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

CNN Bearing Fault Diagnosis Based on Symmetric Point Pattern Feature Fusion with Multi-Source Resonance Sparse

Yan Liu1, Yuxuan Li1,2, Qiang Sun1,2

  • 1Yunnan Dianneng Smart Energy Co., Ltd., Kunming 650228, China.

Sensors (Basel, Switzerland)
|May 27, 2026
PubMed
Summary

Related Concept Videos

Double Resonance Techniques: Overview01:12

Double Resonance Techniques: Overview

Double resonance techniques in Nuclear Magnetic Resonance (NMR) spectroscopy involve the simultaneous application of two different frequencies or radiofrequency pulses to manipulate and observe two distinct nuclear spins. One important application of double resonance is spin decoupling, which selectively suppresses coupling with one type of nucleus while observing the NMR signal from another nucleus, simplifying the spectrum and enhancing resolution.
Spin decoupling is usually achieved by...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Visible-Infrared Fusion Based on CNN and Deformable Transformer.

Journal of imaging·2026
Same author

<i>Acinetobacter pengchengensis</i> sp. nov., isolated from the urban wastewater of Shenzhen, Guangdong Province, China.

International journal of systematic and evolutionary microbiology·2026
Same author

A highly efficient fluorescence-based virus neutralizing test for fowl adenoviruses associated with hepatitis-hydropericardium syndrome and inclusion body hepatitis.

Poultry science·2026
Same author

Weight Changes With Lower Doses of Semaglutide in Clinical Practice: Findings From the Chinese HARMONY Cohort.

Diabetes, obesity & metabolism·2026
Same author

Residue 188 of the Hexon protein governs FAdV-4 pathogenicity by activating PINK1/Parkin-mediated mitophagy.

Veterinary research·2026
Same author

Integrated Transcriptomic and Metabolomic Analysis Reveals Gut Microbiota-Mediated Regulation of Muscle Fiber Composition and Metabolism in Germ-Free Pigs.

Animal genetics·2026

This study introduces a CNN-based method for rolling bearing fault diagnosis using multi-source resonance sparse decomposition and symmetric dot pattern feature fusion. The novel approach significantly improves fault recognition accuracy, even in noisy conditions.

Area of Science:

  • Mechanical Engineering
  • Signal Processing
  • Artificial Intelligence

Background:

  • Bearing vibration signals are non-stationary and prone to noise, obscuring fault characteristics.
  • Incomplete information leads to low recognition accuracy in traditional fault diagnosis methods.
  • Impact features can be masked in contaminated environments, hindering effective diagnosis.

Purpose of the Study:

  • To develop a robust CNN-based fault diagnosis method for rolling bearings.
  • To enhance fault feature extraction and fusion from multi-source vibration signals.
  • To address the challenge of masked impact features in noisy environments.

Main Methods:

  • Resonance sparse decomposition was used for impact-related fault feature extraction.
Keywords:
deep learningfault diagnosismulti-information fusionneural networkresonance sparse decompositionrolling bearingsymmetric dot pattern

Related Experiment Videos

  • Symmetric dot pattern (SDP) method was employed for multi-source feature fusion.
  • A Convolutional Neural Network (CNN) model was developed integrating fused features.

    • Main Results:

    • The proposed method achieved a fault recognition accuracy of 98.63% under varying operating conditions.
    • The method effectively resolves the issue of masked impact features.
    • Recognition precision improved by 8.49%–17.8% compared to existing methods.

    Conclusions:

    • The developed CNN-based fault diagnosis method demonstrates superior performance.
    • Multi-source feature fusion using SDP enhances fault representation and diagnostic accuracy.
    • The RSSD-P method offers a promising solution for reliable rolling bearing fault diagnosis.