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 of the high dimensionality of the design …
computational fluid dynamics simulations because of the high dimensionality of the design …
3d design using generative adversarial networks and physics-based validation
D Shu, J Cunningham, G Stump… - Journal of …, 2020 - asmedigitalcollection.asme.org
The authors present a generative adversarial network (GAN) model that demonstrates how
to generate 3D models in their native format so that they can be either evaluated using …
to generate 3D models in their native format so that they can be either evaluated using …
Learning to design from humans: Imitating human designers through deep learning
Humans as designers have quite versatile problem-solving strategies. Computer agents on
the other hand can access large-scale computational resources to solve certain design …
the other hand can access large-scale computational resources to solve certain design …
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 engineering design, existing generative models …
design space exploration. When applied in engineering design, existing generative models …
Aerodynamic design optimization and shape exploration using generative adversarial networks
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 …
simulations because of the high dimensionality of the design space. One means to combat …
Deep reinforcement learning for heat exchanger shape optimization
H Keramati, F Hamdullahpur, M Barzegari - International Journal of Heat …, 2022 - Elsevier
We present a parametric approach for heat exchanger shape optimization utilizing Deep
Reinforcement Learning (Deep RL) and Boundary Representation (BREP). In this study, we …
Reinforcement Learning (Deep RL) and Boundary Representation (BREP). In this study, we …
High-dimensional reliability method accounting for important and unimportant input variables
Reliability analysis is a core element in engineering design and can be performed with
physical models (limit-state functions). Reliability analysis becomes computationally …
physical models (limit-state functions). Reliability analysis becomes computationally …
Synthesizing designs with interpart dependencies using hierarchical generative adversarial networks
Real-world designs usually consist of parts with interpart dependencies, ie, the geometry of
one part is dependent on one or multiple other parts. We can represent such dependency in …
one part is dependent on one or multiple other parts. We can represent such dependency in …
Machine learning-based surrogate model for accelerating simulation-driven optimisation of hydropower Kaplan turbine
Z Masood, S Khan, L Qian - Renewable Energy, 2021 - Elsevier
In this work, a data-driven technique is proposed for efficient design exploration and
optimisation of the Kaplan turbine. To avoid the curse of dimensionality, the proposed …
optimisation of the Kaplan turbine. To avoid the curse of dimensionality, the proposed …
Efficient aerodynamic shape optimization by using unsupervised manifold learning to filter geometric features
Many aerodynamic shape optimization methods often focus on utilizing the end-to-end
relationship between design variables and aerodynamic performance to find the optimal …
relationship between design variables and aerodynamic performance to find the optimal …