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.

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.

The effects of alloying elements (Si, Cr, Mo) on the solution and diffusion of oxygen (O) atoms at the grain boundary of iron (Fe) Σ5(310)/[001] are investigated by the simulations of ab initio density functional theory (DFT). It is found that Si, Mo and Cr prefer to segregate to the grain boundary, and further affect the solution and diffusion of O atoms at Fe grain boundaries. The segregated Cr promotes the solution of O, while Si and Mo inhibit the solution of O at the grain boundary. Meanwhile, Cr and Si accelerate the diffusion of O, and Mo retards the diffusion of O in the grain boundary. Further analysis indicates that the effects are closely related to the interactions between the alloying elements and O atoms, which are determined by the competition between the distortion of local structure and the charge transfer between local atoms. Finally, the effects of alloying elements on the O concentration distribution near the grain boundary are explored by employing the Langmuir–McLean models. This work not only provides insights into the effects of alloying elements on the solution and diffusion of O at grain boundaries, but also provides parameters of the atomic interactions for the initial oxidation simulation on a large scale, which relates to the growth of oxide in polycrystalline systems with various grain sizes at experimental temperatures.