Datum unit optimization for robustness of a journal bearing diagnosis system

This paper describes a robust diagnosis method for a rotor system with a journal bearing. To enhance the robustness of a journal bearing diagnosis system, it is of great importance to define an optimum datum unit for featuring anomaly states of the rotor system. To support the research goal, this study makes use of three measures for class separation, including Kullback-Leibler divergence (KLD), Fisher discriminant ratio (FDR), and a newly proposed measure: probability of separation (PoS). From the viewpoint of class separability, this work found that PoS is more attractive than other methods for quantification of class separation. PoS offers favorable properties like normalization, boundedness, and high sensitivity. A generic algorithm integrated with one of three measures consistently suggested the optimum datum units among the feasible datum units. Optimum datum units were found to be one-cycle for time-domain features and sixty-cycles for frequency-domain features. The support vector machine (SVM) classifier with the optimum datum units was used for diagnosing a normal and three anomaly states. The health classification results showed that the proposed optimum datum units can outperform other datum units.

[1]  Robert B. Randall,et al.  Use of the acceleration signal of a gearbox in order to perform angular resampling (with limited speed fluctuation) , 2005 .

[2]  S. J. Loutridis.  Gear failure prediction using multiscale local statistics , 2008 .

[3]  Steven X. Ding,et al.  Influence of Sampling Period on a Class of Optimal Fault-Detection Performance , 2009, IEEE Transactions on Automatic Control.

[4]  Chris J. Harris,et al.  Hybrid Computed Order Tracking , 1999 .

[5]  Herman Augusto Lepikson,et al.  Applications of information theory, genetic algorithms, and neural models to predict oil flow , 2009 .

[6]  A. Srividya,et al.  Fault diagnosis of rolling element bearing using time-domain features and neural networks , 2008, 2008 IEEE Region 10 and the Third international Conference on Industrial and Information Systems.

[7]  Wook-Ryun Lee,et al.  Copula-Based Statistical Health Grade System Against Mechanical Faults of Power Transformers , 2012, IEEE Transactions on Power Delivery.

[8]  Robert I. Damper,et al.  A fast separability-based feature-selection method for high-dimensional remotely sensed image classification , 2008, Pattern Recognit..

[9]  Dong Wang,et al.  Robust health evaluation of gearbox subject to tooth failure with wavelet decomposition , 2009 .

[10]  Don H. Johnson,et al.  Information-Theoretic Analysis of Neural Coding , 2004, Journal of Computational Neuroscience.

[11]  Ming J. Zuo,et al.  Multivariate EMD and full spectrum based condition monitoring for rotating machinery , 2012 .

[12]  J. Sanz,et al.  Fault diagnosis of rotating machinery based on auto-associative neural networks and wavelet transforms , 2007 .

[13]  Robert C. Eisenmann.  Machinery Malfunction Diagnosis and Correction: Vibration Analysis and Troubleshooting for Process Industries , 1997 .

[14]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[15]  Hee Soo Kim,et al.  Statistical Health Reasoning of Water-Cooled Power Generator Stator Bars Against Moisture Absorption , 2015, IEEE Transactions on Energy Conversion.

[16]  Byeng D. Youn,et al.  Random Field Characterization Considering Statistical Dependence for Probability Analysis and Design , 2010 .

[17]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[18]  Heonjun Yoon,et al.  Stochastic quantification of the electric power generated by a piezoelectric energy harvester using a time–frequency analysis under non-stationary random vibrations , 2014 .

[19]  Chao-Ming Huang,et al.  Fault Diagnosis of Steam Turbine-Generator Sets Using an EPSO-Based Support Vector Classifier , 2013, IEEE Transactions on Energy Conversion.

[20]  Yaguo Lei,et al.  Application of the EEMD method to rotor fault diagnosis of rotating machinery , 2009 .

[21]  A.B. Fernandes,et al.  Sampling rate of digital fault recorders influence on fault diagnosis , 2004, 2004 IEEE/PES Transmision and Distribution Conference and Exposition: Latin America (IEEE Cat. No. 04EX956).

[22]  Jing Lin,et al.  Feature Extraction Based on Morlet Wavelet and its Application for Mechanical Fault Diagnosis , 2000 .

[23]  Urbano Nunes,et al.  Novel Maximum-Margin Training Algorithms for Supervised Neural Networks , 2010, IEEE Transactions on Neural Networks.

[24]  Ming J. Zuo,et al.  GEARBOX FAULT DIAGNOSIS USING ADAPTIVE WAVELET FILTER , 2003 .

[25]  Yuehua Huang,et al.  A new quantum inspired chaotic artificial bee colony algorithm for optimal power flow problem , 2015 .

[26]  Bo-Suk Yang,et al.  Application of Dempster–Shafer theory in fault diagnosis of induction motors using vibration and current signals , 2006 .

[27]  Shan Suthaharan,et al.  Support Vector Machine , 2016 .

[28]  Fanrang Kong,et al.  Machine condition monitoring using principal component representations , 2009 .

[29]  Marti A. Hearst.  Trends & Controversies: Support Vector Machines , 1998, IEEE Intell. Syst..

[30]  B Liu.  Selection of wavelet packet basis for rotating machinery fault diagnosis , 2005 .

[31]  Fred K. Choy,et al.  Damage Identification of a Gear Transmission Using Vibration Signatures , 2003 .

[32]  Byeng D. Youn,et al.  A co-training-based approach for prediction of remaining useful life utilizing both failure and suspension data , 2015 .

[33]  S. Sinanovic,et al.  Anomaly detection using the Kullback-Leibler divergence metric , 2008, 2008 First International Symposium on Applied Sciences on Biomedical and Communication Technologies.

[34]  Byeng D. Youn,et al.  A probabilistic detectability-based sensor network design method for system health monitoring and prognostics , 2015 .

[35]  José R. Perán,et al.  Angular resampling for vibration analysis in wind turbines under non-linear speed fluctuation , 2011 .

[36]  Walmir M. Caminhas,et al.  SVM practical industrial application for mechanical faults diagnostic , 2011, Expert Syst. Appl..

[37]  K N Gupta.  Vibration — A tool for machine diagnostics and condition monitoring , 1997 .

[38]  Tian Han,et al.  Fault Diagnosis System of Induction Motors Based on Neural Network and Genetic Algorithm Using Stator Current Signals , 2006 .

[39]  Byeng D. Youn,et al.  A generic probabilistic framework for structural health prognostics and uncertainty management , 2012 .

[40]  Yaguo Lei,et al.  Application of an intelligent classification method to mechanical fault diagnosis , 2009, Expert Syst. Appl..

[41]  Bo-Suk Yang,et al.  Support vector machine in machine condition monitoring and fault diagnosis , 2007 .

[42]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[43]  Anoushiravan Farshidianfar,et al.  Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine , 2007 .

[44]  Satish C. Sharma,et al.  Fault diagnosis of ball bearings using continuous wavelet transform , 2011, Appl. Soft Comput..

[45]  Fanrang Kong,et al.  Phase Space Feature Based on Independent Component Analysis for Machine Health Diagnosis , 2012 .

[46]  Seamus D. Garvey,et al.  Dynamics of Rotating Machines , 2010 .

[47]  Singiresu S Rao,et al.  Reliability-Based Design , 1992 .

[48]  L. Jiang,et al.  Fault Diagnosis of Rotating Machinery Based on Multisensor Information Fusion Using SVM and Time-Domain Features , 2014 .

[49]  Chao Hu,et al.  Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful life , 2011, 2011 IEEE Conference on Prognostics and Health Management.

[50]  Yaguo Lei,et al.  A review on empirical mode decomposition in fault diagnosis of rotating machinery , 2013 .