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

Neural network approach for modification and fitting of digitized data in reverse engineering.

Hua Ju1, Wen Wang, Jin Xie

  • 1Institute of Advanced Manufacturing Engineering, Zhejiang University, Hangzhou 310027, China. huaju@zju.edu.cn

Journal of Zhejiang University. Science
|December 10, 2003
PubMed
Summary

This study introduces a Radial Basis Function (RBF) neural network method for reverse engineering in manufacturing. The approach effectively modifies and fits digitized data to reconstruct complex surface models.

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

Phenological Changes in the Fecal Microbiota of <i>Elaphurus davidianus</i> in Inner Mongolia Daqingshan National Nature Reserve.

Animals : an open access journal from MDPI·2026
Same author

Morphine-induced fever: a case report and review of the literature.

Journal of medical case reports·2024
Same author

Combination Therapy with Indigo and Indirubin for Ulcerative Colitis via Reinforcing Intestinal Barrier Function.

Oxidative medicine and cellular longevity·2023
Same author

Tanshinone IIA-loaded nanoparticles and neural stem cell combination therapy improves gut homeostasis and recovery in a pig ischemic stroke model.

Scientific reports·2023
Same author

Identification of a Novel Keto Sugar Component in Streptococcus pneumoniae Serotype 12F Capsular Polysaccharide and Impact on Vaccine Immunogenicity.

Journal of immunology (Baltimore, Md. : 1950)·2023
Same author

Selectively reflective edge detection system based on cholesteric liquid crystal.

Optics letters·2023

Area of Science:

  • Manufacturing Engineering
  • Computer-Aided Design (CAD)
  • Artificial Intelligence (AI)

Background:

  • Reverse engineering is crucial for reconstructing CAD models from existing objects.
  • Digitized data often requires modification and fitting for accurate reconstruction.
  • Existing methods may lack efficiency in handling complex surface data.

Purpose of the Study:

  • To present a novel Radial Basis Function (RBF) neural network approach for modifying and fitting digitized data in reverse engineering.
  • To demonstrate the effectiveness of the RBF neural network in reconstructing surface models from scanned data.
  • To utilize an orthogonal least squares learning algorithm for efficient RBF center selection.

Main Methods:

  • Digitized data from existing objects were processed using an RBF neural network.

Related Experiment Videos

  • Orthogonal least squares learning algorithm was employed for RBF center selection.
  • A known mathematical surface and practical digitizing curves were used for training and testing the network.

    • Main Results:

    • The trained RBF network successfully generated new data points that closely matched calculated points.
    • The approach proved effective in modifying and fitting digitized data from various sources.
    • Accurate reconstruction of surface models was achieved using the proposed method.

    Conclusions:

    • The RBF neural network approach offers an effective solution for data fitting and modification in reverse engineering.
    • This method enhances the accuracy and efficiency of reconstructing surface models from digitized data.
    • The integration of orthogonal least squares learning optimizes the RBF network's performance.