Prognostics of multiple failure modes in rotating machinery using a pattern-based classifier and cumulative incidence functions
- 368 Downloads
This paper presents a novel methodology for multiple failure modes prognostics in rotating machinery. The methodology merges a machine learning and pattern recognition approach, called logical analysis of data (LAD), with non-parametric cumulative incidence functions (CIFs). It considers the condition monitoring data collected from a system that experiences several competing failure modes over its life span. LAD is used as a non-statistical classification technique to detect the actual state of the system, based on the condition monitoring data. The CIF provides an estimate for the marginal probability of each failure mode in the presence of the other competing failure modes. Accordingly, the assumption of independence between the failure modes, which is essential in many prognostic methods, is irrelevant in this paper. The proposed methodology is validated using vibration data collected from bearing test rigs. The obtained results are compared to those of two common machine learning prediction techniques: the artificial neural network and support vector regression. The comparison shows that the proposed methodology has a stable performance and can predict the remaining useful life of an individual system accurately, in the presence of multiple failure modes.
KeywordsFailure prognostics Multiple failure modes Logical analysis of data Machine learning CBM Survival analysis Rotating machinery
This work is funded by the Natural Sciences and Engineering Research Council of Canada (NSERC) under research Grants Numbers 141111 and 231695.
- Avila-Herrera, J. F., & Subasi, M. M. (2015). Logical analysis of multi-class data. In Computing conference (CLEI), 2015 Latin American (pp. 1–10). IEEE.Google Scholar
- Beyersmann, J., Allignol, A., & Schumacher, M. (2011). Competing risks and multistate models with R. New York: Springer Science & Business Media.Google Scholar
- Bishop, C. M. (2006). Pattern recognition and machine learning (Vol. 1). New York: Springer.Google Scholar
- Bouckaert, R. R., Frank, E., Hall, M. A., Holmes, G., Pfahringer, B., Reutemann, P., et al. (2010). WEKA—Experiences with a Java open-source project. The Journal of Machine Learning Research, 11, 2533–2541.Google Scholar
- Chikalov, I., Lozin, V., Lozina, I., Moshkov, M., Nguyen, H. S., Skowron, A., et al. (2012). Three approaches to data analysis: Test theory, rough sets and logical analysis of data (Vol. 41). New York: Springer Science & Business Media.Google Scholar
- Couallier, V. (2008). A competing risks model for degradation and traumatic failure times. In Statistical models and methods for biomedical and technical systems (pp. 83–93). Boston: Birkhäuser.Google Scholar
- Duda, R. O., Hart, P. E., & Stork, D. G. (2001). Pattern classification (2nd ed.). John Wiley.Google Scholar
- Elsayed, E. A. (2003). Mean residual life and optimal operating conditions for industrial furnace tubes. In W. R. Blischke & D. N. P. Murthy (Eds.), Case studies in reliability and maintenance. Hoboken, NJ: John Wiley & Sons, Inc. doi: 10.1002/0471393002.ch22.
- Elsayed, E. A. (2012). Reliability engineering. Hoboken: Wiley.Google Scholar
- Gao, R. X., & Yan, R. (2010). Wavelets: Theory and Applications for manufacturing. New York: Springer.Google Scholar
- Kalbfleisch, J. D., & Prentice, R. L. (2011). The statistical analysis of failure time data (Vol. 360). John Wiley & Sons.Google Scholar
- Kleinbaum, D., & Klein, M. (2011). Survival analysis: A self-learning text, 2005. New York: Springer-Verlag.Google Scholar
- Kothamasu, R., Huang, S. H., & VerDuin, W. H. (2009). System health monitoring and prognostics—A review of current paradigms and practices. In Handbook of maintenance management and engineering (pp. 337–362). London: Springer.Google Scholar
- Misiti, M., Misiti, Y., Oppenheim, G., & Poggi, J. (2008). Matlab user’s guide: Wavelet toolbox ™ 4. Natick, MA: The Math Works Inc.Google Scholar
- Prentice, R. L., Kalbfleisch, J. D., Peterson, A. V. Jr., Flournoy, N., Farewell, V. T., & Breslow, N. (1978). The analysis of failure times in the presence of competing risks. Biometrics, 34(4), 541–554.Google Scholar
- Ragab, A., Ouali, M.-S., Yacout, S., & Osman, H. (2014). Remaining useful life prediction using prognostic methodology based on logical analysis of data and Kaplan–Meier estimation. Journal of Intelligent Manufacturing. doi: 10.1007/s10845-014-0926-3.
- Sapir-Pichhadze, R., Pintilie, M., Tinckam, K., Laupacis, A., Logan, A., Beyene, J., et al. (2016). Survival analysis in the presence of competing risks: The example of wait-listed kidney transplant candidates. American Journal of Transplantation, 16(7), 19581966. doi: 10.1111/ajt.13717.CrossRefGoogle Scholar
- Vachtsevanos, G., Lewis, F., Roemer, M., Hess, A., & Wu, B. (2006). Intelligent fault diagnosis and prognosis for engineering systems. Wiley. http://eu.wiley.com/WileyCDA/WileyTitle/productCd-047172999X.html.
- Vapnik, V., Golowich, S., & Smola, A. (1997). Advances in neural information processing systems 9—Proceedings of the 1996 neural information processing systems conference (NIPS 1996), Denver, CO (pp. 281–287). Cambridge, MA: MIT Press.Google Scholar
- Wang, H., & Gao, J. (2014). A reliability evaluation study based on competing failures for aircraft engines. Eksploatacja i Niezawodność, 16(2), 171–178.Google Scholar
- Witten, I. H., Frank, E., & Hall, M. A. (2011). Data mining: Practical machine learning tools and techniques. Burlington: Morgan Kaufmann.Google Scholar
- Yacout, S., Salamanca, D., & Mortada, M.-A. (2011). Tool and method for fault detection of devices by condition based maintenance. Google Patents.Google Scholar
- Yu, M., & Wang, D. (2014). Model-based health monitoring for a vehicle steering system with multiple faults of unknown types. Industrial Electronics, IEEE Transactions on, 61, 3574–3586.Google Scholar