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

Optimized biogas-fermentation by neural network control.

P Holubar1, L Zani, M Hager

  • 1Institute of Applied Microbiology, BOKU--University of Natural Resources and Applied Life Sciences, Muthgasse 18, A-1190 Vienna, Austria. peter.holubar@boku.ac.at

Communications in Agricultural and Applied Biological Sciences
|August 7, 2004
PubMed
Summary
This summary is machine-generated.

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

First Search for B→X_{s}νν[over ¯] Decays.

Physical review letters·2026
Same author

Search for Feebly Interacting Particles in B Decays with Missing Energy at Belle.

Physical review letters·2026
Same author

Search for B^{0}→K^{*0}τ^{+}τ^{-} Decays at the Belle II Experiment.

Physical review letters·2025
Same author

Search for a Dark Higgs Boson Produced in Association with Inelastic Dark Matter at the Belle II Experiment.

Physical review letters·2025
Same author

Search for Lepton-Flavor-Violating Decay Modes B^{0}→K_{S}^{0}τ^{±}ℓ^{∓} with Hadronic B Tagging at Belle and Belle II.

Physical review letters·2025
Same author

Search for P_{cc[over ¯]s}(4459)^{0} and P_{cc[over ¯]s}(4338)^{0} in ϒ(1S,2S) Inclusive Decays at Belle.

Physical review letters·2025
Same journal

RELATIONSHIPS BETWEEN SOME SOIL PARAMETERS AND WEED COMMUNITY (CASE STUDY: WINTER WHEAT FIELDS OF UREMIA-IRAN).

Communications in agricultural and applied biological sciences·2016
Same journal

EASTERN DODDER (CUSCUTA MONOGYNA VAHL.) SEED GERMINATION AFFECTED BY SOME HERBACEOUS DISTILLATES.

Communications in agricultural and applied biological sciences·2016
Same journal

EFFICACY OF METAMITRON IN APPLE THINNING IN SERBIA.

Communications in agricultural and applied biological sciences·2016
Same journal

RESISTANCE TO ALS-INHIBITING HERBICIDES IN WEED POPULATIONS FROM BELGIAN WHEAT FIELDS.

Communications in agricultural and applied biological sciences·2016
Same journal

INTEGRATED WEED CONTROL IN MAIZE.

Communications in agricultural and applied biological sciences·2016
Same journal

EFFECTS OF SOME BIOINSECTICIDES AND ENTOMOPATHOGENIC FUNGI ON COLORADO POTATO BEETLE (LEPTINOTARSA DECEMLINEATA L.).

Communications in agricultural and applied biological sciences·2016
See all related articles

Neural networks effectively model and control methane production in anaerobic digesters. This system maintains high methane output and stability, optimizing biogas generation from organic waste.

Area of Science:

  • Biotechnology
  • Environmental Engineering
  • Artificial Intelligence

Background:

  • Anaerobic digestion is crucial for biogas production.
  • Controlling methane output and stability in digesters is challenging.
  • Previous models lacked real-time adaptive control capabilities.

Purpose of the Study:

  • To develop and implement a neural network-based system for modeling and controlling methane production in anaerobic digesters.
  • To enhance the stability and efficiency of biogas generation.
  • To simulate co-fermentation processes and their impact on methane output.

Main Methods:

  • Trained feed-forward back-propagation neural networks (FFBP) using data from four anaerobic continuous stirred tank reactors (CSTR).
  • Utilized parameters including gas composition, methane production rate, volatile fatty acid concentration, pH, and chemical oxygen demand (COD).

Related Experiment Videos

  • Developed a hierarchical neural network system integrated into a Decision Support System (DSS).

    • Main Results:

    • FFBP models achieved high regression coefficients for simulating pH (0.82), volatile fatty acid concentration (0.86), and gas production/composition (0.90 and 0.80).
    • A lab-scale anaerobic CSTR controlled by the DSS maintained approximately 60% methane concentration.
    • The system facilitated high gas production rates (5-5.6 m3 x m(-3) x d(-1)) under controlled conditions.

    Conclusions:

    • Hierarchical neural networks provide an effective tool for modeling and controlling anaerobic digestion processes.
    • The developed Decision Support System enhances digester performance, ensuring stable methane production.
    • This approach offers a promising solution for optimizing biogas generation from organic waste.