Scholarlink

<p>Digital twin (DT) model plays a crucial role in accurately depicting physical entities and optimizing production processes. However, synchronous evolution of DT model for precision holding to ensure the consistency between DT model and the performance of physical workshop (PW), and guarantee the accuracy of DT model is still a challenging issue, especially when dealing with new dynamic samples for complex production environment of discrete manufacturing workshop (DMW). This paper proposes a synchronous evolution mechanism for DT model with Stacking-GRU-DNN to enhance the accuracy of DT model prediction with time in industrial environment, which integrates multiple base learners to capture production patterns and triggers synchronization when model performance declines, replacing outdated base learners to maintain accuracy. The experiment is conducted in the realistic production dataset, which demonstrates that the proposed synchronous evolution mechanism has good performance for realizing the synchronization of the performance of PW in industrial environment, and can greatly improve the prediction ability for DT model.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Ensemble learning-based synchronous evolution mechanism for digital twin models in discrete manufacturing workshop

  • 期刊论文

  • 发表日期：

    2025年12月8日

查看全文
  • Weiwei Qian,
  • Liwei Shen,
  • Hanpeng Gao,
  • Yaning Tao,
  • Weiguang Fang,
  • Hao Zhang

摘要

Digital twin (DT) model plays a crucial role in accurately depicting physical entities and optimizing production processes. However, synchronous evolution of DT model for precision holding to ensure the consistency between DT model and the performance of physical workshop (PW), and guarantee the accuracy of DT model is still a challenging issue, especially when dealing with new dynamic samples for complex production environment of discrete manufacturing workshop (DMW). This paper proposes a synchronous evolution mechanism for DT model with Stacking-GRU-DNN to enhance the accuracy of DT model prediction with time in industrial environment, which integrates multiple base learners to capture production patterns and triggers synchronization when model performance declines, replacing outdated base learners to maintain accuracy. The experiment is conducted in the realistic production dataset, which demonstrates that the proposed synchronous evolution mechanism has good performance for realizing the synchronization of the performance of PW in industrial environment, and can greatly improve the prediction ability for DT model.