More Like this

1. Machine learning-enabled parameterization scheme for aerodynamic shape optimization of wind-sensitive structures: A proof-of-concept study

   Li, S; Phillips, B; Jiang, Z (September 2024, Wind and Structures)

   Aerodynamic shape optimization is very useful for enhancing the performance of wind-sensitive structures. However, shape parameterization, as the first step in the pipeline of aerodynamic shape optimization, still heavily depends on empirical judgment. If not done properly, the resulting small design space may fail to cover many promising shapes, and hence hinder realizing the full potential of aerodynamic shape optimization. To this end, developing a novel shape parameterization scheme that can reflect real-world complexities while being simple enough for the subsequent optimization process is important. This study proposes a machine learning-based scheme that can automatically learn a low-dimensional latent representation of complex aerodynamic shapes for bluff-body wind-sensitive structures. The resulting latent representation (as design variables for aerodynamic shape optimization) is composed of both discrete and continuous variables, which are embedded in a hierarchy structure. In addition to being intuitive and interpretable, the mixed discrete and continuous variables with the hierarchy structure allow stakeholders to narrow the search space selectively based on their interests. As a proof-of-concept study, shape parameterization examples of tall building cross sections are used to demonstrate the promising features of the proposed scheme and guide future investigations on data-driven parameterization for aerodynamic shape optimization of wind-sensitive structures 

   more » « less
2. Machine learning-enabled parameterization scheme for aerodynamic shape optimization of wind-sensitive structures: A proof-of-concept study

   Li, Shaopeng; Phillips, Brian M; Jiang, Zhaoshuo (September 2024, Wind and Structures)

   Aerodynamic shape optimization is very useful for enhancing the performance of wind-sensitive structures. However, shape parameterization, as the first step in the pipeline of aerodynamic shape optimization, still heavily depends on empirical judgment. If not done properly, the resulting small design space may fail to cover many promising shapes, and hence hinder realizing the full potential of aerodynamic shape optimization. To this end, developing a novel shape parameterization scheme that can reflect real-world complexities while being simple enough for the subsequent optimization process is important. This study proposes a machine learning-based scheme that can automatically learn a low-dimensional latent representation of complex aerodynamic shapes for bluff-body wind-sensitive structures. The resulting latent representation (as design variables for aerodynamic shape optimization) is composed of both discrete and continuous variables, which are embedded in a hierarchy structure. In addition to being intuitive and interpretable, the mixed discrete and continuous variables with the hierarchy structure allow stakeholders to narrow the search space selectively based on their interests. As a proof-of-concept study, shape parameterization examples of tall building cross sections are used to demonstrate the promising features of the proposed scheme and guide future investigations on data-driven parameterization for aerodynamic shape optimization of wind-sensitive structures. 

   more » « less
3. Surrogate-based cyber-physical aerodynamic shape optimization of high-rise buildings using wind tunnel testing

   https://doi.org/10.1016/j.jweia.2023.105586  

   Lu, Wei-Ting; Phillips, Brian M.; Jiang, Zhaoshuo (November 2023, Journal of Wind Engineering and Industrial Aerodynamics)

   This study proposes a surrogate-based cyber-physical aerodynamic shape optimization (SB-CP-ASO) approach for high-rise buildings under wind loading. Three components are developed in the SB-CP-ASO procedure: (1) an adaptive subtractive manufacturing technique, (2) a high-throughput wind tunnel testing procedure, and (3) a flexible infilling strategy. The downtime of the procedure is minimized through a parallel manufacturing and testing (llM&T) technique. An unexplored double-section setback strategy with various cross-sections and transitions positions is used to demonstrate the performance of the proposed procedure. A total of 173 physical specimens were evaluated to reach the optimization convergence within the reserved testing window. Further analysis of promising shapes considering multiple design wind speeds is suggested to achieve target performance objectives at various hazard levels. Practical information on setback and cross-section modification strategies is discussed based on the optimization results. In comparison with a square benchmark model, the roof drifts for promising candidates with similar building volumes are reduced by more than 70% at wind speeds higher than 50 m/s. This procedure is expected to provide an efficient platform between owners, architects, and structural engineers to identify ideal candidates within a defined design space for real-world applications of high-rise buildings. 

   more » « less
4. Shaping freeform nanophotonic devices with geometric neural parameterization

   https://doi.org/10.1038/s41524-025-01752-w  

   Dai, Tianxiang; Shao, Yixuan; Mao, Chenkai; Wu, Yu; Azzouz, Sara; Zhou, You; Fan, Jonathan A (December 2025, npj Computational Materials)

   Abstract Nanophotonic freeform design has the potential to push the performance of optical components to new limits, but there remains a challenge to effectively perform optimization while reliably enforcing design and manufacturing constraints. We present Neuroshaper, a framework for freeform geometric parameterization in which nanophotonic device layouts are defined using an analytic neural network representation. Neuroshaper serves as a qualitatively new way to perform shape optimization by capturing multi-scalar, freeform geometries in an overparameterized representation scheme, enabling effective optimization in a smoothened, high dimensional geometric design space. We show that Neuroshaper can enforce constraints and topology manipulation in a manner where local constraints lead to global changes in device morphology. We further show numerically and experimentally that Neuroshaper can apply to a diversity of nanophotonic devices. The versatility and capabilities of Neuroshaper reflect the ability of neural representation to augment concepts in topological design. 

   more » « less
5. Learning hierarchical features with joint latent space energy-based prior

   Cui, J; Wu, Y N; Han, T (September 2023, IEEE International Conference on Computer Vision (ICCV 2023))

   This paper studies the fundamental problem of multi-layer generator models in learning hierarchical representations. The multi-layer generator model that consists of multiple layers of latent variables organized in a top-down architecture tends to learn multiple levels of data abstraction. However, such multi-layer latent variables are typically parameterized to be Gaussian, which can be less informative in capturing complex abstractions, resulting in limited success in hierarchical representation learning. On the other hand, the energy-based (EBM) prior is known to be expressive in capturing the data regularities, but it often lacks the hierarchical structure to capture different levels of hierarchical representations. In this paper, we propose a joint latent space EBM prior model with multi-layer latent variables for effective hierarchical representation learning. We develop a variational joint learning scheme that seamlessly integrates an inference model for efficient inference. Our experiments demonstrate that the proposed joint EBM prior is effective and expressive in capturing hierarchical representations and modeling data distribution. 

   more » « less