The classification and regression tree approach to pump failure rate analysis

被引:72
作者
Bevilacqua, M
Braglia, M
Montanari, R
机构
[1] Univ Pisa, Dipartimento Ingn Meccan Nucl & Prod, Fac Ingn, I-56126 Pisa, Italy
[2] Univ Bologna, Dipartimento Ingn Costruz Meccan Nucl Aeronaut &, I-40136 Bologna, Italy
[3] Univ Parma, Dipartimento Ingn Ind, I-43100 Parma, Italy
关键词
failure rate; reliability; rule induction; decision tree; classification and regression tree;
D O I
10.1016/S0951-8320(02)00180-1
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
In this article, a technique based on rule induction is suggested as non-parametric alternative to determine the expected failure rates of 143 centrifugal pumps included in a oil refinery plant and subjected to different operating conditions. At the same time, the procedure-makes it possible to determine the critical operating factors influencing the reliability of the pumps. In particular, the classification and regression tree approach is used to automatically generate rules from an extended data base of the plant concerning information about failures and operating conditions of the different facilities. (C) 2002 Elsevier Science Ltd. All rights reserved.
引用
收藏
页码:59 / 67
页数:9
相关论文
共 13 条
[1]  
*ASTM, 1998, D34193 ASTM
[2]  
Biggs D., 1991, J APPL STAT, V18, P49, DOI [DOI 10.1080/02664769100000005, 10.1080/02664769100000005]
[3]  
Breiman L., 1984, BIOMETRICS, DOI DOI 10.2307/2530946
[4]  
Kass G.V., 1980, J. R. Stat. Soc. Ser. C. Appl. Stat., V29, P119, DOI DOI 10.2307/2986296
[5]  
Loh WY, 1997, STAT SINICA, V7, P815
[6]   A rule induction approach for determining the number of kanbans in a just-in-time production system [J].
Markham, IS ;
Mathieu, RG ;
Wray, BA .
COMPUTERS & INDUSTRIAL ENGINEERING, 1998, 34 (04) :717-727
[8]  
OCONNOR PDT, 1991, PRACTICAL RELIABILIT
[9]   The decision tree approach to stock selection -: An evolving tree model performs the best. [J].
Sorensen, EH ;
Miller, KL ;
Ooi, CK .
JOURNAL OF PORTFOLIO MANAGEMENT, 2000, 27 (01) :42-+
[10]  
*SPSS INC, 1988, ANSW 2 0 US GUID