Adaptive prognosis of centrifugal pump under variable operating conditions

Abstract Condition monitoring and prognosis of a centrifugal pump is essential to increase its reliability and safety, and reduce downtime and maintenance costs. Due to the complexity and variety of its operating conditions in practice, the distribution characteristics of data collected from a centrifugal pump shows complex multivariate distributions. On the other hand, the machinery degradation process is also characterized by stochasticity and nonlinearity. To address these challenges, this paper presents an adaptive prognosis method incorporating operating condition identification and Bayesian prediction in one framework. Specifically, a multivariate distribution based unsupervised clustering method is presented to identify operating conditions of pumps based on Gaussian mixture model and Expectation-Maximization algorithm. Then the future machinery status is predicted for defect severity analysis and remaining useful life estimation under the identified operating conditions based on particle filter method. The uncertainty of the prediction results is also quantified and updated with the instrumented measurements. An experimental study on an oil centrifugal pump in the field is performed to demonstrate the effectiveness of the presented adaptive prognosis method over conventional prediction approaches.

[1]  Marcos E. Orchard,et al.  Particle-filtering-based failure prognosis via sigma-points: Application to Lithium-Ion battery State-of-Charge monitoring , 2017 .

[2]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[3]  T.G. Habetler,et al.  Motor bearing damage detection using stator current monitoring , 1994, Proceedings of 1994 IEEE Industry Applications Society Annual Meeting.

[4]  Robert X. Gao,et al.  Cloud-enabled prognosis for manufacturing , 2015 .

[5]  R. B. Gopaluni,et al.  Fault detection and isolation in stochastic non-linear state-space models using particle filters , 2012 .

[6]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[7]  A. S. Sekhar,et al.  Condition monitoring of brushless DC motor-based electromechanical linear actuators using motor current signature analysis , 2011 .

[8]  Ashkan Moosavian,et al.  Fault diagnosis and classification of water pump using adaptive neuro-fuzzy inference system based on vibration signals , 2015 .

[9]  Andrew Ball,et al.  Diagnosis of Centrifugal Pump Faults Using Vibration Methods , 2012 .

[10]  Bo-Suk Yang,et al.  Machine condition prognosis based on regression trees and one-step-ahead prediction , 2008 .

[11]  Jianbo Yu,et al.  Bearing performance degradation assessment using locality preserving projections and Gaussian mixture models , 2011 .

[12]  David,et al.  Switching Kalman filter for failure prognostic , 2015 .

[13]  George J. Vachtsevanos,et al.  A particle-filtering approach for on-line fault diagnosis and failure prognosis , 2009 .

[14]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[15]  Douglas A. Reynolds,et al.  Robust text-independent speaker identification using Gaussian mixture speaker models , 1995, IEEE Trans. Speech Audio Process..

[16]  Lin Ma,et al.  Machinery Condition Prognosis Using Multivariate Analysis , 2006 .

[17]  Robert X. Gao,et al.  Enhanced particle filter for tool wear prediction , 2015 .

[18]  Jorge Parrondo,et al.  Development of a predictive maintenance system for a centrifugal pump , 1998 .

[19]  Filippo Emanuele Ciarapica,et al.  Managing the condition-based maintenance of a combined-cycle power plant : An approach using soft computing techniques , 2006 .

[20]  H. Shi,et al.  Dynamic Multimode Process Modeling and Monitoring Using Adaptive Gaussian Mixture Models , 2012 .

[21]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[22]  Yang Li,et al.  Demodulation for hydraulic pump fault signals based on local mean decomposition and improved adaptive multiscale morphology analysis , 2015 .

[23]  Amiya R. Mohanty,et al.  Fault detection in a centrifugal pump using vibration and motor current signature analysis , 2012, Int. J. Autom. Control..

[24]  G. Irwin,et al.  Process monitoring approach using fast moving window PCA , 2005 .

[25]  Steven Y. Liang,et al.  Dynamic Prognostic Prediction of Defect Propagation on Rolling Element Bearings , 1999 .

[26]  Sankaran Mahadevan,et al.  Integration of structural health monitoring and fatigue damage prognosis , 2012 .

[27]  Robert X. Gao,et al.  A virtual sensing based augmented particle filter for tool condition prognosis , 2017 .

[28]  P. Pérez,et al.  Tracking multiple objects with particle filtering , 2002 .

[29]  N. R. Sakthivel,et al.  Comparison of decision tree-fuzzy and rough set-fuzzy methods for fault categorization of mono-block centrifugal pump , 2010 .

[30]  C. Spearman.  The proof and measurement of association between two things. By C. Spearman, 1904. , 1987, The American journal of psychology.

[31]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[32]  Mengyan Nie,et al.  Review of condition monitoring and fault diagnosis technologies for wind turbine gearbox , 2013 .

[33]  Wenyuan Lv,et al.  A novel method using adaptive hidden semi-Markov model for multi-sensor monitoring equipment health prognosis , 2015 .