Modelling of COD removal in a biological wastewater treatment plant using adaptive neuro-fuzzy inference system and artificial neural network

This work evaluated artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) modelling methods to estimate organic carbon removal using the correlation among the past information of influent and effluent parameters in a full-scale aerobic biological wastewater treatment plan...

Full description

Saved in:
Bibliographic Details
Published in:Water science and technology 2009-01, Vol.60 (6), p.1475-1487
Main Authors: Civelekoglu, G, Yigit, N O, Diamadopoulos, E, Kitis, M
Format: Article
Language:English
Subjects:
Adaptive systems
Artificial neural networks
Biological activity
Biological wastewater treatment
Decision Making
Effluents
Error analysis
Fuzzy Logic
Fuzzy systems
Inference
Linear Models
Mathematical models
Medical Waste Disposal - methods
Modelling
Models, Chemical
Multivariate Analysis
Neural networks
Neural Networks (Computer)
Organic carbon
Organic Chemicals - chemistry
Organic Chemicals - isolation & purification
Oxygen - chemistry
Oxygen - isolation & purification
Performance prediction
Principal Component Analysis
Reproducibility of Results
Waste Disposal, Fluid - methods
Wastewater treatment
Wastewater treatment plants
Water treatment plants
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This work evaluated artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) modelling methods to estimate organic carbon removal using the correlation among the past information of influent and effluent parameters in a full-scale aerobic biological wastewater treatment plant. Model development focused on providing an adaptive, useful, practical and alternative methodology for modelling of organic carbon removal. For both models, measured and predicted effluent COD concentrations were strongly correlated with determination coefficients over 0.96. The errors associated with the prediction of effluent COD by the ANFIS modelling appeared to be within the error range of analytical measurements. The results overall indicated that the ANFIS modelling approach may be suitable to describe the relationship between wastewater quality parameters and may have application potential for performance prediction and control of aerobic biological processes in wastewater treatment plants.
ISSN:0273-1223
1996-9732
DOI:10.2166/wst.2009.482