Two improvements of similarity-based residual life prediction methods
- 169 Downloads
The similarity-based residual life prediction (SbRLP) approach is an emerging technique and occupies a significant place in remaining useful life (RUL) prediction. Researches on (a) considering different operating conditions; and (b) considering maintenance are rare. But aforesaid factors have great influence on effective utilization of the SbRLP method. In this article, improvements are implemented from two above perspectives and thus a novel weight function and a fresh similarity measurement are advanced. Afterwards, a case study of the gyroscope’ RUL estimation demonstrates the reasonability and effectiveness of the proposed weight function and similarity measurement through comparisons with the classical SbRLP method. Meanwhile, the investigation results reveal that the performance of the SbRLP method with the recommended weight function improves fast with the increment of available reference systems, which have different operating conditions with the operating systems. And with the increase of maintenance frequency, the difference between the local performance of the SbRLP method with the introduced similarity measurement and that of the classical SbRLP method decreases gradually, which is just the opposite of the difference between their overall performances.
KeywordsSbRLP RUL Similarity measure Weight function Gyroscope Performance
- Docin (2011a). Equipment operating environment. http://www.docin.com/p-179003804.html.
- Docin (2011b). Operating environment requirements of a system. http://www.docin.com/p-97226961.html.
- Guan, R. S. (2012). Technical conditions of super filter system equipment configuration and the stable operation. Modern Finishing, 01, 43–45. (in Chinese).Google Scholar
- Jin, J. L., Wei, Y. M., Zou, L. L., Liu, L., & Fu, J. (2012). Risk evaluation of China’s natural disaster systems: An approach based on triangular fuzzy numbers and stochastic simulation. Natural Hazards, 621(1), 554–559.Google Scholar
- Si, X. S., Hu, C. H., & Zhou, D. H. (2013). Nonlinear degradation process modeling and remaining useful life estimation subject to measurement error. Acta Automatica Sinica, 05, 530–541. (in Chinese).Google Scholar
- Wang, C., Wu, S. Q., Shi, W. D., & Yai, J. (2013). Numerical calculation and experimental research of pressure fluctuation in the pump under different operating conditions. Journal of Vibroengineering, 15(4), 2049–2056.Google Scholar
- Wang, T. Y., Yu, J. B., Siegel, D., & Lee, J. (2008). A similarity-based prognostics approach for remaining useful life estimation of engineered systems. In 2008 International conference on prognostics and health management (PHM) (pp. 53–58), Denver, CO, Oct 06-09.Google Scholar
- Xu, G. P., Tian, W. F., Jin, Z. H., & Qian, L. (2007). A statistical parameter analysis and SVM based fault diagnosis strategy for dynamically tuned gyroscopes. Journal of Shanghai Jiaotong University, 12(5), 592–596.Google Scholar
- You, M. Y., & Meng, G. (2013b). Toward effective utilization of similarity based residual life prediction methods: Weight allocation, prediction robustness, and prediction uncertainty. Proceedings of the Institution of Mechanical Engineers Part E: Journal of Process Mechanical Engineering, 227(1), 74–84.CrossRefGoogle Scholar
- Zhang, K. L., & Guo, B. (2010). Application of metamodel approach in product development process. Journal of Computational Information Systems, 6(7), 2159–2166.Google Scholar
- Zhang, J. X., Hu, C. H., Zhang, Z. J., Si, X. S., & Du, D. B. (2014). Multiple degradation variables modeling for remaining useful life estimation of gyros based on copula function. Acta Aeronautica et Astronautica Sinica, 04, 1111–1121. (in Chinese).Google Scholar