Scholarlink

<p>The balance between the accuracy of virtual modeling and the response speed of digital twin system is a key issue in digital twin development. High-fidelity modeling with multi-disciplinary integration optimizes accuracy while increasing computational consumption. Simplifying the digital twin model speeds up the response while reducing the accuracy of modeling. A method of responsive digital twin system modeling was proposed in this paper, via integrating biomimetic perception networks. The biomimetic perception model is used to achieve multidisciplinary integration. And at the same time, based on stress response and cognitive response, it can achieve hierarchical responses to different needs, so as to balance accuracy and response speed. The modeling includes a digital twin perception module based on a fusion biomimetic perception network and a digital twin response module based on biological response. Finally, the ability of the digital twin system is verified by a milling experiment.</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

A responsive digital twin approach for machining based on biomimetic perception and cognition

  • 期刊论文

  • 发表日期：

    2025年7月30日

查看全文
  • Yicheng Sun,
  • Minjun Xu,
  • Jinsong Bao,
  • Shimin Liu

摘要

The balance between the accuracy of virtual modeling and the response speed of digital twin system is a key issue in digital twin development. High-fidelity modeling with multi-disciplinary integration optimizes accuracy while increasing computational consumption. Simplifying the digital twin model speeds up the response while reducing the accuracy of modeling. A method of responsive digital twin system modeling was proposed in this paper, via integrating biomimetic perception networks. The biomimetic perception model is used to achieve multidisciplinary integration. And at the same time, based on stress response and cognitive response, it can achieve hierarchical responses to different needs, so as to balance accuracy and response speed. The modeling includes a digital twin perception module based on a fusion biomimetic perception network and a digital twin response module based on biological response. Finally, the ability of the digital twin system is verified by a milling experiment.