Boosting-based model for solving Sm-Co alloy’s maximum energy product prediction task

• Autorzy: Trostianchyn A.M. , Izonin I.V. , Duriagina Z.A. , Tkachenko R.O. , Kulyk V.V. , Havrysh B.M.

Identyfikatory

DOI

10.5604/01.3001.0016.1191

• Języki publikacji: EN

Abstrakty

EN

Purpose: This paper aims to decide the Sm-Co alloy’s maximum energy product prediction task based on the boosting strategy of the ensemble of machine learning methods. Design/methodology/approach: This paper examines an ensemble-based approach to solving Sm-Co alloy’s maximum energy product prediction task. Because classical machine learning methods sometimes do not supply acceptable precision when solving the regression problem, the authors investigated the boosting ML model, namely Gradient Boosting. Building a boosting model based on several weak submodels, each of which considers the errors of the prior ones, provides substantial growth in the accuracy of the problem-solving. The obtained result is confirmed using an actual data set collected by the authors. Findings: This work demonstrates the high efficiency of applying the ensemble strategy of machine learning to the applied problem of materials science. The experiments determined the highest accuracy of solving the forecast task for the maximum energy product of Sm-Co alloy formed on the boosting model of machine learning in comparison with classical methods of machine learning. Research limitations/implications: The boosting strategy of machine learning, in comparison with single algorithms of machine learning, requires much more computational and time resources to implement the learning process of the model. Practical implications: This work demonstrated the possibility of effectively solving Sm-Co alloy’s maximum energy product prediction task using machine learning. The studied boosting model of machine learning for solving the problem provides high accuracy of prediction, which reveals several advantages of their use in solving issues applied to computational material science. Furthermore, using the Orange modelling environment provides a simple and intuitive interface for using the researched methods. The proposed approach to the forecast significantly reduces the time and resource costs associated with studying expensive rare earth metals (REM)-based ferromagnetic materials. value: The authors have collected and formed a set of data on predicting the maximum energy product of the Sm-Co alloy. We used machine learning tools to solve the task. As a result, the most increased forecasting precision based on the boosting model is demonstrated compared to classical machine learning methods.

Słowa kluczowe

EN

Sm-Co alloy; ensemble learning; gradient boosting; prediction accuracy

PL

Stop Sm-Co; uczenie zespołowe; gradient boosting; dokładność przewidywania

• Wydawca: International OCSCO World Press
• Czasopismo: Archives of Materials Science and Engineering
• Rocznik: 2022
• Tom: Vol. 116, nr 2
• Strony: 71--80
• Opis fizyczny: Bibliogr. 38 poz.

Twórcy

autor

Trostianchyn A.M.

• Department of Materials Science and Engineering, Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

• https://orcid.org/0000-0002-0642-0693

autor

Izonin I.V.

• Department of Artificial Intelligence, Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

• https://orcid.org/0000-0002-9761-0096

autor

Duriagina Z.A.

• Department of Materials Science and Engineering, Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

• https://orcid.org/0000-0002-2585-3849

autor

Tkachenko R.O.

• Department of Publishing Information Technologies, Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

• https://orcid.org/0000-0002-9802-6799

autor

Kulyk V.V.

• Department of Materials Science and Engineering, Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

• https://orcid.org/0000-0001-5999-3551

autor

Havrysh B.M.

• Department of Publishing Information Technologies, Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

• https://orcid.org/0000-0003-3213-9747

Bibliografia

• [1] A. Agrawal, A. Choudhary, Perspective: Materials informatics and big data: Realization of the "fourth paradigm" of science in materials science, APL Materials 4/5 (2016) 053208. DOI: https://doi.org/10.1063/1.4946894
• [2] R. Ramprasad, R. Batra, G. Pilania, A. Mannodi- Kanakkithodi, C. Kim, Machine learning in materials informatics: recent applications and prospects, njp Computational Materials 3/1 (2017) 54. DOI: https://doi.org/10.1038/s41524-017-0056-5
• [3] J. Schmidt, M.R.G. Marques, S. Botti, M.A.L. Marques, Recent advances and applications of machine learning in solid-state materials science, njp Computational Materials 5/1 (2019) 83. DOI: https://doi.org/10.1038/s41524-019-0221-0
• [4] L. Himanen, A. Geurts, A.S. Foster, P. Rinke, Data-driven materials science: Status, Challenges, and Perspectives, Advanced Science 6/21 (2019) 1900808. DOI: https://doi.org/10.1002/advs.201900808
• [5] Y. Liu, T. Zhao, W. Ju, S. Shi, Materials discovery and design using machine learning, Journal of Materiomics 3/3 (2017) 159-177. DOI: https://doi.org/10.1016/j.jmat.2017.08.002
• [6] A. Jain, S.P. Ong, G. Hautier, W. Chen, W.D. Richards, S. Dacek, S. Cholia, D. Gunter, D. Skinner, G. Ceder, K.A. Persson, Commentary: The materials project: A materials genome approach to accelerating materials innovation, APL Materials 1/1 (2013) 011002. DOI: https://doi.org/10.1063/1.4812323
• [7] NOMAD. Available from: http://nomad-coe.eu
• [8] The Materials Project. Available from: http://materialsproject.org
• [9] AFLOW. Available from: http://www.aflowlib.org
• [10] OQMD. The open quantum materials database. Available from: http://oqmd.org
• [11] S.S. Nain, R. Sai, P. Sihag, S. Vambol, V. Vambol, Use of machine learning algorithm for the better prediction of SR peculiarities of WEDM of Nimonic-90 superalloy, Archives of Materials Science and Engineering 95/1 (2019) 12-19. DOI: https://doi.org/10.5604/01.3001.0013.1422
• [12] A. Trostianchyn, Z. Duriagina, I. Izonin, R. Tkachenko, V. Kulyk, O. Pavliuk. Sm-Co alloys coercivity prediction using stacking heterogeneous ensemble model, Acta Metallurgica Slovaca 27/4 (2021) 195- 202. DOI: https://doi.org/10.36547/ams.27.4.1173
• [13] Z.A. Duriagina, R.O. Tkachenko, A.M. Trostianchyn, I.A. Lemishka, A.M. Kovalchuk, V.V. Kulyk, T.M. Kovbasyuk, Determination of the best microstructure network, Journal of Achievements in Materials and Manufacturing Engineering 87/1 (2018) 25-31. DOI: https://doi.org/10.5604/01.3001.0012.0736
• [14] P. Raccuglia, K. Elbert, P. Adler, C. Falk, M.B. Wenny, A. Mollo, M. Zeller, S.A. Friedler, J. Schrier, A.J. Norquist, Machine-learning-assisted materials discovery using failed experiments, Nature 533/7601 (2016) 73-76. DOI: https://doi.org/10.1038/nature17439
• [15] O. Kruzhilko, N. Volodchenkova, V. Maystrenko, B. Bolibrukh, V.P. Kalinchyk, A. Zakora, A. Feshchenko, S. Yeremenko, Mathematical modelling of professional risk at Ukrainian metallurgical industry enterprises, Journal of Achievements in Materials and Manufacturing Engineering 108/1 (2021) 35-41. DOI: https://doi.org/10.5604/01.3001.0015.4797
• [16] T.L. Tepla, I.V. Izonin, Z.A. Duriagina, R.O. Tkachenko, A.M. Trostianchyn, I.A. Lemishka, V.V. Kulyk, T.M. Kovbasyuk, Alloys selection based on the supervised learning technique for design of biocompatible medical materials, Archives of Materials Science and Engineering 93/1 (2018) 32-40. DOI: https://doi.org/10.5604/01.3001.0012.6944
• [17] D. Bodana, N.K. Tiwari, S. Ranjan, U. Ghanekar, Estimation of the depth of penetration in a plunging hollow jet using artificial intelligence techniques, Archives of Materials Science and Engineering 103/2 (2020) 49-61. DOI: https://doi.org/10.5604/01.3001.0014.3354
• [18] A. Khanwalkar, R. Soni, A survey on prediction of diabetes using classification algorithms, Journal of Achievements in Materials and Manufacturing Engineering 104/2 (2021) 77-84. DOI: https://doi.org/10.5604/01.3001.0014.8490
• [19] M. Rahul, S. Baldev, Prediction of scour depth around bridge piers in tandem arrangement using M5 and ANN regression models, Archives of Materials Science and Engineering 102/2 (2020) 49-58. DOI: https://doi.org/10.5604/01.3001.0014.1524
• [20] L. Wang, Discovering phase transitions with unsupervised learning, Physical Review B 94/19 (2016) 195105. DOI: https://doi.org/10.1103/PhysRevB.94.195105
• [21] A. Jain, G. Hautier, S.P. Ong, K. Person, New opportunities for materials informatics: Resources and data mining techniques for uncovering hidden relationships, Journal of Materials Research 31/8 (2016) 977-994. DOI: https://doi.org/10.1557/jmr.2016.80
• [22] J.M.D. Coey, Perspective and prospects for rare earth permanent magnets, Engineering 6/2 (2020) 119-131. DOI: https://doi.org/10.1016/j.eng.2018.11.034
• [23] E.F. Kneller, R. Hawig, The exchange-spring magnet: A new material principle for permanent magnets, IEEE Transactions on Magnetics 27/4 (1991) 3588-3600. DOI: https://doi.org/10.1109/20.102931
• [24] Y. Liu, D.J. Sellmyer, Exchange-coupling behavior in nanostructured FePt/Fe bilayer films, AIP Advances 6/5 (2016) 056010. DOI: https://doi.org/10.1063/1.4943414
• 25] R. Nakayama, T. Takeshita, NdFeB anisotropic magnet powders produced by the HDDR process, Journal of Alloys and Compounds 193/1-2 (1993) 259-261. DOI: https://doi.org/10.1016/0925-8388(93)90364-S
• [26] N. Cannesan, I.R. Harris, Aspects of NdFeB HDDR powders: fundamentals and processing, in: G.C. Hadjipanayis (ed), Bonded magnets, NATO Science series: II. Mathematics, Physics and Chemistry, vol 118, Springer, Dordrecht, 2003, 13-36. DOI: https://doi.org/10.1007/978-94-007-1090-0_2
• [27] M. Kubis, A. Handstein, B. Gebel, О. Gutfleisch, K.-H. Müller, L. Schultz, Highly coercive SmCo5 magnets prepared by a modified hydrogenation-disproportionation-desorption-recombination process, Journal of Applied Physics 85/8 (1999) 5666. DOI: https://doi.org/10.1063/1.369834
• [28] I.I. Bulyk, A.M. Trostianchyn, Hydrogenation-disproportionation of samarium-cobalt ferromagnetic alloy on the basis of Sm2(Co,Fe,Cu,Zr)17, Fiziko- Khimicheskaya Mekhanika Materialov 39/4 (2003) 77- 83.
• [29] І.І. Bulyk, Application of hydrogen in the production of sintered anisotropic nanostructured magnets from alloys of rare-earth and transition metals, Materials Science 54/6 (2019) 761-775. DOI: https://doi.org/10.1007/s11003-019-00262-7
• 30] H.-K. Park, J.-H. Lee, J. Lee, S.-K. Kim, Optimizing machine learning models for granular NdFeB magnets by very fast simulated annealing, Scientific Reports 11/1 (2021) 3792. DOI: https://doi.org/10.1038/s41598-021-83315-9
• [31] Z. Pan, S. Fang, Torque performance improvement of permanent magnet arc motor based on two-step strategy, IEEE Transactions on Industrial Informatics 17/11 (2021) 7523-7534. DOI: https://doi.org/10.1109/TII.2021.3054791
• [32] V.T. Nguyen, M. Bermingham, M.S. Dargusch, Data– driven modelling of the interaction force between permanent magnets, Journal of Magnetism and Magnetic Materials 532 (2021) 167869. DOI: https://doi.org/10.1016/j.jmmm.2021.167869
• [33] W. Kirchgässner, O. Wallscheid, J. Böcker, Data-driven permanent magnet temperature estimation in synchronous motors with supervised machine learning: A Benchmark, IEEE Transactions on Energy Conversion 36/3 (2021) 2059-2067. DOI: https://doi.org/10.1109/TEC.2021.3052546
• [34] Z. Hu, I.A. Tereykovskiy, L.O. Tereykovska, V.V. Pogorelov, Determination of structural parameters of multilayer perceptron designed to estimate parameters of technical systems, International Journal of Intelligent Systems and Applications 9/10 (2017) 57- 62. DOI: https://doi.org/10.5815/ijisa.2017.10.07
• [35] Z. Hu, M. Ivashchenko, L. Lyushenko, D. Klyushnyk, Artificial neural network training criterion formulation using error continuous domain, International Journal of Modern Education and Computer Science 13/3 (2021) 13-22. DOI: https://doi.org/10.5815/ijmecs.2021.03.02
• [36] D. Tiwari, N. Singh, Ensemble approach for twitter sentiment analysis, International Journal of Information Technology and Computer Science 11/8 (2019) 20-26. DOI: https://doi.org/10.5815/ijitcs.2019.08.03
• [37] Z. Hu, Y.V. Bodyanskiy, N.Ye. Kulishova, O.K. Tyshchenko, A multidimensional extended neo-fuzzy neuron for facial expression recognition, International Journal of Intelligent Systems and Applications 9/9 (2017) 29-36. DOI: https://doi.org/10.5815/ijisa.2017.09.04
• [38] M.Z. Khan, Hybrid ensemble learning technique for software defect prediction, International Journal of Modern Education and Computer Science 12/1 (2020) 1-10. DOI: https://doi.org/10.5815/ijmecs.2020.01.01

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).