Comparative evaluation of machine learning models for surface roughness prediction in WEDM of SKD61 under limited data conditions
Tóm tắt: 0
| 
PDF: 1 
##plugins.themes.academic_pro.article.main##
Author
Từ khóa:
WEDM
Độ nhám
Máy học cực đại
Mạng nơ-ron nhân tạo
Hồi quy rừng ngẫu nhiên
SKD61
Tóm tắt
Surface roughness (Ra) is a key quality indicator in Wire Electrical Discharge Machining (WEDM) of SKD61 tool steel. This study compares three machine learning models, Artificial Neural Networks (ANN), Random Forest Regression (RFR), and Extreme Learning Machine (ELM), for Ra prediction under limited data conditions. Experimental data were obtained using a Taguchi L27 design with pulse-on time, pulse-off time, servo voltage, and wire feed rate as input variables. To assess model robustness, nine additional experiments outside the original design were conducted for independent validation. Model performance was evaluated using R², MAE, RMSE, and MAPE. Results showed that ELM provided favourable predictive performance, with a validation MAPE of 0.85%, compared with ANN and RFR under the investigated conditions. The proposed ELM-based framework provides a promising and computationally efficient approach for surface roughness prediction under limited-data WEDM conditions.
Tài liệu tham khảo
-
[1] K. Ho, S. Newman, S. Rahimifard, and R. D. Allen, “State of the art in wire electrical discharge machining (WEDM),” Int. J. Mach. Tools Manuf., vol. 44, pp. 1247–1259, 2004. https://doi.org/10.1016/j.ijmachtools.2004.04.017
[2] K. P. Rajurkar, M. M. Sundaram, and A. P. Malshe, “Review of Electrochemical and Electrodischarge Machining,” Procedia CIRP, vol. 6, pp. 13–26, 2013. https://doi.org/10.1016/j.procir.2013.03.002
[3] D. Scott, S. Boyina, and K. P. Rajurkar, “Analysis and optimization of parameter combinations in wire electrical discharge machining,” Int. J. Prod. Res., vol. 29, pp. 2189–2207, 1991. https://doi.org/10.1080/00207549108948078
[4] T. A. Spedding and Z. Q. Wang, “Parametric optimization and surface characterization of wire electrical discharge machining process,” Precis. Eng., vol. 20, pp. 5–15, 1997. https://doi.org/10.1016/S0141-6359(97)00003-2
[5] M. Rozenek, J. Kozak, L. Dabrowski, and K. Lubkowski, “Electrical discharge machining characteristics of metal matrix composites,” J. Mater. Process. Technol., vol. 109, pp. 367–370, 2001. https://doi.org/10.1016/S0924-0136(00)00823-2
[6] S. S. Mahapatra and A. Patnaik, “Optimization of wire electrical discharge machining (WEDM) process parameters using Taguchi method,” The International Journal of Advanced Manufacturing Technology, vol. 34, pp. 911–925, 2006. https://doi.org/10.1007/S00170-006-0672-6
[7] N. Naeim, M. A. AbouEleaz, and A. Elkaseer, “Experimental Investigation of Surface Roughness and Material Removal Rate in Wire EDM of Stainless Steel 304,” Materials, vol. 16, pp. 1022–1038, 2023. https://doi.org/10.3390/ma16031022
[8] V. Aggarwal, S. S. Khangura, and R. K. Garg, “Parametric modeling and optimization for wire electrical discharge machining of Inconel 718 using response surface methodology,” The International Journal of Advanced Manufacturing Technology, vol. 79, pp. 31–47, 2015. https://doi.org/10.1007/S00170-015-6797-8
[9] P. N. Q. Huy, T. Kha, T. B. Loc, N. Van Cuong, N. D. Tu, and H. T. Thuong, “Studying the effects of cutting parameters on surface roughness in milling of aluminium alloy using the Taguchi method,” The University of Danang - Journal of Science and Technology, vol. 23, no. 11, pp. 54–59, 2025. https://doi.org/10.31130/UD-JST.2025.23(11).331
[10] M. A. Abdullah, B. A. Ahmed, and S. K. Ghazi, “Enhancing of Material Removal Rate and Surface Roughness in Wire EDM Process using Grey Relational Analysis,” Engineering, Technology & Applied Science Research, vol. 14, pp. 17422–17427, 2024. https://doi.org/10.48084/etasr.8450
[11] G. Bin Huang, Q. Y. Zhu, and C. K. Siew, “Extreme learning machine: Theory and applications,” Neurocomputing, vol. 70, pp. 489–501, 2006. https://doi.org/10.1016/j.neucom.2005.12.126
[12] T. Thankachan et al., “Prediction of surface roughness and material removal rate in wire electrical discharge machining on aluminum based alloys/composites using Taguchi coupled Grey Relational Analysis and Artificial Neural Networks,” Appl. Surf. Sci., vol. 472, pp. 22–35, 2019. https://doi.org/10.1016/j.apsusc.2018.06.117
[13] M. Ulas, O. Aydur, T. Gurgenc, and C. Ozel, “Surface roughness prediction of machined aluminum alloy with wire electrical discharge machining by different machine learning algorithms,” Journal of Materials Research and Technology, vol. 9, pp. 12512–12524, 2020. https://doi.org/10.1016/j.jmrt.2020.08.098
[14] S. Shakeri, A. Ghassemi, M. Hassani, and A. Hajian, “Investigation of material removal rate and surface roughness in wire electrical discharge machining process for cementation alloy steel using artificial neural network,” The International Journal of Advanced Manufacturing Technology, vol. 82, pp. 549–557, 2015. https://doi.org/10.1007/S00170-015-7349-Y
[15] G. Zhang, Z. Zhang, J. Guo, W. Ming, M. Li, and Y. Huang, “Modeling and Optimization of Medium-Speed WEDM Process Parameters for Machining SKD11,” Materials and Manufacturing Processes, vol. 28, pp. 1124–1132, 2013. https://doi.org/10.1080/10426914.2013.773024
[16] U. M. R. Paturi, S. Cheruku, S. Salike, V. P. K. Pasunuri, and N. S. Reddy, “Estimation of machinability performance in wire-EDM on titanium alloy using neural networks,” Materials and Manufacturing Processes, vol. 37, pp. 1073–1084, 2022. https://doi.org/10.1080/10426914.2022.2030875
[17] C. Naresh, P. S. C. Bose, and C. S. P. Rao, “Artificial neural networks and adaptive neuro-fuzzy models for predicting WEDM machining responses of Nitinol alloy: comparative study,” SN Applied Sciences, vol. 2, pp. 314–337, 2020. https://doi.org/10.1007/S42452-020-2083-Y
[18] H. T. Thuong and N. Van Cuong, “Prediction of surface roughness in finish milling of 6061 aluminium alloy using artificial neural network and extreme learning machine,” The University of Danang - Journal of Science and Technology, vol. 24, no. 3, pp. 87–93, 2026. https://doi.org/10.31130/UD-JST.2026.24(3).724E
[19] L. Breiman, “Random forests,” Mach. Learn., vol. 45, pp. 5–32, 2001. https://doi.org/10.1023/A:1010933404324
[20] S. Ding, X. Xu, and R. Nie, “Extreme learning machine and its applications,” Neural Computing and Applications, vol. 25, pp. 549–556, 2013. https://doi.org/10.1007/S00521-013-1522-8
[21] G. Bin Huang, D. H. Wang, and Y. Lan, “Extreme learning machines: a survey,” International Journal of Machine Learning and Cybernetics, vol. 2, pp. 107–122, 2011. https://doi.org/10.1007/s13042-011-0019-y
[22] H. T. Thuong, C. H. Tien, and N. D. Tu, “Integrated PSI–Pareto front-based multi-objective optimisation of WEDM parameters for SKD61 tool steel,” International Journal of Advanced Technology and Engineering Exploration, 2026. Accepted 18/06/2026.
[23] S. H. Yeh, L. H. Chiu, Y. T. Pan, and S. C. Lin, “Relative Dimensional Change Evaluation of Vacuum Heat-Treated JIS SKD61 Hot-Work Tool Steels,” Journal of Materials Engineering and Performance, vol. 23, pp. 2075–2082, 2014. https://doi.org/10.1007/S11665-014-0961-4
[24] M. Wang, Y. Wu, Q. Wei, and Y. Shi, “Thermal Fatigue Properties of H13 Hot-Work Tool Steels Processed by Selective Laser Melting,” Metals, vol. 10, pp. 116–126, 2020. https://doi.org/10.3390/MET10010116
[25] H. Nguyen Le Dang, V. T. Nguyen, V. H. Hoang, X. T. Vo, and V. T. T. Nguyen, “Durability Comparison of SKD61 and FDAC Steel Mold Inserts in High-Pressure Die-Casting Process,” Machines, vol. 13, pp. 352–365, 2025. https://doi.org/10.3390/MACHINES13050352
[26] A. Muttamara and P. Nakwong, “Enhancing Wire-EDM Performance with Zinc-Coated Brass Wire Electrode and Ultrasonic Vibration,” Micromachines, vol. 14, pp. 862–876, 2023. https://doi.org/10.3390/MI14040862
[27] J. Wang, S. Lu, S. H. Wang, and Y. D. Zhang, “A review on extreme learning machine,” Multimedia Tools and Applications, vol. 81, pp. 41611–41660, 2022. https://doi.org/10.1007/S11042-021-11007-7
[28] F. J. Pontes, J. R. Ferreira, M. B. Silva, A. P. Paiva, and P. P. Balestrassi, “Artificial neural networks for machining processes surface roughness modeling,” The International Journal of Advanced Manufacturing Technology, vol. 49, pp. 879–902, 2009. https://doi.org/10.1007/S00170-009-2456-2
[29] C. M. Bishop, Pattern Recognition and Machine Learning. Springer, New York, NY, 2006.
[30] S. Kumar, A. Batish, R. Singh, and T. P. Singh, “A hybrid Taguchi-artificial neural network approach to predict surface roughness during electric discharge machining of titanium alloys,” Journal of Mechanical Science and Technology, vol. 28, pp. 2831–2844, 2014. https://doi.org/10.1007/S12206-014-0637-X
[31] Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015. https://doi.org/10.1038/nature14539
[32] G. B. Huang, H. Zhou, X. Ding, and R. Zhang, “Extreme Learning Machine for Regression and Multiclass Classification,” IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 42, pp. 513–529, 2012. https://doi.org/10.1109/TSMCB.2011.2168604
[33] U. M. R. Paturi, H. Devarasetti, N. S. Reddy, N. Kotkunde, and B. K. Patle, “Modeling of surface roughness in wire electrical discharge machining of Inconel 718 using artificial neural network,” Mater. Today Proc., vol. 38, pp. 3142–3148, 2021. https://doi.org/10.1016/j.matpr.2020.09.503
[34] S. Sarkar, S. Mitra, and B. Bhattacharyya, “Parametric optimisation of wire electrical discharge machining of γ titanium aluminide alloy through an artificial neural network model,” The International Journal of Advanced Manufacturing Technology, vol. 27, pp. 501–508, 2006. https://doi.org/10.1007/S00170-004-2203-7
Xem thêm
##plugins.themes.academic_pro.article.sidebar##
Đã Xuất bản
Jun 30, 2026
Download
Cách trích dẫn
Thuong, H. T., H.-T. Cao, và D.-T. Nguyen. “Comparative Evaluation of Machine Learning Models for Surface Roughness Prediction in WEDM of SKD61 under Limited Data Conditions”. Tạp Chí Khoa học Và Công nghệ Đại học Đà Nẵng, vol 24, số p.h 6A, Tháng Sáu 2026, tr 15-23, doi:10.31130/ud-jst.2026.24(6A).331E.
