Adjustable mechanical properties design of microstructure by using generative and adversarial network with gradient penalty

An intelligent microstructural design method based on deep learning is proposed considering performance indicators that contains boundary information and homogenized elastic modules. Microstructure dataset is established by random boundary method and homogenization method. Random boundary method is...

Full description

Saved in:
Bibliographic Details
Published inMechanics of advanced materials and structures Vol. 31; no. 5; pp. 1059 - 1070
Main Authors Li, Jicheng, Ye, Hongling, Zhang, Xing, Wei, Nan
Format Journal Article
LanguageEnglish
Published Abingdon Taylor & Francis 03.03.2024
Taylor & Francis Ltd
Subjects
deep learning
Homogenization
Indicators
Mechanical properties
Microstructure
Modules
random boundary method
Wasserstein distance
Online AccessGet full text

Cover

More Information
Summary:An intelligent microstructural design method based on deep learning is proposed considering performance indicators that contains boundary information and homogenized elastic modules. Microstructure dataset is established by random boundary method and homogenization method. Random boundary method is proposed to design microstructures under given boundary information, and homogenization method is utilized to acquire homogenized elastic modules. A generative and adversarial network with gradient penalty is developed to establish the high-dimensional mapping between performance indicators and microstructure. The Wasserstein distance is imported to overcome mode collapse. Numerical simulation shows that the pre-trained network successfully achieved corresponding microstructure design by given performance indicators.
ISSN:1537-6494
1537-6532
DOI:10.1080/15376494.2022.2129888