A Study on the Cutting Characteristics and Detection of the Abnormal Tool State in Turning of Ti-6Al-4V ELI

Abstract:

The cutting characteristics of biomaterials (Ti-6Al-4V ELI) by tools are investigated with respect to cutting force, work piece surface roughness and tool flank wear by the vision system. Ti-6Al-4V ELI titanium turning is carried out with various cutting conditions; spindle rotational speed and feed rate. Back propagation neural networks (BPNs) are used for detection of tool wear. The input vectors of neural network comprise of spindle rotational speed, feed rates, vision flank wear, and cutting force signals. The output is the tool wear state which is either usable or failure. The detection of the abnormal states using BPNs achieves 97.5% reliability even when the spindle rotational speed and feed rate are changed.

• Periodical: Applied Mechanics and Materials (Volumes 433-435)
• Pages: 2025-2030
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.433-435.2025
• Online since: October 2013
• Authors: Hyung Gon Shin, Seung Hyeon Yoo, Seon Woo Park, Dong Pyo Hong
• Keywords: Back Propagation Neural Networks, Biomaterial, Ti-6Al-4V ELI Titanium, Tool Wear

References

[1] Korea Institute of Materials Science, in: MateriALL 2010. (2010).

[2] S. W. Roh, M. S. Vang, H. S. Yang, S. W. Park, H. O. Park, and H. P. Lim, in: Effect of surface modification on bond strength in titanium- porcelain system, J Kor Ac Prosth., Vol. 5 (2007), pp.589-600.

[3] N. Fang, Q. Wu., in: A comparative study of the cutting forces in high speed machining of Ti–6Al–4V and Inconel 718 with a round cutting edge tool, Journal of Materials Processing Technology, Vol. 209 (2009), pp.4385-4389.

DOI: 10.1016/j.jmatprotec.2008.10.013

[4] Lee, Y. T. and Lee, J. H., in: Machining Technology Titanium, The Korea Metal Journal, Korea (2006), pp.45-65.

[5] J. G. Choi, H. S. Kim and J. O. Chung, in: Turning Characteristics of Various Tool Materials in the Machining of Ti-6Al-4V, Transactions of the Korean Society of Machine Tool Engineers, Vol. 17 (2008), pp.38-44.

[6] Sandeep S. Jaiswal, in: Prediction of Tool wear using Neural Networks, The University of Alabama in Huntsville (1999).