• DocumentCode
    635153
  • Title

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

  • Author

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

  • Author_Institution
    Sch. of Autom., Beijing Inst. of Technol., Beijing, China
  • fYear
    2013
  • fDate
    23-26 June 2013
  • Firstpage
    1
  • Lastpage
    5
  • 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
    effluents; environmental science computing; regression analysis; sewage treatment; sludge treatment; support vector machines; A2O process; ASM2; PSO algorithm; SVM compensation method; SVM regression; activated sludge model; effluent water quality prediction model; kinetic parameters; mechanism model; prediction error compensation; sewage treatment plant; sewage treatment process; water quality soft measurement; Data models; Effluents; Mathematical model; Predictive models; Sewage treatment; Support vector machines; Activated Sludge Model NO.2; Particle Swarm Optimization; Sewage Treatment; Soft Measurement; Support Vector Machine;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Control Conference (ASCC), 2013 9th Asian
  • Conference_Location
    Istanbul
  • Print_ISBN
    978-1-4673-5767-8
  • Type

    conf

  • DOI
    10.1109/ASCC.2013.6606382
  • Filename
    6606382