Surface Roughness Prediction Modelling for WEDM of AA6063 Using Support Vector Machine Technique

Abstract:

This research work presents an incorporated approach to modelling of WEDM of AA6063 (armour applications) using support vector machine technique. The experimental investigation has been carried out with four input variables namely pulse-on-time (P_on), pulse-off-time (P_off), servo-voltage (V_S) and peak-current (I_P). Surface roughness is measured as response parameter. The experimental runs are designed according to 3^k full factorial design (k is number of input variables). It is apparent from this study that values anticipated by developed model are found closer to experimental results. Thus, it ensures appropriateness of model for prediction purpose and smart manufacturing. Machined surfaces are also examined by SEM to critically evaluate the process.

• Periodical: Materials Science Forum (Volume 969)
• Pages: 607-612
• DOI: https://doi.org/10.4028/www.scientific.net/MSF.969.607
• Online since: August 2019
• Authors: Thakur Singh*, Pawan Kumar, J.P. Misra
• Keywords: Support Vector Machine, Surface Roughness, Wire-EDM

References

[1] M.Y. Ali, A. Banu, M. Salehan, E.Y.T. Adesta, M. Hazza, M. Shaffiq, Dimensional accuracy in dry micro wire electrical discharge machining, J. Mech. Engg. Sci. 12 (2018) 3321-3329.

[2] B. Singh, J.P. Misra, A critical review of wire electric discharge machining, DAAAM International Scientific Book, 2016, pp.249-266.

DOI: 10.2507/daaam.scibook.2016.23

[3] E.C. Jamson, Electrical Discharge Machining. Michigan: E-Publishing Inc; (2001).

[4] S. Sarkar, R. Ranjan, A. Das, Optimization of machine process parameters on material removal rate in EDM for AISI P20 tool steel material using RSM. J. Mat. Sci. Mech. Engg, 2 (2015) 117-122.

[5] V. Singh, R. Bhandari, V.K. Yadav, An experimental investigation on machining parameters of AISI D2 steel using WEDM. Int. J. Adv. Manuf. Tech. 93 (2017) 203-214.

DOI: 10.1007/s00170-016-8681-6

[6] B. Singh and J. P. Misra, Empirical modeling of average cutting speed during WEDM of gas turbine alloy, ICDME, MATEC Web of Conferences, vol. 221, 01002, (2018).

DOI: 10.1051/matecconf/201822101002

[7] B. Singh and J. P. Misra, Empirical modeling of average cutting speed during WEDM of hastelloy C22, ICMMM MATEC Web of Conferences, vol. 249, 02003, (2018).

DOI: 10.1051/matecconf/201824902003

[8] B. Singh and J. P. Misra, Empirical modelling of wear ratio during WEDM of nimonic 263, Mat. Today: Proceed., vol. 5, pp.23612-23618, (2018).

DOI: 10.1016/j.matpr.2018.10.150

[9] B. Singh and J. P. Misra, Surface finish analysis of wire electric discharge machined specimens by RSM and ANN modeling, Measurement, vol. 137, pp.225-237, (2019).

DOI: 10.1016/j.measurement.2019.01.044

[10] T. Singh, J.P. Misra, B. Singh, Experimental investigation of influence of process parameters on MRR during WEDM of Al6063 alloy, 5th Int. Conf. Mat. Proc. Charac. Mat. Today: Proceed. Hyderabad, India, 2016, p.2242–2247.

DOI: 10.1016/j.matpr.2017.02.071

[11] T. Singh, J.P. Misra, V. Upadhyay, P.S. Rao, An adaptive neuro-fuzzy inference system (ANFIS) for Wire-EDM of ballistic grade aluminium alloy, Int. J. Auto. Mech. Engg. 15 (2018) 5295-5307.

DOI: 10.15282/ijame.15.2.2018.11.0408

[12] V.K. Jain, Advanced Machining Processes, third ed., New Delhi, (2002).

[13] S.R. Gunn, M. Brown, K.M. Bossly, Network performance assessment for neuro-fuzzy data modeling, Intelligent Data Analysis, 1208 (1997) 313–323.

[14] S. Cho, S. Asfour, A. Onar, N. Kaundinya, Tool breakage detection using support vector machine learning in a milling process, Int. J. Mach. Tools Manuf. 45 (2005) 241–249.

DOI: 10.1016/j.ijmachtools.2004.08.016

[15] P. Bhattacharyya, S.K. Sanadhya, Support vector regression based tool wear assessment in face milling, In: Proceed. IEEE int. Conf. Ind. Tech. New York, 2468–2473, (2006).

DOI: 10.1109/icit.2006.372659