Nothing Special   »   [go: up one dir, main page]

skip to main content
10.1145/3447548.3467414acmconferencesArticle/Chapter ViewAbstractPublication PageskddConference Proceedingsconference-collections
research-article
Open access

PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse Design

Published: 14 August 2021 Publication History

Abstract

Engineering design tasks often require synthesizing new designs that meet desired performance requirements. The conventional design process, which requires iterative optimization and performance evaluation, is slow and dependent on initial designs. Past work has used conditional generative adversarial networks (cGANs) to enable direct design synthesis for given target performances. However, most existing cGANs are restricted to categorical conditions. Recent work on Continuous conditional GAN (CcGAN) tries to address this problem, but still faces two challenges: 1) it performs poorly on non-uniform performance distributions, and 2) the generated designs may not cover the entire design space. We propose a new model, named Performance Conditioned Diverse Generative Adversarial Network (PcDGAN), which introduces a singular vicinal loss combined with a Determinantal Point Processes (DPP) based loss function to enhance diversity. PcDGAN uses a new self-reinforcing score called the Lambert Log Exponential Transition Score (LLETS) for improved conditioning. Experiments on synthetic problems and a real-world airfoil design problem demonstrate that PcDGAN outperforms state-of-the-art GAN models and improves the conditioning likelihood by 69% in an airfoil generation task and up to 78% in synthetic conditional generation tasks and achieves greater design space coverage. The proposed method enables efficient design synthesis and design space exploration with applications ranging from CAD model generation to metamaterial selection.

Supplementary Material

MP4 File (pcdgan_a_continuous_conditional_diverse-amin_heyrani_nobari-wei_chen-38957988-JYmt.mp4)
Formal Presentation Video.

References

[1]
Gabriel Achour, Woong Je Sung, Olivia J Pinon-Fischer, and Dimitri N Mavris. 2020. Development of a Conditional Generative Adversarial Network for Airfoil Shape Optimization. In AIAA Scitech 2020 Forum. 2261.
[2]
Faez Ahmed, Kalyanmoy Deb, and Bishakh Bhattacharya. 2016. Structural topology optimization using multi-objective genetic algorithm with constructive solid geometry representation. Applied Soft Computing, Vol. 39 (2016), 240 -- 250. https://doi.org/10.1016/j.asoc.2015.10.063
[3]
W Kyle Anderson and V Venkatakrishnan. 1999. Aerodynamic design optimization on unstructured grids with a continuous adjoint formulation. Computers & Fluids, Vol. 28, 4--5 (1999), 443--480.
[4]
Martin Philip Bendsoe and Ole Sigmund. 2013. Topology optimization: theory, methods, and applications .Springer Science & Business Media.
[5]
Alexei Borodin. 2009. Determinantal point processes. arxiv: 0911.1153 [math.PR]
[6]
Olivier Chapelle, Jason Weston, Léon Bottou, L Eon Bottou, and Vladimir Vapnik. 2001. Vicinal Risk Minimization. In Advances in Neural Information Processing Systems. MIT Press, 416--422.
[7]
Wei Chen and Faez Ahmed. 2020. PaDGAN: Learning to Generate High-Quality Novel Designs. Journal of Mechanical Design, Vol. 143, 3 (2020). https://doi.org/10.1115/1.4048626
[8]
Wei Chen, Kevin Chiu, and Mark Fuge. [n.d.]. Aerodynamic Design Optimization and Shape Exploration using Generative Adversarial Networks . https://doi.org/10.2514/6.2019--2351 https://doi.org/10.1016/j.enconman.2019.112233
[9]
Vladimir N. Vapnik. 2000. The Nature of Statistical Learning Theory. (2000). https://doi.org/10.1007/978--1--4757--3264--1
[10]
Emre Yilmaz and Brian German. 2020. Conditional Generative Adversarial Network Framework for Airfoil Inverse Design. In AIAA AVIATION 2020 forum .

Cited By

View all
  • (2024)Deep generative model-based synthesis framework of four-bar linkage mechanisms with target conditionsJournal of Computational Design and Engineering10.1093/jcde/qwae08411:5(318-332)Online publication date: 4-Oct-2024
  • (2024)Machine learning for structure-guided materials and process designMaterials & Design10.1016/j.matdes.2024.113453(113453)Online publication date: Nov-2024
  • (2023)Beyond Statistical SimilarityComputer-Aided Design10.1016/j.cad.2023.103609165:COnline publication date: 1-Dec-2023
  • Show More Cited By

Index Terms

  1. PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse Design

        Recommendations

        Comments

        Please enable JavaScript to view thecomments powered by Disqus.

        Information & Contributors

        Information

        Published In

        cover image ACM Conferences
        KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining
        August 2021
        4259 pages
        ISBN:9781450383325
        DOI:10.1145/3447548
        This work is licensed under a Creative Commons Attribution International 4.0 License.

        Sponsors

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        Published: 14 August 2021

        Check for updates

        Qualifiers

        • Research-article

        Conference

        KDD '21
        Sponsor:

        Acceptance Rates

        Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

        Contributors

        Other Metrics

        Bibliometrics & Citations

        Bibliometrics

        Article Metrics

        • Downloads (Last 12 months)361
        • Downloads (Last 6 weeks)56
        Reflects downloads up to 21 Nov 2024

        Other Metrics

        Citations

        Cited By

        View all
        • (2024)Deep generative model-based synthesis framework of four-bar linkage mechanisms with target conditionsJournal of Computational Design and Engineering10.1093/jcde/qwae08411:5(318-332)Online publication date: 4-Oct-2024
        • (2024)Machine learning for structure-guided materials and process designMaterials & Design10.1016/j.matdes.2024.113453(113453)Online publication date: Nov-2024
        • (2023)Beyond Statistical SimilarityComputer-Aided Design10.1016/j.cad.2023.103609165:COnline publication date: 1-Dec-2023
        • (2022)Deep Generative Models in Engineering Design: A ReviewJournal of Mechanical Design10.1115/1.4053859144:7Online publication date: 18-Mar-2022
        • (2022)Virtual surface morphology generation of Ti-6Al-4V directed energy deposition via conditional generative adversarial networkVirtual and Physical Prototyping10.1080/17452759.2022.212492118:1Online publication date: 28-Sep-2022
        • (2022)Generative Design by Reinforcement Learning: Enhancing the Diversity of Topology Optimization DesignsComputer-Aided Design10.1016/j.cad.2022.103225146(103225)Online publication date: May-2022

        View Options

        View options

        PDF

        View or Download as a PDF file.

        PDF

        eReader

        View online with eReader.

        eReader

        Login options

        Media

        Figures

        Other

        Tables

        Share

        Share

        Share this Publication link

        Share on social media