A curated list of awesome engineer design papers, inspired by awesome-aigc-3d.
- Deep Generative Models in Engineering Design: A Review, Regenwetter et al., JMD 2022 | bibtex
- Machine Learning in Aerodynamic Shape Optimization, Li et al., Prog. Aerosp. Sci 2022 | bibtex
Airfoil Inverse Design
- Synthesizing Designs With Inter-Part Dependencies Using Hierarchical Generative Adversarial Networks, Chen et al., JMD 2019 | github | bibtex
- PaDGAN: A Generative Adversarial Network for Performance Augmented Diverse Designs, Chen et al., IDETC 2020 | github | bibtex
- MO-PaDGAN for Design Reparameterization and Optimization, Chen et al., Applied Soft Computing 2021 | github | bibtex
- Data-driven design exploration method using conditional variational autoencoder for airfoil design, Yonekura et al., SAMO 2021 | bibtex
- PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse Design, Nobari et al., SIGKDD 2021 | github | bibtex
- An inverse design method for supercritical airfoil based on conditional generative models, Wang et al., Chinese Journal of Aeronautics 2021 | bibtex
- Generating various airfoil shapes with required lift coefficient using conditional variational autoencoders, Yonekura et al., EAAI 2022 | bibtex
- Inverse airfoil design method for generating varieties of smooth airfoils using conditional WGAN-gp, Yonekura et al., SAMO 2022 | bibtex
- Inverse design of two-dimensional airfoils using conditional generative models and surrogate log-likelihoods, Chen et al., JMD 2022 | bibtex
- Physics-guided training of GAN to improve accuracy in airfoil design synthesis, Wada et al., CMAME 2024 | bibtex
- Airfoil generation and feature extraction using the conditional VAE-WGAN-gp, Yonekura et al., arxiv 2023 | bibtex
- CinDM: Compositional Generative Inverse Design, Wu et al., ICLR 2024 | github | bibtex
- Mesh-Agnostic Decoders for Supercritical Airfoil Prediction and Inverse Design, Li et al., arxiv 2024 | bibtex
- CcDPM: A Continuous Conditional Diffusion Probabilistic Model for Inverse Design, Zhao et al., AAAI 2024 | bibtex
Airfoil Parameterization & Shape Optimization
- Aerodynamic Design Optimization and Shape Exploration using Generative Adversarial Networks, Chen et al., AIAA 2019 | github | bibtex
- Airfoil Design Parameterization and Optimization using Bézier Generative Adversarial Networks, Chen et al., AIAA 2020 | github | bibtex
- A B-Spline-based Generative Adversarial Network Model for Fast Interactive Airfoil Aerodynamic Optimization, Du et al., AIAA 2020 | bibtex
- CST-GANs: A Generative Adversarial Network Based on CST Parameterization for the Generation of Smooth Airfoils, Lin et al., ICUS 2022 | bibtex
- Airfoil GAN: Encoding and Synthesizing Airfoils for Aerodynamic Shape Optimization, Wang et al., JCDE 2022 | bibtex
- Deep Generative Model for Efficient 3D Airfoil Parameterization and Generation, Chen et al., AIAA 2021 | bibtex
- Parametric Generative Schemes with Geometric Constraints for Encoding and Synthesizing Airfoils, Xie et al., EAAI 2024 | bibtex
- An Intelligent Method for Predicting the Pressure Coefficient Curve of Airfoil-Based Conditional Generative Adversarial Networks, Wang et al., TNNLS 2023 | bibtex
- Airfoil Optimization using Design-by-Morphing, Sheikh et al., JCDE 2023 | bibtex
- Compact and Intuitive Airfoil Parameterization Method through Physics-aware Variational Autoencoder, Kang et al., arxiv 2023 | bibtex
- A mechanism-informed reinforcement learning framework for shape optimization of airfoils, Wang et al., arxiv 2024 | bibtex
- Optimizing Diffusion to Diffuse Optimal Designs, Diniz et al., AIAA 2024 | github | bibtex
Airfoil Editing
TODO
Airfoil aerodynamic performace prediction
Based on the solution approach, the methods can be divided into PINNs (Neural Networks for solving equations) and data-driven surrogate models. The latter can be further categorized based on the type of output: direct output of Cl/Cd (similar to classification) or output of the flow field around the airfoil (dense prediction, similar to segmentation).
- An Airfoil Aerodynamic Parameters Calculation Method Based on Convolutional Neural Network, Liu et al., CMU-course project | github
- Prediction and optimization of airfoil aerodynamic performance using deep neural network coupled Bayesian method, Liu et al., PoF 2022 | bibtex
- An extensible Benchmarking Graph-Mesh dataset for studying Steady-State Incompressible Navier-Stokes Equations, Bonnet et al., ICLRW 2022 | github | bibtex
- AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutions, Bonnet et al., NeurIPS 2022 | github | bibtex
- Fast aerodynamics prediction of laminar airfoils based on deep attention network, Zuo et al., PoF 2023 | github | bibtex
- A solver for subsonic flow around airfoils based on physics-informed neural networks and mesh transformation, Cao et al., PoF 2024 | github | bibtex
- Incorporating Riemannian Geometric Features for Learning Coefficient of Pressure Distributions on Airplane Wings, Hu et al., arXiv 2024 | github |bibtex
CAD Design
- BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry, Xu et al., SIGGRAPH 2024 | github | bibtex
- TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds, Dupont et al., arxiv 2024 | bibtex
- SolidGen: An Autoregressive Model for Direct B-rep Synthesis, Jayaraman etal., TMLR 2023 | bibtex
- Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts, Mohammad et al., NeurIPS 2024 | bibtext
Other engineer design
- CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis, Nobari et al., IDETC-CIE 2021 | github | bibtex
- Diffusion Models Beat GANs on Topology Optimization, Mazé et al., AAAI 2023 | github | bibtex
- Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms, Ding et al., TPAMI 2023 | github | bibtex
- Using Graph Neural Networks for Additive Manufacturing, Jain et al., NVIDIA
- Superlative mechanical energy absorbing efficiency discovered through self-driving lab-human partnership, Snapp et al., Nature Communications 2024 | bibtex
- DfAM: Leveraging Generative Design in Design for Additive Manufacturing, Zhang et al. Master’s Project
- Physically Compatible 3D Object Modeling from a Single Image, Guo et al., arxiv 2024 | bibtext
- UIUC Airfoil data
- BigFoil
- G2Aero, Grey et al., JCDE 2023 | github | bibtex
- AFBench, Liu et al., NeurIPS 2024 | github | bibtex
TODO
- Design Computation and Digital Engineering (DeCoDE) Lab, MIT |
- Design, Engineering And Learning (IDEAL) Lab, UMD | github
- Wei Chen, UMD
- Extrality
- AutoDesk
- Zoo: Building Infrastructure for Hardware Designers
- XFoil, MIT
- AeroSandbox, Peter D. | bibtex
- adflow, Mader et al., JAIS 2020 | bibtex
- airfoil-interpolation, Chen
- Anton: generative design framework
- text-to-CAD, Zoo et al., | github
- physics-based deep learning, Thuerey et al., WWW 2021 | bibtex
- Autodesk’s AI Innovations Transforming Sustainable Design and Construction, Autodesk
Awesome Engineer Design is released under the MIT license.
TODO
contact: hitcslj@stu.hit.edu.cn.