Deep Generative Models for Geometric Design Under Uncertainty

• URL: http://arxiv.org/abs/2112.08919v1
• Date: Wed, 15 Dec 2021 18:00:46 GMT
• Title: Deep Generative Models for Geometric Design Under Uncertainty
• Authors: Wei (Wayne) Chen, Doksoo Lee, Wei Chen
• Abstract summary: We propose a Generative Adversarial Network-based Design under Uncertainty Framework (GAN-DUF) GAN-DUF contains a deep generative model that simultaneously learns a compact representation of nominal (ideal) designs and the conditional distribution of fabricated designs. We demonstrated the framework on two real-world engineering design examples and showed its capability of finding the solution that possesses better performances after fabrication.
• Score: 8.567987231153966
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep generative models have demonstrated effectiveness in learning compact and expressive design representations that significantly improve geometric design optimization. However, these models do not consider the uncertainty introduced by manufacturing or fabrication. Past work that quantifies such uncertainty often makes simplified assumptions on geometric variations, while the "real-world" uncertainty and its impact on design performance are difficult to quantify due to the high dimensionality. To address this issue, we propose a Generative Adversarial Network-based Design under Uncertainty Framework (GAN-DUF), which contains a deep generative model that simultaneously learns a compact representation of nominal (ideal) designs and the conditional distribution of fabricated designs given any nominal design. We demonstrated the framework on two real-world engineering design examples and showed its capability of finding the solution that possesses better performances after fabrication.

Related papers

• Cliqueformer: Model-Based Optimization with Structured Transformers [102.55764949282906]
  We develop a model that learns the structure of an MBO task and empirically leads to improved designs. We evaluate Cliqueformer on various tasks, ranging from high-dimensional black-box functions to real-world tasks of chemical and genetic design.
  arXiv  Detail & Related papers  (2024-10-17T00:35:47Z)
• An Uncertainty-aware Deep Learning Framework-based Robust Design Optimization of Metamaterial Units [14.660705962826718]
  We propose a novel uncertainty-aware deep learning framework-based robust design approach for the design of metamaterial units. We demonstrate that the proposed design approach is capable of designing high-performance metamaterial units with high reliability.
  arXiv  Detail & Related papers  (2024-07-19T22:21:27Z)
• Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models [54.132297393662654]
  We introduce a hybrid method that fine-tunes cutting-edge diffusion models by optimizing reward models through RL. We demonstrate the capability of our approach to outperform the best designs in offline data, leveraging the extrapolation capabilities of reward models.
  arXiv  Detail & Related papers  (2024-05-30T03:57:29Z)
• Diffusion Model for Data-Driven Black-Box Optimization [54.25693582870226]
  We focus on diffusion models, a powerful generative AI technology, and investigate their potential for black-box optimization. We study two practical types of labels: 1) noisy measurements of a real-valued reward function and 2) human preference based on pairwise comparisons. Our proposed method reformulates the design optimization problem into a conditional sampling problem, which allows us to leverage the power of diffusion models.
  arXiv  Detail & Related papers  (2024-03-20T00:41:12Z)
• Generative VS non-Generative Models in Engineering Shape Optimization [0.3749861135832073]
  We compare the effectiveness and efficiency of generative and non-generative models in constructing design spaces. Non-generative models generate robust latent spaces with none or significantly fewer invalid designs when compared to generative models.
  arXiv  Detail & Related papers  (2024-02-13T15:45:20Z)
• Compositional Generative Inverse Design [69.22782875567547]
  Inverse design, where we seek to design input variables in order to optimize an underlying objective function, is an important problem. We show that by instead optimizing over the learned energy function captured by the diffusion model, we can avoid such adversarial examples. In an N-body interaction task and a challenging 2D multi-airfoil design task, we demonstrate that by composing the learned diffusion model at test time, our method allows us to design initial states and boundary shapes.
  arXiv  Detail & Related papers  (2024-01-24T01:33:39Z)
• Latent Diffusion Models for Structural Component Design [11.342098118480802]
  This paper proposes a framework for the generative design of structural components. We employ a Latent Diffusion model to generate potential designs of a component that can satisfy a set of problem-specific loading conditions.
  arXiv  Detail & Related papers  (2023-09-20T19:28:45Z)
• Design Space Exploration and Explanation via Conditional Variational Autoencoders in Meta-model-based Conceptual Design of Pedestrian Bridges [52.77024349608834]
  This paper provides a performance-driven design exploration framework to augment the human designer through a Conditional Variational Autoencoder (CVAE) The CVAE is trained on 18'000 synthetically generated instances of a pedestrian bridge in Switzerland.
  arXiv  Detail & Related papers  (2022-11-29T17:28:31Z)
• Hierarchical Deep Generative Models for Design Under Free-Form Geometric Uncertainty [7.362287148334665]
  We propose a Generative Adversarial Network-based Design under Uncertainty Framework (GAN-DUF) It simultaneously learns a compact representation of nominal (ideal) designs and the conditional distribution of fabricated designs given any nominal design. We can combine the proposed deep generative model with robust design optimization or reliability-based design optimization for design under uncertainty.
  arXiv  Detail & Related papers  (2022-02-21T22:21:07Z)
• Inverse design of photonic devices with strict foundry fabrication constraints [55.41644538483948]
  We introduce a new method for inverse design of nanophotonic devices which guarantees that designs satisfy strict length scale constraints. We demonstrate the performance and reliability of our method by designing several common integrated photonic components.
  arXiv  Detail & Related papers  (2022-01-31T02:27:25Z)
• PaDGAN: A Generative Adversarial Network for Performance Augmented Diverse Designs [13.866787416457454]
  We develop a variant of the Generative Adversarial Network, named "Performance Augmented Diverse Generative Adversarial Network" or PaDGAN, which can generate novel high-quality designs with good coverage of the design space. In comparison to a vanilla Generative Adversarial Network, on average, it generates samples with a 28% higher mean quality score with larger diversity and without the mode collapse issue.
  arXiv  Detail & Related papers  (2020-02-26T04:53:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.