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

Construction of COD simulation model for activated sludge process by fuzzy neural network.

S Tomida1, T Hanai, N Ueda

  • 1Department of Biotechnology, Graduate School of Engineering, Nagoya University, Furo-cho, Chikusa-ku, Nagoya 464-8603, Japan.

Journal of Bioscience and Bioengineering
|October 20, 2005
PubMed
Summary

Fuzzy neural networks (FNNs) accurately simulate effluent chemical oxygen demand (COD) in activated sludge processes. This advanced modeling approach offers significantly higher accuracy than traditional multiple regression analysis for wastewater treatment plants.

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

ICSAT overexpression is not sufficient to cause adult T-cell leukemia or multiple myeloma.

Biochemical and biophysical research communications·1999
Same author

Synergism between mild hyperthermia and interferon-beta gene expression.

Cancer letters·1999
Same author

Pseudolesion in segment II of the liver observed on CT during arterial portography caused by the aberrant left gastric venous drainage.

Abdominal imaging·1999
Same author

A toxicokinetic analysis in a patient with acute glufosinate poisoning.

Human & experimental toxicology·1999
Same author

[Generation and analysis of mouse models for leukemia].

[Rinsho ketsueki] The Japanese journal of clinical hematology·1999
Same author

MR diagnosis of adenomyomatosis of the gallbladder and differentiation from gallbladder carcinoma: importance of showing Rokitansky-Aschoff sinuses.

AJR. American journal of roentgenology·1999

Area of Science:

  • Environmental Engineering
  • Artificial Intelligence
  • Wastewater Treatment

Background:

  • Activated sludge processes are crucial for wastewater treatment.
  • Accurate estimation of effluent chemical oxygen demand (COD) is vital for process monitoring and control.
  • Traditional modeling methods may have limitations in capturing complex process dynamics.

Purpose of the Study:

  • To develop and evaluate a Fuzzy Neural Network (FNN) model for simulating effluent COD in an activated sludge process.
  • To compare the accuracy of the FNN model against a Multiple Regression Analysis (MRA) model.
  • To elucidate plant operational characteristics using FNN-derived fuzzy rules.

Main Methods:

  • Application of Fuzzy Neural Network (FNN) to construct a simulation model.

Related Experiment Videos

  • Utilizing hourly process variable data from a "U" plant.
  • Comparison with Multiple Regression Analysis (MRA) model.
  • Development of seasonal FNN models.
  • Application to a second plant "A" with daily data collection.

    • Main Results:

    • The FNN model demonstrated high accuracy in simulating periodic changes in effluent COD.
    • The FNN model was 3.7 times more accurate than the MRA model.
    • Analysis of fuzzy rules provided insights into plant operational characteristics.
    • FNN models developed for different seasons showed applicability.
    • A similarly accurate FNN model was constructed for a plant with daily data collection.

    Conclusions:

    • Fuzzy Neural Networks provide a highly accurate and effective method for simulating effluent COD in activated sludge wastewater treatment.
    • FNN models offer superior performance compared to traditional MRA, especially with complex, time-series data.
    • The interpretability of FNNs through fuzzy rules aids in understanding and optimizing wastewater treatment plant operations.