摘要：Machine learning (ML) has been widely used todesign and develop new materials owing to its low computational cost and powerful predictive capabilities. In recentyears, the shortcomings of ML in materials science have gradually emerged, with a primary concern being the scarcity ofdata. It is challenging to build reliable and accurate ML modelsusing limited data. Moreover, the small sample size problemwill remain long-standing in materials science because of theslow accumulation of material data. Therefore, it is importantto review and categorize strategies for small-sample learningfor the development of ML in materials science. This reviewsystematically sorts the research progress of small-samplelearning strategies in materials science, including ensemblelearning, unsupervised learning, active learning, and transferlearning. The directions for future research are proposed, including few-shot learning, and virtual sample *** importantly, we emphasize the significance of embedding material domain knowledge into ML and elaborate on thebasic idea for implementing this strategy.

摘要：The effects of Ni content, soldering temperature and time on the IMC thickness in Sn-3Ag-0.5Cu and Sn-3Ag-0.5Cu-0.2Co alloys were researched using uniform design method and computer programs. For each alloy, the factors were divided into three levels in the experiment. Two correlative equations are given by regression. They indicate that the effects of three factors on the function are in the mutual and quadratic forms. And the analysis of variance shows the equations are sound and meaningful. Using the equations, it is easy to search, predict and control the IMC thickness. The existence of element Co accelerates the crystallization and growing up of IMC.

摘要：高强复合材料的低位错存储性能及其引发的强塑倒置问题阻碍了该系列材料的进一步发展.本文通过新颖的形变驱动冶金方法,设计了一种巧妙的具有粗细晶粒异质结构的纳微混合SiC增强铝基复合材料.基于背应力理论对累积的几何必须位错和晶内分散的SiC颗粒进行调控,使得背应力与外在施加应力保持动态平衡.这是本策略实现材料强塑性协同的关键.所设计的SiC_(5np-5μp)/Al复合材料的极限抗拉强度和均匀伸长率分别为324 MPa和12.9%,达到SiC_(10μp)/Al抗拉强度的181%,而塑性仅损失了约3%.因此,本文提供了一种基于背应力优化的强度-塑性协同新策略.

摘要：As one of the most promising next-generation energy storage devices,the lithium-metal battery has been extensively ***,safety issues and undesired lithium dendrite growth hinder its *** application of solid-state electrolytes has attracted increasing attention as they can solve safety issues and show great potential to inhibit the growth of lithium *** oxide(PEO)-based electrolytes are very promising due to their enhanced safety and excellent ***,they suffer from low ionic conductivity at room temperature and cannot effectively inhibit lithium dendrites at high temperatures due to the intrinsic semicrystalline properties and poor mechanical *** this work,a novel coral-like Li_(6.25)Al_(0.25)La_(3)Zr_(2)O_(12)(C-LALZO)is synthesized to serve as an active ceramic filler in *** PEO with LALZO coral(PLC)exhibits increased ionic conductivity and mechanical strength,which leads to uniform deposition/stripping of lithium *** Li symmetric cells with PLC do not cause a short circuit after cycling for 1500 h at 60℃.The assembled LiFePO_(4)/PLC/Li batteries display excellent cycling stability at both 60 and 50℃.This work reveals that the electrochemical properties of the composite electrolyte can be effectively improved by tuning the microstructure of the filler,such as the C-LALZO architecture.