Generative adversarial networks with synthetic training data for enforcing manufacturing constraints on topology optimization

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Topology optimization is a powerful tool to generate mechanical designs that use minimal mass to achieve their function. However, the designs obtained using topology optimization are often not manufacturable using a given manufacturing process. There exist some modifications to the traditional topology optimization algorithm that are able to impose manufacturing constraints for a limited set of manufacturing methods. These approaches have the drawback that they are often based on heuristics to obtain the manufacturability constraint and thus cannot be applied generally to multiple manufacturing methods. In order to create a general approach to imposing manufacturing constraints on topology optimization, generative adversarial networks (GANs) are used. GANs have the capability to produce samples from a distribution defined by training data. In this work, the GAN is trained by generating synthetic 3D voxel training data that represent the distribution of designs that can be created by a particular manufacturing method. Once trained, the GAN forms a mapping from a latent vector space to the space of manufacturable designs. The topology optimization is then performed on the latent vector space ensuring that the design obtained is manufacturable. The effectiveness of this approach is demonstrated by training a GAN on designs intended to be manufacturable on a 3-axis computer numerically controlled (CNC) milling machine.

Original languageEnglish (US)
Title of host publication46th Design Automation Conference (DAC)
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791884003
DOIs
StatePublished - 2020
EventASME 2020 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2020 - Virtual, Online
Duration: Aug 17 2020Aug 19 2020

Publication series

NameProceedings of the ASME Design Engineering Technical Conference
Volume11A-2020

Conference

ConferenceASME 2020 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2020
CityVirtual, Online
Period8/17/208/19/20

Keywords

  • Deep learning
  • Design for manufacturability
  • Generative adversarial networks
  • Manufacturing constraints
  • Topology optimization

Fingerprint Dive into the research topics of 'Generative adversarial networks with synthetic training data for enforcing manufacturing constraints on topology optimization'. Together they form a unique fingerprint.

Cite this