Article-Journal

Inverse Design of 2D Airfoils using Conditional Generative Models and Surrogate Log-Likelihoods
This paper shows how to use conditional generative models in two-dimensional (2D) airfoil optimization to probabilistically predict …
Cite Code DOI Link
Inverse Design of 2D Airfoils using Conditional Generative Models and Surrogate Log-Likelihoods
Range-Constrained Generative Adversarial Network: Design Synthesis Under Constraints Using Conditional Generative Adversarial Networks
Typical engineering design tasks require the effort to modify designs iteratively until they meet certain constraints, i.e., …
Cite Code DOI Link
Range-Constrained Generative Adversarial Network: Design Synthesis Under Constraints Using Conditional Generative Adversarial Networks
MO-PaDGAN: Reparameterizing Engineering Designs for Augmented Multi-objective Optimization
Multi-objective optimization is key to solving many Engineering Design problems, where design parameters are optimized for several …
PDF Cite Code DOI Link
MO-PaDGAN: Reparameterizing Engineering Designs for Augmented Multi-objective Optimization
PaDGAN: Learning to Generate High-Quality Novel Designs
Deep generative models are proven to be a useful tool for automatic design synthesis and design space exploration. When applied in …
PDF Cite Code DOI Link
PaDGAN: Learning to Generate High-Quality Novel Designs
Airfoil Design Parameterization and Optimization using Bézier Generative Adversarial Networks
Global optimization of aerodynamic shapes usually requires a large number of expensive computational fluid dynamics simulations because …
PDF Cite Code DOI Link
Airfoil Design Parameterization and Optimization using Bézier Generative Adversarial Networks
Synthesizing Designs with Inter-part Dependencies Using Hierarchical Generative Adversarial Networks
Real-world designs usually consist of parts with inter-part dependencies, i.e., the geometry of one part is dependent on one or …
PDF Cite Code DOI Link
Synthesizing Designs with Inter-part Dependencies Using Hierarchical Generative Adversarial Networks
Active Expansion Sampling for Learning Feasible Domains in an Unbounded Input Space
Many engineering problems require identifying feasible domains under implicit constraints. One example is finding acceptable car body …
PDF Cite Code DOI Link
Active Expansion Sampling for Learning Feasible Domains in an Unbounded Input Space
Beyond the Known: Detecting Novel Feasible Domains over an Unbounded Design Space
To solve a design problem, sometimes it is necessary to identify the feasible design space. For design spaces with implicit …
PDF Cite Code DOI Link
Beyond the Known: Detecting Novel Feasible Domains over an Unbounded Design Space
Design Manifolds Capture the Intrinsic Complexity and Dimension of Design Spaces
This paper shows how to measure the intrinsic complexity and dimensionality of a design space. It assumes that high-dimensional design …
PDF Cite Code DOI Link
Design Manifolds Capture the Intrinsic Complexity and Dimension of Design Spaces