Oil sand pumps are widely used in the mining industry for the delivery of mixtures of abrasive solids and liquids. Because they operate under highly adverse conditions, these pumps usually experience significant wear. Consequently, equipment owners are quite often forced to invest substantially in system maintenance to avoid unscheduled downtime. In this study, an approach combining relevance vector machines (RVMs) with a sum of two exponential functions was developed to predict the remaining useful life (RUL) of field pump impellers. To handle field vibration data, a novel feature extracting process was proposed to arrive at a feature varying with the development of damage in the pump impellers. A case study involving two field datasets demonstrated the effectiveness of the developed method. Compared with standalone exponential fitting, the proposed RVM-based model was much better able to predict the remaining useful life of pump impellers.
References
[1]
Si, X.-S.; Wang, W.; Hu, C.-H.; Zhou, D.-H. Remaining useful life estimation—A review on the statistical data driven approaches. Eur. J. Oper. Res. 2011, 213, 1–14.
[2]
Fan, A.; Long, J.; Tao, Z. Failure analysis of the impeller of a slurry pump subjected to corrosive wear. Wear 1995, 181–183, 876–882.
[3]
Llewellyn, R.; Yick, S.; Dolman, K. Scouring erosion resistance of metallic materials used in slurry pump service. Wear 2004, 256, 592–599.
[4]
Walker, C. Slurry pump side-liner wear: Comparison of some laboratory and field results. Wear 2001, 250, 81–87.
[5]
Dong, X.; Zhang, H.-L.; Wang, X.-Y. Finite element analysis of wear for centrifugal slurry pump. Procedia Earth Planet. Sci. 2009, 1, 1532–1538.
[6]
Bross, S.; Addie, G. Prediction of impeller nose wear behavior in centrifugal slurry pumps. Exp. Therm. Fluid Sci. 2002, 26, 841–849.
[7]
Zhao, X.; Hu, Q.; Lei, Y.; Zuo, M. Vibration-based fault diagnosis of slurry pump impellers using neighbourhood rough set models. Proc. Inst. Mech. Eng, C-J. Mech. Eng. Sci. 2010, 224, 995–1006.
[8]
Qu, J.; Zuo, M. Support vector machine based data processing algorithm for wear degree classification of slurry pump systems. Measurement 2010, 43, 781–791.
[9]
Hancock, K.; Zhang, Q. A hybrid approach to hydraulic vane pump condition monitoring and fault detection. Trans. ASABE 2006, 49, 1203–1211.
[10]
Di Maio, F.; Hu, J.; Tse, P.; Pecht, M.; Tsui, K.; Zio, E. Ensemble-approaches for clustering health status of oil sand pumps. Expert Syst. Appl. 2012, 39, 4847–4859.
[11]
Zhao, X.; Zuo, M.; Patel, T. Generating an indicator for pump impeller damage using half and full spectra, fuzzy preference-based rough sets and PCA. Meas. Sci. Technol. 2012, 23, 1–10.
[12]
Shen, Z.; He, Z.; Chen, X.; Sun, C.; Liu, Z. A monotonic degradation assessment index of rolling bearings using fuzzy support vector data description and running time. Sensors 2012, 12, 10109–10135.
[13]
Zhang, B.; Khawaja, T.; Patrick, R.; Vachtsevanos, G.; Orchard, M.; Saxena, A. Application of blind deconvolution denoising in failure prognosis. IEEE Trans. Instrum. Meas. 2009, 58, 303–310.
[14]
Wang, D.; Tse, P.; Guo, W.; Miao, Q. Support vector data description for fusion of multiple health indicators for enhancing gearbox fault diagnosis and prognosis. Meas. Sci. Technol. 2011, 22, 1–14.
[15]
Miao, Q.; Tang, C.; Liang, W.; Pecht, M. Health assessment of cooling fan bearings using wavelet-based filtering. Sensors 2013, 13, 274–291.
[16]
Wang, D.; Miao, Q.; Kang, R. Robust health evaluation of gearbox subject to tooth failure with wavelet decomposition. J. Sound Vib. 2012, 324, 1141–1157.
[17]
Heng, A.; Zhang, S.; Tan, A.C.; Mathew, J. Rotating machinery prognostics: State of the art, challenges and opportunities. Mech. Syst. Signal Process. 2009, 23, 724–739.
[18]
Pecht, M. Prognostics and Health Management of Electronics; John Wiley: Hoboken, NJ, USA, 2008.
[19]
Jin, G.; Matthews, D.; Fan, Y.; Liu, Q. Physics of failure-based degradation modeling and lifetime prediction of the momentum wheel in a dynamic covariate environment. Eng. Fail. Anal. 2013, 28, 222–240.
[20]
Gu, J.; Barker, D.; Pecht, M. Prognostics implementation of electronics under vibration loading. Microelectron. Reliab. 2007, 47, 1849–1856.
[21]
Hu, C.; Youn, B.; Wang, P.; Yoon, J. Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful life. Reliab. Eng. Syst. Safe. 2012, 103, 120–135.
[22]
Hu, C.; Youn, B.; Wang, P. Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful life. Reliab. Eng. Syst. Safe. 2012, 103, 120–135.
[23]
Si, X.-S.; Wang, W.; Hu, C.-H.; Chen, M.-Y.; Zhou, D.-H. A Wiener-process-based degradation model with a recursive filter algorithm for remaining useful life estimation. Mech. Syst. Signal Pr. 2013, 35, 219–237.
[24]
Saha, B.; Goebel, K.; Poll, S.; Christophersen, J. Prognostics methods for battery health monitoring using a Bayesian framework. IEEE Trans. Instrum. Meas. 2009, 58, 291–296.
[25]
Cheng, S.; Pecht, M. A Fusion Prognostics Method for Remaining Useful Life Prediction of Electronic Products. Proceedings of IEEE International Conference on Automation Science and Engineering, Bangalore, India, 22–25 August 2009; pp. 102–107.
[26]
Tipping, M. Sparse Bayesian learning and the relevance vector machine. J. Mach. Learn. Res. 2001, 1, 211–244.
[27]
Bishop, C.M. Pattern Recognition and Machine Learning; Springer: New York, NY, USA, 2006; pp. 345–349.
[28]
Caesarendra, W.; Widodo, A.; Yang, B.-S. Application of relevance vector machine and logistic regression for machine degradation assessment. Mech. Syst. Signal Pr. 2010, 24, 1161–1171.
[29]
Zio, E.; Di Maio, F. Fatigue crack growth estimation by relevance vector machine. Expert Syst. Appl. 2012, 39, 10681–10692.
[30]
Di Maio, F.; Tsui, K.; Zio, E. Combining relevance vector machines and exponential regression for bearing residual life estimation. Mech. Syst. Signal Pr. 2012, 32, 405–427.
[31]
Wang, P.; Youn, B.; Hu, C. A generic probabilistic framework for structural health prognostic and uncertainty management. Mech. Syst. Signal Pr. 2012, 28, 622–637.
[32]
Wang, D.; Miao, Q.; Pecht, M. Prognostics of lithium-ion batteries based on relevance vectors and a conditional three-parameter capacity degradation model. J. Power Sources 2013, 239, 253–264.
[33]
Fletcher, T. Relevance Vector Machines Explained, 2008. Available online: www.cs.ucl.ac.uk/staff/T.Fletcher (accessed on 19 October 2010).
[34]
Rasmussen, C.; Williams, C. Gaussian Processes for Machine Learning; MIT Press: Cambridge, MA, USA; London, UK, 2006; pp. 149–150.
[35]
Tse, P. A Tailor-made Fault Diagnosis for Syncrude Canada's Slurry Pumps. The Fourth Report for Year 2011. Technical Report (31 pages), 21 September 2010–12 January 2011.
[36]
Li, B.; Chow, M.-Y.; Tipsuwan, Y.; Hung, J. Neural-network-based motor rolling bearing fault diagnosis. IEEE Trans. Ind. Electron. 2000, 47, 1060–1069.
[37]
Beebe, R. Predictive Maintenance of Pumps Using Condition Monitoring; Elsevier Science & Technology: Oxford, UK, 2004; pp. 101–134.
[38]
He, W.; Williard, N.; Osterman, M.; Pecht, M. Prognostics of lithium-ion batteries based on Dempster—Shafer theory and the Bayesian Monte Carlo method. J. Power Sources 2011, 196, 10314–10321.
