计算机集成制造系统 ›› 2019, Vol. 25 ›› Issue (第9): 2140-2148.DOI: 10.13196/j.cims.2019.09.002

• 当期目次 • 上一篇    下一篇

基于功率信号的钻锪刀具监测及其系统开发

万文波,李江雄,毕运波+   

  1. 浙江大学机械工程学院
  • 出版日期:2019-09-30 发布日期:2019-09-30
  • 基金资助:
    国家自然科学基金资助项目(51775495).

Drilling and dimpling tool monitoring based on power signal and its system development

  • Online:2019-09-30 Published:2019-09-30
  • Supported by:
    Project supported by the National Natural Science Foundation,China(No.51775495).

摘要: 刀具切削状态直接影响了加工质量与效率,在柔性制造和计算机集成制造生产线中,监测设备常以功率阈值的方式判断刀具加工状态。而在实际加工中,如切削参数发生改变,则需要对各工序重新设定阈值参数,且无法适用于变切削加工过程。为解决这一问题,提出在功率监测法的基础上,利用自适应神经模糊系统与支持向量回归建立功率与加工参数之间的模型,计算标准切削功率,并与实际切削功率进行实时对比分析,从而判断刀具加工状态并执行换刀策略。最后,在西门子840Dsl数控系统中进行二次开发,完成了刀具状态监测系统的开发并应用于实际生产加工中,验证了所提方法的有效性。

关键词: 刀具状态监测, 功率信号, 钻锪刀具, 自适应神经模糊系统, 支持向量回归

Abstract: The state of cutting tool directly affects the quality and efficiency of machining.In actual production line of flexible manufacturing and computer integrated manufacturing system,the threshold of every process should be reset in the condition of changing parameter drilling.For this problem,based on the power threshold monitoring,the model between power and processing parameters was established by using Adaptive Network-Based Fuzzy Inference System(ANFIS)and Support Vector Regression(SVR),which was used to update the threshold in real time and then compared with the actual cutting power for determining the state of drilling tools and executing the strategy of tool change.The development of Tool Condition Monitoring System(TCMS)was completed in Siemens Sinumerik 840Dsl,and the effectiveness of the proposed model in actually project was certified.

Key words: tool condition monitoring, power signal, drilling and dimpling tool, adaptive network-based fuzzy inference system, support vector regression

中图分类号: