Detection of rotor faults based on Hilbert Transform and neural network for an induction machine

This paper presents a technique to detect and diagnose the broken rotor bars in an induction machine. The main signature used is the stator currents to envelope in the analysis of this kind of fault. Moreover, the envelope analysis of the stator currents is calculated based on the Hilbert Transform. Then, Fast Fourier Transform are introduced to extract the fault components. However, the technique used for improving the fault detection technique is based on the neural network. Finally, the results of the stator currents envelope spectrum (the amplitude Am and frequency fm of the harmonic) shows an efficient of detection under varying loads condition. The efficiency of the proposed method is verified by simulation tests.

[1]  Richard J. Povinelli,et al.  Induction Machine Broken Bar and Stator Short-Circuit Fault Diagnostics Based on Three-Phase Stator Current Envelopes , 2008, IEEE Transactions on Industrial Electronics.

[2]  Elhoussin Elbouchikhi,et al.  An Efficient Hilbert–Huang Transform-Based Bearing Faults Detection in Induction Machines , 2017, IEEE Transactions on Energy Conversion.

[3]  Boubakeur Zegnini,et al.  Diagnosis of the combined rotor faults using air gap magnetic flux density spectrum for an induction machine , 2017, Int. J. Syst. Assur. Eng. Manag..

[4]  P.M. Frank,et al.  Fault detection and isolation in technical processes with neural networks , 1995, Proceedings of 1995 34th IEEE Conference on Decision and Control.

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

[6]  B. Samanta,et al.  Gear fault detection using artificial neural networks and support vector machines with genetic algorithms , 2004 .

[7]  M. E. H. Benbouzid,et al.  What Stator Current Processing Based Technique to Use for Induction Motor Rotor Faults Diagnosis , 2002, IEEE Power Engineering Review.

[8]  I. Jaksch,et al.  Faults diagnosis of three-phase induction motors using envelope analysis , 2003, 4th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives, 2003. SDEMPED 2003..

[9]  R. Puche-Panadero,et al.  Improved Resolution of the MCSA Method Via Hilbert Transform, Enabling the Diagnosis of Rotor Asymmetries at Very Low Slip , 2009, IEEE Transactions on Energy Conversion.

[10]  Boubakeur Zegnini,et al.  Multi-Class Classification Approach for the Diagnosis of Broken Rotor Bars based on Air-Gap Magnetic Flux Density , 2017 .

[11]  Gérard-André Capolino,et al.  Advances in Diagnostic Techniques for Induction Machines , 2008, IEEE Transactions on Industrial Electronics.

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

[13]  B Bessam,et al.  Detection of broken rotor bar faults in induction motor at low load using neural network. , 2016, ISA transactions.

[14]  Vilas N. Ghate,et al.  Optimal MLP neural network classifier for fault detection of three phase induction motor , 2010, Expert Syst. Appl..