用结构模态迁移法评定井架的安全承载能力

在评判在用井架的安全承载能力时,常规方法的可靠性较低。为此,提出了结构模态迁移诊断法。该方法考虑了结构整体的动力特性,由加载试验时的模态奇异,可以识别结构内部状态的变化,如焊口断裂、结点松动、构件变形等。诊断时,井架整体结构的阻尼比和振型变化不明显,模态频率或模态群的变化却很显著,因此用它们作为识别标志。结构模态迁移诊断方法客观地反映了井架整体结构状态,现场应用表明,该方法对车载井架、K形和塔形井架的安全承载能力标定可靠,效果良好。

基于事件的局部行为模型的合并

采用模态迁移系统描述系统行为,针对局部行为模型中存在的不确定行为,提出一种基于事件的局部行为模型合并方法。该方法首先定义局部行为模型之间的精化关系,利用精化关系产生合并规则,运用合并规则产生行为模型的极小共同精化模型或最小共同精化模型,从而消除局部行为模型中存在的不确定行为。最后通过一个示例对该方法的有效性作出说明。

基于特征迹的局部场景演化

局部场景是不同的相关用户根据自己所关注的业务功能并结合自己的知识给出的。而不同用户由于各自的知识背景,所了解的工作领域的局限,描述的需求往往存在各种局限。采用模态迁移系统描述系统行为,并引入系统所属领域的特征知识,对场景工具捕获的局部场景进行演化操作,使其演化为更符合用户需求的局部场景。最后通过一个示例对这一方法的有效性进行了说明。

Dynamic Simulation of Shear-induced Particle Migration in a Two-dimensional Circular Couette Device

The shear-induced migration of neutrally-buoyant non-colloidal circular particles in a two-dimensional circular Couette flow is investigated numerically with a distributed Lagrange multiplier based fictitious domain method.The effects of inertia and volume fraction on the particle migration are examined.The results indicate that inertia has a negative effect on the particle migration.In consistence with the experimental observations,the rapid migration of particles near the inner cylinder at the early stage is observed in the simulation,which is believed to be related to the chain-like clustering of particles.The migration of circular particles in a plane Poiseuille flow is also examined in order to further confirm the effect of such clustering on the particle migration at early stage.There is tendency for the particles in the vicinity of outer cylinder in the Couette device to pack into concentric rings at late stage in case of high particle concentration.

Slope displacement prediction based on multisource domain transfer learning for insufficient sample data

Accurate displacement prediction is critical for the early warning of landslides.The complexity of the coupling relationship between multiple influencing factors and displacement makes the accurate prediction of displacement difficult.Moreover,in engineering practice,insufficient monitoring data limit the performance of prediction models.To alleviate this problem,a displacement prediction method based on multisource domain transfer learning,which helps accurately predict data in the target domain through the knowledge of one or more source domains,is proposed.First,an optimized variational mode decomposition model based on the minimum sample entropy is used to decompose the cumulative displacement into the trend,periodic,and stochastic components.The trend component is predicted by an autoregressive model,and the periodic component is predicted by the long short-term memory.For the stochastic component,because it is affected by uncertainties,it is predicted by a combination of a Wasserstein generative adversarial network and multisource domain transfer learning for improved prediction accuracy.Considering a real mine slope as a case study,the proposed prediction method was validated.Therefore,this study provides new insights that can be applied to scenarios lacking sample data.

生成对抗式网络及其医学影像应用研究综述

生成对抗式网络(generative adversarial network,GAN)由负责学习数据分布的生成器和负责鉴别样本真伪的判别器构成,二者在相互对抗过程中互相学习逐渐变强。该网络模型使深度学习方法可以自动学习损失函数,减少了对专家知识的依赖,已经广泛应用于自然图像处理领域,对解决医学影像处理的相关瓶颈问题亦具有巨大应用前景。本文旨在找到生成对抗式网络与医学影像领域面临挑战的结合点,通过分析已有工作对未来研究方向进行展望,为该领域研究提供参考。1)阐述了生成对抗式网络的基本原理,从任务拆分、条件约束以及图像到图像的翻译等角度对其衍生模型进行分析回顾;2)对生成对抗式网络在医学影像领域中的数据增广、模态迁移、图像分割以及去噪等方面的应用进行回顾,分析各方法的优缺点与适用范围;3)对现有图像生成质量评估方法进行小结;4)总结生成对抗式网络在医学影像领域的研究进展,并结合该领域问题特性,指出现有理论应用存在的不足与改进方向。生成对抗式网络提出以来,理论不断完善,在医学影像的处理应用中也取得了长足发展,但仍然存在一些亟待解决的问题,包括3维数据合成、几何结构合理性保持、无标记和未配对数据使用以及多模态数据交叉应用等。