Lityum-iyon Bataryaların Katot Malzemelerindeki Kristal Yapının Kestirimi için Makine Öğrenimi Yöntemlerinin Uygulanması
Öz
Lityum-iyon silikat katotların fiziksel ve kimyasal özelliklerinin kristal yapı sisteminden önemli ölçüde etkilendiği yaygın olarak kabul edilmektedir. Bu nedenle, kristal yapılarının kestirimi, batarya uygulamalarında katotların diğer birçok özelliğini tahmin etmek için hayati öneme sahiptir. Li-Si-(Mn,Fe,Co)-O bileşik yapılarına sahip silikat bazlı katotların üç ana kristal sistemi (monoklinik, ortorombik ve triklinik) makine öğrenimi yöntemlerinden çeşitli sınıflandırma teknikleri kullanılarak tahmin edilmiştir. Hesaplamalar, Malzeme Projesi’nden elde edilen yoğunluk fonksiyonel teorisi hesaplamalarının sonuçlarına dayanmaktadır. Kristal sistemi ile katotların diğer fiziksel özellikleri arasındaki güçlü korelasyon, istatistiksel modellerdeki özellik değerlendirmesine dayalı olarak doğrulanmıştır. Ayrıca, en iyi tahmin doğruluğunu elde etmek için çeşitli sınıflandırma yöntemlerinin parametreleri optimize edilmiştir. XGBoost ve Destek Vektör Sınıflandırıcı algoritmalarının çapraz doğrulama testlerinde çalışmada kullanılan diğer sınıflandırma yöntemleri arasında en yüksek tahmin doğruluğunu sağlamıştır.
Anahtar Kelimeler
Lityum-iyon bataryalar Makine öğrenimi Optimizasyon Kristal yapı Sınıflandırma teknikleri
Kaynakça
- Askanazi, E.M., Yadav, S., Grinberg, I., 2021. Prediction of Curie temperatures of ferroelectric solid solutions using machine learning methods. Computational Materials Science, 2021 (199), 113-121.
- Bartel, C.J., Trewartha, A., Wang, Q., Dunn, A., Jain, A., Ceder, G., 2020. A critical examination of compund stability predictions from machine-learned formation energies, energies. Npj Computaitional Materials, 6(1),1067-1078.
- Chang, C.C., Lin, C.J., 2011. LIBSVM: A Library for Support Vector Machines, Transactions on Intelligent Systems and Technology, 2(3), 1-27.
- Chen, T., Guestrin, C., 2016. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd International Conference on Knowledge Discovery and Data Mining, 2016, 785-794.
- Cubuk, E.D., Sendek, A.D., Reed, E.J., 2019. Screenig billions of candidates for solid lithium-ion conductors: A transfer learning approach for small data. The Journal of Chemical Physics, 150(21), 214701-1 – 214701-7.
- Demirezen, M.U., Civrizoglu Buz, A., Yavanoglu, U, 2021. Time series- image transformation- based new approaches in detecting underwater objects with machine learning methods. Journal of the Faculty of Engineering and Architecture of Gazi University, 36(3), 1399-1415.
- Jadhav, S.D., Channe, H.P., 2016. Efficient recommendation system using decision tree classifier and collaborative filtering. Int. Res. J. Eng. Technol. 2016, 3(8), 2113-2118.
- Jain, A., Ong, S.P., et al., 2013. Commentary: The Materials Project: A materials genome approach to accelerating materials innovation. APL Materials, 1, 011002-1-11.
- Jha, D., Ward, L., Paul, A., Liao, W., Choudhary, A., Wolverton, C., Agrawal, A., 2018. ElemNet: Deep Learning the Chemistry of Materials from Only Elemental Composition. nature: scientificreports, 8(1), 17593-1-13.
- Longo, R.C., Xiong, K., Santosh, K.C., 2013. Crystal structure and multicomponent effects in Tetrahedral Silicate Cathode Materials for Rechargeable Li-ion Batteries. Electrochemica Acta, 121(1), 434-442.
- Maphanga, R.R., Mokoena, T., Ratsoma, M., 2020. Estimating DFT calculated voltage using machine learning regression models. Materials Today: Proceedings, 38(2), 773- 778.
- Pan, S., Wang, Y., Yu, J., Yang, M., Zhangi Y., Wei, H., Yuechao C., Wu, J., Han, J., Wang, C., Liu, X., 2021. Aceelerated discovery of high performance Cu-Ni-Co-Si alloys through machine learning, Materials & Design, 209(2021), 109929-1-16.
- Park, C.W., Wolverton, C., 2020. Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery. American Physical Society-Physical Review Materials, 4, 063801-1-26.
- Ripley, B.D., 1996. Pattern Recognition and Neural Networks, Cambridge University Press, 143-181.
- Shandiz, M.A, Gauvin, R., 2016. Application of machine learning methods for the prediction of crystal system of cathode materials in lithium-ion batteries. Computational Materials Science, 117(2016): 270-278.
- Venables, W.N., Ripley, B.D., 2002. Modern Applied Statistics with S, fourth ed., Springer, 243-249.
- Yan, L.M, Su, J.M., Sun, C., Yue, B.H., 2014. Review of the first principles calculations and the design of cathode materials for Li-ion batteries. Advances in Manufacturing, 2: 358-368.
- İnternet kaynakları 1-https://www.veribilimiokulu.com/xgboost-nasil-calisir/XGBoost(eXtremeGradientBoosting) (18.04.2022).
- 2-https://medium.com/@k.ulgen90/makine-ogrenimi-bolum-5-karar-agaclari (18.04.2022).
- 3- https://medium.com/deep-learning-turkiye/nedir-bu-destek-vektor-makineleri-makine-ogrenmesi-serisi-2 (18.04.2022).
- 4- https://colab.research.google.com (04.04.2022).
- 5- https://www.kaggle.com (02.04.2022).
Implementation of Machine Learning Approaches for Crystal Structure Estimation in Lithium-ion Battery Cathode Materials
Öz
It has commonly been assumed that the physical and chemical characteristics of lithium-ion silicate cathodes are influenced significantly by the crystal structure system. Because of this, crystal structure estimation has played a vital role in bringing about forecasting many other features of cathodes in battery applications. Using a variety of classification techniques in machine learning which three primary crystal structure (monoclinic, orthorhombic, and triclinic) of silicate-based cathode materials with compound systems of Li-Si-(Mn,Fe,Co)-O has been estimated. The computations are based on the Materials Project's density functional theory computations. In this study, it has been explained that based on property evaluation in statistical models, the considerable correlation between the crystal system and other physical characteristics of the cathodes was validated. Furthermore, the parameters of several categorization techniques have been tuned in order to achieve maximum prediction accuracy. This case has shown that the XGBoost and Support Vector Classifier algorithms carried out in this study the highest forecasting accuracy in this study along with many other classification methods in cross-validation tests.
Anahtar Kelimeler
Lithium-ion batteries Machine learning Optimization Crystal structure Classification techniques
Kaynakça
- Askanazi, E.M., Yadav, S., Grinberg, I., 2021. Prediction of Curie temperatures of ferroelectric solid solutions using machine learning methods. Computational Materials Science, 2021 (199), 113-121.
- Bartel, C.J., Trewartha, A., Wang, Q., Dunn, A., Jain, A., Ceder, G., 2020. A critical examination of compund stability predictions from machine-learned formation energies, energies. Npj Computaitional Materials, 6(1),1067-1078.
- Chang, C.C., Lin, C.J., 2011. LIBSVM: A Library for Support Vector Machines, Transactions on Intelligent Systems and Technology, 2(3), 1-27.
- Chen, T., Guestrin, C., 2016. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd International Conference on Knowledge Discovery and Data Mining, 2016, 785-794.
- Cubuk, E.D., Sendek, A.D., Reed, E.J., 2019. Screenig billions of candidates for solid lithium-ion conductors: A transfer learning approach for small data. The Journal of Chemical Physics, 150(21), 214701-1 – 214701-7.
- Demirezen, M.U., Civrizoglu Buz, A., Yavanoglu, U, 2021. Time series- image transformation- based new approaches in detecting underwater objects with machine learning methods. Journal of the Faculty of Engineering and Architecture of Gazi University, 36(3), 1399-1415.
- Jadhav, S.D., Channe, H.P., 2016. Efficient recommendation system using decision tree classifier and collaborative filtering. Int. Res. J. Eng. Technol. 2016, 3(8), 2113-2118.
- Jain, A., Ong, S.P., et al., 2013. Commentary: The Materials Project: A materials genome approach to accelerating materials innovation. APL Materials, 1, 011002-1-11.
- Jha, D., Ward, L., Paul, A., Liao, W., Choudhary, A., Wolverton, C., Agrawal, A., 2018. ElemNet: Deep Learning the Chemistry of Materials from Only Elemental Composition. nature: scientificreports, 8(1), 17593-1-13.
- Longo, R.C., Xiong, K., Santosh, K.C., 2013. Crystal structure and multicomponent effects in Tetrahedral Silicate Cathode Materials for Rechargeable Li-ion Batteries. Electrochemica Acta, 121(1), 434-442.
- Maphanga, R.R., Mokoena, T., Ratsoma, M., 2020. Estimating DFT calculated voltage using machine learning regression models. Materials Today: Proceedings, 38(2), 773- 778.
- Pan, S., Wang, Y., Yu, J., Yang, M., Zhangi Y., Wei, H., Yuechao C., Wu, J., Han, J., Wang, C., Liu, X., 2021. Aceelerated discovery of high performance Cu-Ni-Co-Si alloys through machine learning, Materials & Design, 209(2021), 109929-1-16.
- Park, C.W., Wolverton, C., 2020. Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery. American Physical Society-Physical Review Materials, 4, 063801-1-26.
- Ripley, B.D., 1996. Pattern Recognition and Neural Networks, Cambridge University Press, 143-181.
- Shandiz, M.A, Gauvin, R., 2016. Application of machine learning methods for the prediction of crystal system of cathode materials in lithium-ion batteries. Computational Materials Science, 117(2016): 270-278.
- Venables, W.N., Ripley, B.D., 2002. Modern Applied Statistics with S, fourth ed., Springer, 243-249.
- Yan, L.M, Su, J.M., Sun, C., Yue, B.H., 2014. Review of the first principles calculations and the design of cathode materials for Li-ion batteries. Advances in Manufacturing, 2: 358-368.
- İnternet kaynakları 1-https://www.veribilimiokulu.com/xgboost-nasil-calisir/XGBoost(eXtremeGradientBoosting) (18.04.2022).
- 2-https://medium.com/@k.ulgen90/makine-ogrenimi-bolum-5-karar-agaclari (18.04.2022).
- 3- https://medium.com/deep-learning-turkiye/nedir-bu-destek-vektor-makineleri-makine-ogrenmesi-serisi-2 (18.04.2022).
- 4- https://colab.research.google.com (04.04.2022).
- 5- https://www.kaggle.com (02.04.2022).
Ayrıntılar
| Birincil Dil | Türkçe |
|---|---|
| Konular | Yapay Zeka |
| Bölüm | Makaleler |
| Yazarlar | |
| Yayımlanma Tarihi | 31 Ağustos 2022 |
| Gönderilme Tarihi | 20 Nisan 2022 |
| Yayımlandığı Sayı | Yıl 2022 Cilt: 22 Sayı: 4 |
