Modeling carbon and nitrogen removal in an industrial wastewater treatment plant using an adaptive network-based fuzzy inference system

Civelekoglu G., Perendeci A., YİĞİT N. Ö. , KİTİŞ M.

CLEAN-SOIL AIR WATER, vol.35, no.6, pp.617-625, 2007 (Peer-Reviewed Journal) identifier identifier

  • Publication Type: Article / Article
  • Volume: 35 Issue: 6
  • Publication Date: 2007
  • Doi Number: 10.1002/clen.200700076
  • Journal Name: CLEAN-SOIL AIR WATER
  • Journal Indexes: Science Citation Index Expanded, Scopus
  • Page Numbers: pp.617-625
  • Keywords: adaptive network-based fuzzy inference system (ANFIS), artificial intelligence, modeling, principal component analysis (PCA), sugar industry, wastewater treatment, ARTIFICIAL NEURAL-NETWORK, PERFORMANCE, PHOSPHORUS


Advanced neuro-fuzzy modeling, namely an adaptive network-based fuzzy inference system (ANFIS), was employed to develop models for the prediction of carbon and nitrogen removal in the aerobic biological treatment stage of a full-scale wastewater treatment plant treating process wastewaters from the sugar production industry. A total of six independent ANFIS models were developed with or without principal component analysis (PCA) using the correlations among the influent and effluent data from the plant. Input variables were reduced from eight to four and from eleven to nine for chemical oxygen demand (COD) and NH4+-N-TN (total nitrogen) models, respectively, by considering PCA results and linear correlation matrices among input and output variables. Correlation coefficients (R) were not in good agreement with root mean square error (RMSE) and average percentage error (APE) values without PCA. For the COD model after PCA; RMSE, APE and R values were 9.4 mg/L, 8.37 and 0.978%, respectively. Such values for the TN model were 4.3 mg/L, 23.65 and 0.992%. The results overall indicated that the simulated effluent COD, NH4+-N, and TN concentrations well fit measured concentrations. The ANFIS modeling approach may have application potential for performance prediction and control of treatment processes in treatment plants.