Machine Learning Algorithms for Remaining Useful Life Prediction of Rolling Bearings

• Débora Zumpichiatti UFRJ
• Janaína Gomide UFRJ

DOI: https://doi.org/10.5753/eniac.2022.227195

Resumo

O aumento da complexidade dos sistemas mecânicos muda drasticamente os métodos usados para monitorar e analisar como esses sistemas envelhecem. O objetivo desse trabalho é realizar a previsão do tempo de vida útil restante de equipamentos utilizando uma abordagem de prognóstico baseada em dados e algoritmos de aprendizado de máquina. O conjunto de dados utilizado apresenta dados de temperatura e vibração de testes até a falha de rolamentos. A metodologia proposta foi avaliada e constatou-se a importância de uma fase de tratamento de dados robusta. Os resultados obtidos para conjuntos de dados julgados como apropriados pela metodologia apresentaram resultados similares ou superiores aos trabalhos relacionados.

Referências

Bastidas-Rodríguez, M.-X., Prieto-Ortiz, F.-A., and Polanía, L. F. (2019). A textural deep neural network combined with handcrafted features for mechanical failure classification. In 2019 IEEE International Conference on Industrial Technology (ICIT), pages 847-852. IEEE.

Bougacha, O., Varnier, C., and Zerhouni, N. (2020). A review of post-prognostics decision-making in prognostics and health management. International Journal of Prognostics and Health Management, 11(15):31.

Géron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. "O'Reilly Media, Inc.".

Iyer, N., Goebel, K., and Bonissone, P. (2006). Framework for post-prognostic decision support. In 2006 ieee aerospace conference, pages 10-pp. IEEE.

Lee, W. J., Wu, H., Yun, H., Kim, H., Jun, M. B., and Sutherland, J. W. (2019). Predictive maintenance of machine tool systems using artificial intelligence techniques applied to machine condition data. Procedia Cirp, 80:506-511.

Lin, S., Zhang, A., and Feng, D. (2016). Maintenance decision-making model based on pomdp for traction power supply equipment and its application. In 2016 Prognostics and System Health Management Conference (PHM-Chengdu), pages 1-6. IEEE.

Nectoux, P., Gouriveau, R., Medjaher, K., Ramasso, E., Chebel-Morello, B., Zerhouni, N., and Varnier, C. (2012). Pronostia: An experimental platform for bearings accelerated degradation tests. In IEEE International Conference on Prognostics and Health Management, PHM'12., pages 1-8. IEEE Catalog Number: CPF12PHM-CDR.

Patil, S., Patil, A., Handikherkar, V., Desai, S., Phalle, V. M., and Kazi, F. S. (2018). Remaining useful life (rul) prediction of rolling element bearing using random forest and gradient boosting technique. In ASME international mechanical engineering congress and exposition, volume 52187. American Society of Mechanical Engineers.

Sloukia, F., Bouarfa, R., Medromi, H., and Wahbi, M. (2013a). Bearings prognostic using mixture of gaussians hidden markov model and support vector machine. International Journal of Network Security Its Applications, 5:85-97.

Sloukia, F., El Aroussi, M., Medromi, H., and Wahbi, M. (2013b). Bearings prognostic using mixture of gaussians hidden markov model and support vector machine. In 2013 ACS International Conference on Computer Systems and Applications (AICCSA), pages 1-4. IEEE.

Sutrisno, E., Oh, H., Vasan, A. S. S., and Pecht, M. (2012). Estimation of remaining useful life of ball bearings using data driven methodologies. In 2012 ieee conference on prognostics and health management, pages 1-7. IEEE.

Zaki, M. J., Meira Jr, W., and Meira, W. (2014). Data mining and analysis: fundamental concepts and algorithms. Cambridge University Press.