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: Dec 27, 2025

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

2.0K

Learning Attention Representation with a Multi-Scale CNN for Gear Fault Diagnosis under Different Working Conditions.

Yong Yao1, Sen Zhang2,3, Suixian Yang1

  • 1School of Mechanical Engineering, Sichuan University, Chengdu 610065, China.

Sensors (Basel, Switzerland)
|February 28, 2020
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 Effect of Medical Robot Information Transfer on Information Adherence of Cancer Patients: Evidence from a Scenario Experiment.

Patient preference and adherence·2026
Same author

Optimal cooperative output regulation with norm-based performance specifications.

ISA transactions·2026
Same author

Altered resting-state prefrontal activity and network topology in adolescents with depression: an fNIRS study.

Frontiers in psychiatry·2026
Same author

Traffic Characterization of Event-Triggered Multiagent Systems Under FDI Attacks.

IEEE transactions on cybernetics·2026
Same author

Dexmedetomidine nasal spray for acute agitation in adults with bipolar disorder: a single-arm open-label trial.

Journal of affective disorders·2025
Same author

Adaptive Label Refinement Network for Domain Generalization in Compound Fault Diagnosis.

Sensors (Basel, Switzerland)·2025

This study introduces an acoustic-based diagnosis (ABD) method for gear fault detection. The novel approach utilizes a multi-scale convolutional learning structure and attention mechanism for improved accuracy in non-linear, non-stationary conditions.

Area of Science:

  • Mechanical Engineering
  • Signal Processing
  • Artificial Intelligence

Background:

  • Gear fault diagnosis is challenging due to non-linear and non-stationary signals.
  • Current vibration-based methods require contact and expertise.
  • Existing methods struggle with varying working conditions.

Purpose of the Study:

  • To develop a novel acoustic-based diagnosis (ABD) method for gear fault detection.
  • To overcome limitations of contact-based vibration analysis.
  • To improve gear fault diagnosis accuracy under diverse working conditions.

Main Methods:

  • Proposed a multi-scale convolutional learning structure to extract features from acoustic signals.
  • Introduced an attention mechanism to focus on relevant fault information.
Keywords:
acoustic-based diagnosisattention mechanismconvolutional neural networkgear fault diagnosis

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.1K

Related Experiment Videos

Last Updated: Dec 27, 2025

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

2.0K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.1K
  • Developed a stacked convolutional neural network (CNN) for fault mode detection.

    • Main Results:

    • The proposed ABD method significantly outperformed standard CNN, end-to-end CNN, and traditional methods.
    • Achieved superior performance in acoustic-based gear fault diagnosis.
    • Demonstrated effectiveness in distinguishing faulty signals under different working conditions.

    Conclusions:

    • The novel acoustic-based diagnosis method is effective for gear fault detection.
    • The combination of multi-scale learning and attention mechanism enhances diagnostic accuracy.
    • This approach offers a promising non-contact alternative for gear health monitoring.