A new data-driven process monitoring scheme for key performance indictors with application to hot strip mill process

被引：17

作者：

Peng, Kaixiang ^{[1
]}

Zhang, Kai ^{[1
]}

Dong, Jie ^{[1
]}

Yang, Xu ^{[1
]}

机构：

[1] Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Key Lab Adv Control Iron & Steel Proc, Beijing 100083, Peoples R China

来源：

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS | 2014年 / 351卷 / 09期

基金：

中国博士后科学基金; 北京市自然科学基金;

关键词：

INDEPENDENT COMPONENT ANALYSIS; PARTIAL LEAST-SQUARES; FAULT-DETECTION; LATENT STRUCTURES; TOTAL PROJECTION; DIAGNOSIS; RELEVANT;

D O I：

10.1016/j.jfranklin.2014.06.006

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Hot strip mill process (HSMP) plays a pivotal role in steel manufacturing industry, but involves significant complexity. Several faults could cause the decreasing evaluation of the key performance indicators (KPIs). Partial least squares (PLS) model has been popularly accepted for KPI-monitoring tasks, whereas some drawbacks have been reported such as high false alarm rate and strict limitation of Gaussian distribution. In this paper, a new scheme is designed without any distributional priority. The process information is extracted by the independent component analysis (ICA) and principal component analysis (PCA) one after another to obtain the Non-Gaussianity and Gaussianity rooted in process variables. Then the correlation canonical analysis (CCA), a classic tool of analyzing the correlation of two data sets, will be utilized to incorporate the process information and KPIs. Finally, two KPI-related indices are formed respectively, which are both bounded by key density estimation based approach. In the end, application of the new approach in a real steel plant will be demonstrated, where the comparison with PLS based results is covered. (C) 2014 The Franklin Institute. Published by Elsevier Ltd. All rights reserved.

引用

页码：4555 / 4569

页数：15

共 30 条

[1]

[Anonymous], 1975, International Perspectives on Mathematical and Statistical Modeling, DOI DOI 10.1016/B978-0-12-103950-9.50017-4

[2] Fault diagnosis in chemical processes using Fisher discriminant analysis, discriminant partial least squares, and principal component analysis [J].

Chiang, LH ;

Russell, EL ;

Braatz, RD .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2000, 50 (02) :243-252

[3] A Novel Scheme for Key Performance Indicator Prediction and Diagnosis With Application to an Industrial Hot Strip Mill [J].

Ding, Steven X. ;

Yin, Shen ;

Peng, Kaixiang ;

Hao, Haiyang ;

Shen, Bo .

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2013, 9 (04) :2239-2247

[4]

Ding SX, 2013, ADV IND CONTROL, P1, DOI 10.1007/978-1-4471-4799-2

[5] Fault Detection for Markovian Jump Systems With Sensor Saturations and Randomly Varying Nonlinearities [J].

Dong, Hongli ;

Wang, Zidong ;

Gao, Huijun .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2012, 59 (10) :2354-2362

[6] Fuzzy-Model-Based Robust Fault Detection With Stochastic Mixed Time Delays and Successive Packet Dropouts [J].

Dong, Hongli ;

Wang, Zidong ;

Lam, James ;

Gao, Huijun .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2012, 42 (02) :365-376

[7] Process monitoring based on independent component analysis-principal component analysis (ICA-PCA) and similarity factors [J].

Ge, Zhiqiang ;

Song, Zhihuan .

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2007, 46 (07) :2054-2063

[8]

Hao HY, 2013, IEEE INT CONF CON AU, P1460

[9] Canonical correlation analysis: An overview with application to learning methods [J].

Hardoon, DR ;

Szedmak, S ;

Shawe-Taylor, J .

NEURAL COMPUTATION, 2004, 16 (12) :2639-2664

[10] Relations between two sets of variates [J].

Hotelling, H .

BIOMETRIKA, 1936, 28 :321-377

← 1 2 3 →