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