Neural network computational techniques are a new alternative to conventional numerical modeling. This paper presents modeling using response surface methodology (RSM). Box and Wilson Central Composite Design (CCD) is used for preparing experiment matrix. The independent parameters in the experiment are speed, feed, force and number of tool passes. These variables are controlled during the burnishing process. The response parameter is micro hardness. Experimental samples are prepared using Single Roller Burnishing Tools (Carbide). Vickers micro hardness tester is used to measure micro hardness. A quadratic mathematical model is developed using RSM. An Artificial neural network (ANN) model is developed using three-layer feed-forward back-propagation. The neural network model is trained using measured values of micro hardness. The different algorithms are used to train the model. Best performance is achieved with correlation coefficient 0.9. This study concludes that an artificial neural network is the best alternative to fit the nonlinear data.

Burnishing , RSM, Micro Hardness, ANN

[1] B. Bhushan, Introduction to tribology: John Wiley & Sons, 2013.
[2] P. Benardos and G. C. Vosniakos, "Prediction of surface roughness in CNC face milling using neural networks and Taguchi`s design of experiments," Robotics and Computer-Integrated Manufacturing, vol. 18, pp. 343-354, 2002.
[3] T. Özel and Y. Karpat, "Predictive modeling of surface roughness and tool wear in hard turning using regression and neural networks," International Journal of Machine Tools and Manufacture, vol. 45, pp. 467-479, 2005.
[4] N. B. Fredj and R. Amamou, "Ground surface roughness prediction based upon experimental design and neural network models," The International Journal of Advanced Manufacturing Technology, vol. 31, pp. 24-36, 2006.
[5] C.-F. J. Kuo and Y.-S. Wu, "Application of a Taguchi-based neural network prediction design of the film coating process for polymer blends," The International Journal of Advanced Manufacturing Technology, vol. 27, pp. 455-461, 2006.
[6] M. Mia and N. R. Dhar, "Prediction of surface roughness in hard turning under high pressure coolant using Artificial Neural Network," Measurement, vol. 92, pp. 464-474, 2016.
[7] K. Çelebi, E. Uludamar, E. Tosun, Ş. Yıldızhan, K. Aydın, and M. Özcanlı, "Experimental and artificial neural network approach of noise and vibration characteristic of an unmodified diesel engine fuelled with conventional diesel, and biodiesel blends with natural gas addition," Fuel, vol. 197, pp. 159-173, 2017.
[8] R. Sharda and R. B. Patil, "Connectionist approach to time series prediction: an empirical test," Journal of Intelligent Manufacturing, vol. 3, pp. 317-323, October 01 1992.
[9] D. Kim, "Normalization methods for input and output vectors in backpropagation neural networks," International Journal of Computer Mathematics, vol. 71, pp. 161-171, 1999/01/01 1999.
[10] I. El-Sonbaty, U. Khashaba, A. Selmy, and A. Ali, "Prediction of surface roughness profiles for milled surfaces using an artificial neural network and fractal geometry approach," Journal of Materials Processing Technology, vol. 200, pp. 271-278, 2008.
[11] G. Zhang, B. E. Patuwo, and M. Y. Hu, "Forecasting with artificial neural networks:: The state of the art," International journal of forecasting, vol. 14, pp. 35-62, 1998.
[12] A. M. Zain, H. Haron, and S. Sharif, "Prediction of surface roughness in the end milling machining using Artificial Neural Network," Expert Systems with Applications, vol. 37, pp. 1755-1768, 2010.
[13] S. Makridakis and R. L. Winkler, "Averages of forecasts: Some empirical results," Management Science, vol. 29, pp. 987-996, 1983.