Journal of Henan University of Science and Technology(Natural Science), Volume. 46, Issue 4, 53(2025)

Adaptive Federated Bucketized Decision Tree Algorithm for Industrial Digital Twins

SUN Shibao1,2,3, ZHAO Yifan2, ZHAO Pengcheng3, LIU Jianfeng3, and LI Xin4
Author Affiliations
  • 1Longmen Laboratory, Luoyang 471000, China
  • 2College of Information Engineering, Luoyang 471023, China
  • 3School of Software, Henan University of Science and Technology, Luoyang 471023, China
  • 4School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China
  • show less

    Accurate modeling between physical devices and digital twins in industrial digital twins requires synchronizing massive amounts of sensing data. This results in difficulty ensuring real-time virtual-physical mapping. To address this issue, this paper proposes a four-layer bidirectional closed-loop architecture suitable for digital twins, consisting of a device, federated, cloud, and application layers. We develop a distributed federated bucketized decision tree algorithm utilizing histogram-based gain for global aggregation based on this architecture. Additionally, we design a pruning algorithm with adaptive gradient-weight redistribution to accelerate model convergence. Experimental results on the dataset demonstrate that the proposed federated aggregation model achieves accuracy improvements of 10%, 11%, and 22% compared to baseline methods. It also achieves convergence improvements of 15%, 20%, and 27%. Moreover, the proposed model maintains additional communication overhead within 300 mJ, even under the worst channel conditions.

    Tools

    Get Citation

    Copy Citation Text

    SUN Shibao, ZHAO Yifan, ZHAO Pengcheng, LIU Jianfeng, LI Xin. Adaptive Federated Bucketized Decision Tree Algorithm for Industrial Digital Twins[J]. Journal of Henan University of Science and Technology(Natural Science), 2025, 46(4): 53

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Received: May. 6, 2025

    Accepted: Aug. 22, 2025

    Published Online: Aug. 22, 2025

    The Author Email:

    DOI:10.15926/j.cnki.issn1672-6871.2025.04.007

    Topics