Addressing the exceptional properties of aluminium alloy composites reinforced with graphene, this study presents an interpretable machine learning approach to aid in the rapid and efficient design of such materials. Initially, data on these composites were gathered and optimised in order to create a dataset of composition/process-property. Several machine learning algorithms were used to train various models. The SHAP method was used to interpret and select the best performing model, which happened to be the CatBoost model. The model achieved accurate predictions of hardness and tensile strength, with coefficients of determination of 0.9597 and 0.9882, respectively, and average relative errors of 6.02% and 5.01%, respectively. The results obtained from the SHAP method unveiled the correlation between the composition, process and properties of aluminium alloy composites reinforced with graphene. By comparing the predicted and experimental data in this study, all machine learning models exhibited prediction errors within 10%, confirming their ability to generalise. This study offers valuable insights and support for designing high-performance aluminium matrix composites reinforced with graphene and showcases the implementation of machine learning in materials science.

Graphene has become an ideal reinforcement for reinforced metal matrix composites due to its excellent mechanical properties. However, the theory of graphene reinforcement in graphene/aluminum matrix composites is not yet well developed. In this paper, the effect of different temperatures on the mechanical properties of the metal matrix is investigated using a classical molecular dynamics approach, and the effects of the configuration and distribution of graphene in the metal matrix on the mechanical properties of the composites are also described in detail. It is shown that in the case of a monolayer graphene-reinforced aluminum matrix, the simulated stretching process does not break the graphene as the strain increases, but rather, the graphene and the aluminum matrix have a shearing behavior, and thus, the graphene “pulls out" from the aluminum matrix. In the parallel stretching direction, the tensile stress tends to increase with the increase of the graphene area ratio. In the vertical stretching direction, the tensile stress tends to decrease as the percentage of graphene area increases. In the parallel stretching direction, the tensile stress of the system tends to decrease as the angle between graphene and the stretching direction increases. It is important to investigate the effect of a different graphene distribution in the aluminum matrix on the mechanical properties of the composites for the design of high-strength graphene/metal matrix composites.

The adsorption of CO, H₂S and CH₄ on the intrinsic SnS₂ monolayer and SnS₂ monolayer with S-vacancy were studied by the first principle method. The most stable adsorption geometry was determined, and the electronic structure and differential charge were calculated. The results show that the band gap value of SnS₂ monolayer with S-vacancy decreases and the surface activity increases. Compared with the intrinsic SnS₂ monolayer, from the adsorption energy, electron transfer and adsorption distance of CO, H₂S and CH₄ on SnS₂ monolayer with S-vacancy, it can be seen that the S vacancy system is more sensitive to these gases. The results show that the SnS₂ monolayer with S-vacancy is more sensitive to three gases, which provides a new design idea for SnS₂ based gas sensor. As seen from the graphical abstract, the gas molecules (CO, H₂S, CH₄) on SnS₂ monolayer with S vacancy has stronger adsorption energy than the intrinsic SnS₂ surface, and the adsorption properties of H₂S gas molecule on SnS₂ monolayer with S-vacancy surface has the strongest adsorption energy −0.77 eV. It indicate that SnS₂ monolayer with S-vacancy can be used as a promising gas detection material. Statement of article significance: First-principles studies were performed to investigate the electronic structures and adsorptive property of SnS₂ monolayer and SnS₂ monolayer with S-Vacancy with adsorbents CH₄, CO and H₂S molecules. The adsorption order of the three gases on the intrinsic surface is H₂S > CH₄ > CO. The adsorption order of the three gases on SnS₂ monolayer with S-vacancy is H₂S > CO > CH₄. In addition, the results indicate that the adsorption energy of H₂S on SnS₂ monolayer with S-vacancy is strong. The work provides a new design idea for SnS₂ based gas sensor. GRAPHICAL ABSTRACT

The creep life prediction of austenitic heat-resistant steel is necessary to guarantee the safe operation of the high-temperature components in thermal power plants. This work presents a machine learning model that can be applied to predict the creep life of austenitic steels, offering a novel method and approach for such predictions. In this paper, creep life data from six typical austenitic heat-resistant steels are used to predict their creep life using various machine learning models. Moreover, the dissimilarities between the machine learning model and the conventional lifetime prediction method are compared. Finally, the influence of different input characteristics on creep life is discussed. The results demonstrate that the prediction accuracy of machine learning depends on both the model and the dataset used. The Gaussian model based on the second dataset achieves the highest level of prediction accuracy. Additionally, the accuracy and the generalization ability of the machine learning model prediction are significantly better than those of the traditional model. Lastly, the effect of the input characteristics on creep life is generally consistent with experimental observations and theoretical analyses.

Inspired by the recent use of two-dimensional nanomaterials as gas sensors, we used density functional theory calculations to study the adsorption of gas molecules (CH ₄ , CO and H ₂ O) on sandwich vanadium dioxide tablets. The results showed that of all these gases, only the CH ₄ gas molecule was the electron acceptor with significant charge transfer on the VO ₂ sheet. The adsorption energies of CH ₄ , CO and H ₂ O are −229.5 meV, −239.1 meV and −388.3 meV, respectively. We have also compared the adsorption energy of three different gas molecules on the VO ₂ surface, our calculation results show that when the three kinds of gases are adsorbed on the VO ₂ surface, the order of the surface adsorption energy is H ₂ O > CO > CH ₄ . It is also found that after adsorption of CH ₄ , CO and H ₂ O molecules, the electronic properties of VO ₂ sheet changed obviously. However, due to the strong adsorption of H ₂ O molecule on VO ₂ sheet, it is difficult to desorption, which hinders its application in gas molecular sensors. The optical properties of VO ₂ sheet are further calculated. The absorption of CH ₄ , CO and H ₂ O molecules is introduced to red-shift the dielectric function of the thin film, which indicates that the optical properties of the thin film have changed significantly. According to the change of optical properties of VO ₂ sheet before and after molecular adsorption, VO ₂ can be used as a highly selective optical gas sensor for CH ₄ , CO and H ₂ O detection. These results provide a new approach for the potential application of VO ₂ based optical gas sensors.

First-principles calculations based on density functional theory were employed to study the adsorption of gas molecules (CH₄, CO, H₂O) on various SnO₂ (110) surfaces. We found that CO and CH₄ molecules are weakly adsorbed on intrinsic SnO₂ (110) surfaces, and intrinsic SnO₂ is sensitive only to the H₂O molecule. Compared with the gas molecules adsorbed on the intrinsic SnO₂ surfaces, the significantly increased adsorption energy indicates that there is an improvement in the gas sensitivity properties of Co-doped SnO₂ (Co/SnO₂) and oxygen vacancy modified Co-doped SnO₂ (Co/V_O/SnO₂) to CO, CH₄, and H₂O gas. The CO adsorbed on the Co/V_O/SnO₂ surface has the strongest adsorption energy (−1.402 eV). We also studied the optical properties of the Co/SnO₂ and Co/V_O/SnO₂ surfaces influenced by the three gas molecules. We found that the three gas molecules cause an enhancement of the adsorption peaks of Co/SnO₂ configuration in the visible light range. Our study benefits research on the potential application of SnO₂ sensor materials.