A new fault detection method for nonlinear process monitoring

被引：37

作者：

Fazai, Radhia ^{[1
]}

Taouali, Okba ^{[1
]}

Harkat, Mohamed Faouzi ^{[2
]}

Bouguila, Nasereddine ^{[1
]}

机构：

[1] Univ Monastir, Natl Sch Engineers Monastir, Lab Automat Signal & Image Proc, Monastir 5019, Tunisia

[2] Badji Mokthar Anaba Univ, BP 12, Anaba 2300, Algeria

来源：

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY | 2016年 / 87卷 / 9-12期

基金：

加拿大健康研究院; 美国国家卫生研究院;

关键词：

KPCA; MWKPCA; AKPCA; Variable Moving Window Kernel PCA (VMWKPCA); Fault detection; IDENTIFICATION; CHARTS;

D O I：

10.1007/s00170-016-8745-7

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Kernel Principal Component Analysis (KPCA) is a nonlinear extension of Principal Component Analysis (PCA). Recently, it is the most popular technique for monitoring nonlinear processes. However, the time-varying property of the industrial processes requires the adaptive ability of the KPCA. Therefore, in this paper, a Variable Moving Window Kernel PCA (VMWKPCA) method is proposed to update the KPCA model. The concept of this method consists of varying the size of the moving window according to the change of the normal process. To evaluate the performance of the proposed method, the VMWKPCA is applied for monitoring a Continuous Stirred Tank Reactor (CSTR) and a Tennessee Eastman process (TE). The results are satisfactory compared to the conventional Moving Window Kernel PCA (MWKPCA) and the Adaptive Kernel PCA (AKPCA).

引用

页码：3425 / 3436

页数：12

共 20 条

[1]

[Anonymous], 2015, Appl. Math.

[2] Variable MWPCA for adaptive process monitoring [J].

Bin He, Xiao ;

Yang, Yu Pu .

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2008, 47 (02) :419-427

[3] Fault detection and identification of nonlinear processes based on kernel PCA [J].

Choi, SW ;

Lee, C ;

Lee, JM ;

Park, JH ;

Lee, IB .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2005, 75 (01) :55-67

[4] A PLANT-WIDE INDUSTRIAL-PROCESS CONTROL PROBLEM [J].

DOWNS, JJ ;

VOGEL, EF .

COMPUTERS & CHEMICAL ENGINEERING, 1993, 17 (03) :245-255

[5] Identification of faulty sensors using principal component analysis [J].

Dunia, R ;

Qin, SJ ;

Edgar, TF ;

McAvoy, TJ .

AICHE JOURNAL, 1996, 42 (10) :2797-2812

[6] Online prediction model based on the SVD-KPCA method [J].

Elaissi, Ilyes ;

Jaffel, Ines ;

Taouali, Okba ;

Messaoud, Hassani .

ISA TRANSACTIONS, 2013, 52 (01) :96-104

[7] Adaptive process monitoring using efficient recursive PCA and moving window PCA algorithms [J].

Jeng, Jyh-Cheng .

JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS, 2010, 41 (04) :475-481

[8] Nonlinear process monitoring using kernel principal component analysis [J].

Lee, JM ;

Yoo, CK ;

Choi, SW ;

Vanrolleghem, PA ;

Lee, IB .

CHEMICAL ENGINEERING SCIENCE, 2004, 59 (01) :223-234

[9] Moving window kernel PCA for adaptive monitoring of nonlinear processes [J].

Liu, Xueqin ;

Kruger, Uwe ;

Littler, Tim ;

Xie, Lei ;

Wang, Shuqing .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2009, 96 (02) :132-143

[10] MULTIVARIATE SPC CHARTS FOR MONITORING BATCH PROCESSES [J].

NOMIKOS, P ;

MACGREGOR, JF .

TECHNOMETRICS, 1995, 37 (01) :41-59

← 1 2 →