ICARUS: design and deployment of a case-based reasoning system for locomotive diagnostics

被引：44

作者：

Varma, A ^{[1
]}

Roddy, N ^{[1
]}

机构：

[1] GE, Corp Res & Dev, Informat Technol Lab, Schenectady, NY 12301 USA

来源：

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE | 1999年 / 12卷 / 06期

关键词：

case-based reasoning; locomotives; diagnosis; feature extraction; feature weighting; fault codes;

D O I：

10.1016/S0952-1976(99)00039-1

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Locomotives, like many complex modern machines, are equipped with the capability to generate on-board fault messages indicating the presence of anomalous conditions. Such messages tend to be generated in large quantities, and are difficult and lime consuming to interpret manually. This paper presents the design and development of a case-based reasoning system for diagnosing locomotive faults using such fault messages as input. The process of using historical repair data and expert input for case generation and validation is described. An algorithm for case matching is presented, along with some results on pilot data. (C) 1999 Elsevier Science Ltd. All rights reserved.

引用

页码：681 / 690

页数：10

共 17 条

[1]

ACORN T, 1992, P AAAI 92

[2]

Bonzano A, 1997, LECT NOTES ARTIF INT, V1266, P291

[3]

DATTANI I, 1996, APPL INNOVATIONS EXP, V4, P189

[4]

DETERS R, 1995, LECT NOTES COMPUTER, V1010, P411

[5]

Faltings B, 1997, LECT NOTES ARTIF INT, V1266, P611

[6]

GEORGIN E, 1995, LECT NOTES COMPUT SC, V1020, P175

[7] APPLYING CASE-BASED REASONING TO AUTOCLAVE LOADING [J].

HENNESSY, D ;

HINKLE, D .

IEEE EXPERT-INTELLIGENT SYSTEMS & THEIR APPLICATIONS, 1992, 7 (05) :21-26

[8]

Howe N, 1997, LECT NOTES ARTIF INT, V1266, P455

[9]

Jarmulak J, 1997, LECT NOTES ARTIF INT, V1266, P43

[10]

KITANO H, 1993, PROCEEDINGS OF THE ELEVENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, P303

← 1 2 →