Prediction of Surface Roughness in Magneto Rheological Abrasive Flow Finishing Process by Artificial Neural Networks and Regression Analysis

Abstract:

In this study, to predict the surface roughness of stainless steel-304 in Magneto rheological Abrasive flow finishing (MRAFF) process, an artificial neural network (ANN) and regression models have been developed. In this models, the parameters such as hydraulic pressure, current to the electromagnet and number of cycles were taken as variables of the model.Taguchi’s technique has been used for designing the experiments in order to observe the different values of surface roughness . A neural network with feed forward with the help of back propagation was made up of 27 input neurons, 7 hidden neurons and one output neuron. The 6 sets of experiments were randomly selected from orthogonal array for training and residuals were used to analyze the performance. To check the validity of regression model and to determine the significant parameter affecting the surface roughness, Analysis of variance (ANOVA) and F-test were made. The numerical analysis depict that the current to the electromagnet was an paramount parameter on surface roughness.Key words: MRAFF, ANN, Regression analysis

• Periodical: Applied Mechanics and Materials (Volumes 766-767)
• Pages: 1076-1084
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.766-767.1076
• Online since: June 2015
• Authors: S. Kathiresan*, K. Hariharan, B. Mohan
• Keywords: ANN, MRAFF, Regression Analysis

References

[1] T. Shimura,K. Takazawa,E. Hatano, Study of magnetic abrasive finishing, Annals of CIRP 39(1) (1990) 325-328.

DOI: 10.1016/s0007-8506(07)61064-6

[2] Y. Tani,K. Kawata, Development of high-efficient fine finshing process using magnetic fluid, Annals of CIRP 33 (1) (1984) 217-220.

DOI: 10.1016/s0007-8506(07)61412-7

[3] W. Korodonski, D. Golini, Progress update in magnetorheological finishing, International journal of Modern Physics B 13 (14-16) (1999) 2205-2212.

DOI: 10.1142/s0217979299002320

[4] L.J. Rhoads, Abrasive flow machining, Manufacturing Engineering, November (1988) 75-78.

[5] V.K. Jain S.G. Adsul, Experimental investigations into abrasive flow machining, International Journal of Machine Tool and Manufacture 40 (2001) 1003-1021.

DOI: 10.1016/s0890-6955(99)00114-5

[6] W.I. Korodonski, S.D. Jacobs, Magnetorheological finishing, International Journal of modern Physica B 10 (23, 24) (1996) 2837-2838.

[7] Jha Sunil, Jain V.K., Design and Development of Magnetorheological Abrasive Flow Finishing Process, International Journal of Machine tool and Manufacture, Volume 44, Issue 10 , August 2004, pages 1019-1029.

DOI: 10.1016/j.ijmachtools.2004.03.007

[8] Rainbow J., The Magnetic Fluid clutch, AIEE Trans. 67 (1948) 1308.

[9] Klingenberg D. J., Magnetorheology: Applications and challenges, AIChE Journal 47 (2) (2001) 246-249.

DOI: 10.1002/aic.690470202

[10] Azouzi, R., Guillot, M., 1999. On-line prediction of surface finish and dimensional deviations in turning using neural network based sensor fusion. Int. J. Mach. Tool Manuf. 37 (9), 1201–1217.

DOI: 10.1016/s0890-6955(97)00013-8

[11] Huang, J.T., Liao, Y.S., Hsue, W.J., 1999. Determination of finish –cutting operation number and machining – parameters settings in wire electrical discharge machining. J. Mater. Process. Technol. 87, 69–81.

DOI: 10.1016/s0924-0136(98)00334-3

[12] Jegaraj, J.J.R., Babu, N.R., 2007. A soft approach for controlling the quality of cut with abrasive waterjet cutting system experiencing orifice and focusing tube wear. J. Mater. Process. Technol. 185, 217–227.

DOI: 10.1016/j.jmatprotec.2006.03.124

[13] Ko, D.C., Kim, D.H., Kim, B.M., 1999. Application of neural network and Taguchi method to perform design in metal forming considering workability. Int. J. Mach. Tool. Manuf. 39, 771–785.

DOI: 10.1016/s0890-6955(98)00055-8

[14] Lee, B.Y., Liu, H.S., Tarng, Y.S., 1998. Modeling and optimization of drilling process. J. Mater. Process. Technol. 74, 149–157.

[15] Lin, B.T., Jean, M.D., Chou, J.H., 2007. Using response surface methodology for optimizing deposited partially stabilized zirkonia in plasma spraying. Appl. Surf. Sci. 253, 3254–3262.

DOI: 10.1016/j.apsusc.2006.07.021

[16] Liu, T.C., Li, R.K., Chen, M.C., 2006. Development of an artificial neural network to predict lead frame dimensions in an etching process. Int. J. Adv. Manuf. Technol. 27, 1211–1216.

DOI: 10.1007/s00170-004-2310-5

[17] Nalbant, M., G¨okkaya, H., Sur, G., 2007. Application of Taguchi method in the optimization of cutting parameters for surface roughness in turning. Mater. Des. 28, 1379–1385.

DOI: 10.1016/j.matdes.2006.01.008

[18] Ozc，elik, B., Oktem, H., Kurtaran, H., 2005. Optimum surface roughness in end milling Inconel 718 by coupling neural network model and genetic algorithm. Int. J. Adv. Manuf. Technol. 27, 234–241.

DOI: 10.1007/s00170-004-2175-7

[19] Ozel, T., Karpat, Y., 2005. Predictive modeling of surface roughness and tool wear in turning using regression and neural networks. Int. J. Mach. Tool Manuf. 45, 467–479.

DOI: 10.1016/j.ijmachtools.2004.09.007

[20] Singh, A.K., Panda, S.S., Pal, S.K., Chakraborty, D., 2006. Prediction drill wear using an artificial neural network. Int. J. Adv. Manuf. Technol. 28, 456–462.

DOI: 10.1007/s00170-004-2376-0

[21] Spedding, T.A., Wang, Z.Q., 1997. Study on modeling of wire EDM process. J. Mater. Process. Technol. 69, 18–28.

[22] Tosun, N., Cogun, C., 2003. An investigation on wire wear in WEDM. J. Mater. Process. Technol. 134, 273–278.

DOI: 10.1016/s0924-0136(02)01045-2

[23] Tosun, N., Ozler, L., 2002. A study of tool life in hot machining using artificial neural networks and regression analysis method. J. Mater. Process. Technol. 124, 99–104.

DOI: 10.1016/s0924-0136(02)00086-9

[24] Tsai, Chen, C., Lou, S.J., 1999. In in-process surface recognition system based on neural networks in end milling cutting operations. Int. J. Mach. Tool Manuf. 39, 583–605.

DOI: 10.1016/s0890-6955(98)00053-4

[25] http: /en. wikipedia. org/wiki/Neural network.

[26] http: /www. doc. ic. ac. uk/nd/surprise96/journal/vol4/csll/report. html.