Intelligent condition-based prediction of machinery reliability

被引:158
作者
Heng, Aiwina [1 ]
Tan, Andy C. C. [1 ]
Mathew, Joseph [1 ]
Montgomery, Neil [2 ]
Banjevic, Dragan [2 ]
Jardine, Andrew K. S. [2 ]
机构
[1] Queensland Univ Technol, CRC Integrated Engn Asset Management, Fac Built Environm & Engn, Brisbane, Qld 4109, Australia
[2] Univ Toronto, Dept Mech & Ind Engn, Ctr Maintenance Optimizat & Reliabil Engn, Toronto, ON, Canada
关键词
Artificial neural networks; Condition-based maintenance; Condition monitoring; Prognostics; Reliability; Suspended data; PROGNOSTICS; SYSTEM;
D O I
10.1016/j.ymssp.2008.12.006
中图分类号
TH [机械、仪表工业];
学科分类号
120111 [工业工程];
摘要
The ability to forecast machinery failure is vital to reducing maintenance costs, operation downtime and safety hazards. Recent advances in condition monitoring technologies have given rise to a number of prognostic models that attempt to forecast machinery health based on condition data. This paper presents a novel approach for incorporating population characteristics information and suspended condition trending data of historical units into prognosis. The population characteristics information extracted from statistical failure distribution enables longer-range prognosis. The accurate modelling of suspended data is also found to be of great importance, since in practice machines are rarely allowed to run to failure and hence data are commonly suspended. The proposed model consists of a feed-forward neural network whose training targets are asset survival probabilities estimated using a variation of the Kaplan-Meier estimator and a degradation-based failure probability density function (PDF) estimator. The trained network is capable of estimating the future survival probabilities of an operating asset when a series of condition indices are inputted. The output survival probabilities collectively form an estimated survival curve. Pump vibration data were used for model validation. The proposed model was compared with two similar models that neglect suspended data, as well as with a conventional time series prediction model. The results support our hypothesis that the proposed model can predict more accurately and further ahead than similar methods that do not include population characteristics and/or suspended data in prognosis. (C) 2009 Elsevier Ltd. All rights reserved.
引用
收藏
页码:1600 / 1614
页数:15
相关论文
共 23 条
[1]
ABDULNOUR G, 1995, INT J PROD RES, V33, P565, DOI 10.1080/00207549508930166
[2]
Survey and critique of techniques for extracting rules from trained artificial neural networks [J].
Andrews, R ;
Diederich, J ;
Tickle, AB .
KNOWLEDGE-BASED SYSTEMS, 1995, 8 (06) :373-389
[3]
Bostwick DG, 2001, CANCER, V91, P1643, DOI 10.1002/1097-0142(20010415)91:8+<1643::AID-CNCR1177>3.0.CO
[4]
2-I
[5]
FINDING STRUCTURE IN TIME [J].
ELMAN, JL .
COGNITIVE SCIENCE, 1990, 14 (02) :179-211
[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]
JANTUNEN E, 2004, ADV MAINTENANCE MODE
[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]
JOSHI R, 2006, P 18 INT C SYST ENG, P179
[10]
NONPARAMETRIC-ESTIMATION FROM INCOMPLETE OBSERVATIONS [J].
KAPLAN, EL ;
MEIER, P .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1958, 53 (282) :457-481