Selection of optimum operational conditions for the treatment performance of geotextile biofilters using artificial neural networks

Cevat Yaman, Ferhat Karaca, Eyüp N. Korkut, Joseph Paul Martin, Özer Çinar

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The premise of this study is to develop an artificial neural networks (ANNs) based method to model and simulate the effluent concentrations of NH 3, NO3-, BOD5 and other parameters for a geotextile biofilter developed for wastewater treatment. The model selects the best backpropagation algorithm and optimizes the structure of selected algorithm for any type of input and output parameters. Using the obtained model, the effluent concentrations of a specially designed geotextile biofilter are predicted under different operational conditions and the results are compared with the measured data. It is concluded that neural networks based models are appropriate for modeling nonlinear dependence of the treatment performance of geotextile biofilters. Then, this model is used to simulate the effects of input variables on the treatment performance of the geotextile biofilter. Finally, the model is used as a tool to define the optimum range of operational parameters of the geotextile biofilter.

Original languageEnglish
Pages (from-to)2587-2596
Number of pages10
JournalFresenius Environmental Bulletin
Volume19
Issue number11
Publication statusPublished - Dec 27 2010
Externally publishedYes

Keywords

  • Backpropagation
  • Design
  • Modeling
  • Optimization
  • Simulation
  • Treatment

ASJC Scopus subject areas

  • Environmental Chemistry
  • Waste Management and Disposal
  • Pollution

Fingerprint Dive into the research topics of 'Selection of optimum operational conditions for the treatment performance of geotextile biofilters using artificial neural networks'. Together they form a unique fingerprint.

  • Cite this