Fault detection and identification of nonlinear processes based on kernel PCA

被引:365
作者
Choi, SW [1 ]
Lee, C
Lee, JM
Park, JH
Lee, IB
机构
[1] Newcastle Univ, Sch Chem Engn & Adv Mat, Foresight Ctr Proc Analyt & Control Technol, Newcastle Upon Tyne NE1 7RU, Tyne & Wear, England
[2] Pohang Univ Sci & Technol, Dept Chem Engn, Pohang 790784, South Korea
[3] PNI Consulting Co Ltd, Pohang 790784, South Korea
关键词
kernel principal component analysis; data reconstruction; fault detection and isolation; monitoring statistics;
D O I
10.1016/j.chemolab.2004.05.001
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A new fault detection and identification method based on kernel principal component analysis (PCA) is described. In the past, numerous PCA-based statistical process monitoring methods have been developed and applied to various chemical processes. However, these previous methods assume that the monitored process is linear, whereas most of the chemical reactions in chemical processes are nonlinear. For such nonlinear systems, PCA-based monitoring has proved inefficient and problematic, prompting the development of several nonlinear PCA methods. In this paper, we propose a new nonlinear PCA-based method that uses kernel functions, and we compare the proposed method with previous methods. A unified fault detection index is developed based on the energy approximation concept. In particular, a new approach to fault identification, which is a challenging problem in nonlinear PCA, is formulated based on a robust reconstruction error calculation. The proposed monitoring method was applied to two simple nonlinear processes and the simulated continuous stirred tank reactor (CSTR) process. The monitoring results confirm that the proposed methodology affords credible fault detection and identification. (C) 2004 Elsevier B.V. All rights reserved.
引用
收藏
页码:55 / 67
页数:13
相关论文
共 23 条
[1]  
[Anonymous], 1991, IFAC ADV CONTROLOF C
[2]  
Beardahy CC, 1995, Technical report
[3]  
Bishop C. M., 1996, Neural networks for pattern recognition
[4]   Shape statistics in kernel space for variational image segmentation [J].
Cremers, D ;
Kohlberger, T ;
Schnörr, C .
PATTERN RECOGNITION, 2003, 36 (09) :1929-1943
[5]   Projection methods in chemistry [J].
Daszykowski, M ;
Walczak, B ;
Massart, DL .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2003, 65 (01) :97-112
[6]   Nonlinear principal component analysis - Based on principal curves and neural networks [J].
Dong, D ;
McAvoy, TJ .
COMPUTERS & CHEMICAL ENGINEERING, 1996, 20 (01) :65-78
[7]   Identification of faulty sensors using principal component analysis [J].
Dunia, R ;
Qin, SJ ;
Edgar, TF ;
McAvoy, TJ .
AICHE JOURNAL, 1996, 42 (10) :2797-2812
[8]   PRINCIPAL CURVES [J].
HASTIE, T ;
STUETZLE, W .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1989, 84 (406) :502-516
[9]  
Jackson JE, 1991, A user's guide to principal components
[10]  
JIA F, 1998, NONLINEAR PRINCIPAL, V22, pS851