Abstract

This paper shows how to use conditional generative models in two-dimensional (2D) airfoil optimization to probabilistically predict good initialization points within the vicinity of the optima given the input boundary conditions, thus warm starting and accelerating further optimization. We accommodate the possibility of multiple optimal designs corresponding to the same input boundary condition and take this inversion ambiguity into account when designing our prediction framework. To this end, we first employ the conditional formulation of our previous work BézierGAN–Conditional BézierGAN (CBGAN)—as a baseline, then introduce its sibling conditional entropic BézierGAN (CEBGAN), which is based on optimal transport regularized with entropy. Compared with CBGAN, CEBGAN overcomes mode collapse plaguing conventional GANs, improves the average lift-drag (Cl/Cd) efficiency of airfoil predictions from 80.8% of the optimal value to 95.8%, and meanwhile accelerates the training process by 30.7%. Furthermore, we investigate the unique ability of CEBGAN to produce a log-likelihood lower bound that may help select generated samples of higher performance (e.g., aerodynamic performance). In addition, we provide insights into the performance differences between these two models with low-dimensional toy problems and visualizations. These results and the probabilistic formulation of this inverse problem justify the extension of our GAN-based inverse design paradigm to other inverse design problems or broader inverse problems.

References

1.
Tarantola
,
A.
,
2005
,
Inverse Problem Theory and Methods for Model Parameter Estimation
,
SIAM
,
Philadelphia, PA
.
2.
Arridge
,
S.
,
Maass
,
P.
,
Öktem
,
O.
, and
Schönlieb
,
C.-B.
,
2019
, “
Solving Inverse Problems Using Data-Driven Models
,”
Acta Numerica
,
28
, pp.
1
174
.
3.
Engl
,
H.
,
Hanke
,
M.
, and
Neubauer
,
A.
,
1996
,
Regularization of Inverse Problems
(
Mathematics and Its Applications
),
Springer, Netherlands
.
4.
Hornik
,
K.
,
Stinchcombe
,
M.
, and
White
,
H.
,
1989
, “
Multilayer Feedforward Networks are Universal Approximators
,”
Neural Netw.
,
2
(
5
), pp.
359
366
.
5.
Goodfellow
,
I. J.
,
Pouget-Abadie
,
J.
,
Mirza
,
M.
,
Xu
,
B.
,
Warde-Farley
,
D.
,
Ozair
,
S.
,
Courville
,
A.
, and
Bengio
,
Y.
,
2014
, “
Generative Adversarial Networks
,”
Advances in Neural Information Processing Systems 27
,
Montréal, Canada
,
Dec. 8–13
. arXiv preprint arXiv:1406.2661.
6.
Nowozin
,
S.
,
Cseke
,
B.
, and
Tomioka
,
R.
,
2016
, “
f-GAN: Training Generative Neural Samplers Using Variational Divergence Minimization
,”
Advances in Neural Information Processing Systems 29
,
Barcelona, Spain
,
Dec. 4–9
. arXiv:1606.00709.
7.
Mao
,
X.
,
Li
,
Q.
,
Xie
,
H.
,
Lau
,
R. Y.
,
Wang
,
Z.
, and
Paul Smolley
,
S.
,
2017
, “
Least Squares Generative Adversarial Networks
,”
IEEE International Conference on Computer Vision, ICCV 2017
,
Venice, Italy
,
Oct. 22–29
.
8.
Arjovsky
,
M.
,
Chintala
,
S.
, and
Bottou
,
L.
,
2017
, “
Wasserstein Generative Adversarial Networks
,”
Proceedings of the 34th International Conference on Machine Learning
,
Sydney, NSW, Australia
,
Aug. 6–11
.
9.
Gulrajani
,
I.
,
Ahmed
,
F.
,
Arjovsky
,
M.
,
Dumoulin
,
V.
, and
Courville
,
A.
,
2017
, “
Improved Training of Wasserstein Gans
,”
Advances in Neural Information Processing Systems 30
,
Long Beach, CA
,
Dec 4–9
.
10.
Kingma
,
D. P.
, and
Welling
,
M.
,
2014
, “
Auto-Encoding Variational Bayes
,”
2nd International Conference on Learning Representations
,
Banff, AB, Canada
,
Apr. 14–16
. arXiv preprint arXiv:1312.6114.
11.
Kingma
,
D. P.
,
Salimans
,
T.
,
Jozefowicz
,
R.
,
Chen
,
X.
,
Sutskever
,
I.
, and
Welling
,
M.
,
2016
, “
Improving Variational Inference with Inverse Autoregressive Flow
,”
Advances in Neural Information Processing Systems 29
,
Barcelona, Spain
,
Dec. 5–10
. arXiv preprint arXiv:1606.04934
12.
Chen
,
X.
,
Kingma
,
D. P.
,
Salimans
,
T.
,
Duan
,
Y.
,
Dhariwal
,
P.
,
Schulman
,
J.
,
Sutskever
,
I.
, and
Abbeel
,
P.
,
2016
, “
Variational Lossy Autoencoder
,”
5th International Conference on Learning Representations
,
Toulon, France
,
Apr. 24–26
. arXiv preprint arXiv:1611.02731
13.
Mescheder
,
L.
,
Nowozin
,
S.
, and
Geiger
,
A.
,
2017
, “
Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
,”
Proceedings of the 34th International Conference on Machine Learning
,
Sydney, NSW, Australia
,
Aug. 6–11
, PMLR, pp.
2391
2400
.
14.
Higgins
,
I.
,
Matthey
,
L.
,
Pal
,
A.
,
Burgess
,
C.
,
Glorot
,
X.
,
Botvinick
,
M.
,
Mohamed
,
S.
, and
Lerchner
,
A.
,
2017
, “
beta-VAE: Learning Basic Visual Concepts with A Constrained Variational Framework
,”
5th International Conference on Learning Representations, ICLR 2017
,
Toulon, France
,
Apr. 24–26
, Conference Track Proceedings.
15.
Kim
,
H.
, and
Mnih
,
A.
,
2018
, “
Disentangling by Factorising
,”
Proceedings of the 35th International Conference on Machine Learning
,
Stockholmsmässan, Stockholm, Sweden
,
July 10–15
, PMLR, pp.
2649
2658
.
16.
Dinh
,
L.
,
Krueger
,
D.
, and
Bengio
,
Y.
,
2015
, “
NICE: Non-Linear Independent Components Estimation
,”
3rd International Conference on Learning Representations
,
San Diego, CA
,
May 7–9
, arXiv preprint arXiv:1410.8516.
17.
Dinh
,
L.
,
Sohl-Dickstein
,
J.
, and
Bengio
,
S.
,
2017
, “
Density Estimation Using Real NVP
,”
5th International Conference on Learning Representations
,
Toulon, France
,
Apr. 24–26
. arXiv preprint arXiv:1605.08803.
18.
Kingma
,
D. P.
, and
Dhariwal
,
P.
,
2018
, “
Glow: Generative Flow With Invertible 1 × 1 Convolutions
,”
Advances in Neural Information Processing Systems 31
,
Montréal, Canada
,
Dec. 3–8
. arXiv preprint arXiv:1807.03039.
19.
Wiecha
,
P.
,
Arbouet
,
A.
,
Girard
,
C.
, and
Muskens
,
O.
,
2021
, “
Deep Learning in Nano-Photonics: Inverse Design and Beyond
,”
Photon. Res.
,
9
(
5
), pp.
B182
B200
.
20.
Liu
,
Z.
,
Zhu
,
D.
,
Rodrigues
,
S. P.
,
Lee
,
K.-T.
, and
Cai
,
W.
,
2018
, “
Generative Model for the Inverse Design of Metasurfaces
,”
Nano. Lett.
,
18
(
10
), pp.
6570
6576
. PMID: 30207735.
21.
So
,
S.
, and
Rho
,
J.
,
2019
, “
Designing Nanophotonic Structures Using Conditional Deep Convolutional Generative Adversarial Networks
,”
Nanophotonics
,
8
(
7
), pp.
1255
1261
.
22.
Jiang
,
J.
,
Sell
,
D.
,
Hoyer
,
S.
,
Hickey
,
J.
,
Yang
,
J.
, and
Fan
,
J. A.
,
2019
, “
Free-Form Diffractive Metagrating Design Based on Generative Adversarial Networks
,”
ACS. Nano.
,
13
(
8
), pp.
8872
8878
. PMID: 31314492.
23.
Jiang
,
J.
, and
Fan
,
J. A.
,
2020
, “
Simulator-based Training of Generative Neural Networks for the Inverse Design of Metasurfaces
,”
Nanophotonics
,
9
(
5
), pp.
1059
1069
.
24.
Dong
,
Y.
,
Li
,
D.
,
Zhang
,
C.
,
Wu
,
C.
,
Wang
,
H.
,
Xin
,
M.
,
Cheng
,
J.
, and
Lin
,
J.
,
2020
, “
Inverse Design of Two-Dimensional Graphene/h-bn Hybrids by a Regressional and Conditional Gan
,”
Carbon
,
169
, pp.
9
16
.
25.
Wang
,
J.
,
Chen
,
W.
,
Fuge
,
M.
, and
Rai
,
R.
,
2021
, “
Ih-gan: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures
.”
arXiv preprint arXiv:2103.02588
.
26.
Kim
,
B.
,
Lee
,
S.
, and
Kim
,
J.
,
2020
, “
Inverse Design of Porous Materials Using Artificial Neural Networks
,”
Sci. Adv.
,
6
(
1
), p.
eaax9324
.
27.
Kim
,
S.
,
Noh
,
J.
,
Gu
,
G. H.
,
Aspuru-Guzik
,
A.
, and
Jung
,
Y.
,
2020
, “
Generative Adversarial Networks for Crystal Structure Prediction
,”
ACS Central Sci.
,
6
(
8
), pp.
1412
1420
.
28.
Deshpande
,
S.
, and
Purwar
,
A.
,
2019
, “
Computational Creativity Via Assisted Variational Synthesis of Mechanisms Using Deep Generative Models
,”
ASME J. Mech. Des.
,
141
(
12
), p.
121402
.
29.
Sanchez-Lengeling
,
B.
, and
Aspuru-Guzik
,
A.
,
2018
, “
Inverse Molecular Design Using Machine Learning: Generative Models for Matter Engineering
,”
Science
,
361
(
6400
), pp.
360
365
.
30.
Adler
,
J.
, and
Öktem
,
O.
,
2018
, “
Deep Bayesian Inversion
.”
arXiv preprint arXiv:1811.05910
.
31.
Ongie
,
G.
,
Jalal
,
A.
,
Metzler
,
C. A.
,
Baraniuk
,
R. G.
,
Dimakis
,
A. G.
, and
Willett
,
R.
,
2020
, “
Deep Learning Techniques for Inverse Problems in Imaging
,”
IEEE J. Sel. Areas in Inf. Theory
,
1
(
1
), pp.
39
56
.
32.
Wang
,
X.
,
Ghasedi Dizaji
,
K.
, and
Huang
,
H.
,
2018
, “
Conditional Generative Adversarial Network for Gene Expression Inference
,”
Bioinformatics
,
34
(
17
), pp.
i603
i611
.
33.
Isola
,
P.
,
Zhu
,
J.-Y.
,
Zhou
,
T.
, and
Efros
,
A. A.
,
2017
, “
Image-to-Image Translation With Conditional Adversarial Networks
,”
2017 IEEE Conference on Computer Vision and Pattern Recognition
,
Honolulu, HI
,
July 21–26
, pp.
1125
1134
.
34.
Smyl
,
D.
,
2018
, “
An Inverse Method for Optimizing Elastic Properties Considering Multiple Loading Conditions and Displacement Criteria
,”
ASME J. Mech. Des.
,
140
(
11
), p.
111411
.
35.
Bostanabad
,
R.
,
Chan
,
Y.-C.
,
Wang
,
L.
,
Zhu
,
P.
, and
Chen
,
W.
,
2019
, “
Globally Approximate Gaussian Processes for Big Data with Application to Data-driven Metamaterials Design
,”
ASME J. Mech. Des.
,
141
(
11
), p.
111402
.
36.
Lee
,
X. Y.
,
Balu
,
A.
,
Stoecklein
,
D.
,
Ganapathysubramanian
,
B.
, and
Sarkar
,
S.
,
2019
, “
A Case Study of Deep Reinforcement Learning for Engineering Design: Application to Microfluidic Devices for Flow Sculpting
,”
ASME J. Mech. Des.
,
141
(
11
), p.
111401
.
37.
Chen
,
W.
, and
Fuge
,
M.
,
2019
, “
Synthesizing Designs with Interpart Dependencies Using Hierarchical Generative Adversarial Networks
,”
ASME J. Mech. Des.
,
141
(
11
), p.
111403
.
38.
Oh
,
S.
,
Jung
,
Y.
,
Kim
,
S.
,
Lee
,
I.
, and
Kang
,
N.
,
2019
, “
Deep Generative Design: Integration of Topology Optimization and Generative Models
,”
ASME J. Mech. Des.
,
141
(
11
), p.
111405
.
39.
Shu
,
D.
,
Cunningham
,
J.
,
Stump
,
G.
,
Miller
,
S. W.
,
Yukish
,
M. A.
,
Simpson
,
T. W.
, and
Tucker
,
C. S.
,
2020
, “
3D Design Using Generative Adversarial Networks and Physics-Based Validation
,”
ASME J. Mech. Des.
,
142
(
7
), p.
071701
.
40.
Yilmaz
,
E.
, and
German
,
B.
,
2020
, “
Conditional Generative Adversarial Network Framework for Airfoil Inverse Design
,”
AIAA Aviation 2020 Forum
,
Virtual Event
,
June 15–19
, p.
3185
.
41.
Achour
,
G.
,
Sung
,
W. J.
,
Pinon-Fischer
,
O. J.
, and
Mavris
,
D. N.
,
2020
, “
Development of A Conditional Generative Adversarial Network For Airfoil Shape Optimization
,”
AIAA Scitech. 2020 Forum
,
Orlando, FL
,
Jan. 6–10
, p.
2261
.
42.
Yang
,
G.
, and
Da Ronch
,
A.
,
2018
, “
Aerodynamic Shape Optimisation of Benchmark Problems Using SU2
,”
2018 AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference
,
Kissimmee, FL
,
Jan. 8–12
, p.
0412
.
43.
Menčík
,
J.
,
2016
, “
Latin Hypercube Sampling
.”
Concise Reliability for Engineers
, p.
117
.
44.
Chen
,
W.
,
Chiu
,
K.
, and
Fuge
,
M.
,
2020
, “
Airfoil Design Parameterization and Optimization Using Bézier Generative Adversarial Networks
,”
AIAA. J.
,
58
(
11
), pp.
4723
4735
.
45.
Chen
,
W.
, and
Fuge
,
M.
,
2018
, “
BézierGAN: Automatic Generation of Smooth Curves From Interpretable Low-Dimensional Parameters
.”
arXiv preprint arXiv:1808.08871
.
46.
Chen
,
X.
,
Duan
,
Y.
,
Houthooft
,
R.
,
Schulman
,
J.
,
Sutskever
,
I.
, and
Abbeel
,
P.
,
2016
, “
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
,”
Advances in Neural Information Processing Systems 29
,
Barcelona, Spain
,
Dec. 5–10
. arXiv preprint arXiv:1606.03657
47.
Arjovsky
,
M.
, and
Bottou
,
L.
,
2017
, “
Towards Principled Methods for Training Generative Adversarial Networks
,”
5th International Conference on Learning Representations
,
Toulon, France
,
Apr. 24–26
. arXiv preprint arXiv:1701.04862
48.
Goodfellow
,
I.
,
2016
, “
Nips 2016 Tutorial: Generative Adversarial Networks
,”
Advances in Neural Information Processing Systems 29
,
Barcelona, Spain
,
Dec. 5–10
. arXiv preprint arXiv:1701.00160
49.
Metz
,
L.
,
Poole
,
B.
,
Pfau
,
D.
, and
Sohl-Dickstein
,
J.
,
2016
, “
Unrolled Generative Adversarial Networks
,”
5th International Conference on Learning Representations
,
Toulon, France
,
Apr. 24–26
. arXiv preprint arXiv:1611.02163
50.
Mirza
,
M.
, and
Osindero
,
S.
,
2014
, “
Conditional Generative Adversarial Nets
.”
arXiv preprint arXiv:1411.1784
.
51.
Genevay
,
A.
,
Peyré
,
G.
, and
Cuturi
,
M.
,
2018
, “
Learning Generative Models With Sinkhorn Divergences
,”
International Conference on Artificial Intelligence and Statistics, AISTATS 2018
,
Playa Blanca, Lanzarote, Canary Islands, Spain
,
Apr. 9–11
, PMLR, pp.
1608
1617
.
52.
Sanjabi
,
M.
,
Ba
,
J.
,
Razaviyayn
,
M.
, and
Lee
,
J. D.
,
2018
, “
On the Convergence and Robustness of Training Gans with Regularized Optimal Transport
,”
Advances in Neural Information Processing Systems 31
,
Montréal, Canada
,
Dec. 3–8
. arXiv preprint arXiv:1802.08249
53.
Salimans
,
T.
,
Zhang
,
H.
,
Radford
,
A.
, and
Metaxas
,
D.
,
2018
, “
Improving GANs Using Optimal Transport
,”
6th International Conference on Learning Representations
,
Vancouver, BC, Canada
,
Apr. 30–May 3
. arXiv preprint arXiv:1803.05573
54.
Balaji
,
Y.
,
Hassani
,
H.
,
Chellappa
,
R.
, and
Feizi
,
S.
,
2019
, “
Entropic GANs Meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs
,”
International Conference on Machine Learning
,
Long Beach, CA
,
June 9–15
, PMLR, pp.
414
423
.
55.
Pope
,
P.
,
Zhu
,
C.
,
Abdelkader
,
A.
,
Goldblum
,
M.
, and
Goldstein
,
T.
,
2021
, “
The Intrinsic Dimension of Images and Its Impact on Learning
,”
9th International Conference on Learning Representations
,
Virtual Event, Austria
,
May 3–7
.
56.
Cuturi
,
M.
,
2013
, “
Sinkhorn Distances: Lightspeed Computation of Optimal Transport
,”
Advances in Neural Information Processing Systems 26
,
Lake Tahoe, NV
,
Dec. 5–8
, Vol. 2, p.
4
.
57.
Peyré
,
G.
,
Cuturi
,
M.
, et al.,
2019
, “
Computational Optimal Transport: With Applications to Data Science
,”
Foundations and Trends® in Machine Learning
,
11
(
5–6
), pp.
355
607
.
58.
Feydy
,
J.
,
Séjourné
,
T.
,
Vialard
,
F.-X.
,
Amari
,
S.-i.
,
Trouvé
,
A.
, and
Peyré
,
G.
,
2019
, “
Interpolating Between Optimal Transport and MMD Using Sinkhorn Divergences
,”
The 22nd International Conference on Artificial Intelligence and Statistics
,
Naha, Okinawa, Japan
,
Apr. 16–18
, PMLR, pp.
2681
2690
.
59.
Theis
,
L.
,
Oord
,
A. v. d.
, and
Bethge
,
M.
,
2016
, “
A Note on the Evaluation of Generative Models
,”
4th International Conference on Learning Representations
,
San Juan, Puerto Rico
,
May 2–4
. arXiv preprint arXiv:1511.01844
60.
Smola
,
A.
,
Gretton
,
A.
,
Song
,
L.
, and
Schölkopf
,
B.
,
2007
, “
A Hilbert Space Embedding for Distributions
,”
Algorithmic Learning Theory, 18th International Conference, ALT 2007
,
Sendai, Japan
,
Oct. 1–4
, Springer, pp.
13
31
.
61.
Bishop
,
C. M.
,
2006
,
Pattern Recognition and Machine Learning
,
Springer
,
New York
.
62.
Economon
,
T. D.
,
Palacios
,
F.
,
Copeland
,
S. R.
,
Lukaczyk
,
T. W.
, and
Alonso
,
J. J.
,
2016
, “
Su2: An Open-source Suite for Multiphysics Simulation and Design
,”
AIAA. J.
,
54
(
3
), pp.
828
846
.
63.
Chen
,
W.
, and
Ramamurthy
,
A.
,
2021
, “
Deep Generative Model for Efficient 3D Airfoil Parameterization and Generation
,”
AIAA Scitech 2021 Forum
,
Nashville, TN
,
Jan. 11–15
, p.
1690
.
You do not currently have access to this content.