Application of relevance vector machine and logistic regression for machine degradation assessment

被引:180
作者
Caesarendra, Wahyu [1 ]
Widodo, Achmad [2 ]
Yang, Bo-Suk [1 ]
机构
[1] Pukyong Natl Univ, Sch Mech Engn, Pusan 608739, South Korea
[2] Diponegoro Univ, Dept Mech Engn, Tembalang 50275, Semarang, Indonesia
关键词
Relevance vector machine; Logistic regression; Failure degradation; Prognostics; ROLLING ELEMENT BEARING; RESIDUAL-LIFE DISTRIBUTIONS; STATISTICAL MOMENTS; CLASSIFICATION; PROGNOSTICS; PREDICTIONS; DIAGNOSTICS; SIGNALS;
D O I
10.1016/j.ymssp.2009.10.011
中图分类号
TH [机械、仪表工业];
学科分类号
120111 [工业工程];
摘要
Degradation parameter or deviation parameter from normal to failure condition of machine part or system is needed as an object of prediction in prognostics method. This study proposes the combination between relevance vector machine (RVM) and logistic regression (LR) in order to assess the failure degradation and prediction from incipient failure until final failure occurred. LR is used to estimate failure degradation of bearing based on run-to-failure datasets and the results are then regarded as target vectors of failure probability. RVM is selected as intelligent system then trained by using run-to-failure bearing data and target vectors of failure probability estimated by LR. After the training process, RVM is employed to predict failure probability of individual units of machine component. The performance of the proposed method is validated by applying the system to predict failure time of individual bearing based on simulation and experimental data. The result shows the plausibility and effectiveness of the proposed method, which can be considered as the machine degradation assessment model. (C) 2009 Elsevier Ltd. All rights reserved.
引用
收藏
页码:1161 / 1171
页数:11
相关论文
共 33 条
[1]
[Anonymous], ADV NEURAL INFORM PR
[2]
AUSTIN PC, 2009, J CLIN EPID IN PRESS
[3]
Residual life, predictions from vibration-based degradation signals: A neural network approach [J].
Gebraeel, N ;
Lawley, M ;
Liu, R ;
Parmeshwaran, V .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2004, 51 (03) :694-700
[4]
Sensory-updated residual life distributions for components with exponential degradation patterns [J].
Gebraeel, Nagi .
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2006, 3 (04) :382-393
[5]
Residual-life distributions from component degradation signals: A Bayesian approach [J].
Gebraeel, NZ ;
Lawley, MA ;
Li, R ;
Ryan, JK .
IIE TRANSACTIONS, 2005, 37 (06) :543-557
[6]
Rotating machinery prognostics: State of the art, challenges and opportunities [J].
Heng, Aiwina ;
Zhang, Sheng ;
Tan, Andy C. C. ;
Mathew, Joseph .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2009, 23 (03) :724-739
[7]
Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods [J].
Huang, Runqing ;
Xi, Lifeng ;
Li, Xinglin ;
Liu, C. Richard ;
Qiu, Hai ;
Lee, Jay .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2007, 21 (01) :193-207
[8]
A review on machinery diagnostics and prognostics implementing condition-based maintenance [J].
Jardine, Andrew K. S. ;
Lin, Daming ;
Banjevic, Dragan .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2006, 20 (07) :1483-1510
[9]
LEE HH, 2007, LECT NOTES COMPUTER
[10]
Lee J., 2007, Rexnord Technical Services, Bearing Data Set, IMS, University of Cincinnati. NASA Ames Prognostics Data Repository