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 Video

Updated: Nov 22, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

812

A Deep Neural Network-Based Feature Fusion for Bearing Fault Diagnosis.

Duy Tang Hoang1, Xuan Toa Tran2, Mien Van3

  • 1Department of Electrical Engineering, University of Ulsan, Ulsan 44610, Korea.

Sensors (Basel, Switzerland)
|January 6, 2021
PubMed
Summary

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

The Impact of LiDAR Configuration on Goal-Based Navigation within a Deep Reinforcement Learning Framework.

Sensors (Basel, Switzerland)·2023
Same author

Real-Time Implementation of the Prescribed Performance Tracking Control for Magnetic Levitation Systems.

Sensors (Basel, Switzerland)·2022
Same author

Case Study: Improving the Quality of Dairy Cow Reconstruction with a Deep Learning-Based Framework.

Sensors (Basel, Switzerland)·2022
Same author

An Adaptive Prescribed Performance Tracking Motion Control Methodology for Robotic Manipulators with Global Finite-Time Stability.

Sensors (Basel, Switzerland)·2022
Same author

A Novel Prescribed-Performance-Tracking Control System with Finite-Time Convergence Stability for Uncertain Robotic Manipulators.

Sensors (Basel, Switzerland)·2022
Same author

A Novel Active Fault-Tolerant Tracking Control for Robot Manipulators with Finite-Time Stability.

Sensors (Basel, Switzerland)·2021

This study introduces a new method using a wide convolutional neural network for bearing fault diagnosis. This approach effectively fuses data from multiple sensors, improving fault detection accuracy.

Area of Science:

  • Mechanical Engineering
  • Artificial Intelligence
  • Signal Processing

Background:

  • Bearing faults are critical in rotating machinery.
  • Current diagnostic methods often rely on single sensors, limiting accuracy.
  • Effective fusion of multi-sensor data is needed for robust fault diagnosis.

Purpose of the Study:

  • To develop a novel method for bearing fault diagnosis using multi-sensor information fusion.
  • To leverage deep learning for simultaneous processing of multiple signal sources.
  • To enhance diagnostic performance compared to existing techniques.

Main Methods:

  • A convolutional neural network (CNN) architecture was employed.
  • The CNN was designed with a wide structure to process multiple signals concurrently.
Keywords:
bearing fault diagnosisdeep learningdeep neural networksensor fusion

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K

Related Experiment Videos

Last Updated: Nov 22, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

812
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K
  • Feature fusion was integrated directly as a layer within the deep neural network.

    • Main Results:

    • The wide CNN successfully extracted discriminant features from multi-sensor signals.
    • The integrated feature fusion layer demonstrated high efficiency.
    • The proposed method outperformed single-sensor approaches and other fusion techniques in experiments.

    Conclusions:

    • A novel and effective deep learning-based method for multi-sensor fusion in bearing fault diagnosis is presented.
    • Wide CNNs are capable of automatic and efficient feature extraction and fusion.
    • The proposed approach offers superior performance for real-world bearing fault detection.