A Machine Learning with an Inlier/Outlier Separation Approach for the Prediction of Wagon Maintenance Times

  • Josemar Coelho Felix Universidade Federal de Ouro Preto
  • Vanessa Miranda Oliveira Universidade Federal de Ouro Preto
  • Rodrigo Silva Universidade Federal de Ouro Preto

Resumo


Time spent in wagons maintenance consumes a significant part of a rail freight company's budget. Thus, knowing how much time it is going to be spent in a maintenance procedure is critical for their management and planning. A common approach used to predict these time expenditures is the so called chronoanalysis. Despite their wide spread use, they may be inaccurate in some scenarios. Thus, in this paper, we try to replace it with machine leaning models which did not work at first. Then we propose a methodology that uses the chronoanalysis to divide the maintenance procedures into outliers and inliers. Hence, we were able to create independent models for each class. With this approach, the average mean absolute error was reduced from about 6 man-hour to a little above 2 man-hours. The best tested configuration presented an average mean absolute error of 0.417 man-hours compared with a 4.490 man-hours from the chronoanalysis.

Palavras-chave: machine learning, maintenance, outlier detection, regression

Referências

European Federation of National Maintenance Societies. http://www.efnms.eu/. Accessed: 2022-07-06.

XGBoost. https://xgboost.readthedocs.io/en/stable/. Accessed: 2022-07-20.

Ayadi, A., Ghorbel, O., Obeid, A. M., and Abid, M. Outlier detection approaches for wireless sensor networks: A survey. Computer Networks vol. 129, pp. 319–333, 2017.

Choi, H., Kim, D., Kim, J., Kim, J., and Kang, P. Explainable anomaly detection framework for predictive maintenance in manufacturing systems. Applied Soft Computing vol. 125, pp. 109147, 2022.

Cipolletta, G., Delle Femine, A., Gallo, D., Luiso, M., and Landi, C. Design of a stationary energy recovery system in rail transport. Energies 14 (9), 2021.

Coelho, W. L. V., de Souza Matos, I., Gauto, R. F., and Bueno, A. F. Chrono-analysis: Study applied to a processing unit of swine in brazil. Zeiki-Revista Interdisciplinar da Unemat Barra do Bugres 2 (1): 4–28, 2021.

Dunn, O. J. Multiple comparisons using rank sums. Technometrics 6 (3): 241–252, 1964.

Friedman, M. A comparison of alternative tests of significance for the problem of m rankings. The Annals of Mathematical Statistics 11 (1): 86–92, 1940.

Hendry, J. W. A Manual of Time and Motion Study: A Practical Guide to the Measurement of Human Endeavor in Industry and to the Development of Productive Efficiency. I. Pitman, 1947.

Liyanage, J. P. Operations and maintenance performance in production and manufacturing assets: The sustainability perspective. CIRP Journal of Manufacturing Technology Management, 2007.

Mongomery, D. Montgomery: design and analysis of experiments. John Willy & Sons, 2017.

Moura, D. A. and Liu, R. D. Sistemas de produção, o uso de ferramentas adequadas para aumento de competitividade na área de tempos e métodos. Revista Gestão Industrial 10 (1), 2014.

Office of the Chairman of the Joint Chiefs of Staff. DOD dictionary of military and associated terms. Tech. rep., Washington DC: The Joint Staff, 2021.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al. Scikit-learn: Machine learning in python. The Journal of Machine Learning research vol. 12, pp. 2825–2830, 2011.

Souiden, I., Omri, M. N., and Brahmi, Z. A survey of outlier detection in high dimensional data streams. Computer Science Review vol. 44, pp. 100463, 2022.

Yun, U., Ryang, H., and Kwon, O.-C. Monitoring vehicle outliers based on clustering technique. Applied Soft Computing vol. 49, pp. 845–860, 2016.
Publicado
28/11/2022
Como Citar

Selecione um Formato
FELIX, Josemar Coelho; OLIVEIRA, Vanessa Miranda; SILVA, Rodrigo. A Machine Learning with an Inlier/Outlier Separation Approach for the Prediction of Wagon Maintenance Times. In: SYMPOSIUM ON KNOWLEDGE DISCOVERY, MINING AND LEARNING (KDMILE), 10. , 2022, Campinas/SP. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 9-16. ISSN 2763-8944. DOI: https://doi.org/10.5753/kdmile.2022.227789.