Predicting mechanical properties of metals from big data is of great importance to materials engineering. The present work aims at applying artificial neural network (ANN) models to predict the tensile properties including yield strength (YS) and ultimate tensile strength (UTS) on austenitic stainless steel as a function of chemical composition, heat treatment and test temperature. The developed models have good prediction performance for YS and UTS, with R values over 0.93. The models were also tested to verify the reliability and accuracy in the context of metallurgical principles and other data published in the literature. In addition, the mean impact value analysis was conducted to quantitatively examine the relative significance of each input variable for the improvement of prediction performance. The trained models can be used as a guideline for the preparation and development of new austenitic stainless steels with the required tensile properties.

Vibration of Br⁻ during the Na⁺ ion migration can significantly reduce ion migration activation energy. Therefore, compared to chlorides, bromide should be able to achieve lower migration activation energy and higher Na⁺ ion conduction.

In accelerator driven systems (ADSs), steels will suffer not only from the irradiation damage produced by protons or neutrons, but also from the dissolution corrosion induced by the liquid lead–bismuth eutectic (LBE). In this work we investigate the interactions between LBE atoms (Pb, Bi) and the irradiation induced defects X (X is helium, vacancy or divacancy) in α-Fe based on first-principles calculations. It is found that LBE atoms repulse each other without irradiation defects, while they aggregate easily with the defects to form X–Pb_n and X–Bi_n complexes. This indicates that the irradiation defects could promote the aggregation of LBE atoms in iron, especially Bi atoms. The total binding energies of the X–Pb_n and X–Bi_n complexes increase with the number of Pb and Bi atoms, respectively. The origin of the total binding energies of the complexes is further discussed via the electronic structures and the distortion of the crystalline lattice. Finally, the concentration evolutions of the Vac–(Bi)_n complexes and unbound vacancies with temperature are predicted by the mass action analysis. This work provides important information for the synergistic effect of irradiation and LBE corrosion on the steels in the ADSs, which can be used as basic parameters for further study.

The strengthening energy or embrittling potency of an alloying element is a fundamental energetics of the grain boundary (GB) embrittlement that control the mechanical properties of metallic materials. A data-driven machine learning approach has recently been used to develop prediction models to uncover the physical mechanisms and design novel materials with enhanced properties. In this work, to accurately predict and uncover the key features in determining the strengthening energies, three machine learning methods were used to model and predict strengthening energies of solutes in different metallic GBs. In addition, 142 strengthening energies from previous density functional theory calculations served as our dataset to train three machine learning models: support vector machine (SVM) with linear kernel, SVM with radial basis function (RBF) kernel, and artificial neural network (ANN). Considering both the bond-breaking effect and atomic size effect, the nonlinear kernel based SVR model was found to perform the best with a correlation of r² ~ 0.889. The size effect feature shows a significant improvement to prediction performance with respect to using bond-breaking effect only. Moreover, the mean impact value analysis was conducted to quantitatively explore the relative significance of each input feature for improving the effective prediction.