Home Technology Surface roughness prediction of wire electric discharge machining (WEDM)-machined AZ91D magnesium alloy using multilayer perceptron, ensemble neural network, and evolving product-unit neural network
Article
Licensed
Unlicensed Requires Authentication

Surface roughness prediction of wire electric discharge machining (WEDM)-machined AZ91D magnesium alloy using multilayer perceptron, ensemble neural network, and evolving product-unit neural network

  • Turan Gurgenc

    Turan Gurgenc was born in 1983. He received his PhD degree from the Mechanical Engineering Department of the Firat University in 2017. He is an associate professor in Automotive Engineering Department, Firat University, Turkey. His research interests include surface coating, wear analysis, friction, manufacturing, and machine learning.

     ORCID logo EMAIL logo     and Osman Altay

    Osman Altay was born in 1988. He received his BS degree from the Department of Electronic Computer Education of the Selcuk University, Turkey, in 2011. He received his PhD in software engineering from the Firat University, Turkey, in 2020. He is an assistant professor at the Department of Software Engineering, Manisa Celal Bayar University, Turkey. His research interests include data mining, bioinformatics, machine learning, and data science.

     ORCID logo
Published/Copyright: March 16, 2022
Become an author with De Gruyter Brill
Submit Manuscript Author Information
Materials Testing
From the journal Materials Testing Volume 64 Issue 3

Abstract

Magnesium (Mg) alloy parts have become very interesting in industries due to their lightness and high specific strengths. The production of Mg alloys by conventional manufacturing methods is difficult due to their high affinity for oxygen, low melting points, and flammable properties. These problems can be solved using nontraditional methods such as wire electric discharge machining (WEDM). The parts with a quality surface have better properties such as fatigue, wear, and corrosion resistance. Determining the surface roughness (SR) by analytical and experimental methods is very difficult, time-consuming, and costly. These disadvantages can be eliminated by predicting the SR with artificial intelligence methods. In this study, AZ91D was cut with WEDM in different voltage (V), pulse-on-time (µs), pulse-off-time (µs), and wire speed (mm s−1) parameters. The SR was measured using a profilometer, and a total of 81 data were obtained. Multilayer perceptron, ensemble neural network and optimization-based evolving product-unit neural network (EPUNN) were used to predict the SR. It was observed that the EPUNN method performed better than the other two methods. The use of this model in industries producing Mg alloys with WEDM expected to provide advantages such as time, material, and cost.

Keywords: ensemble neural network; evolutionary neural network; multilayer perceptron; surface roughness; wire electrical discharge machining
Corresponding author: Turan Gurgenc, PhD, Automotive Engineering Department, Firat University, Elazig, 23119, Turkey, E-mail:

Funding source: Firat University Research Fund (FUBAP)

Award Identifier / Grant number: FUBAP-TEKF.21.02

About the authors

Turan Gurgenc

Turan Gurgenc was born in 1983. He received his PhD degree from the Mechanical Engineering Department of the Firat University in 2017. He is an associate professor in Automotive Engineering Department, Firat University, Turkey. His research interests include surface coating, wear analysis, friction, manufacturing, and machine learning.

Osman Altay

Osman Altay was born in 1988. He received his BS degree from the Department of Electronic Computer Education of the Selcuk University, Turkey, in 2011. He received his PhD in software engineering from the Firat University, Turkey, in 2020. He is an assistant professor at the Department of Software Engineering, Manisa Celal Bayar University, Turkey. His research interests include data mining, bioinformatics, machine learning, and data science.

  1. Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.

  2. Research funding: This study was funded by the Firat University Research Fund (grant number FUBAP-TEKF.21.02).

  3. Conflict of interest statement: The authors declare no conflicts of interest regarding this article.

References

[1] R. Viswanathan, S. Ramesh, S. Maniraj, and V. Subburam, “Measurement and multi- response optimization of turning parameters for magnesium alloy using hybrid combination of Taguchi-GRA-PCA technique,” Measurement, vol. 159, no. 107800, 2020, https://doi.org/10.1016/j.measurement.2020.Search in Google Scholar

[2] A. Rakoch, E. Monakhova, Z. Khabibullina, et al.., “Plasma electrolytic oxidation of AZ31 and AZ91 magnesium alloys: comparison of coatings formation mechanism,” J. Magnes. Alloys, vol. 8, no. 3, pp. 587–600, 2020, https://doi.org/10.1016/j.jma.2020.06.002.Search in Google Scholar

[3] C. K. Padhee, M. Masanta, and A. Mondal, “Feasibility of Al–TiC coating on AZ91 magnesium alloy by TIG alloying method for tribological application,” Trans. Nonferrous Metals Soc. China, vol. 30, no. 6, pp. 1550–1559, 2020, https://doi.org/10.1016/S1003-6326(20)65318-3.Search in Google Scholar

[4] F. Iranshahi, M. B. Nasiri, F. G. Warchomicka, and C. Sommitsch, “Corrosion behavior of electron beam processed AZ91 magnesium alloy,” J. Magnes. Alloys, vol. 8, no. 4, pp. 1314–1327, 2020, https://doi.org/10.1016/j.jma.2020.08.012.Search in Google Scholar

[5] J. Majhi and A. Mondal, “Microstructure and impression creep characteristics of squeeze-cast AZ91 magnesium alloy containing Ca and/or Bi,” Mater. Sci. Eng. A, vol. 744, pp. 691–703, 2019, https://doi.org/10.1016/j.msea.2018.12.067.Search in Google Scholar

[6] S. Chowdary, R. Dumpala, and V. Kondaiah, “Influence of heat treatment on the machinability and corrosion behavior of AZ91 Mg alloy,” J. Magnes. Alloys, vol. 6, no. 1, pp. 52–58, 2018, https://doi.org/10.1016/j.jma.2017.12.001.Search in Google Scholar

[7] B. R. Sunil, K. Ganesh, P. Pavan, et al.., “Effect of aluminum content on machining characteristics of AZ31 and AZ91 magnesium alloys during drilling,” J. Magnes. Alloys, vol. 4, no. 1, pp. 15–21, 2016, https://doi.org/10.1016/j.jma.2015.10.003.Search in Google Scholar

[8] M. K. Debta, R. Mishra, and M. Masanta, “Experimental investigation on the machining performance of AZ91D (90% Mg) alloy by wire-cut EDM,” Mater. Today Proc., vol. 33, no. 8, pp. 5557–5560, 2020, https://doi.org/10.1016/j.matpr.2020.03.540.Search in Google Scholar

[9] A. Mostafapor and H. Vahedi, “Wire electrical discharge machining of AZ91 magnesium alloy; investigation of effect of process input parameters on performance characteristics,” Eng. Res. Express, vol. 1, p. 015005, 2019, https://doi.org/10.1088/2631-8695/ab26c8.Search in Google Scholar

[10] P. Gopal, “Wire electric discharge machining of silica rich E-waste CRT and BN reinforced hybrid magnesium MMC,” Silicon, vol. 11, pp. 1429–1440, 2019, https://doi.org/10.1007/s12633-018-9951-8.Search in Google Scholar

[11] V. Kavimani, K. S. Prakash, and T. Thankachan, “Multi-objective optimization in WEDM process of graphene–SiC–magnesium composite through hybrid techniques,” Measurement, vol. 145, pp. 335–349, 2019, https://doi.org/10.1016/j.measurement.2019.04.076.Search in Google Scholar

[12] 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,” J. Mater. Res. Technol., vol. 9, no. 6, pp. 12512–12524, 2020, https://doi.org/10.1016/j.jmrt.2020.08.098.Search in Google Scholar

[13] T. B. Rao, “Optimizing machining parameters of wire-EDM process to cut Al7075/SiCp composites using an integrated statistical approach,” Adv. Manufact., vol. 4, pp. 202–216, 2016, https://doi.org/10.1007/s40436-016-0148-3.Search in Google Scholar

[14] M. Altuğ, “Investigation of material removal rate (MRR) and wire wear ratio (WWR) for alloy Ti6Al4V exposed to heat treatment processing in WEDM and optimization of parameters using Grey relational analysis,” Mater. Test., vol. 58, no. 9, pp. 794–805, 2016, https://doi.org/10.3139/120.110916.Search in Google Scholar

[15] K. Kanlayasiri and S. Boonmung, “Effects of wire-EDM machining variables on surface roughness of newly developed DC 53 die steel: design of experiments and regression model,” J. Mater. Process. Technol., vol. 192, pp. 459–464, 2007, https://doi.org/10.1016/j.jmatprotec.2007.04.085.Search in Google Scholar

[16] H. Basak and M. Yücel, “Effect of burnishing parameters on surface roughness and hardness,” Mater. Test., vol. 59, no. 1, pp. 57–63, 2017, https://doi.org/10.3139/120.110963.Search in Google Scholar

[17] P. Benardos and G.-C. Vosniakos, “Predicting surface roughness in machining: a review,” Int. J. Mach. Tools Manuf., vol. 43, no. 8, pp. 833–844, 2003, https://doi.org/10.1016/S0890-6955(03)00059-2.Search in Google Scholar

[18] A. M. Zain, H. Haron, and S. Sharif, “Prediction of surface roughness in the end milling machining using Artificial Neural Network,” Expert Syst. Appl., vol. 37, no. 2, pp. 1755–1768, 2010, https://doi.org/10.1016/j.eswa.2009.07.033.Search in Google Scholar

[19] A. Sagbas, F. Gürtuna, and U. Polat, “Comparison of ANN and RSM modeling approaches for WEDM process optimization,” Mater. Test., vol. 63, no. 4, pp. 386–392, 2021, https://doi.org/10.1515/mt-2020-0057.Search in Google Scholar

[20] P. Kumar and J. P. Misra, “Process modeling and optimization using ANN and RSM during dry turning of titanium alloy used in automotive industry,” Proc. Inst. Mech. Eng. Part D J. Automob. Eng., vol. 235, no. 7, pp. 2040–2050, 2021, https://doi.org/10.1177/0954407020969255.Search in Google Scholar

[21] K. Tyagi, S. Nguyen, R. Rawat, and M. Manry, “Second order training and sizing for the multilayer perceptron,” Neural Process. Lett., vol. 51, pp. 963–991, 2020, https://doi.org/10.1007/s11063-019-10116-7.Search in Google Scholar

[22] P. M. Kumar and R. Kavitha, “Prediction of nanofluid viscosity using multilayer perceptron and Gaussian process regression,” J. Therm. Anal. Calorim., vol. 144, no. 4, pp. 1151–1160, 2021, https://doi.org/10.1007/s10973-020-09990-4.Search in Google Scholar

[23] M. Ulas, O. Altay, T. Gurgenc, and C. Ozel, “A new approach for prediction of the wear loss of PTA surface coatings using artificial neural network and basic, kernel-based, and weighted extreme learning machine,” Friction, vol. 8, no. 6, pp. 1102–1116, 2020, https://doi.org/10.1007/s40544-017-0340-0.Search in Google Scholar

[24] E. V. Panfilova, S. V. Sidorova, and D. Y. Shramko, “Application of neural network for forecasting reliability of vacuum equipment,” in 2019 International Russian Automation Conference (RusAutoCon), Sochi, Russia, IEEE, 2019, vol. 2019, pp. 1–5.10.1109/RUSAUTOCON.2019.8867815Search in Google Scholar

[25] H. Li, X. Wang, and S. Ding, “Research and development of neural network ensembles: a survey,” Artif. Intell. Rev., vol. 49, pp. 455–479, 2018, https://doi.org/10.1007/s10462-016-9535-1.Search in Google Scholar

[26] M. Hajihassani, D. J. Armaghani, M. Monjezi, E. T. Mohamad, and A. Marto, “Blast-induced air and ground vibration prediction: a particle swarm optimization-based artificial neural network approach,” Environ. Earth Sci., vol. 74, pp. 2799–2817, 2015, https://doi.org/10.1007/s12665-015-4274-1.Search in Google Scholar

[27] J. Wu and E. Chen, “A novel nonparametric regression ensemble for rainfall forecasting using particle swarm optimization technique coupled with artificial neural network,” in International symposium on neural networks, Springer, 2009, pp. 49–58.10.1007/978-3-642-01513-7_6Search in Google Scholar

[28] Z.-S. Zhao, X. Feng, Y.-Y. Lin, et al.., “Evolved neural network ensemble by multiple heterogeneous swarm intelligence,” Neurocomputing, vol. 149, pp. 29–38, 2015, https://doi.org/10.1016/j.neucom.2013.12.062.Search in Google Scholar

[29] J. James, A. Y. Lam, and V. O. Li, “Evolutionary artificial neural network based on chemical reaction optimization,” in 2011 IEEE Congress of Evolutionary Computation (CEC), New Orleans, LA, USA, IEEE, 2011, pp. 2083–2090.10.1109/CEC.2011.5949872Search in Google Scholar

[30] A. A. Alduroobi, A. M. Ubaid, M. A. Tawfiq, and R. R. Elias, “Wire EDM process optimization for machining AISI 1045 steel by use of Taguchi method, artificial neural network and analysis of variances,” Int. J. Syst. Assur. Eng. Manag., vol. 11, no. 6, pp. 1314–1338, 2020, https://doi.org/10.1007/s13198-020-00990-z.Search in Google Scholar

[31] M. Sreenivasulu, A. Muniappan, G. Bharathiraja, and N. Karunagaran, “Enhancement of surface quality in Wire EDM machining of Magnesium alloy using ANN modeling approach,” in IOP conference series: materials science and engineering, 2020, vol. 912, p. 032073.10.1088/1757-899X/912/3/032073Search in Google Scholar

[32] G. Ugrasen, H. Ravindra, G. N. Prakash, and R. Keshavamurthy, “Estimation of machining performances using MRA, GMDH and artificial neural network in wire EDM of EN-31,” Proc. Mater. Sci., vol. 6, pp. 1788–1797, 2014, https://doi.org/10.1016/j.mspro.2014.07.209.Search in Google Scholar

[33] U. Esme, A. Sagbas, and F. Kahraman, “Prediction of surface roughness in wire electrical discharge machining using design of experiments and neural networks,” Iran. J. Sci. Technol. Trans. B Eng., vol. 33, no. 3, pp. 231–240, 2009.Search in Google Scholar

[34] P. S. Rao, K. Ramji, and B. Satyanarayana, “Prediction of material removal rate for aluminum BIS-24345 alloy in wire-cut EDM,” Int. J. Eng. Sci. Technol., vol. 2, no. 12, pp. 7729–7739, 2010.Search in Google Scholar

[35] V. Lalwani, P. Sharma, C. I. Pruncu, and D. R. Unune, “Response surface methodology and artificial neural network-based models for predicting performance of wire electrical discharge machining of Inconel 718 Alloy,” J. Manuf. Mater. Process., vol. 4, no. 2, 2020, https://doi.org/10.3390/jmmp4020044.Search in Google Scholar

[36] Y. Yusoff, A. M. Zain, S. Sharif, R. Sallehuddin, and M. S. Ngadiman, “Potential ANN prediction model for multiperformances WEDM on Inconel 718,” Neural Comput. Appl., vol. 30, pp. 12113–12127, 2018, https://doi.org/10.1007/s00521-016-2796-4.Search in Google Scholar

[37] P. Saha, A. Singha, S. K. Pal, and P. Saha, “Soft computing models based prediction of cutting speed and surface roughness in wire electro-discharge machining of tungsten carbide cobalt composite,” Int. J. Adv. Manuf. Technol., vol. 39, pp. 74–84, 2008, https://doi.org/10.1007/s00170-007-1200-z.Search in Google Scholar

[38] T. Singh, P. Kumar, and J. Misra, “Modelling of MRR during wire-EDM of ballistic grade alloy using artificial neural network technique,” J. Phys. Conf. Ser., vol. 1240, no. 012114, 2019, https://doi.org/10.1088/1742-6596/1240/1/012114.Search in Google Scholar

[39] S. Sack and M. Åbom, “Acoustic plane-wave decomposition by means of multilayer perceptron neural networks,” J. Sound Vib., vol. 486, no. 115518, 2020, https://doi.org/10.1016/j.jsv.2020.115518.Search in Google Scholar

[40] L. F. S. Hoffmann, F. C. P. Bizarria, and J. W. P. Bizarria, “Detection of liner surface defects in solid rocket motors using multilayer perceptron neural networks,” Polym. Test., vol. 88, no. 106559, 2020, https://doi.org/10.1016/j.polymertesting.2020.106559.Search in Google Scholar

[41] P. G. Nieto, J. M. Torres, F. J. de Cos Juez, and F. S. Lasheras, “Using multivariate adaptive regression splines and multilayer perceptron networks to evaluate paper manufactured using Eucalyptus globulus,” Appl. Math. Comput., vol. 219, no. 2, pp. 755–763, 2012, https://doi.org/10.1016/j.amc.2012.07.001.Search in Google Scholar

[42] E. Avuçlu and F. Başçiftçi, “New approaches to determine age and gender in image processing techniques using multilayer perceptron neural network,” Appl. Soft Comput., vol. 70, pp. 157–168, 2018, https://doi.org/10.1016/j.asoc.2018.05.033.Search in Google Scholar

[43] U. Orhan, M. Hekim, and M. Ozer, “EEG signals classification using the K-means clustering and a multilayer perceptron neural network model,” Exp. Syst. Appl., vol. 38, no. 10, pp. 13475–13481, 2011, https://doi.org/10.1016/j.eswa.2011.04.149.Search in Google Scholar

[44] S. Chatterjee, S. Bandopadhyay, and D. Machuca, “Ore grade prediction using a genetic algorithm and clustering based ensemble neural network model,” Math. Geosci., vol. 42, pp. 309–326, 2010, https://doi.org/10.1007/s11004-010-9264-y.Search in Google Scholar

[45] L. K. Hansen and P. Salamon, “Neural network ensembles,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 12, no. 10, pp. 993–1001, 1990, https://doi.org/10.1109/34.58871.Search in Google Scholar

[46] A. J. C. Sharkey, “On combining artificial neural nets,” Connect. Sci., vol. 8, nos 3–4, pp. 299–314, 1996, https://doi.org/10.1080/095400996116785.Search in Google Scholar

[47] X. Yao, “Evolving artificial neural networks,” Proc. IEEE, vol. 87, no. 9, pp. 1423–1447, 1999, https://doi.org/10.1109/5.784219.Search in Google Scholar

[48] A. Martínez-Estudillo, F. Martínez-Estudillo, C. Hervás-Martínez, and N. García-Pedrajas, “Evolutionary product unit based neural networks for regression,” Neural Netw., vol. 19, no. 4, pp. 477–486, 2006, https://doi.org/10.1016/j.neunet.2005.11.001.Search in Google Scholar PubMed

[49] P. A. Gutiérrez, F. López-Granados, J. M. Peña-Barragán, M. Jurado-Expósito, M. T. Gómez-Casero, and C. Hervás-Martínez, “Mapping sunflower yield as affected by Ridolfia segetum patches and elevation by applying evolutionary product unit neural networks to remote sensed data,” Comput. Electron. Agric., vol. 60, no. 2, pp. 122–132, 2008, https://doi.org/10.1016/j.compag.2007.07.011.Search in Google Scholar

[50] T. Gurgenc, O. Altay, M. Ulas, and C. Ozel, “Extreme learning machine and support vector regression wear loss predictions for magnesium alloys coated using various spray coating methods,” J. Appl. Phys., vol. 127, no. 18, p. 185103, 2020, https://doi.org/10.1063/5.0004562.Search in Google Scholar
Published Online: 2022-03-16
Published in Print: 2022-03-28

© 2022 Walter de Gruyter GmbH, Berlin/Boston

Articles in the same Issue

  1. Frontmatter
  2. Effect of water absorption and hydroxyapatite addition on mechanical and microstructural properties of dental luting cements
  3. Mechanical properties and corrosion behavior of a friction stir processed magnesium alloy composite AZ31B–SiC
  4. Multi-objective optimization of build orientation considering support structure volume and build time in laser powder bed fusion
  5. Fatigue properties and crack growth behavior of 7N01 and 6N01 aluminum alloys
  6. Surface roughness prediction of wire electric discharge machining (WEDM)-machined AZ91D magnesium alloy using multilayer perceptron, ensemble neural network, and evolving product-unit neural network
  7. Effect of FeTi-FeB inoculation on the shape of carbide reinforcements in hypoeutectic high chromium white cast iron
  8. Development of an eutectic-based self-healing in Al–Si cast alloy
  9. Effect of process parameters on mechanical properties of additive manufactured SMP structures based on FDM
  10. Effect of calcination and sintering temperature on porosity and microstructure of porcelain tiles
  11. Effect of particles on tensile and bending properties of jute epoxy composites
  12. Effect of cutting parameters on the machinability of X37CrMoV5-1 hot work tool steel
  13. Cutting forces during drilling of a SiCp reinforced Al-7075 matrix composite
  14. Modeling and simulation of tensile properties of r-LDPE/GSF composite using the response surface methododology
  15. Machinability of alloy ductile iron and forged 16MnCr5 steel
https://doi.org/10.1515/mt-2021-2034
Keywords for this article
ensemble neural network; evolutionary neural network; multilayer perceptron; surface roughness; wire electrical discharge machining

Articles in the same Issue

  1. Frontmatter
  2. Effect of water absorption and hydroxyapatite addition on mechanical and microstructural properties of dental luting cements
  3. Mechanical properties and corrosion behavior of a friction stir processed magnesium alloy composite AZ31B–SiC
  4. Multi-objective optimization of build orientation considering support structure volume and build time in laser powder bed fusion
  5. Fatigue properties and crack growth behavior of 7N01 and 6N01 aluminum alloys
  6. Surface roughness prediction of wire electric discharge machining (WEDM)-machined AZ91D magnesium alloy using multilayer perceptron, ensemble neural network, and evolving product-unit neural network
  7. Effect of FeTi-FeB inoculation on the shape of carbide reinforcements in hypoeutectic high chromium white cast iron
  8. Development of an eutectic-based self-healing in Al–Si cast alloy
  9. Effect of process parameters on mechanical properties of additive manufactured SMP structures based on FDM
  10. Effect of calcination and sintering temperature on porosity and microstructure of porcelain tiles
  11. Effect of particles on tensile and bending properties of jute epoxy composites
  12. Effect of cutting parameters on the machinability of X37CrMoV5-1 hot work tool steel
  13. Cutting forces during drilling of a SiCp reinforced Al-7075 matrix composite
  14. Modeling and simulation of tensile properties of r-LDPE/GSF composite using the response surface methododology
  15. Machinability of alloy ductile iron and forged 16MnCr5 steel
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 31.12.2025 from https://www.degruyterbrill.com/document/doi/10.1515/mt-2021-2034/html
Scroll to top button