Cause-effect analysis of industrial alarm variables using transfer entropies

被引：45

作者：

Hu, Wenkai ^{[1
]}

Wang, Jiandong ^{[2
]}

Chen, Tongwen ^{[1
]}

Shah, Sirish L. ^{[3
]}

机构：

[1] Univ Alberta, Dept Elect & Comp Engn, Edmonton, AB, Canada

[2] Shandong Univ Sci & Technol, Qingdao, Shandong, Peoples R China

[3] Univ Alberta, Dept Chem & Mat Engn, Edmonton, AB, Canada

来源：

CONTROL ENGINEERING PRACTICE | 2017年 / 64卷

基金：

中国国家自然科学基金; 加拿大自然科学与工程研究理事会;

关键词：

Industrial alarm systems; Cause-effect analysis; Binary sequences; Transfer entropy; Direct causality; CORRELATED ALARMS; PROPAGATION;

D O I：

10.1016/j.conengprac.2017.04.012

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 method is proposed to analyze cause-effect relationships among binary-valued alarm variables. A normalized transfer entropy (NTE) and a normalized direct transfer entropy (NDTE) are formulated as basic statistical metrics, with consideration of two specific characteristics of alarm variables, namely, random delays and mutual independence among alarm occurrences. A modified statistical test is developed to determine significance thresholds of NTEs and NDTEs, based on which the cause-effect relationships can be inferred. The effectiveness of the proposed method is illustrated via numerical and industrial case studies. (C) 2017 Elsevier Ltd. All rights reserved.

引用

页码：205 / 214

页数：10

共 28 条

[1] A practical method for identifying the propagation path of plant-wide disturbances [J].

Bauer, Margret ;

Thornhill, Nina F. .

JOURNAL OF PROCESS CONTROL, 2008, 18 (7-8) :707-719

[2] Finding the direction of disturbance propagation in a chemical process using transfer entropy [J].

Bauer, Margret ;

Cox, John W. ;

Caveness, Michelle H. ;

Downs, James J. ;

Thornhill, Nina F. .

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2007, 15 (01) :12-21

[3] Graphical methods for diagnosis of dynamic systems: Review [J].

Bouamama, B. Ould ;

Biswas, G. ;

Loureiro, R. ;

Merzouki, R. .

ANNUAL REVIEWS IN CONTROL, 2014, 38 (02) :199-219

[4] Process monitoring using causal map and multivariate statistics: fault detection and identification [J].

Chiang, LH ;

Braatz, RD .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2003, 65 (02) :159-178

[5] Transfer Zero-Entropy and Its Application for Capturing Cause and Effect Relationship Between Variables [J].

Duan, Ping ;

Yang, Fan ;

Shah, Sirish L. ;

Chen, Tongwen .

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2015, 23 (03) :855-867

[6] Direct Causality Detection via the Transfer Entropy Approach [J].

Duan, Ping ;

Yang, Fan ;

Chen, Tongwen ;

Shah, Sirish L. .

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2013, 21 (06) :2052-2066

[7]

Folmer Jens., 2014, IFAC Proceedings Volumes, V47, P1802

[8] Sequential Implementation of Monte Carlo Tests With Uniformly Bounded Resampling Risk [J].

Gandy, Axel .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2009, 104 (488) :1504-1511

[9] Evaluating information transfer between auditory cortical neurons [J].

Gourevitch, Boris ;

Eggermont, Jos J. .

JOURNAL OF NEUROPHYSIOLOGY, 2007, 97 (03) :2533-2543

[10] INVESTIGATING CAUSAL RELATIONS BY ECONOMETRIC MODELS AND CROSS-SPECTRAL METHODS [J].

GRANGER, CWJ .

ECONOMETRICA, 1969, 37 (03) :424-438

← 1 2 3 →