The Use of a Multilabel Classification Framework for the Detection of Broken Bars and Mixed Eccentricity Faults Based on the Start-Up Transient

In this paper, a data-driven approach for the classification of simultaneously occurring faults in an induction motor is presented. The problem is treated as a multilabel classification problem, with each label corresponding to one specific fault. The faulty conditions examined include the existence of a broken bar fault and the presence of mixed eccentricity with various degrees of static and dynamic eccentricity, while three “problem transformation” methods are tested and compared. For the feature extraction stage, the start-up current is exploited using two well-known time–frequency (scale) transformations. This is the first time that a multilabel framework is used for the diagnosis of co-occurring fault conditions using information coming from the start-up current of induction motors. The efficiency of the proposed approach is validated using simulation data with promising results irrespective of the selected time–frequency transformation.

[1]  Vicente Climente-Alarcon,et al.  Induction Motor Diagnosis Based on a Transient Current Analytic Wavelet Transform via Frequency B-Splines , 2011, IEEE Transactions on Industrial Electronics.

[2]  H. Henao,et al.  Wavelet Based Instantaneous Power Analysis for Induction Machine Fault Diagnosis , 2006, IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics.

[3]  Jiansheng Chen,et al.  Palmprint authentication using a symbolic representation of images , 2010, Image Vis. Comput..

[4]  Subhasis Nandi,et al.  Detection of Eccentricity Faults in Induction Machines Based on Nameplate Parameters , 2011, IEEE Transactions on Industrial Electronics.

[5]  Christos Faloutsos,et al.  Fast Time Sequence Indexing for Arbitrary Lp Norms , 2000, VLDB.

[6]  S. Nandi,et al.  A detailed model of induction machines with saturation extendable for fault analysis , 2004, IEEE Transactions on Industry Applications.

[7]  Sebastián Ventura,et al.  A Tutorial on Multilabel Learning , 2015, ACM Comput. Surv..

[8]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[9]  Hubert Razik,et al.  Induction Motor Diagnosis Using Line Neutral Voltage Signatures , 2009, IEEE Transactions on Industrial Electronics.

[10]  Anthonio Teolis,et al.  Computational signal processing with wavelets , 1998, Applied and numerical harmonic analysis.

[11]  Bo-Suk Yang,et al.  Fault diagnosis of induction motor based on decision trees and adaptive neuro-fuzzy inference , 2009, Expert Syst. Appl..

[12]  Chrysostomos D. Stylios,et al.  A Symbolic Representation Approach for the Diagnosis of Broken Rotor Bars in Induction Motors , 2015, IEEE Transactions on Industrial Informatics.

[13]  Antero Arkkio,et al.  DWT analysis of numerical and experimental data for the diagnosis of dynamic eccentricities in induction motors , 2007 .

[14]  W. T. Thomson,et al.  Current signature analysis to detect induction motor faults , 2001 .

[15]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[16]  Eyke Hüllermeier,et al.  Multilabel classification via calibrated label ranking , 2008, Machine Learning.

[17]  Eric O. Postma,et al.  Dimensionality Reduction: A Comparative Review , 2008 .

[18]  Cursino B. Jacobina,et al.  A Simplified Induction Machine Model to Study Rotor Broken Bar Effects and for Detection , 2006 .

[19]  Arturo Garcia-Perez,et al.  The Application of High-Resolution Spectral Analysis for Identifying Multiple Combined Faults in Induction Motors , 2011, IEEE Transactions on Industrial Electronics.

[20]  Hamid A. Toliyat,et al.  Condition monitoring and fault diagnosis of electrical machines-a review , 1999, Conference Record of the 1999 IEEE Industry Applications Conference. Thirty-Forth IAS Annual Meeting (Cat. No.99CH36370).

[21]  M. Sahraoui,et al.  A winding function-based model of air-gap eccentricity in saturated induction motors , 2012, 2012 XXth International Conference on Electrical Machines.

[22]  Vicente Climente-Alarcon,et al.  Automatizing the broken bar detection process via short time Fourier transform and two-dimensional piecewise aggregate approximation representation , 2014, 2014 IEEE Energy Conversion Congress and Exposition (ECCE).

[23]  Eyke Hüllermeier,et al.  Label ranking by learning pairwise preferences , 2008, Artif. Intell..

[24]  G.E. Dawson,et al.  The detection of broken bars in the cage rotor of an induction machine , 1988, Conference Record of the 1988 IEEE Industry Applications Society Annual Meeting.

[25]  George Nikolakopoulos,et al.  Principal Component Analysis of the start-up transient and Hidden Markov Modeling for broken rotor bar fault diagnosis in asynchronous machines , 2013, Expert Syst. Appl..

[26]  Gerardo G. Acosta,et al.  A current monitoring system for diagnosing electrical failures in induction motors , 2006 .

[27]  Chi-Man Vong,et al.  A New Framework of Simultaneous-Fault Diagnosis Using Pairwise Probabilistic Multi-Label Classification for Time-Dependent Patterns , 2013, IEEE Transactions on Industrial Electronics.

[28]  G. Nikolakopoulos,et al.  Stator winding short circuit fault detection based on set membership identification for three phase induction motors , 2012, 2012 20th Mediterranean Conference on Control & Automation (MED).

[29]  Jose A. Antonino-Daviu,et al.  Instantaneous Frequency of the Left Sideband Harmonic During the Start-Up Transient: A New Method for Diagnosis of Broken Bars , 2009, IEEE Transactions on Industrial Electronics.

[30]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[31]  Jesse Read,et al.  Scalable Multi-label Classification , 2010 .

[32]  David J. Hand,et al.  Classifier Technology and the Illusion of Progress , 2006, math/0606441.

[33]  Mohamed El Hachemi Benbouzid.  A review of induction motors signature analysis as a medium for faults detection , 2000, IEEE Trans. Ind. Electron..

[34]  Grigorios Tsoumakas,et al.  Mining Multi-label Data , 2010, Data Mining and Knowledge Discovery Handbook.

[35]  Zhi-Hua Zhou,et al.  Multi-instance multi-label learning , 2008, Artif. Intell..

[36]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[37]  H.A. Toliyat,et al.  Condition Monitoring and Fault Diagnosis of Electrical Motors—A Review , 2005, IEEE Transactions on Energy Conversion.

[38]  Antero Arkkio,et al.  Detection of combined faults in induction machines with stator parallel branches through the DWT of the startup current , 2009 .

[39]  Vilas N. Ghate,et al.  Cascade Neural-Network-Based Fault Classifier for Three-Phase Induction Motor , 2011, IEEE Transactions on Industrial Electronics.

[40]  Jawad Faiz,et al.  Static-, Dynamic-, and Mixed-Eccentricity Fault Diagnoses in Permanent-Magnet Synchronous Motors , 2009, IEEE Transactions on Industrial Electronics.

[41]  Martin Riera-Guasp,et al.  Enhanced Simulink Induction Motor Model for Education and Maintenance Training , 2012 .

[42]  Jose Antonino-Daviu,et al.  Reliable detection of induction motor rotor faults under the rotor axial air duct influence , 2013, 2013 IEEE Energy Conversion Congress and Exposition.

[43]  Robert H. Kushler,et al.  Exploratory Data Analysis With MATLAB® , 2006, Technometrics.

[44]  Lior Rokach,et al.  Data Mining And Knowledge Discovery Handbook , 2005 .

[45]  Eamonn J. Keogh,et al.  Locally adaptive dimensionality reduction for indexing large time series databases , 2001, SIGMOD '01.