Application of Machine Learning Techniques for Multi Objective Optimization of Response Variables in Wire Cut Electro Discharge Machining Operation

Abstract:

Wire Cut Electrical Discharge Machining (WEDM) is a non-conventional thermal machining process which is capable of accurately machine alloys having high hardness or part having complex shapes that are very difficult to be machined by the conventional machining processes. The WEDM finds applications in automobiles, aero–space, medical instruments, tool and die industries, etc. The input parameters considered for WEDM are pulse on time, pulse off time, flushing pressure, servo voltage, wire feed rate and wire tension. Performance of WEDM is mainly assessed by output variables such as, material removal rate (MRR), kerf width (Kw) and surface roughness (Ra) of the work piece being machined. Looking at the need of a suitable optimization model, the present work explores the feasibility of machine learning concepts to predict optimum surface roughness and kerf width simultaneously by making use of experimental data available in the literature for machining of Hastelloy C– 276 using WEDM. In most of the literatures, single objective optimization has been carried out for predicting optimum cutting parameters for WEDM. Hence, the present work presents a methodology that makes use of a machine learning algorithm namely, gradient descent method as an optimization technique to optimize both surface roughness and kerf width simultaneously (multi objective optimization) and compare the results with the existing literatures. It was observed that the input parameters such as pulse on time, pulse off time, and peak current have significant effect on both surface roughness and kerf width. The gradient descent method was successfully used for predicting the optimum values of response variables.

• Periodical: Materials Science Forum (Volume 969)
• Pages: 800-806
• DOI: https://doi.org/10.4028/www.scientific.net/MSF.969.800
• Online since: August 2019
• Authors: Sidharth Kumar Shukla, Amrita Priyadarshini*
• Keywords: Gradient Descent Method, Kerf Width, Normal Equation, Surface Roughness, WEDM

References

[1] Chen J., Wang J.-Z., Yan F.-Y. and Zhang Q., Corrosion wear synergistic behavior of Hastelloy C276 alloy in artificial seawater, Transactions of Nonferrous Metals Society of China, 25 (2015) 661-668.

DOI: 10.1016/s1003-6326(15)63650-0

[2] Xu K. , Zou B.,  Huang C., Yao Y., Zhou H. and Liu Z., Machinability of Hastelloy C-276 using Hot-pressed sintered Ti(C7N3)-based cermet cutting tools, Chinese Journal of Mechanical Engineering, 28 (2015), 599–606.

DOI: 10.3901/cjme.2015.0316.031

[3] Mahapatra S. and Patnaik A., Optimization of Wire Electrical Discharge Machining (WEDM) Process Parameters Using Taguchi Methods, International Journal of Advance Manufacturing Technology, 34 (2006) 911-925.

DOI: 10.1007/s00170-006-0672-6

[4] Huang J. T., Liao Y. S and Hsue W. J., Determination of Finish-Cutting Operation Number and Machining-Parameters Setting in Wire Electrical Discharge Machining, Journal of Materials Processing Technology, 87 (1999) 69–81.

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

[5] Liao Y. S. and Yu Y. P., Study of Specific Discharge Energy in WEDM and its Application, International Journal of Machine Tools and Manufacture, 44 (2004) 1373–1380.

DOI: 10.1016/j.ijmachtools.2004.04.008

[6] Patil N. G.,  Brahmankar P. K. and  Navale L. G., On the Optimisation Into Wire Electro-Discharge Machining of Al/Al2O3P, ASME International Mechanical Engineering Congress and Exposition, USA, (2007) 573-582.

DOI: 10.1115/imece2007-41775

[7] Patil N. G.,  Brahmankar P. K. and  Navale L. G., Some Investigations Into Multi-Objective Optimization of Wire Electro-Discharge Machining of Al/SiCp Composites, ASME International Manufacturing Science and Engineering Conference Atlanta, (2007) 967-974.

DOI: 10.1115/msec2007-31060

[8] Puri Y. M. and  Deshpande N. V., Parametric Optimization of WEDM of High Chromium High Carbon Die Steel Using ANN, International Mechanical Engineering Congress and Exposition Manufacturing Engineering and Textile Engineering Chicago, (2006) 167-175.

DOI: 10.1115/imece2006-14306

[9] Gonchikar U.,  Venkatadas R. H.,  Prakash N. and Dev G. V.,  Ramaiah K. and  Gudekota G., Comparison of Machining Performances in Wire EDM for HCHCr Material Using Group Method Data Handling Technique and Artificial Neural Network, International Mechanical Engineering Congress and Exposition Volume 2A, Advanced Manufacturing Houston, Texas, USA, (2015).

DOI: 10.1115/imece2015-50588

[10] Ubaid A. M.,  Dweiri F. T.,  Aghdeab S. H. and Al-Juboori L. A., Optimization of Electro Discharge Machining Process Parameters With Fuzzy Logic for Stainless Steel 304 (ASTM A240), Journal of Manufacturing Science and Engineering 140 (2017).

DOI: 10.1115/1.4038139

[11] Jain P. S , Venkatadas R. H.,  Prakash N., Dev G. V. and  Gonchikar U., Estimation and Comparison of Acoustic Emission Parameters and Surface Roughness in Wire Cut Electric Discharge Machining of Stavax Material Using Multiple Regression Analysis and Group Method Data Handling Technique, ASME International Mechanical Engineering Congress and Exposition Volume 2A: Advanced Manufacturing Houston, Texas, USA (2015).

DOI: 10.1115/imece2015-50596

[12] Majumder H. and Maity K., Prediction and optimization of surface roughness and micro-hardness using grnn and MOORA-fuzzy-a MCDM approach for nitinol in WEDM, Measurement, 118 (2018), 1-13.

DOI: 10.1016/j.measurement.2018.01.003

[13] Panner Selvam M. and Kumar P. R, Optimization Kerf Width and Surface Roughness in Wire cut Electrical Discharge Machining Using Brass Wire, Mechanics and Mechanical Engineering Vol. 21, No. 1 (2017) 37–55.

DOI: 10.1016/j.matpr.2020.02.955

[14] Shwartz S. S. and David S. B., Understanding Machine Learning: From Theory to Algorithms, Cambtidge University Press, (2014).