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

[Column efficiency prediction of two dimensional chromatography by artificial neural network].

J Huang1, S F Zhou, Z S Guo

  • 1College of Chemical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China.

Se Pu = Chinese Journal of Chromatography
|January 25, 2003
PubMed
Summary

Artificial neural network (ANN) modeling effectively predicts column efficiency in chromatography. This method accurately captures complex, non-linear relationships between operating conditions and performance.

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

[Learning curve of uniportal video-assisted thoracoscopic surgery lobectomy for the treatment of resectable lung cancer].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2018
Same author

[A prospective comparative study examing the impact of uniportal and three portal video-assisted thoracic surgery on short-term quality of life in lung cancer].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2018
Same author

[A serum lipidomic study of patients with non-alcoholic fatty liver disease].

Zhonghua gan zang bing za zhi = Zhonghua ganzangbing zazhi = Chinese journal of hepatology·2017
Same author

Magnetic mediation effect of a C impurity in a Mn-doped Zn₁₂O₁₂ nanocluster: a case of multiple exchange interactions.

Journal of physics. Condensed matter : an Institute of Physics journal·2015
Same author

A low-copy-number Sorghum DNA sequence that detects hypervariable EcoRV fragments.

TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik·2013
Same author

A RFLP linkage map of Sorghum bicolor (L.) Moench.

TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik·2013

Area of Science:

  • Chromatography
  • Artificial Intelligence
  • Chemical Engineering

Background:

  • Traditional modeling methods struggle with complex, non-linear relationships between column efficiency and operating conditions in chromatography.
  • Establishing quantitative models for predicting column performance is challenging due to intricate factor interactions.

Purpose of the Study:

  • To investigate the relationship between column efficiency and operating conditions using artificial neural network (ANN) modeling.
  • To develop a predictive model for column efficiency in a two-dimensional column chromatography system.
  • To demonstrate the suitability of ANN for modeling complex chromatographic systems.

Main Methods:

  • Utilized a three-layer, weight-connected artificial neural network (ANN) model.

Related Experiment Videos

  • Employed the varied-pace back-propagation (BP) learning algorithm.
  • Defined input vectors as pre-column temperature, main column temperature, pressure difference, and vent rate.
  • Defined output vectors as the effective plate number, representing column efficiency.

    • Main Results:

    • The ANN model accurately predicted column efficiency (effective plate number) under various operating conditions.
    • Model predictions showed strong consistency with experimentally found values.
    • The developed model successfully captured the non-linear dynamics of the chromatographic system.

    Conclusions:

    • Artificial neural network (ANN) modeling is a suitable and effective method for studying column efficiency in two-dimensional column chromatography.
    • ANN provides a robust approach to quantitatively model complex, non-linear relationships in chromatographic systems.
    • This study validates the application of ANN for optimizing operating conditions to enhance column performance.