Microstructural and mechanical properties assessment of transient liquid phase bonding of CoCuFeMnNi high entropy alloy

The transient liquid phase (TLP) bonding of CoCuFeMnNi high entropy alloy (HEA) was studied. The TLP bonding was performed using AWS BNi-2 interlayer at 1050 °C with the TLP bonding time of 20, 60, 180 and 240 min. The effect of bonding time on the joint microstructure was characterized by SEM and EDS. Microstructural results confirmed that complete isothermal solidification occurred approximately at 240 min of bonding time. For samples bonded at 20, 60 and 180 min, athermal solidification zone was formed in the bonding area which included Cr-rich boride and Mn₃Si intermetallic compound. For all samples, the γ solid solution was formed in the isothermal solidification zone of the bonding zone. To evaluate the effect of TLP bonding time on mechanical properties of joints, the shear strength and micro-hardness of joints were measured. The results indicated a decrement of micro-hardness in the bonding zone and an increment of micro-hardness in the adjacent zone of joints. The minimum and maximum values of shear strength were 100 and 180 MPa for joints with the bonding time of 20 and 240 min, respectively.     

高熵形状记忆合金的研究进展

高熵形状记忆合金是在等原子比NiTi合金的基础上,结合高熵合金的概念,逐渐发展起来的一种新型高温形状记忆合金。近年来,已开发出了综合性能优异的(TiZrHf)50(NiCoCu)50系和(TiZrHf)50(NiCuPd)50系高熵形状记忆合金,引起了广泛的关注和研究兴趣。本文从物相组成、微观组织、马氏体相变行为、形状记忆效应和超弹性等角度出发,综述了高熵形状记忆合金的研究进展,并对高熵形状记忆合金未来的研究重点进行了展望。     

Machine learning of phases and mechanical properties in complex concentrated alloys

The mechanical properties of complex concentrated alloys (CCAs) depend on their formed phases and corresponding microstructures.The data-driven prediction of the phase formation and associated mechanical properties is essential to discovering novel CCAs.The present work collects 557 samples of various chemical compositions,comprising 61 amorphous,167 single-phase crystalline,and 329 multi-phases crystalline CCAs.Three classification models are developed with high accuracies to category and understand the formed phases of CCAs.Also,two regression models are constructed to predict the hard-ness and ultimate tensile strength of CCAs,and the correlation coefficient of the random forest regression model is greater than 0.9 for both of two targeted properties.Furthermore,the Shapley additive expla-nation (SHAP) values are calculated,and accordingly four most important features are identified.A significant finding in the SHAP values is that there exists a critical value in each of the top four fea-tures,which provides an easy and fast assessment in the design of improved mechanical properties of CCAs.The present work demonstrates the great potential of machine learning in the design of advanced CCAs.     

Investigation the effect of FeNiCoCrMo HEA addition on properties of B4C ceramic prepared by spark plasma sintering

In this study, monolithic B₄C and B₄C-based ceramics incorporating FeNiCoCrMo dual-phase (FCC and BCC) high entropy alloys (HEAs) were produced by spark plasma sintering (SPS). The effect of additives on the densification behavior, mechanical properties, microstructures, and phase evaluation of the samples were investigated. X-ray analysis confirmed the existence of FCC structured HEA and depletion of BCC structured HEA, after high-temperature reaction between B₄C-HEAs. The addition of HEAs enhanced the densification behavior by liquid phase sintering. Furthermore, hardness and fracture toughness values of the samples increased with increasing HEAs content. Fracture toughness and hardness values for all composites were higher than the monolithic B₄C. A combination of the highest density (∼99.22 %) and the best mechanical properties (32.3 GPa hardness and 4.53 MPa m^1/2 fracture toughness) was achieved with 2.00 vol.% HEA addition.     

基于GA-BP的汽车风振噪声声品质预测模型

目前对于汽车风振噪声的优化研究主要以声压级（Sound pressure level，SPL）作为单一评价指标，既不能全面反映噪声的物理属性，也无法考虑人耳对噪声的主观认知过程。为准确评价风振噪声，引入声品质，运用大涡模拟（Large eddy simulation，LES）对风振噪声进行数值仿真，根据实车道路试验判断仿真的准确性；对仿真结果进行声品质客观评价与主观评价，综合声品质客观评价参数与声品质主观评价试验结果建立BP神经网络预测模型；利用遗传算法（Genetic algorithm，GA），进一步对BP神经网络的结构参数进行优化，建立GA-BP声品质预测模型。研究结果表明，GA-BP声品质预测模型在训练速度和预测精度上都优于BP神经网络预测模型。预测模型基于声品质主客观评价结果，其预测值可以代替传统的声压级评价指标，为风振噪声提供更为准确合理的评价。     

基于PBFT区块链技术的电网企业仓储系统

提出了一种基于实用拜占庭容错(PBFT)算法的区块链技术,首先对传统的实用拜占庭容错算法原理进行了阐述,该传统算法包含前期、需求、预准备、准备、确认、答复6个阶段,但传统算法具有实时性差、缺乏惩罚机制、带宽高的缺点。针对出现的这些问题,又对传统算法进行了改进,具体涉及记账节点、共识过程以及视图切换过程。通过测试进一步证明了该改进算法的实用性,并将该算法应用于电网企业中,构建的虚拟仓库实现了联储联备,降低了库存资金的耗费,并且提高了电网企业库存管理的效率。     

基于NR-Transformer的集群作业运行时间预测

高性能集群的作业调度通常使用作业调度系统来实现，准确填写作业运行时间能在很大程度上提升作业调度效率。现有的研究通常使用机器学习的预测方式，在预测精度和实用性上还存在一定的提升空间。为了进一步提高集群作业运行时间预测的准确率，考虑先对集群作业日志进行聚类，将作业类别信息添加到作业特征中，再使用基于注意力机制的NR-Transformer网络对作业日志数据建模和预测。在数据处理上，根据与预测目标的相关性、特征的完整性和数据的有效性，从历史日志数据集中筛选出7维特征，并按作业运行时间的长度将其划分为多个作业集，再对各作业集分别进行训练和预测。实验结果表明，相比于传统机器学习和BP神经网络，时序神经网络结构有更好的预测性能，其中NR-Transformer在各作业集上都有较好的性能。