Optimization of Wire Electrical Discharge Machining (WEDM) Process Parameters Using Neuro-Regression Analysis for Fabrication of Precision Electrodes with Complex Shapes

Abstract

The wire electrical discharge process is extremely important in the fabrication of complex electrodes with delicate structures. Identifying optimal operating combinations is a challenge in industry due to the large number of process variables. To overcome this difficulty, neuro-regression analysis was used and optimization was performed. Various regression models have been tested in the literature using 𝑅^2𝑡𝑟𝑎𝑖𝑛𝑖𝑛𝑔, 𝑅^2𝑡𝑒𝑠𝑡𝑖𝑛𝑔, 𝑎𝑛𝑑 𝑅^2𝑣𝑎𝑙𝑖𝑑𝑎𝑡𝑖𝑜n. Multiple regression model types including linear, quadratic, trigonometric and rational forms were tested. Taguchi design and regression analysis were used to test the output-input models in the reference study. In this study, twelve regression models with six parameters were tested. These parameters are discharge current, pulse duration, pulse frequency, wire speed, wire tension and dielectric flow rate. The study shows that WEDM process parameters can be adjusted to achieve better surface finish and cutting width at the same time. The process is optimized by minimizing kerf and surface roughness. Optimization results are 0.17044 mm for kerf and 3.60393 µm for surface roughness. It is seen that the processing model is suitable and the optimization technique meets the practical requirements.

Keywords

• WEDM
• neuro-regression analysis
• optimization
• kerf
• surface roughness

References

1. [1] Khatri, Bharat C., and Rathod, Pravin P. (2017) . “Investigations on the performance of concentric flow dry wire electric discharge machining (WEDM) for thin sheets of titanium alloy. ” Int J Adv Manuf Technol SpringerVerlag London , 92,1945–1954.
2. [2] Saha, A., and Mondal, S. C. (2016). “ Experimental investigation and modelling of WEDM process for machining nano-structured hardfacing material. ” J Braz. Soc. Mech. Sci. Eng. The Brazilian Society of Mechanical Sciences and Engineering 2, 39, 3439–3455.
3. [3] Kumar, A., Grover N., Manna, A., Kumar, R., Chohan J. S., Singh, S., Singh, S., and Prunchu, C. L. (2021). “Multi‑Objective Optimization of WEDM of Aluminum Hybrid Composites Using AHP and Genetic Algorithm. ” Arabian Journal for Science and Engineering Crown 2.
4. [4] Shihab, K. (2018). “Optimization of WEDM Process Parameters for Machining of Friction-Stir-Welded 5754 Aluminum Alloy Using Box–Behnken Design of RSM.” Arabian Journal for Science and Engineering King Fahd University of Petroleum & Minerals , 43, 5017-5027.
5. [5] Ming, W., Hou, J., Zhang, Z., Huang, H., Xu, Z., Zhang, G., and Huang, Y. (2015). “Integrated ANN-LWPA for cutting parameter optimization in WEDM.” Int J Adv Manuf Technol Springer-Verlag London , 84, 1277–1294.
6. [6] Majumder, H., and Maity, K. P. (2018) “Predictive Analysis on Responses in WEDM of Titanium Grade 6 Using General Regression Neural Network (GRNN) and Multiple Regression Analysis (MRA).” Silicon Springer Science+Business Media B.V. 2018, 10,1763–1776.
7. [7] Phate, M. R., Toney, S. B., and Phate, V. R. (2020). “Multi-parametric Optimization of WEDM Using Artificial Neural Network (ANN)-Based PCA for Al/SiCp MMC.” J. Inst. Eng. India Ser. C The Institution of Engineers (India) , 102(1), 169–181.
8. [8] Mouralova, K., Kovar, J., Klakurkova, L.,and Prokes, T. (2018). “Effect of Width of Kerf on Machining Accuracy and Subsurface Layer After WEDM.” JMEPEG ASM International, 27(4), 1908-1916.

9. [9] Han, F., Jiang, J., Yu, D. (2006). “Influence of machining parameters on surface roughness in finish cut of WEDM.” Int J Adv Manuf Technol Springer-Verlag London Limited, 34, 538–546.
10. [10] Manjaiah, M., Laubscher, R. F., Kumar, A., and Basavarajappa, S. (2016). “Parametric optimization of MRR andsurface roughness in wire electro dischargemachining (WEDM) of D2 steel using Taguchi-based utility approach.” International Journal of Mechanical and Materials Engineering Springer-Verlag London Limited, 11(7), 237-248.
11. [11] Polatoğlu, I., Aydın, L., Nevruz, B. Ç.,and Öze, S. (2020). “A Novel Approach for the Optimal Design of a Biosensor.” Analytical Letters Taylor & Francis Group, LLC.
12. [12] Akcair, M., Savran, M., Aydın, L., Ayakdas, O., Ozturk, S.,and Kucukdogan, N. (2019) “Optimum design of anti-buckling behaviour of graphite/epoxy laminated composites by differential evolution and simulated annealing method. ” Research on Engineering Structures and Materials, 5, 175–88.
13. [13] Zhang, Y., Price, C. J., Coope, I. D., Byatt, D. (2002). “A Convergent Variant of the Nelder–Mead Algorithm.” JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS Plenum Publishing Corporation, 113(1), 5-19.
14. [14] Majumder, A., Das, A., Das, P. Kr. (2016). “A standard deviation based firefly algorithm for multiobjectiveoptimization of WEDM process during machining of Indian RAFM steel.” Neural Comput & Applic The Natural Computing Applications, 29, 665–677.
15. [15] Somashekhar, K. P., Mathew, J., & Ramachandran, N. (2012). “A feasibility approach by simulated annealing on optimization of micro-wire electric discharge machining parameters.” Int J Adv Manuf Technol SpringerVerlag London, 61, 1209–1213.
16. [16] Kaelo, P., and Alİ, M. M. (2006). “Some Variants of the Controlled Random Search Algorithm for Global Optimization.” JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS Springer Science+Business Media, Inc., 130(2), 253-264.