A sparsity preserving genetic algorithm for extracting diverse functional 3D designs from deep generative neural networks

3Citations
Citations of this article
26Readers
Mendeley users who have this article in their library.

Abstract

Generative neural networks (GNNs) have successfully used human-created designs to generate novel 3D models that combine concepts from disparate known solutions, which is an important aspect of design exploration. GNNs automatically learn a parameterization (or latent space) of a design space, as opposed to alternative methods that manually define a parameterization. However, GNNs are typically not evaluated using an explicit notion of physical performance, which is a critical capability needed for design. This work bridges this gap by proposing a method to extract a set of functional designs from the latent space of a point cloud generating GNN, without sacrificing the aforementioned aspects of a GNN that are appealing for design exploration. We introduce a sparsity preserving cost function and initialization strategy for a genetic algorithm (GA) to optimize over the latent space of a point cloud generating autoencoder GNN. We examine two test cases, an example of generating ellipsoid point clouds subject to a simple performance criterion and a more complex example of extracting 3D designs with a low coefficient of drag. Our experiments show that the modified GA results in a diverse set of functionally superior designs while maintaining similarity to human-generated designs in the training data set.

References Powered by Scopus

Deep residual learning for image recognition

163438Citations
N/AReaders
Get full text

PointNet: Deep learning on point sets for 3D classification and segmentation

10053Citations
N/AReaders
Get full text

3D ShapeNets: A deep representation for volumetric shapes

4710Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Range-Constrained Generative Adversarial Network: Design Synthesis Under Constraints Using Conditional Generative Adversarial Networks

16Citations
N/AReaders
Get full text

Exploiting Linear Interpolation of Variational Autoencoders for Satisfying Preferences in Evolutionary Design Optimization

5Citations
N/AReaders
Get full text

Design representation for performance evaluation of 3D shapes in structure-aware generative design

3Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Cunningham, J. D., Shu, D., Simpson, T. W., & Tucker, C. S. (2020). A sparsity preserving genetic algorithm for extracting diverse functional 3D designs from deep generative neural networks. Design Science, 6. https://doi.org/10.1017/dsj.2020.9

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 6

55%

Researcher 4

36%

Professor / Associate Prof. 1

9%

Readers' Discipline

Tooltip

Engineering 5

50%

Computer Science 3

30%

Design 1

10%

Social Sciences 1

10%

Save time finding and organizing research with Mendeley

Sign up for free