Effects of phase vector and history extension on prediction power of adaptive-network based fuzzy inference system (ANFIS) model for a real scale anaerobic wastewater treatment plant operating under unsteady state

Perendeci A., ARSLAN S., Tanyolac A., Celebi S. S.

BIORESOURCE TECHNOLOGY, cilt.100, sa.20, ss.4579-4587, 2009 (SCI-Expanded) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 100 Sayı: 20
  • Basım Tarihi: 2009
  • Doi Numarası: 10.1016/j.biortech.2009.04.049
  • Dergi Adı: BIORESOURCE TECHNOLOGY
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.4579-4587
  • Anahtar Kelimeler: Anaerobic wastewater treatment, Adaptive-network based fuzzy inference system, History extension, Modeling, Phase vector, EXPERT-SYSTEM, NEURAL-NETWORK, DIAGNOSIS, DIGESTION, IDENTIFICATION, SUPERVISION, VARIABLES
  • Akdeniz Üniversitesi Adresli: Evet

Özet

A conceptual neural fuzzy model based on adaptive-network based fuzzy inference system, ANFIS, was proposed using available input on-line and off-line operational variables for a Sugar factory anaerobic wastewater treatment plant operating under unsteady state to estimate the effluent chemical oxygen demand, COD. The predictive power of the developed model was improved as a new approach by adding the phase vector and the recent values of COD up to 5-10 days, longer than overall retention time of wastewater in the system. History of last 10 days for COD effluent with two-valued phase vector in the input variable matrix including all parameters had more predictive power. History of 7 days with two-valued phase vector in the matrix comprised of only on-line variables yielded fairly well estimations. The developed ANFIS model with phase vector and history extension has been able to adequately represent the behavior of the treatment system. (C) 2009 Elsevier Ltd. All rights reserved.