Closed-loop fault diagnosis based on a nonlinear process model and automatic fuzzy rule generation

被引:21
作者
Ballé, P
Fuessel, D
机构
[1] Tech Univ Darmstadt, Inst Automat Control, D-64283 Darmstadt, Germany
[2] Westend Carree, D-60322 Frankfurt, Germany
关键词
fault detection; fault diagnosis; fuzzy classification; fuzzy model; closed-loop supervision;
D O I
10.1016/S0952-1976(00)00049-X
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this contribution a new approach for fault detection and diagnosis (FDD) for nonlinear processes is presented. A nonlinear fuzzy model with transparent inner structure is used for the generation of relevant symptoms. The resulting symptom patterns are classified with a new self-learning classification structure based on fuzzy rules. The approach is successfully applied to an electropneumatic valve in a closed control loop. (C) 2000 Elsevier Science Ltd. All rights reserved.
引用
收藏
页码:695 / 704
页数:10
相关论文
共 18 条
[1]  
[Anonymous], PRENTICE HALL INT SE
[2]  
ARTE P, 1995, EUR CONTR C ROM
[3]  
Brown M, 1994, NEUROFUZZY ADAPTIVE
[4]  
DEIBERT R, 1994, EL COMP C ERK 94 POR
[5]  
FISCHER M, 1997, 2 INT S FUZZ LOG APP
[6]  
FUESSEL D, 1998, P 24 ANN C IEEE IND
[7]  
Gertler J., 1998, FAULT DETECTION DIAG
[8]  
Haykin S., 1994, NEURAL NETWORKS COMP
[9]  
HOFLING T, 1995, IFAC WORKSH ON LIN F