A novel ASM2 and SVM compensation method for the effluent quality prediction model of A2O process

Xiaoting Li; Pan Feng; Gao Qi; Weixing Li; Xiaofeng Lian

doi:10.1109/ASCC.2013.6606382

A novel ASM2 and SVM compensation method for the effluent quality prediction model of A²O process

Xiaoting Li, Pan Feng, Gao Qi, Weixing Li, Xiaofeng Lian

School of Automation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

For the soft measurement of water quality for sewage treatment process, a novel prediction model is proposed to predict the effluent water quality in this paper, which combines the mechanism model with compensation model. Firstly, the ASM2 model is built as the mechanism model to imitate the sewage treatment process, as well as PSO algorithm is used to adjust the kinetic parameters of the ASM2 model. Next, SVM regression is adopted to compensate the prediction error of mechanism model. Finally, the model is tested with real data collected in a sewage treatment plant. The simulation results show that the model can obtain accuracy prediction results and reflect the behavior of sewage treatment efficiently.

Original language	English
Title of host publication	2013 9th Asian Control Conference, ASCC 2013
DOIs	https://doi.org/10.1109/ASCC.2013.6606382
Publication status	Published - 2013
Event	2013 9th Asian Control Conference, ASCC 2013 - Istanbul, Turkey Duration: 23 Jun 2013 → 26 Jun 2013

Publication series

Name	2013 9th Asian Control Conference, ASCC 2013

Conference

Conference	2013 9th Asian Control Conference, ASCC 2013
Country/Territory	Turkey
City	Istanbul
Period	23/06/13 → 26/06/13

Keywords

Activated Sludge Model NO.2
Particle Swarm Optimization
Sewage Treatment
Soft Measurement
Support Vector Machine

Access to Document

10.1109/ASCC.2013.6606382

Cite this

@inproceedings{27479eb74f4444ef919afb7345302685,

title = "A novel ASM2 and SVM compensation method for the effluent quality prediction model of A2O process",

abstract = "For the soft measurement of water quality for sewage treatment process, a novel prediction model is proposed to predict the effluent water quality in this paper, which combines the mechanism model with compensation model. Firstly, the ASM2 model is built as the mechanism model to imitate the sewage treatment process, as well as PSO algorithm is used to adjust the kinetic parameters of the ASM2 model. Next, SVM regression is adopted to compensate the prediction error of mechanism model. Finally, the model is tested with real data collected in a sewage treatment plant. The simulation results show that the model can obtain accuracy prediction results and reflect the behavior of sewage treatment efficiently.",

keywords = "Activated Sludge Model NO.2, Particle Swarm Optimization, Sewage Treatment, Soft Measurement, Support Vector Machine",

author = "Xiaoting Li and Pan Feng and Gao Qi and Weixing Li and Xiaofeng Lian",

year = "2013",

doi = "10.1109/ASCC.2013.6606382",

language = "English",

isbn = "9781467357692",

series = "2013 9th Asian Control Conference, ASCC 2013",

booktitle = "2013 9th Asian Control Conference, ASCC 2013",

note = "2013 9th Asian Control Conference, ASCC 2013 ; Conference date: 23-06-2013 Through 26-06-2013",

}

TY - GEN

T1 - A novel ASM2 and SVM compensation method for the effluent quality prediction model of A2O process

AU - Li, Xiaoting

AU - Feng, Pan

AU - Qi, Gao

AU - Li, Weixing

AU - Lian, Xiaofeng

PY - 2013

Y1 - 2013

N2 - For the soft measurement of water quality for sewage treatment process, a novel prediction model is proposed to predict the effluent water quality in this paper, which combines the mechanism model with compensation model. Firstly, the ASM2 model is built as the mechanism model to imitate the sewage treatment process, as well as PSO algorithm is used to adjust the kinetic parameters of the ASM2 model. Next, SVM regression is adopted to compensate the prediction error of mechanism model. Finally, the model is tested with real data collected in a sewage treatment plant. The simulation results show that the model can obtain accuracy prediction results and reflect the behavior of sewage treatment efficiently.

AB - For the soft measurement of water quality for sewage treatment process, a novel prediction model is proposed to predict the effluent water quality in this paper, which combines the mechanism model with compensation model. Firstly, the ASM2 model is built as the mechanism model to imitate the sewage treatment process, as well as PSO algorithm is used to adjust the kinetic parameters of the ASM2 model. Next, SVM regression is adopted to compensate the prediction error of mechanism model. Finally, the model is tested with real data collected in a sewage treatment plant. The simulation results show that the model can obtain accuracy prediction results and reflect the behavior of sewage treatment efficiently.

KW - Activated Sludge Model NO.2

KW - Particle Swarm Optimization

KW - Sewage Treatment

KW - Soft Measurement

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=84886555939&partnerID=8YFLogxK

U2 - 10.1109/ASCC.2013.6606382

DO - 10.1109/ASCC.2013.6606382

M3 - Conference contribution

AN - SCOPUS:84886555939

SN - 9781467357692

T3 - 2013 9th Asian Control Conference, ASCC 2013

BT - 2013 9th Asian Control Conference, ASCC 2013

T2 - 2013 9th Asian Control Conference, ASCC 2013

Y2 - 23 June 2013 through 26 June 2013

ER -