What question did this study set out to answer?

To develop a dynamic feature-embedding digital twin framework using diffusion models to overcome data imbalance in rolling bearing fault diagnosis.

August 14, 2026Journal of Computing and Information Science in Engineering

DDPM-based Dynamic Feature Embedding Digital Twin Fault Diagnosis of Rolling Bearing

View Full Paper

Ask AI

Bookmark

Authors

JDJiewei DengGuangdong University of Technology GWGuangrui WenXi'an Jiaotong University ZLZihao LeiSouthern University of Science and Technology

Discussion

Member takes

Implication

Computational modeling study demonstrates improved fault diagnosis accuracy in rolling bearings using diffusion-based digital twins, indicating robust performance under imbalanced data.

Key Points

To develop a dynamic feature-embedding digital twin framework using diffusion models to overcome data imbalance in rolling bearing fault diagnosis.
Constructed a dynamics-based bearing mechanism model to generate one-dimensional raw fault signals.
Combined Variational Autoencoders (VAE) with diffusion models to enable stable generative modeling on low-dimensional signals.
Implemented a dynamic feature embedding mechanism within the diffusion model and compared diagnostic performance against Generative Adversarial Network (GAN) baselines.
Generated synthetic bearing fault data with accurate feature representations to effectively complement imbalanced training datasets.
Achieved higher diagnostic accuracy and robustness compared to conventional GAN-based digital twin approaches.

Cite This Study

Deng et al. (2026) studied this question.

synapsesocial.com/papers/6a7ec78db70b84ec8b913f19 https://doi.org/10.1115/1.4072512

View Full Paper

Ask AI

Bookmark

Implication

Computational modeling study demonstrates improved fault diagnosis accuracy in rolling bearings using diffusion-based digital twins, indicating robust performance under imbalanced data.

DDPM-based Dynamic Feature Embedding Digital Twin Fault Diagnosis of Rolling Bearing

Discussion

Member takes

Implication

Key Points

Cite This Study

DDPM-based Dynamic Feature Embedding Digital Twin Fault Diagnosis of Rolling Bearing

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider