Robust adaptive boosted canonical correlation analysis for quality-relevant process monitoring of wastewater treatment

被引：24

作者：

Cheng, Hongchao ^{[1
,2
]}

Wu, Jing ^{[1
]}

Huang, Daoping ^{[1
]}

Liu, Yiqi ^{[1
]}

Wang, Qilin ^{[2
]}

机构：

[1] South China Univ Technol, Sch Automat Sci & Engn, Guangzhou 510640, Peoples R China

[2] Univ Technol Sydney, Sch Civil & Environm Engn, Ctr Technol Water & Wastewater, Ultimo, NSW 2007, Australia

来源：

ISA TRANSACTIONS | 2021年 / 117卷

基金：

中国国家自然科学基金; 澳大利亚研究理事会;

关键词：

Canonical correlation analysis (CCA); Adaptive threshold; Fault detection; Quality-relevant; Wastewater treatment; FAULT-DETECTION;

D O I：

10.1016/j.isatra.2021.01.039

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Quality-relevant process monitoring has attracted much attention for its ability to assist in maintaining efficient plant operation. However, when the process suffers from non-stationary and over-complex (with noise, multiplicative faults, etc.) characteristics, the traditional methods usually cannot be effectively applied. To this end, a novel method, termed as Robust adaptive boosted canonical correlation analysis (Rab-CCA), is proposed to monitor the wastewater treatment processes. First, a robust decomposition method is proposed to mitigate the defects of standard CCA by decomposing the corrupted matrix into a low-matrix and a sparse matrix. Second, to further improve the performance of the standard process monitoring method, a novel criterion function and control charts are reconstructed accordingly. Moreover, an adaptive statistical control limit is proposed that can adjust the thresholds according to the state of a system and can effectively reduce the missed alarms and false alarms simultaneously. The superiority of Rab-CCA is verified by Benchmark Simulation Model 1 (BSM1) and a real full-scale wastewater treatment plant (WWTP). (C) 2021 ISA. Published by Elsevier Ltd. All rights reserved.

引用

页码：210 / 220

页数：11

共 34 条

[1] Reconstruction-based contribution for process monitoring [J].

Alcala, Carlos F. ;

Qin, S. Joe .

AUTOMATICA, 2009, 45 (07) :1593-1600

[2] Robust canonical correlations: A comparative study [J].

Branco, JA ;

Croux, C ;

Filzmoser, P ;

Oliveira, MR .

COMPUTATIONAL STATISTICS, 2005, 20 (02) :203-229

[3] Robust Principal Component Analysis? [J].

Candes, Emmanuel J. ;

Li, Xiaodong ;

Ma, Yi ;

Wright, John .

JOURNAL OF THE ACM, 2011, 58 (03)

[4] Fault Detection for Non-Gaussian Processes Using Generalized Canonical Correlation Analysis and Randomized Algorithms [J].

Chen, Zhiwen ;

Ding, Steven X. ;

Peng, Tao ;

Yang, Chunhua ;

Gui, Weihua .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2018, 65 (02) :1559-1567

[5] Adaptive Transfer Learning of Cross-Spatiotemporal Canonical Correlation Analysis for Plant-Wide Process Monitoring [J].

Cheng, Hongchao ;

Liu, Yiqi ;

Huang, Daoping ;

Pan, Yongping ;

Wang, Qilin .

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2020, 59 (49) :21602-21614

[6] A Novel Ensemble Adaptive Sparse Bayesian Transfer Learning Machine for Nonlinear Large-Scale Process Monitoring [J].

Cheng, Hongchao ;

Liu, Yiqi ;

Huang, Daoping ;

Xu, Chong ;

Wu, Jing .

SENSORS, 2020, 20 (21) :1-17

[7] Optimized Forecast Components-SVM-Based Fault Diagnosis With Applications for Wastewater Treatment [J].

Cheng, Hongchao ;

Liu, Yiqi ;

Huang, Daoping ;

Liu, Bin .

IEEE ACCESS, 2019, 7 :128534-128543

[8] A novel fault identification and root-causality analysis of incipient faults with applications to wastewater treatment processes [J].

Cheng, Hongchao ;

Wu, Jing ;

Liu, Yiqi ;

Huang, Daoping .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2019, 188 :24-36

[9]

Friman O, 2001, MAGNET RESON MED, V45, P323, DOI 10.1002/1522-2594(200102)45:2<323::AID-MRM1041>3.0.CO

[10]

2-#

← 1 2 3 4 →