Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 6, 2026

Induction of Paralysis and Visual System Injury in Mice by T Cells Specific for Neuromyelitis Optica Autoantigen Aquaporin-4

Induction of Paralysis and Visual System Injury in Mice by T Cells Specific for Neuromyelitis Optica Autoantigen Aquaporin-4

Published on: August 21, 2017

Bearing fault diagnosis method based on SAGAN and improved ResNet.

Guoqiang Wang^1,2, Nianfeng Shi^1,2, Xianglan Yang^3,4

¹School of Computer and Information Engineering, Luoyang Institute of Technology, Luoyang, China.

Scientific Reports

|September 29, 2025

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

Energy stress-induced PKCζ S-glutathionylation is essential for LKB1 cytoplasmic translocation and AMPK activation.

Life metabolism·2025

Same author

Lipid-Coated Mesoporous Silica Particles for pH-Sensitive Tumor-Targeted Paclitaxel: Development, Characterization.

Journal of Cancer·2025

Same author

Circular RNA profiling and functional analysis implicate circ-ANKRD36C as a potential prognostic biomarker in gastric cancer.

BMC gastroenterology·2025

Same author

A Transformer-Based Deep Diffusion Model for Bulk RNA-Seq Deconvolution.

Biology·2025

Same author

Extreme soil moisture conditions is more likely to cause deviations between soil respiration and ecosystem respiration.

Journal of environmental management·2025

Same author

Quantitative characterization of uncertainty in the source apportionment induced by the dual spatial heterogeneity of soil heavy metals.

Journal of hazardous materials·2025

This study introduces a novel bearing fault diagnosis method using Self-Attention Generative Adversarial Networks (SAGAN) and Improved Deep Residual Networks (IResNet). The approach enhances feature extraction and data augmentation for robust fault detection in challenging industrial conditions.

Area of Science:

Mechanical Engineering
Artificial Intelligence
Signal Processing

Background:

Traditional rolling bearing fault diagnosis faces challenges in feature extraction within complex industrial settings.
Acquiring extensive fault data under real operating conditions is often difficult and costly.

Purpose of the Study:

To address limitations in adaptive feature extraction and data scarcity for bearing fault diagnosis.
To develop a robust method capable of handling noisy and variable load conditions.

Main Methods:

Vibration signals transformed into 2D time-frequency images via continuous wavelet transform.
Self-Attention Generative Adversarial Networks (SAGAN) used for data augmentation.
Improved Deep Residual Networks (IResNet) with Multi-head Self-Attention (MHA) for adaptive global feature extraction.

Keywords:

Continuous wavelet transform Deep residual network Fault diagnosis Multi-head self-attention

Related Experiment Videos

Last Updated: Jan 6, 2026

Induction of Paralysis and Visual System Injury in Mice by T Cells Specific for Neuromyelitis Optica Autoantigen Aquaporin-4

Induction of Paralysis and Visual System Injury in Mice by T Cells Specific for Neuromyelitis Optica Autoantigen Aquaporin-4

Published on: August 21, 2017

Main Results:

The proposed SAGAN_IResNet method demonstrates strong bearing fault diagnosis performance.
Effective handling of scenarios with limited samples, high noise levels, and variable loads.
Validated using datasets from Case Western Reserve University, Southeast University, and Jiangnan University.

Conclusions:

The SAGAN_IResNet method offers a significant advancement in bearing fault diagnosis.
The integration of SAGAN and MHA-enhanced IResNet improves diagnostic accuracy and robustness.
The approach is suitable for real-world industrial applications with challenging environmental factors.