A Comparative Study of the RSM and ANN Models for Predicting Surface Roughness in Roller Burnishing

Abstract In this paper the comparison of the surface roughness prediction models based on response surface methodology (RSM) and artificial neural networks (ANN) is described. The models were developed based on five-level design of experiments conducted on Aluminum alloy 6061 work material with spindle speed, interference, feed, and number of tool pass as the roller burnishing process parameters. The ANN predictive models of surface roughness was developed using a multilayer feed forward neural network and trained with the help of an error back propagation learning algorithm based on the generalized delta rule. Mathematical models of second order RSM and developed ANN models were compared for surface roughness. The comparison evidently indicates that the prediction capabilities of ANN models are far better as compared to the RSM models. The minutiae of experimentation, development of model, testing, and performance comparison are presented in the paper.

[1]  Anna Witek-Krowiak,et al.  Application of response surface methodology and artificial neural network methods in modelling and optimization of biosorption process. , 2014, Bioresource technology.

[2]  Václav Dvorák,et al.  Neural networks and fuzzy systems : B Kosko Prentice-Hall , 1993, Knowl. Based Syst..

[3]  M. H El-Axir,et al.  An Investigation into Roller Burnishing , 2000 .

[4]  Aitzol Lamikiz,et al.  Surface improvement of shafts by the deep ball-burnishing technique , 2012 .

[5]  Kiran A. Patel,et al.  Comparative Analysis for Surface Roughness of Al Alloy 6061 using MLR and RSM , 2015 .

[6]  M. H. El-Axir,et al.  Investigations into the burnishing of external cylindrical surfaces of 7030 Cu-Zn alloy , 1988 .

[7]  Habibollah Haron,et al.  Prediction of surface roughness in the end milling machining using Artificial Neural Network , 2010, Expert Syst. Appl..

[8]  Shigeo Abe,et al.  Neural Networks and Fuzzy Systems , 1996, Springer US.

[9]  Zheng Qiang Tang,et al.  Analytical prediction and experimental verification of surface roughness during the burnishing process , 2012 .

[10]  Tuncay Erzurumlu,et al.  Comparison of response surface model with neural network in determining the surface quality of moulded parts , 2007 .

[11]  Robert J. Schalkoff,et al.  Artificial neural networks , 1997 .

[12]  Mirko Ficko,et al.  Prediction of surface roughness with genetic programming , 2004 .

[13]  Aysun Sagbas,et al.  Analysis and optimization of surface roughness in the ball burnishing process using response surface methodology and desirabilty function , 2011, Adv. Eng. Softw..

[14]  H. F. Al-Jalil,et al.  Burnishing force and number of ball passes for the optimum surface finish of brass components , 1998 .

[15]  William G. Cochran,et al.  Experimental designs, 2nd ed. , 1957 .

[16]  Byeongho Kim,et al.  The Application of Neural Networks and Statistical Methods to Process Design in Metal Forming Processes , 1999 .

[17]  Ping Zhang,et al.  Effect of roller burnishing on the high cycle fatigue performance of the high-strength wrought magnesium alloy AZ80 , 2005 .

[18]  Pragnesh K Brahmbhatt,et al.  Surface Roughness Prediction for Roller Burnishing of Al Alloy 6061 Using Response Surface Method , 2015 .

[19]  Ridha Amamou,et al.  Ground surface roughness prediction based upon experimental design and neural network models , 2006 .

[20]  H. Haldun Goktas,et al.  Burnishing process on al-alloy and optimization of surface roughness and surface hardness by fuzzy logic , 2009 .