Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Modeling a full-scale primary sedimentation tank using artificial neural networks.

A Gamal El-Din1, D W Smith

  • 1Department of Civil and Environmental Engineering, University of Alberta, Edmonton, Canada.

Environmental Technology
|June 29, 2002
PubMed
Summary

Artificial neural networks effectively predict primary sedimentation tank performance, offering a promising approach for real-time process control. This method surpasses traditional models by accurately forecasting effluent quality using dynamic influent data.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Cancer mortality at very old ages.

Cancer·1996
Same author

Racial differences on psychological measures in combat veterans seeking treatment for PTSD.

Journal of personality assessment·1996
Same author

Mosquito-borne viruses and epidemic polyarthritis.

The Medical journal of Australia·1996
Same author

Consensus phylogeny of Dictyostelium.

Experientia·1995
Same author

Role of ventrolateral medulla catecholamine cells in hypothalamic neuroendocrine cell responses to systemic hypoxia.

The Journal of neuroscience : the official journal of the Society for Neuroscience·1995
Same author

Hypovolaemic and osmotic stimuli induce distinct patterns of c-Fos expression in the rat subfornical organ.

Brain research·1995

Area of Science:

  • Environmental Engineering
  • Wastewater Treatment
  • Process Modeling

Background:

  • Traditional regression and hydraulic efficiency models have limitations in predicting dynamic full-scale primary sedimentation tank performance.
  • Existing models are often based on empirical data or controlled studies, hindering real-world application.
  • Accurate dynamic modeling is crucial for optimizing wastewater treatment processes.

Purpose of the Study:

  • To develop and validate an artificial neural network (ANN) model for predicting the dynamic response of full-scale primary sedimentation tanks.
  • To assess the capability of ANNs to forecast effluent total suspended solids (TSS) and chemical oxygen demand (COD).
  • To explore the potential of ANN models for real-time process control in wastewater treatment.

Main Methods:

Related Experiment Videos

  • Development of a two-network ANN architecture: one for TSS prediction (inputs: flow, influent TSS) and another for COD prediction (inputs: flow, influent COD).
  • Extensive data collection through a comprehensive sampling program for training and validation.
  • Systematic model building process to ensure parsimony, learning, and generalization capabilities.

Main Results:

  • The developed ANN model demonstrated promising results in predicting effluent TSS and COD.
  • The model successfully learned from historical data and generalized well to unseen validation data.
  • ANNs proved capable of capturing the dynamic behavior of primary sedimentation tanks.

Conclusions:

  • Artificial neural networks offer a viable and effective alternative to traditional modeling approaches for primary sedimentation tanks.
  • The proposed ANN model shows significant potential for integration into real-time process control systems.
  • Further research can explore the application of ANNs for other unit processes in wastewater treatment.