Integrating machine learning and CALPHAD method for exploring low-modulus near-β-Ti alloys AITranslate

1Alejandra Rodriguez-Contreras,Miquel Punset,JoséA.Calero,Francisco Javier Gil,Elisa Ruperez,JoséMaría Manero.Powder metallurgy with space holder for porous titanium implants:A review[J].Journal of Materials Science & Technology,2021(17):129-149. 被引量：5

2Jonathan Schmidt,Mário R.G.Marques,Silvana Botti,Miguel A.L.Marques.Recent advances and applications of machine learning in solidstate materials science[J].npj Computational Materials,2019(1):394-429. 被引量：68

3Qing-Kun Meng,Yu-Fei Huo,Wen Ma,Yan-Wei Sui,Jin-Yong Zhang,Shun Guo,Xin-Qing Zhao.Design and fabrication of a low modulus β-type Ti-Nb-Zr alloy by controlling martensitic transformation[J].Rare Metals,2018,37(9):789-794. 被引量：5

4Chunbo Lan,Yu Wu,Lili Guo,Huijuan Chen,Feng Chen.Microstructure,texture evolution and mechanical properties of cold rolled Ti-32.5Nb-6.8Zr-2.7Sn biomedical beta titanium alloy[J].Journal of Materials Science & Technology,2018,34(5):788-792. 被引量：13

5Fei Yang,Zhen Li,Qing Wang,Beibei Jiang,Biaojie Yan,Pengcheng Zhang,Wei Xu,Chuang Dong,Peter K.Liaw.Cluster-formula-embedded machine learning for design of multicomponent β-Ti alloys with low Young’s modulus[J].npj Computational Materials,2020(1):824-834. 被引量：7

6X.Li,X.N.Wang,K.Liu,G.H.Cao,M.B.Li,Z.S.Zhu,S.J.Wu.Hierarchical structure and deformation behavior of a novel multicomponent β titanium alloy with ultrahigh strength[J].Journal of Materials Science & Technology,2022(12):227-242. 被引量：5

1Fangping Wang,Yaxiong Guo,Qibin Liu,Xiaojuan Shang.Nanoparticle-strengthened Ni_(2)CoCrNb_(0.2)medium-entropy alloy with an ultrastrong cryogenic yield strength fabricated by additive manufacturing[J].Journal of Materials Science & Technology,2023(32):17-31.

3Adel Got,Djaafar Zouache,Abdelouahab Moussaoui,Laith Abualigah,Ahmed Alsayat.Improved Manta Ray Foraging Optimizer-based SVM for Feature Selection Problems:A Medical Case Study[J].Journal of Bionic Engineering,2024,21(1):409-425.

6Chenying Shi,Muzhi Ma,Biaobiao Yang,Yuling Liu,Yushen Huang,Yong Du.Effect of Ti additions on microstructure and mechanical properties of Cu-Cr-Zr alloy[J].Journal of Materials Science & Technology,2023(32):69-80.

7Xuemeng Gan,Shaofu Li,Shunyuan Xiao,Yafeng Yang.Integrated high-performance and accurate shaping technology of low-cost powder metallurgy titanium alloys: A comprehensive review[J].International Journal of Minerals,Metallurgy and Materials,2024,31(3):413-426.

9Yunping Chen,Jie Hu,Zhiwen Cai,Jingya Yang,Wei Zhou,Qiong Hu,Cong Wang,Liangzhi You,Baodong Xu.A phenology-based vegetation index for improving ratoon rice mapping using harmonized Landsat and Sentinel-2 data[J].Journal of Integrative Agriculture,2024,23(4):1164-1178. 被引量：1

10Wenyan Guo,Zhuolin Hou,Fang Dai,Xiaoxia Wang,Yufan Qiang.Bald Eagle Search Optimization Algorithm Combined with Spherical Random Shrinkage Mechanism and Its Application[J].Journal of Bionic Engineering,2024,21(1):572-605.

Basic Information:

DOI：

Chinese Library Classification Number:TG146.23[金属学及工艺—金属材料]

Citation Information:

Traditional theoretical and empirical calculation methods can guide the design of β-and metastable β-alloys for bio-titanium. However, it is still difficult to obtain novel near-β-Ti alloys with low modulus. This study developed a method that combines machine learning with calculation of phase diagrams(CALPHAD) to facilitate the design of near-β-Ti alloys. An elastic modulus database of Ti–Nb–Zr–Mo–Ta–Sn system was constructed first, and then three features(the electron to atom ratio, mean absolute deviation of atom mass, and mean electronegativity) were selected as the key factors of modulus by performing a three-step feature selection. With these features, a highly accurate model was built for predicting the modulus of near-β-Ti alloys. To further ensure the accuracy of modulus prediction, machine learning with the elastic constants calculated was leveraged by CALPHAD database. The root mean square error of the well-trained model can be as low as 6.75 GPa. Guided by the prediction of machine learning and CALPHAD, three novel near-β-Ti alloys with elastic modulus below 50 GPa were successfully designed in this study. The best candidate alloy(Ti–26Nb–4Zr–4Sn–1Mo–Ta) exhibits an ultra-low modulus(36.6 GPa) after cold rolling with a thickness reduction of 20%. Our method can greatly save time and resources in the development of novel Ti alloys, and experimental verifications have demonstrated the reliability of this method.