International Journal of Computer Science & Network Security

International Journal of Computer Science & Network Security (국제컴퓨터통신보호논문지학회)
권호 표지
DOI QR코드

DOI QR Code

LSTM based Supply Imbalance Detection and Identification in Loaded Three Phase Induction Motors

  • Majid, Hussain (Department of Electronic Engineering, Quaid-e-Awam University of Engineering, Science & Technology) ;
  • Fayaz Ahmed, Memon (Department of Computer Systems Engineering, Quaid-e-Awam University of Engineering, Science & Technology) ;
  • Umair, Saeed (Department of Electronic Engineering, Quaid-e-Awam University of Engineering, Science & Technology) ;
  • Babar, Rustum (Department of Electronic Engineering, Quaid-e-Awam University of Engineering, Science & Technology) ;
  • Kelash, Kanwar (Department of Electronic Engineering, Quaid-e-Awam University of Engineering, Science & Technology) ;
  • Abdul Rafay, Khatri (Department of Electronic Engineering, Quaid-e-Awam University of Engineering, Science & Technology)
  • Received : 2023.01.05
  • Published : 2023.01.30
Download PDF
⟨ Previous Next ⟩

Abstract

Mostly in motor fault detection the instantaneous values 3 axis vibration and 3phase current in time domain are acquired and converted to frequency domain. Vibrations are more useful in diagnosing the mechanical faults and motor current has remained more useful in electrical fault diagnosis. With having some experience and knowledge on the behavior of acquired data the electrical and mechanical faults are diagnosed through signal processing techniques or combine machine learning and signal processing techniques. In this paper, a single-layer LSTM based condition monitoring system is proposed in which the instantaneous values of three phased motor current are firstly acquired in simulated motor in in health and supply imbalance conditions in each of three stator currents. The acquired three phase current in time domain is then used to train a LSTM network, which can identify the type of fault in electrical supply of motor and phase in which the fault has occurred. Experimental results shows that the proposed single layer LSTM algorithm can identify the electrical supply faults and phase of fault with an average accuracy of 88% based on the three phase stator current as raw data without any processing or feature extraction.

Keywords

References

  1. D. Xiao, Y. Huang, X. Zhang, H. Shi, C. Liu, and Y. Li, "Fault diagnosis of asynchronous motors based on LSTM neural network," in 2018 prognostics and system health management conference (PHMChongqing), 2018, pp. 540-545: IEEE.
  2. T. Han, B.-S. Yang, W.-H. Choi, and J.-S. J. I. J. o. R. M. Kim, "Fault diagnosis system of induction motors based on neural network and genetic algorithm using stator current signals," vol. 2006, 2006.
  3. T. Han, B. S. Yang, and Z. J. J. J. o. Q. i. M. E. Yin, "Feature-based fault diagnosis system of induction motors using vibration signal," 2007.
  4. C. Huang, F. Wu, J. Zhao, D. J. I. J. o. A. E. Zhou, and Mechanics, "A novel fault diagnosis method in SVPWM voltage-source inverters for vector controlled induction motor drives," vol. 50, no. 1, pp. 97-111, 2016. https://doi.org/10.3233/JAE-150073
  5. P. Gangsar, R. J. M. S. Tiwari, and S. Processing, "Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review," vol. 144, p. 106908, 2020.
  6. P. Gangsar, R. J. M. S. Tiwari, and S. Processing, "Comparative investigation of vibration and current monitoring for prediction of mechanical and electrical faults in induction motor based on multiclass-support vector machine algorithms," vol. 94, pp. 464-481, 2017. https://doi.org/10.1016/j.ymssp.2017.03.016
  7. G. Bossio, C. De Angelo, P. Donolo, A. Castellino, and G. Garcia, "Effects of voltage unbalance on IM power, torque and vibrations," in 2009 IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives, 2009, pp. 1-6: IEEE.
  8. C.-Y. J. I. T. o. E. C. Lee, "Effects of unbalanced voltage on the operation performance of a three-phase induction motor," vol. 14, no. 2, pp. 202-208, 1999. https://doi.org/10.1109/60.766984
  9. D. K. Soother et al., "The importance of feature processing in deep-learning-based condition monitoring of motors," vol. 2021, 2021.
  10. M. Hussain, R. R. Ahmed, I. Hussain, and T. D. J. c. T. g. d. i. a. a. l. p. Memon, "Multiple faults detection and identification of three phase induction motor using advanced signal processing techniques," vol. 9, no. 1, pp. 93-117, 2020. https://doi.org/10.17993/3ctecno.2020.specialissue6.93-117
  11. M. Hussain et al., "Stator winding fault detection and classification in three-phase induction motor," vol. 29, no. 3, pp. 869-883, 2021. https://doi.org/10.32604/iasc.2021.017790
  12. M. Hussain, T. D. Memon, I. Hussain, Z. A. Memon, D. J. C.-C. M. I. E. Kumar, and SCIENCES, "Fault Detection and Identification Using Deep Learning Algorithms in Induction Motors," 2022.
  13. S. Hochreiter and J. J. N. c. Schmidhuber, "Long short-term memory," vol. 9, no. 8, pp. 1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735
  14. Y. L. Karnavas, I. D. Chasiotis, M. Drakaki, and I. A. Tziafettas, "Recent advances of neural network based methods in induction motor fault diagnosis," in 2020 International Conference on Electrical Machines (ICEM), 2020, vol. 1, pp. 1411-1417: IEEE.
  15. D. K. Soother and J. J. T. o. t. C. S. f. M. E. Daudpoto, "A brief review of condition monitoring techniques for the induction motor," Transactions of the Canadian Society for Mechanical Engineering, vol. 43, no. 4, pp. 499-508, 2019. https://doi.org/10.1139/tcsme-2018-0234
  16. Y. Luo, J. Qiu, and C. Shi, "Fault detection of permanent magnet synchronous motor based on deep learning method," in 2018 21st International Conference on Electrical Machines and Systems (ICEMS), 2018, pp. 699-703: IEEE.
  17. R. Zhao, J. Wang, R. Yan, and K. Mao, "Machine health monitoring with LSTM networks," in 2016 10th international conference on sensing technology (ICST), 2016, pp. 1-6: IEEE.
  18. R. Sabir, D. Rosato, S. Hartmann, and C. Guehmann, "Lstm based bearing fault diagnosis of electrical machines using motor current signal," in 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), 2019, pp. 613-618: IEEE.