Anti-wear performance is vital for the lifespan of moving component. Herein, ultra-low wear, even negative wear was obtained for the tungsten carbide/bronze composites prepared by additive manufactured binder jet printing (BJPWC), especially when sliding contact with silicon carbide (SiC) ceramic. Sliding interface observation reveals that the promising tribological performance of SiC/BJPWC is ascribed to the in-situ formed stable tribofilm which can deliver beneficial friction reduction and anti-wear effects. The friction process between SiC balls and WC/bronze composite under varying loads induces the diffusion of Si atoms toward the sliding interface, where they form negative mixing enthalpy and network chemical bonds with other metals, promoting the amorphization of the tribo-layer. An in-situ formed unique nanocomposite protective layer is generated, in which Cu/WC nanocrystals are uniformly dispersed within a silicate amorphous matrix. This unique structure effectively accommodates friction-induced plastic deformation and resist damage. This work can provide some basic understandings for the ultra-low wear materials, and guides the selection of sliding counterparts for future application of additive manufactured component.

One key challenge in materials informatics is how to effectively use the material data of small size to search for desired materials from a huge unexplored material space. We review the recent progress on the use of tools from data science and domain knowledge to mitigate the issues arising from limited materials data. The enhancement of data quality and amount via data augmentation and feature engineering is first summarized and discussed. Then the strategies that use ensemble model and transfer learning for improved machine learning model are overviewed. Next, we move to the active learning with emphasis on the uncertainty quantification and evaluation. Subsequently, the merits of the combination of domain knowledge and machine learning are stressed. Finally, we discuss some applications of large language models in the field of materials science. We summarize this review by posing the challenges and opportunities in the field of machine learning for small material data.