Bearing fault diagnosis using machine learning and a novel set of fault-related spectral features

• João Paulo Vieira UFSC
• Rodrigo Kobashikawa Rosa UFSC
• Victor Afonso Bauler UFSC
• Danilo Braga Dynamox
• Danilo Silva UFSC

DOI: https://doi.org/10.5753/eniac.2024.245033

Resumo

Este artigo desenvolve métodos baseados em aprendizado de máquina para diagnóstico de falhas em rolamentos com dados da Case Western Reserve University (CWRU). Adota-se uma abordagem multirrótulo proposta na literatura, com três classificadores binários para identificar falhas na trilha interna, externa e no elemento rolante, dividindo o conjunto de dados por rolamentos distintos, visando eliminar vazamento. Utilizam-se features no domínio do tempo e frequência, incluindo uma nova proposta de features espectrais, denominadas PFRs (Peak-To-Floor Ratios), calculadas sobre frequências ligadas ao fenômeno da falha. Os resultados, comparados com outras features da literatura, mostram melhorias no desempenho e explicabilidade.

Palavras-chave: Falha em rolamentos, Vazamento de dados, Atributos espectrais

Referências

Abburi, H., Chaudhary, T., Ilyas, S. H. W., Manne, L., Mittal, D., Bowen, E., Williams, D., Snaidauf, D., and Veeramani, B. (2023). A closer look at bearing fault classification approaches. Annual Conference of the PHM Society, 15(1).

Ahmed, H. and Nandi, A. K. (2020). Condition Monitoring with Vibration Signals: Compressive Sampling and Learning Algorithms for Rotating Machines, chapter 6, pages 117–128. John Wiley & Sons, Inc, Hoboken, NJ, USA.

Barreto, L., Rosa, R., Silva, D., and Braga, D. (2023). Fault detection for rotating machinery based on vibration data using machine learning. In Anais do XX Encontro Nacional de Inteligência Artificial e Computacional, pages 242–256, Porto Alegre, RS, Brasil. SBC.

Chen, T. and Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, pages 785–794, New York, NY, USA. Association for Computing Machinery.

González, M., Díaz, V. G., Pérez, B. L., G-Bustelo, B. C. P., and Anzola, J. P. (2023). Bearing fault diagnosis with envelope analysis and machine learning approaches using cwru dataset. IEEE Access, 11:57796–57805.

Hendriks, J., Dumond, P., and Knox, D. (2022). Towards better benchmarking using the cwru bearing fault dataset. Mechanical Systems and Signal Processing, 169:108732.

Juodelyte, D., Cheplygina, V., Graversen, T., and Bonnet, P. (2022). Predicting bearings degradation stages for predictive maintenance in the pharmaceutical industry. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’22. ACM.

Kapoor, S. and Narayanan, A. (2023). Leakage and the reproducibility crisis in machine-learning-based science. Patterns, 4(9):100804.

Maleki, F., Ovens, K., Najafian, K., Forghani, B., Reinhold, C., and Forghani, R. (2020). Overview of Machine Learning Part 1. Neuroimaging Clinics of North America, 30(4):e17–e32.

Neupane, D. and Seok, J. (2020). Bearing fault detection and diagnosis using case western reserve university dataset with deep learning approaches: A review. IEEE Access, 8:93155–93178.

Randall, R. B. (2021). Vibration–based Condition Monitoring, chapter 1, pages 1–24. John Wiley Sons, Ltd.

Rosa, R. K., Braga, D., and Silva, D. (2024). Benchmarking deep learning models for bearing fault diagnosis using the cwru dataset: A multi-label approach. arXiv:2407.14625 [eess].

Smith, W. A. and Randall, R. B. (2015). Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study. Mechanical Systems and Signal Processing, 64–65:100–131.

Tsamardinos, I., Rakhshani, A., and Lagani, V. (2015). Performance-Estimation Properties of Cross-Validation-Based Protocols with Simultaneous Hyper-Parameter Optimization. International Journal on Artificial Intelligence Tools, 24(05):1540023.