DOI QR코드

DOI QR Code

도시철도차량 주행차륜의 직경/플랜지 변화 데이터와 머신러닝 기법을 활용한 주행거리 예측 연구

A Study on the Mileage Prediction of Urban Railway Vehicle using Wheel Diameter/Flange change Data and Machine Learning Techniques

  • 노학락 (서울과학기술대학교 글로벌철도시스템공학과) ;
  • 임원식 (서울과학기술대학교 기계자동차공학과)
  • Hak Rak Noh (Department of Global Railway Systems, Seoul National University of Science and Technology) ;
  • Won Sik Lim (Dep. Mechanical and Automotive Engineering, Seoul National University of Science and Technology)
  • 투고 : 2023.07.20
  • 심사 : 2023.08.16
  • 발행 : 2023.08.31

초록

The steel wheels of urban railway vehicles gather a lot of data through regular measurements during maintenance. However, limited research has been carried out utilizing this data, resulting in difficulties predicting the maintenance period. This paper studied a machine learning model suitable for mileage prediction by studying the characteristics of mileage change according to diameter and flange thickness changes. The results of this study indicate that the larger the diameter, the longer the travel distance, and the longest flange thickness is at 30 mm, which gradually shortened at other times. As a result of research on the machine learning prediction model, it was confirmed that the random forest model is the optimal model with a high coefficient of determination and a low root mean square error.

키워드

참고문헌

  1. S. H. Lee and H. K. Kim, "Estimation of Fatigue Damage due to Rolling Contact ina Railway Wheel Using FEM Analysis", J. Korean Soc. Saf., Vol. 26, No. 3, pp. 1-7, 2011.
  2. D. Lee and G. Koo, "Study on Securing the Reliability of the Supply and Demand Plan for Wheel Exchange through the Prediction of Wheel Exchange Cycle", J. Korean Soc. Saf., Vol. 36, No. 6, pp. 86-93, 2021.
  3. J. Y. Kim, S. S. Park and J. M. Kim, "A Study on Compressive Residual Stress Characteristics and Wear Limits of Steel Wheels for Railway Vehicles", Journal of Korean Society for Urban Railway, Vol. 9, No. 4, pp. 1151-1161, 2021. https://doi.org/10.24284/JKOSUR.2021.12.9.4.1151
  4. J. G. Ahn, S. J. Kwon and H. K. Kim, "Wear Characteristics depended on Wear Index in Wheel-Rail Interface", Journal of Korean Society for Urban Railway, Vol. 1, No. 2, pp. 51-56, 2013.
  5. F. Braghin, R. Lewis, R. S. Dwyer-Joyce and S. Bruni, "A Mathematical Model to Predict Railway Wheel Profile Evolution Due to Wear", Vol. 261, Issues 11-12, pp. 1253-1264, 2006. https://doi.org/10.1016/j.wear.2006.03.025
  6. S. H. Brown, "Multiple Linear Regression Analysis: A Matrix Approach with MATLAB", Alabama Journal of Mathematics, Vol. 34, pp. 1-3, 2009.
  7. J. R. Quinlan, "Induction of Decision Trees", Machine Learning", Vol. 1, pp. 81-106, 1986. https://doi.org/10.1007/BF00116251
  8. N. S. Altman, "An Introduction to Kernel and Nearest-neighbor Nonparametric Regression", The American Statistician, Vol. 46, Issue 3, pp. 175-185, 1992. https://doi.org/10.1080/00031305.1992.10475879
  9. L. Breiman, "Random Forests, Machine Learning", Vol. 45, pp. 5-32, 2001. https://doi.org/10.1023/A:1010933404324
  10. W. S. Noble, "What is a Support Vector Machine?", Nature Biotechnology, Vol. 24, pp. 1565-1567, 2006.
  11. S. C. Wang, "Artificial Neural Network. in Interdisciplinary Computing in Java Programming Springer", Boston, MA, pp. 81-100, 2003.