Scholarlink

<p>Modern manufacturing environments call for increased sensorization and data usage toward the optimization of manufacturing processes. Milling is also a process where data-driven diagnostics and optimization are pursued to ensure optimal resource utilization and quality of the manufactured products. Tool wear is a significant aspect that should be controlled during a machining process. Machining with worn tools leads to increased cutting forces, poor surface quality, and dimensional accuracy due to geometrical deviations of the cutting edge compared to the nominal value. A consistent requirement related to in-process diagnostic applications for machining is the reconfigurability of the approach that allows it to be easily transferred between different machines, machining operations, cutting tools, and workpiece materials. Additionally, computational efficiency is key for industrial adoption. Breakthroughs in sensor technology and electronics enable the development of sensor-integrated tooling for machining that can be integrated very close to the cutting edge and can provide high quality data that can be used to evaluate the process status, simplifying the algorithmic approach for process diagnosis without accuracy loss. This paper demonstrates an approach for in-line tool wear monitoring, using cutting force and cutting temperature data from a sensor-integrated, indexable milling head. The approach is demonstrated in a large-scale milling scenario of high-performance tool steel.</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

Tool condition monitoring in milling using cutting force and temperature data from an instrumented milling head

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月12日

查看全文
  • Thanassis Souflas,
  • Eleftheria Triantopoulou,
  • Christos Papaioannou,
  • Christoph Ramsauer,
  • Julian-Amon Greitler,
  • Paul Schörghofer,
  • Norbert Leder,
  • Panagiotis Stavropoulos

摘要

Modern manufacturing environments call for increased sensorization and data usage toward the optimization of manufacturing processes. Milling is also a process where data-driven diagnostics and optimization are pursued to ensure optimal resource utilization and quality of the manufactured products. Tool wear is a significant aspect that should be controlled during a machining process. Machining with worn tools leads to increased cutting forces, poor surface quality, and dimensional accuracy due to geometrical deviations of the cutting edge compared to the nominal value. A consistent requirement related to in-process diagnostic applications for machining is the reconfigurability of the approach that allows it to be easily transferred between different machines, machining operations, cutting tools, and workpiece materials. Additionally, computational efficiency is key for industrial adoption. Breakthroughs in sensor technology and electronics enable the development of sensor-integrated tooling for machining that can be integrated very close to the cutting edge and can provide high quality data that can be used to evaluate the process status, simplifying the algorithmic approach for process diagnosis without accuracy loss. This paper demonstrates an approach for in-line tool wear monitoring, using cutting force and cutting temperature data from a sensor-integrated, indexable milling head. The approach is demonstrated in a large-scale milling scenario of high-performance tool steel.