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

A deployed engineering design retrieval system using neural networks.

S G Smith1, R Escobedo, M Anderson

  • 1Div. of Integrated Support Services, Boeing Co., Seattle, WA.

IEEE Transactions on Neural Networks
|January 1, 1997
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

Azimuthal anisotropy and correlations in the hard scattering regime at RHIC.

Physical review letters·2003
Same author

Coherent rho(0) production in ultraperipheral heavy-ion collisions.

Physical review letters·2003
Same author

Centrality dependence of high-p(T) hadron suppression in Au+Au collisions at sqrt[s(NN)]=130 GeV.

Physical review letters·2002
Same author

Modelling the transmission dynamics of Ross River virus in Southwestern Australia.

IMA journal of mathematics applied in medicine and biology·2002
Same author

Azimuthal anisotropy of K(0)(S) and Lambda+Lambda production at midrapidity from Au+Au collisions at sqrt[s(NN)]=130 GeV.

Physical review letters·2002
Same author

3D visualisation of the middle ear and adjacent structures using reconstructed multi-slice CT datasets, correlating 3D images and virtual endoscopy to the 2D cross-sectional images.

Neuroradiology·2002
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

A neural information retrieval system (NIRS) identifies and retrieves engineering designs using adaptive resonance theory (ART-1) neural networks. This system aids in design reuse, offering significant cost savings for industry.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Engineering Design

Background:

  • Engineering design retrieval is crucial for cost-efficiency and innovation.
  • Manual design retrieval is time-consuming and prone to errors.
  • Existing systems often lack the ability to handle complex design variations.

Purpose of the Study:

  • To introduce a production-ready neural information retrieval system (NIRS) for engineering designs.
  • To demonstrate the application of adaptive resonance theory (ART-1) neural networks in design retrieval.
  • To highlight the practical value and cost-saving potential of NIRS in industry.

Main Methods:

  • Utilized adaptive resonance theory (ART-1) neural networks for clustering similar engineering parts.
  • Inputted 2D and 3D design representations into ART-1 networks.

Related Experiment Videos

  • Developed a system for recalling appropriate design clusters based on new part queries.

    • Main Results:

    • Successfully clustered similar engineering parts using ART-1 networks.
    • Enabled efficient retrieval of engineering designs through neural network recall.
    • Demonstrated the system's capability for practical industrial application.

    Conclusions:

    • The developed NIRS is effective for identifying and retrieving engineering designs.
    • ART-1 neural networks provide a robust solution for design clustering and retrieval.
    • The system offers significant potential for reducing nonrecurring costs through design reuse.