FAILURE DIAGNOSIS SYSTEM USING ARTMAP NEURAL NETWORKS

被引：5
作者：
DA, R
LIN, CF
机构：
[1] American GNC Corporation, Chatsworth, CA
来源：
JOURNAL OF GUIDANCE CONTROL AND DYNAMICS | 1995年 / 18卷 / 04期
关键词：
D O I：
10.2514/3.21449
中图分类号：
V [航空、航天];
学科分类号：
08 ; 0825 ;
摘要：
A novel scheme for diagnosing failures in dynamic systems is presented. After a failure is detected by the state chi-square test, two ARTMAP neural networks are applied to recognize patterns formed by data of the state chi-square test in order to determine when the failure happened, how serious the failure is, and where the failure is located. The efficacy of the proposed scheme is demonstrated by simulation examples where soft failures in an integrated global positioning system/inertial navigation system are successfully diagnosed, An effective approach is also developed to overcome the difficulty of distinguishing gyro failures from accelerometer failures.
引用
收藏
页码：696 / 701
页数：6
相关论文
共 21 条
[1]   A FAULT-TOLERANT MULTISENSOR NAVIGATION SYSTEM-DESIGN [J].
BRUMBACK, BD ;
SRINATH, MD .
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 1987, 23 (06) :738-756
[2]   ARTMAP - SUPERVISED REAL-TIME LEARNING AND CLASSIFICATION OF NONSTATIONARY DATA BY A SELF-ORGANIZING NEURAL NETWORK [J].
CARPENTER, GA ;
GROSSBERG, S ;
REYNOLDS, JH .
NEURAL NETWORKS, 1991, 4 (05) :565-588
[3]   A MASSIVELY PARALLEL ARCHITECTURE FOR A SELF-ORGANIZING NEURAL PATTERN-RECOGNITION MACHINE [J].
CARPENTER, GA ;
GROSSBERG, S .
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1987, 37 (01) :54-115
[4]   NEURAL NETWORK MODELS FOR PATTERN-RECOGNITION AND ASSOCIATIVE MEMORY [J].
CARPENTER, GA .
NEURAL NETWORKS, 1989, 2 (04) :243-257
[5]   FAILURE-DETECTION OF DYNAMICAL-SYSTEMS WITH THE STATE CHI-SQUARE TEST [J].
DA, R .
JOURNAL OF GUIDANCE CONTROL AND DYNAMICS, 1994, 17 (02) :271-277
[6]  
DA R, IN PRESS J GUIDANCE
[7]   FAULT-DIAGNOSIS IN DYNAMIC-SYSTEMS USING ANALYTICAL AND KNOWLEDGE-BASED REDUNDANCY - A SURVEY AND SOME NEW RESULTS [J].
FRANK, PM .
AUTOMATICA, 1990, 26 (03) :459-474
[8]   NEOCOGNITRON - A HIERARCHICAL NEURAL NETWORK CAPABLE OF VISUAL-PATTERN RECOGNITION [J].
FUKUSHIMA, K .
NEURAL NETWORKS, 1988, 1 (02) :119-130
[9]  
Gertler J. J., 1993, Control Engineering Practice, V1, P3, DOI 10.1016/0967-0661(93)92097-N
[10]   OBSERVABILITY ANALYSIS OF PIECE-WISE CONSTANT SYSTEMS .1. THEORY [J].
GOSHENMESKIN, D ;
BARITZHACK, IY .
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 1992, 28 (04) :1056-1067
123