Improved canonical correlation analysis-based fault detection methods for industrial processes

被引：103

作者：

Chen, Zhiwen ^{[1
]}

Zhang, Kai ^{[1
]}

Ding, Steven X. ^{[1
]}

Shardt, Yuri A. W. ^{[1
]}

Hu, Zhikun ^{[2
]}

机构：

[1] Univ Duisburg Essen, Inst Automat Control & Complex Syst, Bismarckstr 81 BB, D-47057 Duisburg, Germany

[2] Cent S Univ, Sch Phys & Elect, Changsha 410083, Peoples R China

来源：

JOURNAL OF PROCESS CONTROL | 2016年 / 41卷

基金：

中国国家自然科学基金;

关键词：

Canonical correlation analysis; Incipient multiplicative fault detection; Statistical local approach; PRINCIPAL COMPONENT ANALYSIS; PART I; DISTURBANCE DETECTION; DIAGNOSIS; INFORMATION; PERFORMANCE; SYSTEMS;

D O I：

10.1016/j.jprocont.2016.02.006

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Recent research has emphasized the successful application of canonical correlation analysis (CCA) to perform fault detection (FD) in both static and dynamic processes with additive faults. However, dealing with multiplicative faults has not been as successful. Thus, this paper considers the application of CCA to deal with the detection of incipient multiplicative faults in industrial processes. The new approaches incorporate the CCA-based FD with the statistical local approach. It is shown that the methods are effective in detecting incipient multiplicative faults. Experiments using a continuous stirred tank heater and simulations on the Tennessee Eastman process are provided to validate the proposed methods. (C) 2016 Elsevier Ltd. All rights reserved.

引用

页码：26 / 34

页数：9

共 51 条

[11]

Ding SX, 2014, ADV IND CONTROL, P1, DOI 10.1007/978-1-4471-6410-4

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

DOWNS, JJ ;

VOGEL, EF .

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

[13] Efficient Recursive Principal Component Analysis Algorithms for Process Monitoring [J].

Elshenawy, Lamiaa M. ;

Yin, Shen ;

Naik, Amol S. ;

Ding, Steven X. .

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2010, 49 (01) :252-259

[14]

Gao ZW, 2015, IEEE T IND ELECTRON, V62, P3768, DOI [10.1109/TIE.2015.2417501, 10.1109/TIE.2015.2419013]

[15]

Ge Z. Q., AICHE J, V58

[16] Review of Recent Research on Data-Based Process Monitoring [J].

Ge, Zhiqiang ;

Song, Zhihuan ;

Gao, Furong .

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2013, 52 (10) :3543-3562

[17] A data-driven multiplicative fault diagnosis approach for automation processes [J].

Hao, Haiyang ;

Zhang, Kai ;

Ding, Steven X. ;

Chen, Zhiwen ;

Lei, Yaguo .

ISA TRANSACTIONS, 2014, 53 (05) :1436-1445

[18] Incipient fault detection and diagnosis based on Kullback-Leibler divergence using Principal Component Analysis: Part I [J].

Harmouche, Jinane ;

Delpha, Claude ;

Diallo, Demba .

SIGNAL PROCESSING, 2014, 94 :278-287

[19] A unified framework for contrast research of the latent variable multivariate regression methods [J].

He, Zhangming ;

Zhou, Haiyin ;

Wang, Jiongqi ;

Zhai, Shouchao .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2015, 143 :136-145

[20] Adaptive PCA based fault diagnosis scheme in imperial smelting process [J].

Hu, Zhikun ;

Chen, Zhiwen ;

Gui, Weihua ;

Jiang, Bin .

ISA TRANSACTIONS, 2014, 53 (05) :1446-1455

← 1 2 3 4 5 6 →