Analysis of Grain Size Effect of Titanium Ti-6Al-4V Depending on Surface Roughness at Different Cutting Parameters Using Artificial Intelligence Methods

Authors

V.F. Makarov ¹ , M.V. Pesin ¹ , V.Yu. Stolbov ¹ , A.V. Khabarova ¹ , A.V. Polyakov ² , I.P. Semenova ²

¹ Perm National Research Polytechnic University, 614990, Komsomolsky prospekt, 29, Perm, Russian Federation

² Ufa University of Science and Technology, 450076, Zaki Validi st., 32, Ufa, Bashkortostan Republic, Russian Federation

10.17586/2687-0568-2024-6-4-171-177

Rev. Adv. Mater. Technol., 2024, vol. 6, no. 4, pp. 171–177

Abstract

The article presents the results of a study of the effect of cutting modes of Ti-6Al-4V alloy with different grain size, including in the ultrafine-grained state obtained by severe plastic deformation, on the roughness of the machined surface using a neural network model. A neural network model has been developed that predicts the surface roughness of titanium alloy during cutting depending on the grain size and processing modes (speed, feed per revolution, and cutting depth). To form a data set of sufficient power for training neural networks, a data augmentation method was used, for which an auxiliary regression model was built. To select the most rational network architecture, a random search in the hyperparameter space was used. Testing the developed neural network model on actual data showed an error not exceeding 8.7% according to mean absolute percentage error.

Keywords

Titanium alloy; Cutting modes; Roughness; Neural network; Deep learning

Foundings

Russian Science Foundation project: 23-43-00041

References

1.    D.T. Bran, C.F. Elefterie, B. Ghiban, Aeronautical Industry Requirements for Titanium Alloys, IOP Conf. Ser.: Mater. Sci. Eng., 2017, vol. 209, art. no. 012059.
2.    S.A. Niknam, R. Khettabi, V. Songmene, Erratum to: Machinability and Machining of Titanium Alloys: A Review, in: J.P. Davim (Ed.), Machining of Titanium Alloys, Springer, Berlin, Heidelberg, 2014, pp. E1.
3.    S. Sun, M. Brandt, M.S. Dargusch, Thermally enhanced machining of hard-to-machine materials-A review, Int. J. Mach. Tools Manuf., 2010, vol. 50, no. 8, pp. 663-680.
4.    M. Rahman, Z.-G. Wang, Y.-S. Wong, A Review on High-Speed Machining of Titanium Alloys, JSME Int. J. Ser. C, 2006, vol. 49, no. 1, pp. 11-20.
5.    S.V. Telrandhe, A.K. Saxena, S. Mishra, Effect of microstructure and cutting speed on machining behavior of Ti6Al4V alloy, J. Mech. Sci. Technol., 2017, vol. 31, pp. 2177-2184.
6.    D. Suárez Fernández, B.P. Wynne, P. Crawforth, M. Jackson, Titanium alloy microstructure fingerprint plots from in-process machining, Mater. Sci. Eng. A, 2021, vol. 811, art. no. 141074.
7.    P.-J. Arrazola, A. Garay, L.-M. Iriarte, M. Armendia, S. Marya, F. Le Maître, Machinability of titanium alloys (Ti6Al4V and Ti555.3), J. Mater. Process. Technol., 2009, vol. 209, no. 5, pp. 2223-2230.
8.    R.Z. Valiev, A.P. Zhilyaev, T.G. Langdon, Bulk Nano-structured Materials: Fundamentals and Applications, 1st ed., Wiley, 2013.
9.    R.Z. Valiev, Y. Estrin, Z. Horita, T.G. Langdon, M.J. Zehetbauer, Y. Zhu, Producing Bulk Ultrafine-Grained Materials by Severe Plastic Deformation: Ten Years Later, JOM, 2016, vol. 68, pp. 1216-1226.
10.    I.P. Semenova, V.V. Polyakova, G.S. Dyakonov, A.V. Polyakov, Ultrafine-Grained Titanium-Based Alloys: Structure and Service Properties for Engineering Applications, Adv. Eng. Mater., 2020, vol. 22, no. 1, art. no. 1900651.
11.    G. Jiang, H. Yang, G. Xiao, Z. Zhao, Y. Wu, Titanium alloys surface integrity of belt grinding considering different machining trajectory direction, Front. Ma-ter., 2022, vol. 9, art. no. 1052523.
12.    J. Guo, Y.Y. Shi, Z. Chen, T. Yu, P. Zhao, B. Shirinzadeh, Optimal parameter selection in robotic belt polishing for aeroengine blade based on GRARSM method, Symmetry, 2019, vol. 11, no. 12, art. no. 1526.
13.    Z. Tao, S. Yaoyao, S. Laakso, J.M. Zhou, Investigation of the effect of grinding parameters on surface quality in grinding of TC4 titanium alloy, Procedia Manuf., 2017, vol. 11, pp. 2131-2138.
14.    I. Semenova, A. Polyakov, A. Gareev, V. Makarov, I. Kazakov, M. Pesin, Machinability Features of Ti-6Al-4V Alloy with Ultrafine-Grained Structure, Metals, 2023, vol. 13, no. 10, art. no. 1721.
15.    Cutting Speed Calculator by Sandvik-Coromant, Electronic resource, URL: https://toolguide.sandvik.coromant.com/cdc/calculatorType (accessed: 10.11.2024).
16.    Y. Chen, Y. Li, T. Kong, L. Qi, R. Chu, L. Li, J. Jia, Scale-aware Automatic Augmentation for Object Detection, arXiv:2103.17220, 2021.
17.    Z. Zhong, L. Zheng, G. Kang, S. Li, Y. Yang, Random Erasing Data Augmentation, Proceedings of the AAAI Conference on Artificial Intelligence, 2020, vol. 34, no. 7, pp. 13001-13008.
18.    J. Heaton, Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning, Genet. Program. Evolvable Mach., 2018, vol. 19, pp. 305-307.
19.    F. Chollet, Deep learning with Python, Manning, Shelter Island, NY, 2018.
20.    D.P. Kingma, J. Ba, Adam: A Method for Stochastic Optimization, arXiv:1412.6980, 2014.

Volume 6, No 4

pages 171-177

Files

full text article

abstract

XML file

History

Receive Date: 13 November 2024

Accepted Date: 18 November 2024

Available online: 30 December 2024

© 2024 ITMO University.
This is an open access article under the terms
of the CC BY-NC 4.0 license.
Metadata is available under the terms of the CC BY 4.0 license