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 human operators using neural networks.

C G Gingrich1, D R Kuespert, T J McAvoy

  • 1Chemical Engineering Department, University of Maryland.

ISA Transactions
|January 1, 1992
PubMed
Summary

This study introduces artificial neural networks to capture expert operator knowledge in process industries. This approach economically enhances control by transferring skills, outperforming traditional expert systems.

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

Field-Cage Evaluation of Survival, Reproduction, and Feeding Behavior of Adult Scymnus coniferarum (Coleoptera: Coccinellidae), a Predator of Adelges tsugae (Hemiptera: Adelgidae).

Environmental entomology·2016
Same author

Host-range testing of Eucryptorrhynchus brandti (Coleoptera: Curculionidae), a candidate for biological control of tree-of-heaven, Ailanthus altissima.

Environmental entomology·2012
Same author

A comparison of neural networks and partial least squares for deconvoluting fluorescence spectra.

Biotechnology and bioengineering·1992
Same author

Comparison of four neural net learning methods for dynamic system identification.

IEEE transactions on neural networks·1992
Same author

Pharmacokinetic modeling of heparin and its clinical implications.

Journal of pharmacokinetics and biopharmaceutics·1979
Same author

The biologic half-life of heparin.

Clinical pharmacology and therapeutics·1979

Area of Science:

  • Process control
  • Artificial intelligence
  • Knowledge engineering

Background:

  • Human operators often provide product control in process industries.
  • Operator performance varies significantly between shifts.
  • Capturing and disseminating expert operator knowledge can yield substantial economic benefits.

Purpose of the Study:

  • To present a methodology for capturing process operator knowledge using artificial neural networks.
  • To enable the economic transfer of expertise from top-performing operators to others.
  • To compare the proposed artificial neural network approach with traditional expert systems.

Main Methods:

  • Utilizing artificial neural networks to model and capture operator expertise.
  • Employing readily available process control computer data for network training.
  • Applying a stripping technique to simplify the neural network and analyze operator behavior.

Main Results:

  • A converged artificial neural network can represent expert operator knowledge.
  • The stripping technique facilitates understanding the differences between skilled and less-skilled operators.
  • The proposed method is suggested to be more effective than conventional expert system knowledge extraction.

Conclusions:

  • Artificial neural networks offer an effective and economical method for capturing operator expertise in process industries.
  • Knowledge extraction from expert operators via neural networks can lead to improved process control and economic gains.
  • This methodology presents a superior alternative to traditional expert system approaches for operator skill transfer.

Related Experiment Videos