Clasificación de fallas en rodamientos utilizando aprendizaje de móquinas
DOI:
https://doi.org/10.23857/dc.v7i4.2082Palabras clave:
Clasificación de fallas, aprendizaje de máquinas, análisis de vibraciones, monitoreo de la condición, rodamientos.Resumen
Debido a la creciente demanda de confiabilidad, disponibilidad y seguridad, se tienen como componentes críticos de una maquina rotativa, a los rodamientos, la caja de engranajes, el rotor, que son fócilmente sujetos a fallos. Hasta estos momentos, existen una variedad de técnicas de mantenimiento basado en la condición, por lo cual el anólisis de vibraciones se ha aceptado como una herramienta de diagnóstico importante, porque las señales de vibraciones se pueden obtener fócilmente y contienen abundante información sobre las condiciones de las móquinas.
En este estudio se utiliza la extracción de características de las fallas, y a través de estos analizar cuóles son las mejores que aplican en este caso. A partir de esta extracción de características se utilizaron técnicas de aprendizaje de móquinas para obtener la clasificación de las fallas en rodamientos.
El aprendizaje de móquinas es utilizado a través de cinco técnicas de clasificación, las cuales son: support vector machine, random forest, gradiendt boosting, extra trees y XGBoost, con el fin de presentar un marco comparativo, para determinar cuól de ellos es el mejor clasificador en términos de exactitud de reconocimiento. En comparación las técnicas de aprendizaje de móquinas superan a las técnicas de clasificación de fallas tradicionales. Estos resultados sugieren que el aprendizaje de móquinas utilizando XGBoost es un método prometedor y ofrece un gran aporte para la ingeniería próctica.
Citas
T. Han, D. Jiang, Q. Zhao, L. Wang, and K. Yin, "Comparison of random forest, artificial neural networks and support vector machine for intelligent diagnosis of rotating machinery," Transactions of the Institute of Measurement and Control, vol. 40, no. 8, pp. 2681-2693, 2018.
A. Yunusa-Kaltungo, J. K. Sinha, and A. D. Nembhard, "A novel fault diagnosis technique for enhancing maintenance and reliability of rotating machines," Structural Health Monitoring, vol. 14, no. 6, pp. 604-621, 2015.
L. Guo, H. Gao, H. Huang, X. He, and S. Li, "Multifeatures fusion and nonlinear dimension reduction for intelligent bearing condition monitoring," Shock and Vibration, vol. 2016, 2016.
T. Han, D. Jiang, and N. Wang, "The fault feature extraction of rolling bearing based on EMD and difference spectrum of singular value," Shock and vibration, vol. 2016, 2016.
P. Sun, Y. Liao, and J. Lin, "The shock pulse index and its application in the fault diagnosis of rolling element bearings," Sensors, vol. 17, no. 3, p. 535, 2017.
G. Tang, G. Luo, W. Zhang, C. Yang, and H. Wang, "Underdetermined blind source separation with variational mode decomposition for compound roller bearing fault signals," Sensors, vol. 16, no. 6, p. 897, 2016.
M. Yaqub and K. A. Loparo, "An automated approach for bearing damage detection," Journal of Vibration and Control, vol. 22, no. 14, pp. 3253-3266, 2016.
S. Bogoevska, M. Spiridonakos, E. Chatzi, E. Dumova-Jovanoska, and R. Hí¶ffer, "A data-driven diagnostic framework for wind turbine structures: A holistic approach," Sensors, vol. 17, no. 4, p. 720, 2017.
G. Cheng, X.-h. Chen, X.-l. Shan, H.-g. Liu, and C.-f. Zhou, "A new method of gear fault diagnosis in strong noise based on multi-sensor information fusion," Journal of Vibration and Control, vol. 22, no. 6, pp. 1504-1515, 2016.
T. Han, D. Jiang, X. Zhang, and Y. Sun, "Intelligent diagnosis method for rotating machinery using dictionary learning and singular value decomposition," Sensors, vol. 17, no. 4, p. 689, 2017.
C. Liu, D. Jiang, and W. Yang, "Global geometric similarity scheme for feature selection in fault diagnosis," Expert Systems with Applications, vol. 41, no. 8, pp. 3585-3595, 2014.
D. Jiang and C. Liu, "Machine condition classification using deterioration feature extraction and anomaly determination," IEEE Transactions on Reliability, vol. 60, no. 1, pp. 41-48, 2011.
Y. Lei, Z. He, and Y. Zi, "EEMD method and WNN for fault diagnosis of locomotive roller bearings," Expert Systems with Applications, vol. 38, no. 6, pp. 7334-7341, 2011.
Y. Tian, J. Ma, C. Lu, and Z. Wang, "Rolling bearing fault diagnosis under variable conditions using LMD-SVD and extreme learning machine," Mechanism and Machine Theory, vol. 90, pp. 175-186, 2015.
D. Dou and S. Zhou, "Comparison of four direct classification methods for intelligent fault diagnosis of rotating machinery," Applied Soft Computing, vol. 46, pp. 459-468, 2016.
B. Zhou and Y. Cheng, "Fault diagnosis for rolling bearing under variable conditions based on image recognition," Shock and Vibration, vol. 2016, 2016.
B. Li and Y. Zhang, "Supervised locally linear embedding projection (SLLEP) for machinery fault diagnosis," Mechanical Systems and Signal Processing, vol. 25, no. 8, pp. 3125-3134, 2011.
J. Yang, Y. Zhang, and Y. Zhu, "Intelligent fault diagnosis of rolling element bearing based on SVMs and fractal dimension," Mechanical Systems and Signal Processing, vol. 21, no. 5, pp. 2012-2024, 2007.
J. Friedman, "Greedy Function Approximation: A Gradient Boosting Machine http://www.salford-systems. com/doc," GreedyFuncApproxSS. pdf, 1999.
R. Maree, P. Geurts, J. Piater, and L. Wehenkel, "Random subwindows for robust image classification," in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 2005, vol. 1, pp. 34-40: IEEE.
P. Geurts, D. Ernst, and L. Wehenkel, "Extremely randomized trees," Machine learning, vol. 63, no. 1, pp. 3-42, 2006.
Y. Freund and R. E. Schapire, "Experiments with a new boosting algorithm," in Icml, 1996, vol. 96, pp. 148-156: Citeseer.
T. Chen and C. Guestrin, "Xgboost: A scalable tree boosting system," in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785-794: ACM.
C.-C. Chang and C.-J. Lin, "LIBSVM: a library for support vector machines," ACM transactions on intelligent systems and technology (TIST), vol. 2, no. 3, p. 27, 2011
W. A. Smith and R. B. Randall, "Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study," Mechanical Systems and Signal Processing, vol. 64, pp. 100-131, 2015.
Publicado
Cómo citar
Número
Sección
Licencia
Authors retain copyright and guarantee the Journal the right to be the first publication of the work. These are covered by a Creative Commons (CC BY-NC-ND 4.0) license that allows others to share the work with an acknowledgment of the work authorship and the initial publication in this journal.
