Online monitoring of tool wear in drilling and milling by multi-sensor neural network fusion


KANDİLLİ İ., Soenmez M., Ertunc H. M., Cakur B.

IEEE International Conference on Mechatronics and Automation, Harbin, China, 5 - 08 August 2007, pp.1388-1391 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/icma.2007.4303752
  • City: Harbin
  • Country: China
  • Page Numbers: pp.1388-1391
  • Kocaeli University Affiliated: Yes

Abstract

In manufacturing systems the detection of tool :wear during cutting process is one of the most important considerations. In order to perform online tool condition monitoring (TCM) for different cutting conditions, a sensor-integration strategy with machining parameters is proposed. TCM systems are most frequently based on the research which attempts to correlate the condition of drilling and milling tools to the signals obtained from multiple sensors (namely, cutting forces, vibration, current and sound connected to a CNC machine). The aim of the proposed study is to create a TCM system that will lead to a more efficient and economical machining tool usage. The used system is capable of accurate tool wear monitoring in around 97% accuracy. Experimental results under different conditions have demonstrated that TCM can be implemented by using neural network.