Recent advances in generative modeling, namely Diffusion models, have
revolutionized generative modeling, enabling high-quality image generation
tailored to user needs. This paper proposes a framework for the generative
design of structural components. Specifically, we employ a Latent Diffusion
model to generate potential designs of a component that can satisfy a set of
problem-specific loading conditions. One of the distinct advantages our
approach offers over other generative approaches, such as generative
adversarial networks (GANs), is that it permits the editing of existing
designs. We train our model using a dataset of geometries obtained from
structural topology optimization utilizing the SIMP algorithm. Consequently,
our framework generates inherently near-optimal designs. Our work presents
quantitative results that support the structural performance of the generated
designs and the variability in potential candidate designs. Furthermore, we
provide evidence of the scalability of our framework by operating over voxel
domains with resolutions varying from $32^3$ to $128^3$. Our framework can be
used as a starting point for generating novel near-optimal designs similar to
topology-optimized designs.

该论文提出了一个用于生成结构组件设计的框架，利用潜在扩散模型生成满足一系列问题特定加载条件的潜在设计，从而具有编辑现有设计的优势。通过使用结构拓扑优化得到的几何数据集进行训练，我们的框架生成了近乎最优的设计，并提供了定量结果支持生成设计的结构性能和潜在候选设计的变化性，以及框架的可扩展性的证据。此框架可用作生成类似拓扑优化设计的新近乎最优设计的起点。

结构部件设计的潜在扩散模型

Latent Diffusion Models for Structural Component Design

Predicting potential risks associated with the fatigue of key structural
components is crucial in engineering design. However, fatigue often involves
entangled complexities of material microstructures and service conditions,
making diagnosis and prognosis of fatigue damage challenging. We report a
statistical learning framework to predict the growth of fatigue cracks and the
life-to-failure of the components under loading conditions with uncertainties.
Digital libraries of fatigue crack patterns and the remaining life are
constructed by high-fidelity physical simulations. Dimensionality reduction and
neural network architectures are then used to learn the history dependence and
nonlinearity of fatigue crack growth. Path-slicing and re-weighting techniques
are introduced to handle the statistical noises and rare events. The predicted
fatigue crack patterns are self-updated and self-corrected by the evolving
crack patterns. The end-to-end approach is validated by representative examples
with fatigue cracks in plates, which showcase the digital-twin scenario in
real-time structural health monitoring and fatigue life prediction for
maintenance management decision-making.

研究设计了一种统计学习框架来预测具有不确定性的加载条件下，疲劳裂纹的增长和构件失效寿命，并通过降维和神经网络等技术处理了疲劳裂纹增长的历史依赖性和非线性问题，通过路径切片和重新加权等技术应对了统计噪声和罕见事件，对疲劳裂纹进行了自更新和自纠正，实时监测结构健康和疲劳寿命预测以支持维修管理决策的数字孪生情景进行了验证。

通过路径切片和重新加权预测疲劳裂纹扩展

Predicting Fatigue Crack Growth via Path Slicing and Re-Weighting

We present a two-dimensional (2-D) fitting algorithm (GALFIT) designed to
extract structural components from galaxy images, with emphasis on closely
modeling light profiles of spatially well-resolved, nearby galaxies observed
with the Hubble Space Telescope. Our algorithm improves on previous techniques
in two areas, by being able to simultaneously fit a galaxy with an arbitrary
number of components, and with optimization in computation speed, suited for
working on large galaxy images. We use 2-D models such as the ``Nuker'' law,
the Sersic (de Vaucouleurs) profile, an exponential disk, and Gaussian or
Moffat functions. The azimuthal shapes are generalized ellipses that can fit
disky and boxy components. Many galaxies with complex isophotes, ellipticity
changes, and position-angle twists can be modeled accurately in 2-D. When
examined in detail, we find that even simple-looking galaxies generally require
at least three components to be modeled accurately, rather than the one or two
components more often employed. We illustrate this by way of 7 case studies,
which include regular and barred spiral galaxies, highly disky lenticular
galaxies, and elliptical galaxies displaying various levels of complexities. A
useful extension of this algorithm is to accurately extract nuclear point
sources in galaxies. We compare 2-D and 1-D extraction techniques on simulated
images of galaxies having nuclear slopes with different degrees of cuspiness,
and we then illustrate the application of the program to several examples of
nearby galaxies with weak nuclei.

本文提出了一个用于从星系图像中提取结构组成的二维拟合算法（GALFIT），并指出在优化计算速度方面相较于以往技术有了改进。该算法可适应任意数量零散构件的拟合，并广泛适用于通过哈勃太空望远镜观察到的近距离星系的光线轮廓。同时，文章进行了七个案例研究以演示其结果的精度.