Integrating data mining and machine learning to discover high-strength ductile titanium alloys

Zou, Chengxiong; Li, Jinshan; Wang, William Yi; Zhang, Ying; Lin, De-Ye; Yuan, Ruihao; Wang, Xiaodan; Tang, Bin; Wang, Jun; Gao, Xingyu; Kou, Hongchao; Hui, Xidong; Zeng, Xiaoqin; Qian, Ma; Song, Haifeng; Liu, Zhe; Xu, Dongsheng

doi:10.1016/j.actamat.2020.10.056

Cited by 113 publications

(38 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Without changing the chemical composition, the introduction of defects provides more freedom to optimize microstructures and mechanical properties [ 4 , 5 , 8 ]. In particular, dual-phase materials [ 9 , 10 , 11 ] present ultra-strong and ductile behaviors through solid solution strengthening, the grain refinement effect, and precipitation hardening, which excellently deal with the planar defects, including stacking faults, grain boundaries, and phase boundaries. Through combining a high volume fraction of pyramidally arranged non-shearable super-refined α precipitates in the constrained β matrix, the ultimate strength of α+β dual-phase Ti-15Mo-3Nb-2.7Al-0.2Si (wt %) alloy (the β-21S or TB8 alloy) can be optimized in the range of 1–2 GPa [ 12 ].…”

Section: Introductionmentioning

confidence: 99%

Effect of High Strain Rate on Adiabatic Shearing of α+β Dual-Phase Ti Alloy

Fang

et al. 2021

Materials

Self Cite

View full text Add to dashboard Cite

In the present work, the localized features of adiabatic shear bands (ASBs) of our recently designed damage tolerance α+β dual-phase Ti alloy are investigated by the integration of electron backscattering diffraction and experimental and theoretical Schmid factor analysis. At the strain rate of 1.8 × 104 s−1 induced by a split Hopkinson pressure bar, the shear stress reaches a maximum of 1951 MPa with the shear strain of 1.27. It is found that the α+β dual-phase colony structures mediate the extensive plastic deformations along α/β phase boundaries, contributing to the formations of ASBs, microvoids, and cracks, and resulting in stable and unstable softening behaviors. Moreover, the dynamic recrystallization yields the dispersion of a great amount of fine α grains along the shearing paths and in the ASBs, promoting the softening and shear localization. On the contrary, low-angle grain boundaries present good resistance to the formation of cracks and the thermal softening, while the non-basal slipping dramatically contributes to the strain hardening, supporting the promising approaches to fabricate the advanced damage tolerance dual-phase Ti alloy.

show abstract

Section: Introductionmentioning

confidence: 99%

Effect of High Strain Rate on Adiabatic Shearing of α+β Dual-Phase Ti Alloy

Fang

et al. 2021

Materials

Self Cite

View full text Add to dashboard Cite

show abstract

“…Such processing has widely been conrmed to achieve effective and accurate ML models with a small database (dozens to hundreds of data points) in many previous studies. 44,45 10fold cross-validation suggested by the empirical evidence is utilized here. Since strength and work of fracture are considered in this work, the averaged R 2 of two targets is used for comprehensive performance evaluation of SISSO model in the following discussion.…”

Section: Paper Nanoscale Advancesmentioning

confidence: 99%

SISSO-assisted prediction and design of mechanical properties of porous graphene with a uniform nanopore array

Wei

Guo

et al. 2022

Nanoscale Adv.

View full text Add to dashboard Cite

show abstract

“…Recently, the ML method has been used to develop the atomistic potentials that can boost the computational efficiency of first-principles methods by order of magnitude without affecting the accuracy in, i.e., Al-Mg [153] , Al-Cu [154] , and Al-Si-Mg alloys [155] . Meanwhile, the integration of FP calculations and the ML method to achieve high-throughput calculations and storage of data is also one key for material theory design [156][157][158][159][160] . For example, Wang et al [156] studied the power-law scaled hardness of solute strengthened nonequilibrium solid solutions.…”

Section: Machine Learning Toward Materials-property Relationmentioning

confidence: 99%

Boosting for concept design of casting aluminum alloys driven by combining computational thermodynamics and machine learning techniques

Wang¹,

Liu²,

Gao³

et al. 2021

JMI

View full text Add to dashboard Cite

Casting aluminum alloys are commonly used in industries due to their excellent comprehensive performance. Alloying/microalloying and post-solidification heat treatments are the most common measures to tune the microstructure for enhancing their mechanical properties. However, it is very challenging to achieve accurate and efficient development of novel casting aluminum alloys using the traditional trial-and-error method. With the rapid development of computer technology, the computational thermodynamics (CT) in the framework of the CALculation of PHAse Diagram approach, the data-driven machine learning (ML) technique, and also their combinations have been proved to be effective approaches for the design of casting aluminum alloys. In this review, the state-of-the-art computational alloy design approaches driven by CT and ML techniques, as well as their combinations, were comprehensively summarized. The current status of the thermodynamic database for aluminum alloys, as the core for CT, was also briefly introduced. After that, a variety of successful case studies on the design of different casting aluminum alloys driven by CT, ML, and their combinations were demonstrated, including common applications, CT-driven design of Sc-additional Al-Si-Mg series casting alloys, and design of Srmodified A356 alloys driven by combing CT and ML. Finally, the conclusions of this review were drawn, and perspectives for boosting the computational design approach driven by combining CT and ML techniques were pointed out.

show abstract

Integrating data mining and machine learning to discover high-strength ductile titanium alloys

Cited by 113 publications

References 75 publications

Effect of High Strain Rate on Adiabatic Shearing of α+β Dual-Phase Ti Alloy

Effect of High Strain Rate on Adiabatic Shearing of α+β Dual-Phase Ti Alloy

SISSO-assisted prediction and design of mechanical properties of porous graphene with a uniform nanopore array

Boosting for concept design of casting aluminum alloys driven by combining computational thermodynamics and machine learning techniques

Contact Info

Product

Resources

About