Tehran University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share this content! On (X network) By
Predicting Toc Removal Efficiency in Hybrid Biological Aerated Filter Using Artificial Neural Network Publisher



Alvani V1 ; Nabizadeh R2, 4 ; Ansarizadeh M3 ; Mahvi AH2, 4 ; Rahmani H5
Authors
Show Affiliations
Authors Affiliations
  1. 1. Centre of Applied Science, Shiraz University of Medical Sciences, Shiraz, Iran
  2. 2. Department of Environmental Health Engineering, School of Public Health, Tehran University of Medical Sciences, Tehran, Iran
  3. 3. Department of Environmental Health Engineering, Mamassani Higher Education Complex for Health, Shiraz University of Medical Sciences, Shiraz, Iran
  4. 4. Department of Environmental Health Engineering, School of Public Health, Tehran University of Medical Sciences, Tehran, Iran
  5. 5. Department of Environmental Health Engineering, School of Public Health, Ahvaz Jundishapur University of Medical Sciences, Hasan Rahmani, Ahvaz, Iran

Source: Desalination and Water Treatment Published:2016


Abstract

The present study employs artificial neural network (ANN) models to forecast the total organic carbon (TOC) removal efficiency in biological aerated filter in a laboratory-scale reactor. This model is based on the measured values of TOC at inlet and outlet under different organic loading rates. One layer radial basis function (RBF) neural network and one layer multilayer perceptron (MLP) algorithm of ANN models were used to predict the TOC removal concentrations in the effluent. Data from experimental study (187 records) were employed for training and confirming the models. The best error on test samples was 0.032 for RBF and 0.026 and 0.027 for two methods of MLP (goal set and validation set), respectively. The ANN-based simulation model demonstrated accurate results for TOC removal and provided an efficient tool for estimating parameters in wastewater treatment processes. © 2015 Balaban Desalination Publications. All rights reserved.
Related Docs
Experts (# of related papers)