Modeling of Wastewater Treatment Processes Using Dynamic Bayesian Networks Based on Fuzzy PLS

被引：24

作者：

Liu, Hongbin ^{[1
,2
]}

Zhang, Hao ^{[1
]}

Zhang, Yuchen ^{[1
]}

Zhang, Fengshan ^{[2
]}

Huang, Mingzhi ^{[3
,4
]}

机构：

[1] Nanjing Forestry Univ, Coinnovat Ctr Efficient Proc & Utilizat Forest Re, Nanjing 210037, Peoples R China

[2] Shandong Huatai Paper Co Ltd, Lab Comprehens Utilizat Paper Waste Shandong Prov, Dongying 257335, Peoples R China

[3] South China Normal Univ, Sch Environm, SCNU Environm Res Inst, Guangdong Prov Key Lab Chem Pollut & Environm Saf, Guangzhou 510006, Peoples R China

[4] South China Normal Univ, Sch Environm, MOE Key Lab Theoret Chem Environm, Guangzhou 510006, Peoples R China

来源：

IEEE ACCESS | 2020年 / 8卷

关键词：

Bayes methods; Data models; Feature extraction; Wastewater treatment; Monitoring; Uncertainty; Process modeling; Fuzzy partial least squares; latent variables; Bayesian networks; dynamic process modeling; wastewater treatment processes; PARTIAL LEAST-SQUARES; SOFT-SENSORS; TREATMENT PLANTS; FAULT-DIAGNOSIS; PREDICTION; SYSTEM; FRAMEWORK;

D O I：

10.1109/ACCESS.2020.2995068

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The complicated characteristics of wastewater treatment plants (WWTPs) significantly hinder the monitoring of industrial processes, and thus much attention has been paid to process modeling and prediction. A fuzzy partial least squares-based dynamic Bayesian networks (FPLS-DBN) is proposed to improve the modeling ability in WWTPs. To adapt the nonlinear process data, fuzzy partial least squares (FPLS) is introduced by using a fuzzy system to extract nonlinear features from process data. In addition, a dynamic extension is included by embedding augmented matrices into Bayesian networks to fit the uncertainty and time-varying characteristics. Regarding the quality indices for effluent suspended solid in the WWTP, the root mean square error of the FPLS-DBN model is decreased by 28.63% and 69.47%, respectively, in comparison with that for partial least squares and Bayesian networks. The results demonstrate the superiority of FPLS-DBN in modeling performance for an actual industrial WWTP application.

引用

页码：92129 / 92140

页数：12

共 31 条

[1] Nonlinear PLS modeling with fuzzy inference system [J].

Bang, YH ;

Yoo, CK ;

Lee, IB .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2002, 64 (02) :137-155

[2] A real-time fault diagnosis methodology of complex systems using object-oriented Bayesian networks [J].

Cai, Baoping ;

Liu, Hanlin ;

Xie, Min .

MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2016, 80 :31-44

[3] Bayesian network based extreme learning machine for subjectivity detection [J].

Chaturvedi, Iti ;

Ragusa, Edoardo ;

Gastaldo, Paolo ;

Zunino, Rodolfo ;

Cambria, Erik .

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2018, 355 (04) :1780-1797

[4] Bayesian Network Based Approach for Diagnosis of Modified Sequencing Batch Reactor [J].

Li D. ;

Wang H. ;

Liang X. .

Journal of Shanghai Jiaotong University (Science), 2019, 24 (04) :417-429

[5] Minimax Probability TSK Fuzzy System Classifier: A More Transparent and Highly Interpretable Classification Model [J].

Deng, Zhaohong ;

Cao, Longbing ;

Jiang, Yizhang ;

Wang, Shitong .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2015, 23 (04) :813-826

[6] Dynamic latent variable analytics for process operations and control [J].

Dong, Yining ;

Qin, S. Joe .

COMPUTERS & CHEMICAL ENGINEERING, 2018, 114 :69-80

[7] Data-derived soft-sensors for biological wastewater treatment plants: An overview [J].

Haimi, Henri ;

Mulas, Michela ;

Corona, Francesco ;

Vahala, Riku .

ENVIRONMENTAL MODELLING & SOFTWARE, 2013, 47 :88-107

[8] Discussion on Time Difference Models and Intervals of Time Difference for Application of Soft Sensors [J].

Kaneko, Hiromasa ;

Funatsu, Kimito .

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2013, 52 (03) :1322-1334

[9] Design of inferential sensors in the process industry: A review of Bayesian methods [J].

Khatibisepehr, Shima ;

Huang, Biao ;

Khare, Swanand .

JOURNAL OF PROCESS CONTROL, 2013, 23 (10) :1575-1596

[10] Disturbance detection and isolation by dynamic principal component analysis [J].

Ku, WF ;

Storer, RH ;

Georgakis, C .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1995, 30 (01) :179-196

← 1 2 3 4 →