Skip to main content
SpringerLink
Log in

Neural-Network Prediction of the Surface Roughness in Milling

  • Published:
Russian Engineering Research Aims and scope

Abstract

An artificial neural network is developed for predicting the surface roughness in milling materials of different hardness. Experimental data are used to train the network. Experimental data for the attainable surface roughness in milling are analyzed for different cutting conditions (speed and supply) and different groups of materials (aluminum, structural steel, stainless steel, heat-resistant steel), and the basic patterns are noted. Families of graphs illustrate the results for the surface roughness. The characteristics of the neural network trained using data from various researchers are outlined.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.

REFERENCES

  1. Duyun, T.A. and Beshevli, O.B., Influence of technological parameters on temperature condition and the received quality of the surface when milling babbits, Vestn. Belgorod. Gos. Tekhnol. Univ. im. V.G. Shukhova, 2015, no. 2, pp. 112–117.

  2. Moskvitin, A.A., Gubanov, A.E., and Duyun, T.A., Development of methods for cutting force components determination when milling aviation materials, Vestn. Irkutsk. Gos. Tekh. Univ., 2019, vol. 23, no. 4 (147), pp. 678–688.

  3. Baranov, D.S. and Duyun, T.A., Application of artificial neural networks for predicting roughness at cleaning and getting point, Vestn. Belgorod. Gos. Tekhnol. Univ. im. V.G. Shukhova, 2019, no. 7, pp. 128–134.

  4. Gubanov, A.E., Moskvitin, A.A., and Duyun, T.A., Methodology development for cutting force components determination for aerospace materials milling, IOP Conf. Ser.: Mater. Sci. Eng., 2019, vol. 560, no. 1, p. 012018. https://doi.org/10.1088/1757-899X/560/1/012018

  5. Beshevli, O.B., Duyun, T.A., and Shrubchenko, I.V., Optimization of babbit milling processing methods u-sing a machine module for big bearings treatment, IOP Conf. Ser.: Mater. Sci. Eng., 2019, vol. 560, no. 1, p. 012140. https://doi.org/10.1088/1757-899X/560/1/012140

  6. Erygin, E.V. and Duyun, T.A., Forecasting of the surface roughness in finishing milling using neural networks, Vestn. Belgorod. Gos. Tekhnol. Univ. im. V.G. Shukhova, 2019, no. 10, pp. 135–141.

  7. Erygin, E.V. and Duyun, T.A., Development of neural networks for forecasting roughness when milling various materials, Vestn. Belgorod. Gos. Tekhnol. Univ. im. V.G. Shukhova, 2020, no. 11, pp. 113–124.

  8. Palani, S. and Kesavanarayana, Y., Prediction of surface roughness in end milling process by machine vision using neuro fuzzy network, Proc. Int. Conf. on Science, Engineering and Management Research (ICSEMR), 2014, pp. 1–5.

  9. Kovač, P., Savković, B., Gostimirovic, M., et al., Modeling of the machining surface roughness parameters for steel difficult to machining, Analele Univ. “Eftimie Murgu” Reşiţa, 2017, vol. 24, no. 1, pp. 175–183. http://anale-ing.uem.ro/2017/20.pdf.

  10. Soltan, I.M., Eltaib, M.E.H., and El-Zahry, R.M., Surface roughness prediction in end milling using multiple regression and adaptive neuro-fuzzy inference system, Proc. 4th Assiut Univ. Int. Conf. on Mech. Eng. Adv. Tech. for Indus. Prod., 2006, pp. 614–620.

  11. Xiao, M., Shen, X., Ma, Y., et al., Prediction of surface roughness and optimization of cutting parameters of stainless steel turning based on RSM, Math. Probl. Eng., 2018, vol. 2018, p. 9051084. https://doi.org/10.1155/2018/9051084

    Article  Google Scholar 

  12. Parmar, J.G. and Makwana, A., Prediction of surface roughness for end milling process using Artificial Neural Network, Int. J. Mod. Eng. Res., 2012, vol. 2, pp. 1006–1013.

    Google Scholar 

  13. Davim, J.P., A note on the determination of optimal cutting conditions for surface finish obtained in turning using design of experiments, J. Mater. Process. Technol., 2001, vol. 116, pp. 305–308.

    Article  Google Scholar 

  14. Sahin, Y. and Motorcu, A.R., Surface roughness model in machining hardened steel with cubic boron nitride cutting tool, Int. J. Refract. Met. Hard Mater., 2008, vol. 26, pp. 84–90.

    Article  Google Scholar 

  15. Sarkar, B., Reddy, M.M., and Debnath, S., Effect of machining parameters on surface finish of Inconel 718 in end milling, MATEC Web Conf., 2017, vol. 95, p. 02009. https://doi.org/10.1051/matecconf/20179502009

  16. Tao, F., Weijun, L., and Jibin, Z., Optimization of cutting parameters using multi-objective evolutionary algorithm based on decomposition, J. Vibroeng., 2013, vol. 15, pp. 833–844.

    Google Scholar 

Download references

ACKNOWLEDGMENTS

This research was conducted using equipment at the High-Technology Center, Shukhov Belgorod State Technical University and at OOO Region Resurs.

Funding

Financial support was provided within the framework of the Priority 2030 program at Shukhov Belgorod State Technical University.

Author information

Authors and Affiliations

  1. Shukhov Belgorod State Technical University, Belgorod, Russia

    E. V. Erygin, T. A. Duyun & A. D. Korop

Authors
  1. E. V. Erygin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. T. A. Duyun
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. A. D. Korop
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to E. V. Erygin or T. A. Duyun.

Ethics declarations

The authors declare that they have no conflicts of interest.

Additional information

Translated by B. Gilbert

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Erygin, E.V., Duyun, T.A. & Korop, A.D. Neural-Network Prediction of the Surface Roughness in Milling. Russ. Engin. Res. 43, 84–87 (2023). https://doi.org/10.3103/S1068798X23020119

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.3103/S1068798X23020119

Keywords:

Search

Navigation