Talks and presentations

Hierarchical Deep Generative Models for Design Under Free-Form Geometric Uncertainty

August 15, 2022

Conference proceedings talk, ASME 2022 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (IDETC-CIE2020), St. Louis, Missouri, USA

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 simplifying assumptions on geometric variations, while the “real-world”, “free-form” 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. This opens up new possibilities of 1) building a universal uncertainty quantification model compatible with both shape and topological designs, 2) modeling free-form geometric uncertainties without the need to make any assumptions on the distribution of geometric variability, and 3) allowing fast prediction of uncertainties for new nominal designs. We can combine the proposed deep generative model with robust design optimization or reliability-based design optimization for design under uncertainty. 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.

IH-GAN: A Conditional Generative Model for Inverse Design of Heterogeneous Cellular Structures

July 22, 2022

Conference workshop talk, ICML 2022 Workshop on Machine Learning in Computational Design, Baltimore, Maryland, USA

Cellular structures with controlled local structures can realize heterogeneous material properties and hence enable a much wider range of functions than homogeneous structures. However, the design of heterogeneous cellular structures is challenging due to the high degrees of design freedom. We propose a simple yet principled way to achieve the fast design of heterogeneous cellular structures. This method uses physics-based optimization to find the optimal material property distribution under given design requirements, and uses a conditional generative model, named Inverse Homogenization Generative Adversarial Network (IH-GAN), to find the local structures that correspond to the optimal material properties. Results show that compared to the conventional variable-density approach, our method achieves a 3.03% reduction in displacement in a compliance minimization problem, and reduces the errors by around 80% in two target deformation problems.

Deep Generative Models for Geometric Design Under Uncertainty

March 01, 2022

Conference workshop talk, AAAI 2022 Workshop on AI for Design and Manufacturing (ADAM), Virtual Conference

FFD-GAN: Deep Generative Model for Efficient 3D Airfoil Parameterization

January 20, 2021

Conference proceedings talk, AIAA Scitech 2021 Forum, Virtual Conference

In aerodynamic shape optimization, the convergence and computational cost are greatly affected by the representation capacity and compactness of the design space. Previous research has demonstrated that using a deep generative model to parameterize two-dimensional (2D) airfoils achieves high representation capacity/compactness, which significantly benefits shape optimization. In this work, we propose a deep generative model, Free-Form Deformation Generative Adversarial Networks (FFD-GAN), that provides an efficient parameterization for three-dimensional (3D) aerodynamic/hydrodynamic shapes like aircraft wings, turbine blades, car bodies, and hulls. The learned model maps a compact set of design variables to 3D surface points representing the shape. We ensure the surface smoothness and continuity of generated geometries by incorporating an FFD layer into the generative model. We demonstrate FFD-GAN’s performance using a wing shape design example. The results show that FFD-GAN can generate realistic designs and form a reasonable parameterization. We further demonstrate FFD-GAN’s high representation compactness and capacity by testing its design space coverage, the feasibility ratio of the design space, and its performance in design optimization. We demonstrate that over 94% feasibility ratio is achieved among wings randomly generated by the FFD-GAN, while FFD and B-spline only achieve less than 31%. We also show that the FFD-GAN leads to an order of magnitude faster convergence in a wing shape optimization problem, compared to the FFD and the B-spline parameterizations.

PaDGAN: A Generative Adversarial Network for Performance Augmented Diverse Designs

August 19, 2020

Conference proceedings talk, ASME 2020 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (IDETC-CIE2020), Virtual Conference

Deep generative models are proven to be a useful tool for automatic design synthesis and design space exploration. When applied in engineering design, existing generative models face three challenges: 1) generated designs lack diversity and do not cover all areas of the design space, 2) it is difficult to explicitly improve the overall performance or quality of generated designs, and 3) existing models generate do not generate novel designs, outside the domain of the training data. In this work, we simultaneously address these challenges by proposing a new Determinantal Point Processes based loss function for probabilistic modeling of diversity and quality. With this new loss function, 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. Using three synthetic examples and one real-world airfoil design example, we demonstrate that PaDGAN can generate diverse and high-quality designs. In comparison to a vanilla Generative Adversarial Network, on average, it generates samples with 28% higher mean quality score with larger diversity and without the mode collapse issue. Unlike typical generative models that usually generate new designs by interpolating within the boundary of training data, we show that PaDGAN expands the design space boundary outside the training data towards high-quality regions. The proposed method is broadly applicable to many tasks including design space exploration, design optimization, and creative solution recommendation.

MO-PaDGAN: Generating Diverse Designs with Multivariate Performance Enhancement

July 18, 2020

Conference workshop talk, Thirty-eighth International Conference on Machine Learning (ICML 2020) workshop on Negative Dependence and Submodularityfor ML, Virtual Conference

Deep generative models have proven useful for automatic design synthesis and design space exploration. However, they face three challenges when applied to engineering design: 1) generated designs lack diversity, 2) it is difficult to explicitly improve all the performance measures of generated designs, and 3) existing models generally do not generate high-performance novel designs, outside the domain of the training data. To address these challenges, we propose MO-PaDGAN, which contains a new Determinantal Point Processes based loss function for probabilistic modeling of diversity and performances. Through a real-world airfoil design example, we demonstrate that MO-PaDGAN expands the existing boundary of the design space towards high-performance regions and generates new designs with high diversity and performances exceeding training data.

Aerodynamic Design Optimization and Shape Exploration using Generative Adversarial Networks

January 11, 2019

Conference proceedings talk (Invited), AIAA Scitech 2019 Forum, San Diego, California, USA

Global optimization of aerodynamic shapes requires a large number of expensive CFD simulations because of the high dimensionality of the design space. One means to combat that problem is to reduce the dimension of the design space—for example, by constructing low dimensional parametric functions (such as PARSEC and others)—and then optimizing over those parameters instead. Such approaches require first a parametric function that compactly describes useful variation in airfoil shape—a non-trivial and error-prone task. In contrast, we propose to use a deep generative model of aerodynamic designs (specifically airfoils) that reduces the dimensionality of the optimization problem by learning from shape variations in the UIUC airfoil database. We show that our data-driven model both (1) learns realistic and compact airfoil shape representations and (2) empirically accelerates optimization convergence by over an order of magnitude.

Synthesizing Designs with Inter-Part Dependencies Using Hierarchical Generative Adversarial Networks

August 28, 2018

Conference proceedings talk, ASME 2018 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (IDETC-CIE2018), Quebec City, Canada

Real-world designs usually consist of parts with hierarchical dependencies, i.e., the geometry of one component (a child shape) is dependent on another (a parent shape). We propose a method for synthesizing this type of design. It decomposes the problem of synthesizing the whole design into synthesizing each component separately but keeping the inter-component dependencies satisfied. This method constructs a two-level generative adversarial network to train two generative models for parent and child shapes, respectively. We then use the trained generative models to synthesize or explore parent and child shapes separately via a parent latent representation and infinite child latent representations, each conditioned on a parent shape. We evaluate and discuss the disentanglement and consistency of latent representations obtained by this method. We show that shapes change consistently along any direction in the latent space. This property is desirable for design exploration over the latent space.

How Designs Differ: Non-linear Embeddings Illuminate Intrinsic Design Complexity

August 22, 2016

Conference proceedings talk, ASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (IDETC-CIE2016), Charlotte, North Carolina, USA

This work shows how to measure the complexity and reduce the dimensionality of a geometric design space. We assume that high-dimensional design parameters actually lie in a much lower-dimensional space that represents semantic attributes. Past work has shown how to embed designs using techniques like autoencoders; in contrast, this work quantifies when and how various embeddings are better than others. It captures the intrinsic dimensionality of a design space, the performance of recreating new designs for an embedding, and the preservation of topology of the original design space. We demonstrate this with both synthetic superformula shapes of varying non-linearity and real glassware designs. We evaluate multiple embeddings by measuring shape reconstruction error, topology preservation, and required semantic space dimensionality. Our work generates fundamental knowledge about the inherent complexity of a design space and how designs differ from one another. This deepens our understanding of design complexity in general.

Qian Chen

Talks and presentations