Journal of information and communication convergence engineering

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지

Winding Fault Diagnosis of Induction Motor Using Neural Network

  • Song Myung-Hyun (Department of Electrical Control Engineering, Sunchon National University) ;
  • Park Kyu-Nam (Department of Electrical Control Engineering, Sunchon National University) ;
  • Woo Hyeok-Jae (Department of Electrical Control Engineering, Sunchon National University) ;
  • Lee Tae-Hun (Department of Electrical Control Engineering, Sunchon National University) ;
  • Han Min-Kwan (Korea Electrotechnology Research Institute)
  • Published : 2005.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposed a fault diagnosis technique of induction motors winding fault based on an artificial neural network (ANN). This method used Park's vector pattern as input data of ANN. The ANN are firstly learned using this pattern, and then classify between 'healthy' and 'winding fault' (with 2, 10, and 20 shorted turn) induction motor under 0, 50, and $100\%$ load condition. Also the possibility of classification of untrained turn-fault and load condition are tested. The proposed method has been experimentally tested on a 3-phase, 1 HP squirrel-cage induction motor. The obtained results provided a high level of accuracy especially in small turn fault, and showed that it is a reliable method for industrial application

Keywords

References

  1. W. T.Thomson and Mark Fenger,'Current signature analysis to detect induction motor faults,' IEEE Industry Application Magazines, pp. 26-34. July/August 2001
  2. R. A. Leonhard and W.T. Thompson, 'Vibration and stray flux monitoring for unbalanced supply and intertum winding fault diagnosis in induction machines,' British Journal ofNondestructive testing. pp. 211-215, July 1986
  3. Chen Li'an and Zhang Peiming, 'Simulation of Motor Faults and Protection Based on MATLAB,' Electrical Machines and Systems, 2001. lCEMS 2001.Proceedings of the Fifth International Conference on, Vol. 1, pp 452-455, 18-20, Aug. 2001 https://doi.org/10.1109/ICEMS.2001.970709
  4. G. B. Kliman, W. J. Premerlani, R. A. Koegl and D. Hoeweler 'A new approach to on-line tum fault detection in AC motors,' Conference Records IEEE-lAS Annual Meeting, Vol. 1, pp. 687-693, 1996 https://doi.org/10.1109/IAS.1996.557113
  5. Sang-Bin Lee, R. M. Tallam and T. G. Habetler, 'A robust, on-line Tun-fault detection technique for induction machines based on monitoring the sequence component impedance matrix,' Power Electronics Specialists Conference, 2001. PESC. 2001 IEEE 32nd Annual, Vol 4, pp. 2217-2223 17-21, June 2001 https://doi.org/10.1109/PESC.2001.954449
  6. C. Filippetti, G. Franceschini, F. Tassoni, and P. Vas, 'Integrated condition monitoring and diagnosis of electrical machines using minimum configuration artificial intelligence,' Proceedings of EPE97, Vol. 2,pp.983-988,1997
  7. A. J. M. Cardoso et aI., 'Inter tum stator winding fault diagnosis in three-phase induction motors, by Park's Vector Approach,' IEEE Trans. Ind Applicat., Vol. 29, no. 3, pp. 595-598, Sept. 1999
  8. A. J. M. Cardoso et al, 'Computer-aided detection of airgap eccentricity in operating three-phase induction motors by park's vector approach,' IEEE Trans. Ind. Applicat., Vol. 29, pp. 897-901, Sept./Oct. 1993 https://doi.org/10.1109/28.245712
  9. Hamid Nejjari and Mohamed EI Hachemi Benbouzid, 'Monitoring and Diagnosis of Induction Motors Electrical Faults Using a Current Park's Vector pattern Learning Approach,' IEEE Trans. Power Electron pp. 730-735, 2000