期刊文献+

基于改进EGM(1,1)的刀具磨损预测

Tool Wear Prediction Based on Metabolized EGM(1,1)Model
下载PDF
导出
摘要 刀具磨损及寿命预测一直是刀具管理研究的重要领域,但由于加工工艺、使用强度及环境因素的极度未确知性,很难取得对刀具寿命的准确判断,因而增加了机床或工件损坏的风险,所以需要构建模型实现对磨损程度的有效预测。本文首先通过一定条件下的刀具磨损实验,测量出刀具在相同工作时间内的磨损值,然后采用新信息优先的新陈代谢EGM(1,1)模型对特定条件下的数据序列进行拟合与预测,并与传统EGM(1,1)进行比较。结论发现新陈代谢EGM(1,1)模型具有更高的预测精度、更小的拟合误差,对提高刀具磨损及寿命预测的准确性具有重要方法意义。 It has always been an important field for tool wear and life prediction in tool management research.But due to the extreme uncertainty of processing technology,strength of use and environmental factors,it is difficult to obtain an accurate judgment of tool life,thus resulting in risk of machine tool or workpiece damage.In order to realize effective prediction of wear degree,the tool wear values were measured by tool wear experiments in certain conditions.Then,metabolism EGM(1,1)model was employed to perform fitting and prediction of data sequences.And by comparison with traditional EGM(1,1),it is found that the metabolism EGM(1,1)model has higher prediction accuracy,and as an effective life prediction method,it presents important significance to improve the accuracy of tool wear.
作者 李光宇 李守军 Li Guang-yu;Li Shou-jun(School of Mechanical&Electrical Engineering,Suqian College,Suqian 223800,China)
出处 《内燃机与配件》 2022年第22期108-110,共3页 Internal Combustion Engine & Parts
基金 宿迁市科技计划项目(Z2019106) 江苏高校品牌专业建设工程资助项目(PPZY2015C252)。
关键词 刀具磨损 灰色预测 EGM(1 1) 新陈代谢 Tool wear Gray prediction EGM(1,1) Metabolize
  • 相关文献

参考文献6

二级参考文献53

  • 1雷小宝,廖文和,谢峰,郑侃,赵吉文.义齿用预烧结氧化锆高速铣削时刀具磨损及寿命预测[J].南京理工大学学报,2013,37(4):567-572. 被引量:7
  • 2ZAREENA A R, VELDHUIS S C. Tool wear mecha- nisms and tool life enhancement in ultra-precision ma- chining of titanium [ J ]. Journal of Materials Processing Technology, 2012,210 : 560 -570.
  • 3ZHU DAHU, ZHANG XIAOMING, DING HAN. Tool wear characteristics in machining of nickel-based su- peralloys [ J ]. International Journal of Machine Tools & Manufacture, 2013,64 : 60-77.
  • 4KAYA B, OYSU C, ERTUNC H M. Force-torquebased on-line tool wear estimation system for CNC milling of Inconel 718 using neural networks [ J]. Ad- vances in Engineering Software,2011,42 (3) :76-84.
  • 5TANSEL I N, LI M, DEMETGUL M,et al. Detecting chatter and estimating wear from the torque of end milling signals by using Index Based Reasoner (IBR) [ J]. International Journal of Advanced Manufacturing Technology ,2012,58 ( 1-4 ) : 109-118.
  • 6ZHANG CHEN, ZHANG JINLIN. On-line tool wear measurement for ball-end milling cutter based on ma- chine vision [ J]. Computers in Industry, 2013, 64: 708 -719.
  • 7KISHAWY H A , PANG L, BALAZINSKI M. Model- ing of tool wear during hard turning with self-propelled rotary tools [ J ]. International Journal of Mechanical Sciences ,2011,53 : 1015-1021.
  • 8SIVASAKTHIVEL P S, MURUGAN V V, SUDHAKA- RAN R. Prediction of tool wear from machining param- eters by response surface methodology in end milling [ J ]. International Journal of Engineering Science andTeehnology,2010, 2 (6) : 1780-1789.
  • 9RIAZ MUHAMMAD, ANISH ROY,VADIM V. Silber- schmidt. Finite Element Modelling of Conventional and Hybrid Oblique Turning Processes of Titanium Alloy [ C ]//14th CIRP Conference on Modelling of Machi- ning Operations ,2013:510-515.
  • 10HSU C Y, LIN Y Y,LEE W S,et al. Transient,Machi- ning characteristics of Inconel 718 using ultrasonic and high temperature-aided cutting [ J ]. Journal of Materi- als Processing Technology, 2008,198:359-365.

共引文献53

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部