• CN:11-2187/TH
  • ISSN:0577-6686

机械工程学报 ›› 2026, Vol. 62 ›› Issue (17): 453-462.doi: 10.3901/JME.260336

• 制造工艺与装备 • 上一篇    

扫码分享

基于Bi-LSTM热传导反问题快速求解的整体立铣刀切削区温度场重构研究

殷增斌, 赵腾, 郑轶彤   

  1. 南京理工大学机械工程学院 南京 210094
  • 收稿日期:2025-09-20 修回日期:2026-02-26 发布日期:2026-11-20
  • 作者简介:殷增斌(通信作者),男,1987年出生,博士,教授,博士研究生导师。主要研究方向为高性能陶瓷刀具/智能刀具设计制造应用、加工状态智能监测。E-mail:zengbinyin@njust.edu.cn;赵腾,男,2000年出生,硕士研究生。主要研究方向为铣削刀具温度场在线重构。E-mail:njust_zt401@163.com
  • 基金资助:
    中央高校基本科研业务费专项资金资助项目(2024203001)。

Research on the Reconstruction of the Temperature Field in the Cutting Zone of Integral Milling Cutters Based on Rapid Solution of Heat Conduction Inverse Problems by Bi-LSTM

YIN Zengbin, ZHAO Teng, ZHENG Yitong   

  1. School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094
  • Received:2025-09-20 Revised:2026-02-26 Published:2026-11-20

摘要: 面向铣削过程中切削区温度场在线精确监测的需求,提出一种有限元法与Duhamel叠加原理相结合的铣削刀具切削区温度场在线重构方法。通过安装在铣刀内部的热敏陶瓷温度传感器获取实时温度数据,基于双向长短期记忆网络(Bi-directional long short-term memory,Bi-LSTM)反求预测实际热流密度,根据实时温度数据从温度敏感系数数据集中选择最合适的温度敏感系数,最后利用针对铣削加工特性的Duhamel原理改进模型实现对铣刀切削区温度场的快速重构。试验验证表明,该方法不仅计算效率高,而且能够准确地反映实际铣削过程中刀具切削区温度场变化情况,为切削工艺智能优化奠定了技术基础。

关键词: 立铣刀, 切削温度, 温度场重构, 热传导反问题, 热传导正问题, Bi-LSTM网络

Abstract: To meet the demand for online precise monitoring of the temperature field in the cutting zone during the milling process, an online reconstruction method of the temperature field in the cutting zone of the milling tool is proposed by combining the finite element method and the Duhamel superposition principle. The real-time temperature data is obtained by the thermistor sensor installed inside the milling tool, and the actual heat flux is reversely predicted based on the Bi-directional long short-term memory network (Bi-LSTM) with excellent training effect. According to the real-time temperature data, the most appropriate temperature sensitivity coefficient is selected from the temperature sensitivity coefficient data set. Finally, the improved Duhamel principle model for milling machining characteristics is used to realize the rapid reconstruction of the temperature field of the milling cutter. The experimental results show that the method not only improves the calculation efficiency, but also can accurately reflect the temperature field changes in the cutting area of the tool in the actual milling process, which lays a technical foundation for the intelligent optimization of the cutting process.

Key words: end mill, cutting temperature, temperature field reconstruction, inverse heat conduction problem, heat conduction forward problem, Bi-directional long short-term memory network(Bi-LSTM)

中图分类号: