α-CoSn3 IMC弹性模量各向异性的第一性原理

焊点微型化的同时,界面IMC在整个焊点中所占比例显著增大,微焊点在服役过程中对界面IMC的取向变得更加敏感. 文中基于密度泛函理论计算了α-CoSn₃的晶格常数和弹性模量各向异性,并比较了常见IMC的各向异性指数. 结果表明,[100]方向的抗线性压缩能力小于其它两个主晶轴;(100)剪切面抵抗剪切变形的能力大于其它两个主晶面. 根据差分电子密度图分析了成键轨道的具体贡献. α-CoSn₃三维弹性模量随晶体取向变化的三维图及投影图直观的展现它们各向异性的性质. 计算了α-CoSn₃各向异性指数,并与常见IMC比较了各向异性程度,得到α-CoSn₃各向异性程度居中的结论.     

Semantic segmentation of track image based on deep neural network

In this paper, deep learning technology was utilited to solve the railway track recognition in intrusion detectionproblem. The railway track recognition can be viewed as semantic segmentation task which extends imageprocessing to pixel level prediction. An encoder-decoder architecture DeepLabv3 + model was applied in this workdue to its good performance in semantic segmentation task. Since images of the railway track collected from thevideo surveillance of the train cab were used as experiment dataset in this work, the following improvements weremade to the model. The first aspect deals with over-fitting problem due to the limited amount of training data. Dataaugmentation and transfer learning are applied consequently to rich the diversity of data and enhance modelrobustness during the training process. Besides, different gradient descent methods are compared to obtain theoptimal optimizer for training model parameters. The third problem relates to data sample imbalance, cross entropy(CE) loss is replaced by focal loss (FL) to address the issue of serious imbalance between positive and negativesample. Effectiveness of the improved DeepLabv3 + model with above solutions is demonstrated by experimentresults with different system parameters.