Journal of the Korean Society of Manufacturing Process Engineers (한국기계가공학회지)

The Korean Society of Manufacturing Process Engineers (한국기계가공학회)
권호 표지
DOI QR코드

DOI QR Code

Failure Prognostics of Start Motor Based on Machine Learning

머신러닝을 이용한 스타트 모터의 고장예지

  • Ko, Do-Hyun (Department of Mechanical System Engineering, Kumoh National institute of Technology) ;
  • Choi, Wook-Hyun (Department of Mechanical System Engineering, Kumoh National institute of Technology) ;
  • Choi, Seong-Dae (Department of Mechanical System Engineering, Kumoh National institute of Technology) ;
  • Hur, Jang-Wook (Department of Mechanical System Engineering, Kumoh National institute of Technology)
  • 고도현 (금오공과대학교 기계시스템공학과) ;
  • 최욱현 (금오공과대학교 기계시스템공학과) ;
  • 최성대 (금오공과대학교 기계시스템공학과) ;
  • 허장욱 (금오공과대학교 기계시스템공학과)
  • Received : 2021.05.27
  • Accepted : 2021.07.13
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In our daily life, artificial intelligence performs simple and complicated tasks like us, including operating mobile phones and working at homes and workplaces. Artificial intelligence is used in industrial technology for diagnosing various types of equipment using the machine learning technology. This study presents a fault mode effect analysis (FMEA) of start motors using machine learning and big data. Through multiple data collection, we observed that the primary failure of the start motor was caused by the melting of the magnetic switch inside the start motor causing it to fail. Long-short-term memory (LSTM) was used to diagnose the condition of the magnetic locations, and synthetic data were generated using the synthetic minority oversampling technique (SMOTE). This technique has the advantage of increasing the data accuracy. LSTM can also predict a start motor failure.

Keywords

Acknowledgement

이 논문은 2019년도 정부(교육부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업임(No. 2019R1I1A3A01063935).

References

  1. Choi, J. H., An, D. W. and Gang, J. H., "A Survey on Prognostics and Comparison Study on the Model-Based Prognostics," Journal of Institute of Control, Robotics and Systems, Vol. 17, Issue 11, pp. 1095-1100, 2011. https://doi.org/10.5302/J.ICROS.2011.17.11.1095
  2. Woo, S. W., Park, J. M., Hyun, B. S., Nam, J. W., Park, W. S., Kim, J. P., Cho, Y. J., Ko, J. M. and Park, N. G., "A Experimental Study on Insulation Breaking Fire Case of Starter Motor B Terminal," Journal of the Korean Society of Safety, Vol. 34 Issue 5, pp. 55-62, 2019.
  3. Kook, J. H., Ahn, J. W. and Lee, H. H., "Output Characteristics of Helical Magnetic Flux Compression Generators with Varing Current Density Flowing through Coil," The Journal of KIEE Vol. 2002, No. 11, pp. 21-23, 2002.
  4. "LSTM and It's Equations," https://medium.com/@divyanshu132/lstm-and-its-equations-5ee9246d04af(accessed 06, JUL, 2018)
  5. "Understanding LSTM Networks," http://colah.github.io/posts/2015-08-Understanding-LSTMs(accessed 27, Aug, 2015)
  6. Shin, D. I., "Synthetic Minority Over-Sampling Technique with Adversarial Auto-Encoder for Imbalanced Data" Graduate School of Sogang University, Republic of Korea, 2018.
  7. "Language Model (2) Smoothing," https://heiwais25.github.io/nlp/2019/10/06/Language-model2/(accessed 06, Oct, 2019)
  8. Lee, S. H. and Park, K. S., "A Local Alignment Algorithm using Normalization by Functions," Journal of KIISE, Vol. 34, No. 5/6, pp. 187-194, 2007.
  9. Cheong, W. S., Lee, B. K., Han, C. H., Kwon, S. G., Jang, J. K. and Lee, K. I., "A Fast Block Matching Algorithm Using Mean Absolute Error of Neighbor Search Point and Search Region Reduction," The Journal of Korean Institute of Communications and Information Sciences, Vol. 25, Issue. 1B, pp. 128-140, 2000.
  10. Kim, E. M. and Lee, B. H., "Performance and Root Mean Squared Error of Kernel Relaxation by the Dynamic Change of the Moment," Journal of Korea Multimedia Society, Vol. 6, No. 5, pp. 788-796, 2003.
  11. Jung, H. and Kim, J. W., "A Machine Learning Approach for Mechanical Motor Fault Diagnosis," Journal of the Society of Korea Industrial and Systems Engineering, Vol. 40, Issue. 1, pp. 57-64, 2017. https://doi.org/10.11627/jkise.2017.40.1.057