Closing the Simulation-to-Reality Gap for Digital Twin-Assisted Fault Diagnosis: Sim2real Knowledge Transfer with Contrastive Learning

25 Pages Posted: 18 Jan 2024

See all articles by Jiahong Chen

Jiahong Chen

affiliation not provided to SSRN

Kuangen Zhang

affiliation not provided to SSRN

Jing Wang

affiliation not provided to SSRN

Weiming Shen

Huazhong University of Science and Technology

Abstract

Digital twin technology, crucial for fault diagnosis in smart manufacturing, provides accurate models of physical equipment and generates labeled synthetic data efficiently. Despite its benefits, a challenge arises from the distribution divergence between synthetic and real-world data, affecting model generalization. To address this, we propose the Contrastive Sim2Real Adaptation (CSRA) approach. CSRA leverages a pre-trained model on the labeled source data for self-supervised learning and knowledge transfer to the real-world unlabeled target data, effectively bridging the domain gap between the simulated and real-world environments. This method addresses training data privacy concerns and eliminates the need for source data when adapting pre-trained models to real-world scenarios. It benefits both providers of pre-trained models and clients using these models for customized applications. CSRA demonstrates superior performance in handling large domain gaps, improving model generalization in new environments, and narrowing the synthetic-to-real-world gap compared to standard cross-domain models in extensive experiments.

Keywords: Transfer Learning, contrastive learning, domain adaptation, digital twins, fault diagnosis, smart manufacturing

undefined

Suggested Citation

Chen, Jiahong and Zhang, Kuangen and Wang, Jing and Shen, Weiming, Closing the Simulation-to-Reality Gap for Digital Twin-Assisted Fault Diagnosis: Sim2real Knowledge Transfer with Contrastive Learning. Available at SSRN: https://ssrn.com/abstract=4699149 or http://dx.doi.org/10.2139/ssrn.4699149

Jiahong Chen

affiliation not provided to SSRN ( email )

No Address Available

Kuangen Zhang

affiliation not provided to SSRN ( email )

No Address Available

Jing Wang (Contact Author)

affiliation not provided to SSRN ( email )

No Address Available

Weiming Shen

Huazhong University of Science and Technology ( email )

1037 Luoyu Rd
Wuhan, 430074
China

0 References

    0 Citations

      Do you have a job opening that you would like to promote on SSRN?

      Paper statistics

      Downloads
      67
      Abstract Views
      206
      Rank
      693,124
      PlumX Metrics
      Plum Print visual indicator of research metrics
      • Citations
        • Citation Indexes: 1
      • Usage
        • Abstract Views: 170
        • Downloads: 54
      see details