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

06/07/2021
by   Amin Heyrani Nobari, et al.
19

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 up to 78 space coverage. The proposed method enables efficient design synthesis and design space exploration with applications ranging from CAD model generation to metamaterial selection.

READ FULL TEXT
research
02/26/2020

PaDGAN: A Generative Adversarial Network for Performance Augmented Diverse Designs

Deep generative models are proven to be a useful tool for automatic desi...
research
03/10/2021

Range-GAN: Range-Constrained Generative Adversarial Network for Conditioned Design Synthesis

Typical engineering design tasks require the effort to modify designs it...
research
07/07/2020

MO-PaDGAN: Generating Diverse Designs with Multivariate Performance Enhancement

Deep generative models have proven useful for automatic design synthesis...
research
03/10/2021

CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis

Modern machine learning techniques, such as deep neural networks, are tr...
research
03/14/2021

DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network

Conditional generative adversarial networks (cGANs) target at synthesizi...
research
07/01/2019

Modeling Tabular data using Conditional GAN

Modeling the probability distribution of rows in tabular data and genera...
research
10/08/2016

Learning What and Where to Draw

Generative Adversarial Networks (GANs) have recently demonstrated the ca...

Please sign up or login with your details

Forgot password? Click here to reset