As a generalized method of mathematical statistics, machine learning (ML) is playing an increasingly significant role in the realm of materials design. More sophisticated methodologies for in-depth understandings and wide applications have been developed from initially simple data relation mappings. The present work first summarizes the basic technical issues of ML and then systematically reviews the main implementation strategies for ML methods in accelerating materials research and development process in recent years, encompassing three primary aspects. Firstly, it is necessary to establish the relationship between the key characteristic parameters and properties in any given materials system for a better prediction and exploration of new materials. Then, the computational algorithms in materials science need to be optimized to replace complex calculations with model-predicted data. Finally, the ML methods are applied to summarize the one-dimensional property data and two-dimensional microstructural images of materials to establish standardized analysis methods. During this process, the domain knowledge in a specific system is of great significance to improving the prediction accuracy and efficiency of ML methods, whether pre-processing experimental or computational databases. The powerful capability of ML methods to handle high-dimensional data will enable researchers to make more effective decisions in materials design. In the future, the relationship between the microstructure and mechanical properties, which is necessary to establish a more effective search engine for alloys with targeted mechanical properties, will be the focus of ML mechanical properties of alloy materials.

The integrity and reliability of surface protective coatings deposited on metal surface could be in-situ monitored via the attractive luminescence sensing technique. In this paper, we report the influence of substrate temperature on the properties of erbium (Er) doped aluminum nitride (AlN) film, which could be applied as a luminescent layer for monitoring the health of multilayered Al/AlN coating. The AlN:Er films were deposited via reactive radio-frequency magnetron sputtering, and the silicon substrate temperature was varied from non-intentional heating up to 400 °C. The composition, morphology, crystalline structure, and dielectric function of the AlN:Er films deposited under these different substrate temperature conditions were studied. These properties of the AlN:Er films show strong correlation with the substrate temperature maintained during film fabrication. The obtained AlN:Er films, without further annealing, exhibited photoluminescence peaks of the Er³⁺ ions in the visible wavelength range and the strongest photoluminescence intensity was observed for the AlN:Er film deposited with the temperature of substrate kept at 300 °C. The results demonstrated in this work offer guidance to optimize the substrate temperature for the deposition of AlN:Er film for future application of this sensing technique to thin metal components.

Depleted uranium has been widely applied in nuclear energy fields. However, its poor corrosion and wear resistance restrict its applications. A titanium/titanium nitride (Ti/TiN) multilayer film was deposited on a uranium surface to improve its fretting wear resistance. Fretting wear tests were carried out using a pin-on-disc configuration. The fretting behaviors of uranium and the Ti/TiN film were investigated under different normal loads. With the normal load increasing, the mode of fretting wear gradually transformed from slip region (SR) to mixed fretting region (MFR) and then to partial slip region (PSR). It is illustrated that the normal load had an obvious effect on the fretting wear behavior. The friction coefficients of both uranium and Ti/TiN multilayer film decreased with the increase of the normal load. In SR, the main wear mechanisms were delamination and abrasion for uncoated uranium, and delamination and oxidation for uranium coated with the Ti/TiN multilayer film. Photoelectron spectroscopy (XPS) analysis also showed that the Ti/TiN coating was oxidized and formed TiO₂ during fretting wear. The wear depth of naked uranium was much greater than that of coated uranium, which demonstrated that the Ti/TiN multilayer film could effectively improve the wear properties of uranium.

Depleted uranium (DU) is oxidized readily due to its chemical activities, which limits its applications in nuclear industry. TiN film has been applied widely due to its good mechanical properties and its excellent corrosion resistance. In this work, TiN protection films were deposited on DU by direct current magnetron sputtering (DCMS) and high power pulsed magnetron sputtering (HPPMS), respectively. The surface morphology and microstructures were investigated by atomic force microscope (AFM), scanning electron microscopy (SEM), and grazing incidence X-ray diffraction (GIXRD). The hardness and Young’s modulus were determined by nano-Indenter. The wear behavior and adhesion was analyzed by pin-on-disc tests and scratch adhesion tests and the corrosion resistance was evaluated by electrochemical measurements. The results show that the TiN films that were deposited by HPPMS outperformed TiN film deposited by DCMS, with improvements on surface roughness, mechanical properties, wear behavior, adhesion strength, and corrosion resistance, thanks to its much denser columnar grain growth structure and preferred orientation of (111) plane with the lowest strain energy. Besides, the process of Ti interlayer deposition by HPPMS can enhance the film properties to an extent as compared to DCMS, which is attributed to the enhanced ion bombardment during the HPPMS.