Residual useful life estimation based on stable distribution feature extraction and SVM classifier

The This paper deals with a data-driven diagnostic and prognostic method based on Stable distribution feature extraction and SVM Classier. The prognostic process of the proposed method is made in two steps. In the first step, which is performed online, the monitoring data provided by sensors are processed to extract features based on stable distribution, which are then used to learn SVM classifier that capture the time evolution of the degradation and therefore of the systems health state. In the second step, performed on-line, the learned models are exploited to do failure prognostic by estimating the assets current health state, its remaining useful life. The experiments on the recently published database taken from Pronostia of FEMTO, Prognostic data repository: Bearing data set, clearly show the superiority of the proposed approach compared to well establish method in literature. [ABSTRACT FROM AUTHOR]

[1]  Noureddine Zerhouni,et al.  CNC machine tool's wear diagnostic and prognostic by using dynamic Bayesian networks , 2012 .

[2]  Michael Osterman,et al.  Prognostics Assessment of Aluminum Support Structure on a Printed Circuit Board , 2006 .

[3]  Moe Z. Win,et al.  NLOS identification and mitigation for localization based on UWB experimental data , 2010, IEEE Journal on Selected Areas in Communications.

[4]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[5]  Pavan Kumar Kankar,et al.  A Review on Prognosis of Rolling Element Bearings , 2011 .

[6]  J. Logsdon.  The challenger launch decision: Risky technology, culture, and deviance at NASA , 1997 .

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

[8]  Jay Lee,et al.  Robust performance degradation assessment methods for enhanced rolling element bearing prognostics , 2003, Adv. Eng. Informatics.

[9]  Argon Chen,et al.  Real-time health prognosis and dynamic preventive maintenance policy for equipment under aging Markovian deterioration , 2007 .

[10]  P.W. Kalgren,et al.  Defining PHM, A Lexical Evolution of Maintenance and Logistics , 2006, 2006 IEEE Autotestcon.

[11]  Kurt Hornik,et al.  Support Vector Machines in R , 2006 .

[12]  Irem Y. Tumer,et al.  Mapping function to failure mode during component development , 2003 .

[13]  B. Dickson,et al.  Feasibility Study of a Rotorcraft Health and Usage Monitoring System (HUMS): Usage and Structural Life Monitoring Evaluation. Phase 2. , 1996 .

[14]  J. McCulloch,et al.  Simple consistent estimators of stable distribution parameters , 1986 .

[15]  Joseph Mathew,et al.  Machine Prognostics Based on Health State Estimation Using SVM , 2008, WCE 2009.

[16]  Lifeng Xi,et al.  Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods , 2007 .

[17]  Jianping Li,et al.  A multiple kernel support vector machine scheme for feature selection and rule extraction from gene expression data of cancer tissue , 2007, Artif. Intell. Medicine.

[18]  Ming-Chang Lee,et al.  Comparison of Support Vector Machine and Back Propagation Neural Network in Evaluating the Enterprise Financial Distress , 2010, ArXiv.

[19]  K. Goebel,et al.  Standardizing research methods for prognostics , 2008, 2008 International Conference on Prognostics and Health Management.

[20]  Qing Li,et al.  A Hybrid LSSVR-HMM Based Prognostics Approach , 2012 .

[21]  Gang Yu,et al.  A New Statistical Model for Rolling Element Bearing Fault Signals Based on Alpha-Stable Distribution , 2010, 2010 Second International Conference on Computer Modeling and Simulation.

[22]  Jay Lee,et al.  A review on prognostics and health monitoring of Li-ion battery , 2011 .

[23]  A. Hess,et al.  The Joint Strike Fighter (JSF) PHM concept: Potential impact on aging aircraft problems , 2002, Proceedings, IEEE Aerospace Conference.