

[26]  Weihua Li,et al.  Feature extraction and classification of gear faults using principal component analysis , 2003 .

[27]  Tielin Shi,et al.  A Novel Technique for Data Visualization Based on SOM , 2005, ICANN.

[28]  S. P. Luttrell,et al.  Self-organisation: a derivation from first principles of a class of learning algorithms , 1989, International 1989 Joint Conference on Neural Networks.

[29]  Lifeng Xi,et al.  Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods , 2007 .

[30]  Weihua Li.  KERNEL PRINCIPAL COMPONENT ANALYSIS AND ITS APPLICATION IN GEAR FAULT DIAGNOSIS , 2003 .

[31]  Naim Baydar,et al.  A comparative study of acoustic and vibration signals in detection of gear failures using Wigner-Ville distribution. , 2001 .

[32]  O. A. Rosso,et al.  EEG analysis using wavelet-based information tools , 2006, Journal of Neuroscience Methods.

[33]  Maria-Florina Balcan,et al.  A discriminative model for semi-supervised learning , 2010, J. ACM.

[34]  Lijun Zhang,et al.  Gearbox pitting detection using linear discriminant analysis and distance preserving self-organizing map , 2012, 2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings.

[35]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

[36]  Mikhail Belkin,et al.  Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples , 2006, J. Mach. Learn. Res..

[37]  Jun-Ming Xu,et al.  OASIS: Online Active Semi-Supervised Learning , 2011, AAAI.

[38]  Fulei Chu,et al.  Support vector machines-based fault diagnosis for turbo-pump rotor , 2006 .

[39]  Peter W. Tse,et al.  Prediction of Machine Deterioration Using Vibration Based Fault Trends and Recurrent Neural Networks , 1999 .