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

Study of Fuel Pump Failure Prognostic Based on Machine Learning Using Artificial Neural Network

인공신경망을 이용한 머신러닝 기반의 연료펌프 고장예지 연구

  • Choi, Hong (Department of Mechanical System Engineering, Kumoh National institute of Technology) ;
  • Kim, Tae-Kyung (Department of Mechanical System Engineering, Kumoh National institute of Technology) ;
  • Heo, Gyeong-Rin (Department of Mechanical System Engineering, Kumoh National institute of Technology) ;
  • Choi, Sung-Dae (Department of Mechanical System Engineering, Kumoh National institute of Technology) ;
  • Hur, Jang-Wook (Department of Mechanical System Engineering, Kumoh National institute of Technology)
  • 최홍 (금오공과대학교 기계시스템공학과) ;
  • 김태경 (금오공과대학교 기계시스템공학과) ;
  • 허경린 (금오공과대학교 기계시스템공학과) ;
  • 최성대 (금오공과대학교 기계시스템공학과) ;
  • 허장욱 (금오공과대학교 기계시스템공학과)
  • Received : 2019.06.08
  • Accepted : 2019.07.18
  • Published : 2019.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

The key technology of the fourth industrial revolution is artificial intelligence and machine learning. In this study, FMEA was performed on fuel pumps used as key items in most systems to identify major failure components, and artificial neural networks were built using big data. The main failure mode of the fuel pump identified by the test was coil damage due to overheating. Based on the artificial neural network built, machine learning was conducted to predict the failure and the mean error rate was 4.9% when the number of hidden nodes in the artificial neural network was three and the temperature increased to $140^{\circ}C$ rapidly.

Keywords

References

  1. Choi, H., Kim, T. K., Heo, G. R., Hur, J. W. and Choi, S. D., "A Study on the Prediction of Failure of Fuel Pump Based on Big Data and Machine Learning", Proceedings of the KSMPE Spring Conference, pp. 231, 2019.
  2. Kim, B. R., Lee, Y. H., Roh, H. U., Kim, D. J. and Kim, K. J., "Deep Learning System Based on Time Series Data for Robot Prognostics", 2018 Summer Conference of IEICE, pp. 1340-1342, 2018.
  3. Kim, S. H., Chang, M. S., Lee, K. S., Lee, S. K., Baek, M. H. and Park, J. W., "A Study on the Life Prediction of Vibro-hammer Structure Part Using Field Data", Proceedings of the KSME Spring Conference, pp. 1640-1645, 2018.
  4. Ashwini, K., Lukumon, O., Marina, M. and Gehan, S., "Big data: A New Revolution in the UK Facilities Management Sector", Royal Institution of Chartered Surveyors (RICS), 2018.
  5. Seo, B. S., Jang, B. C. and Hwang, S. D., "Success Cases and Vision in Engineering System of Failure Prediction Diagnosis Technology", The Korea Society for Noise and Vibration Enginnering(KSNVE), Vol. 25, No. 1, pp. 7-15, 2015.
  6. Lee, J. H., "A Study on Automation of Big Data Quality Diagnosis Using Machine Learning", The Korean Journal of Big Data, Vol. 2, No. 2, pp. 75-86, 2017.
  7. Park, H. Y. and Lee, K. Y., "Pattern Recognition and Machine Learning Foundation to Use", Ehan Publication, pp. 236-237, 2011.
  8. Cho, H., Cha, D. W., Lee, H. S. and Jung, S. S., "Survey of Prognostics and Health Management Processes in Automotive Lead-acid Batteries for Estimating Remaining Useful Life in Real Time", 2014 Fall Conference of the Korean Society of Industrial and Engineering Engineers, pp. 2883-2888, 2014.