Harnessing structural stochasticity in the computational discovery and design of microstructures

• Published in: Materials & design Vol. 223; p. 111223
• Main Authors: Xu, Leidong, Hoffman, Nathaniel, Wang, Zihan, Xu, Hongyi
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.11.2022; Elsevier
• Subjects: Deep generative model; Design optimization; MATERIALS SCIENCE; Microstructure design; Stochastically graded structures; Stochasticity; Deep generative model; Stochasticity; Microstructure design; Stochastically graded structures; Design optimization
• ISSN: 0264-1275; 1873-4197
• DOI: 10.1016/j.matdes.2022.111223

[Display omitted] •Proposed a property-aware deep generative model to provide a unified design space for stochastic and periodic (deterministic) microstructures.•Established the first of its kind microstructure database that includes various types of stochastic and periodic structural patterns.•Proposed a microstructure design approach that tailors structural stochasticity and property simultaneously.•Created stochastically graded structure designs using microstructure designs with continuously increasing structural stochasticity. This paper presents a deep generative model-based design methodology for tailoring the structural stochasticity of microstructures. Although numerous methods have been established for designing deterministic (periodic) or stochastic microstructures, a systematic design approach that allows the unified treatment of both deterministic and stochastic microstructure design domains has yet to be created. The proposed methodology resolves this issue by learning a unified feature space that embodies diverse structural patterns with continuously varying stochasticity levels. A highly diverse microstructure database is established to incorporate various types of deterministic and stochastic microstructure patterns. A property-aware deep generative model is proposed to learn a unified feature space of the structural characteristics, as well as the relationship between structure features and properties of interest. Autoencoder (AE), Variational Autoencoder (VAE), and Adversarial Autoencoder (AAE) are compared to understand their relative merits in the property-aware learning of the unified feature space. Microstructural designs with tailorable stochasticity and properties are obtained by searching the unified feature space. Multiple design cases are presented to demonstrate the capability of designing microstructures for structural stochasticity and properties. Furthermore, the proposed method is employed to create stochastically graded structures, which manipulate the mechanical behaviors by varying the local stochasticity of the structure.