Investigation on the Predictive Model for Burr in Laser Cutting Titanium Alloy


Article Preview

The purpose of this study is to develop two predictive models for burr height in cutting titanium alloy plates by using Nd:YAG laser. Firstly, Taguchi method has been used to arrange the experimental scheme and analyze the results via analysis of mean . The important laser cutting parameters affecting burr height can be found. It shows that the pressure of assistant gas, the focusing position and the pulsed frequency are the most important cutting parameters in order. Then they have been chosen as the input variables for response surface methodology and used to construct a mathematical equation for predicting burr height. Secondly, the laser cutting parameters and experimental results obtained from conducting the schematic arrangement using Taguchi method and response surface methodology have been treated as training patterns and recalling patterns for the back-propagation neural network. As a result, a predictive model for burr height prediction in laser cutting titanium alloy has been established. To verify the accuracy of above two prediction models, there are 9 sets of experiment have been performed. It shows that the average error for predicting burr height by the mathematical equation derived from response surface methodology is 5.52% and by the predictive model established by back-propagation neural network is 4.51%, respectively. Obviously, both predictive models are good enough for the relational research and practical applications. It can be concluded that the procedure used in this research and the obtaining predictive models can be used practically in correlate industry.



Edited by:

M. Marcos and L. Sevilla




W. T. Chien and W.C. Hung, "Investigation on the Predictive Model for Burr in Laser Cutting Titanium Alloy", Materials Science Forum, Vol. 526, pp. 133-138, 2006

Online since:

October 2006




[1] Rajaram N., Sheikh-Ahmad J., and Cheraghi S. H., CO2 laser cut quality of 4130 steel, International Journal of Machine Tools & Manufacture, Vol. 43(2003), pp.351-358.


[2] Yang W. H., and Tarng Y. S., Design optimization of cutting parameters for turning operations based on Taguchi method, Journal of Materials Processing Technology, Vol. 84(1998), pp.122-129.


[3] Benardos P. G., and Vosniakos G. C., Prediction of surface roughness in CNC face milling using neural networks and Taguchi's design of experiments, Robotics and Computer Integrated Manufacturing, Vol. 18(2002), pp.343-354.


[4] Tsao Chung-Chen, Prediction of flank wear of different coated drills for JIS SUS 304 stainless steel using neural network, Journal of Materials Processing Technology, Vol. 123(2000), pp.354-360.


[5] Hambli Ridha, Prediction of burr height formation in blanking processes using neural network, International Journal of Mechanical Science, Vol. 44(2002), pp.2089-2102.


[6] Alauddin M., EI Baradic M. A., and Hashmi M. S. J., Prediction of tool life in end milling by response surface methodology, Journal of Materials Processing Technology, Vol. 71(1997), pp.456-165.


[7] Choudhury I. A., and EI-Baradie M. A., Surface roughness prediction in the turning of highstrength steel by factorial design of experiments, Journal of Materials Processing Technology, Vol. 67(1997), pp.55-61.