You are in:Home/Publications/“Online Tool Wear Monitoring In Turning Using Vibration Analysis And Artificial Neural Network”, Ain Shams Journal of Mechanical Engineering (ASJME) ,Vol. 2, pp.201-212, October.

Prof. AbdelKader AbdelKarim Ibrahim :: Publications:

Title:
“Online Tool Wear Monitoring In Turning Using Vibration Analysis And Artificial Neural Network”, Ain Shams Journal of Mechanical Engineering (ASJME) ,Vol. 2, pp.201-212, October.
Authors: A. A. Ibraheem, S. M. Abdrabbo, H. Gheith , M. Abd El-Salam, and M. El-Samanty
Year: 2009
Keywords: Tool wear, Turning, Vibration, Neural Network
Journal: Not Available
Volume: Not Available
Issue: Not Available
Pages: Not Available
Publisher: Not Available
Local/International: Local
Paper Link: Not Available
Full paper Abdel-Kader Abdel-Karim Ibrahim_paper.pdf
Supplementary materials Not Available
Abstract:

The need for new and more reliable tool wear sensors for metal cutting has become a necessity. In this context, and based on a computer monitoring technique an online method for the prediction and estimation of tool wear was developed using the vibration measurement and analysis of the tool during turning. The vibration results from rubbing conditions between the tool and the machined workpiece surface. It was observed that the vibration level increased with the increase of tool wear land width. A slight vibration level variations due to the effect of the cutting conditions was also observed. From the results obtained an empirical formula was formulated. This formula can be used for the prediction and estimation of tool wear from the online vibration level measurement. Multi layer Neural Network (MNN) system with back propagation algorithm has been developed and used for cutting tool wear monitoring based on the measurement of the tool vibration level of the tool. The results of the Neural Network showed close matching between the model output and the directly measured flank wear, both results are quite successfully but the trained data accuracy shows a small scatter relative to the measured data. The measured and estimated values of the tool wear using the empirical formula and Neural Network were in agreement with a maximum deviation of less than 10%.

Google ScholarAcdemia.eduResearch GateLinkedinFacebookTwitterGoogle PlusYoutubeWordpressInstagramMendeleyZoteroEvernoteORCIDScopus