Soft-Sensing Model on the Roughness of Machining Surface under the Numerical Control and its Application

Abstract:

In order to make sure a high-accuracy and fast- speed survey, a Soft-sensing model for the roughness of machining surface was built based on the support vector machines using rotate speed n, feed peed vf, and depth of cutting as independent parameters, taking groups of actual machining experiment data as samples.The allowable error ε and the positive aligned c and the kernel function parameter r were optimized by an adaptive genetic algorithm. After being optimized 300 steps, the following results can be gained through the training, testing and application. The average relative error tended to saturation training was 4.0%; the test error was less than 2.6%; the average relative error between the Soft-sensing value for the roughness of machining surface under the numerical control and the test value of the profile and roughness tester for the SV-C3000 super surface of was ranging from 0.4% to 1.25%.

• Periodical: Applied Mechanics and Materials (Volumes 48-49)
• Pages: 1077-1085
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.48-49.1077
• Online since: February 2011
• Authors: Yi Hui Zeng, Jia Qiang E, Xian Ping Yang, Hong Mei Li
• Keywords: Adaptive Genetic Algorithm (AGA), Numerical Control Machining, Support Vector Machine (SVM), Surface Roughness (SR)

References

[1] REN Jinxin, KANG Renke, SHI Xingkuan. Griding processes for difficult processed metal materials[M]. Beijing: Nation Defence Industry Press, 1999. (in Chinese).

[2] CHANDRA Nath, RAHMAN M. Effect of machining parameters in ultrasonic vibration cutting[J]. International Journal of Machine Tools and Manufacture, 2008, 48(9): 965-974.

DOI: 10.1016/j.ijmachtools.2008.01.013

[3] Jin Masahiko, Murakawa Masao. Development of a practical ultrasonic vibration cutting tool system[J]. Journal of Materials Processing Technology, 2001, 113(1-3): 342-347.

DOI: 10.1016/s0924-0136(01)00649-5

[4] XIE Hongmei, HUANG Wei. Forecasting study on the roughness of griding surface based on artificial neural networks, Grinder and Grinding, 2001, (4): 30-31. (in Chinese).

[5] WSLin, et al. Modeling the surface roughness and cutting force for turning[J]. Journal of Material Processing Technology, 2001(108): 286-293.

[6] Benardos P G, Vosniakos G C. Prediction of surface roughness in CNC face milling using neural networks and Taugchi's design of experiments. Robotics and Computer Integrated Manufactur-ing, 2002 (18): 343-354.

DOI: 10.1016/s0736-5845(02)00005-4

[7] Ezugwu E O, Fadare D A, et al. Modeling the correlation between cutting and process parameters in high-speed machining of Inconel718 alloy using an artificial neural network[J]. International Journal of Machine Tools&Manufacture, 2005, 45(): 1375-1385.

DOI: 10.1016/j.ijmachtools.2005.02.004

[8] Vapnik V. The nature of statistical learning theory[M]. New York: Springer, (1999).

[9] Isabelle GuYon, Jason Weston, Stephen Barnhill. Gene Selection for Cancer Classification using Support Vector Machines[J]. Machine Learning, 2002, 46: 389-422.

[10] Vapnik V. Statistical learning theory[M]. New York: Wiley, (1998).

[11] Willis M. J. Artificial neural networks in process engineering[J]. IEE Proceedings-D, 1991, 138(3): 256-266.

[12] E Jia-qiang. Intelligent fault diagnosis and its application [M]. Changsha: Hunan University Press, 2006. (in Chinese).