Deep Reinforcement Learning for Multi-Phase Microstructure Design

作     者：Jiongzhi Yang Srivatsa Harish Candy Li Hengduo Zhao Brittney Antous Pinar Acar 

作者机构：Virginia Polytechnic Institute and State UniversityBlacksburg24061VAUSA 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2021年第68卷第7期

页      面：1285-1302页

核心收录：

学科分类：08[工学] 080502[工学-材料学] 0805[工学-材料科学与工程（可授工学、理学学位）] 

基　　金：funded by the NASA Virginia Space Grant Consortium Grant(Project Title:“Deep Reinforcement Learning for De-Novo Computational Design of Meta-Materials”) 

主　　题：Deep learning reinforcement learning microstructure design 

摘      要：This paper presents a de-novo computational design method driven by deep reinforcement learning to achieve reliable predictions and optimum properties for periodic *** recent developments in 3-D printing,microstructures can have complex geometries and material phases fabricated to achieve targeted mechanical *** material property enhancements are promising in improving the mechanical,thermal,and dynamic performance in multiple engineering systems,ranging from energy harvesting applications to spacecraft *** study investigates a novel and efficient computational framework that integrates deep reinforcement learning algorithms into finite element-based material simulations to quantitatively model and design 3-D printed periodic *** algorithms focus on improving the mechanical and thermal performance of engineering components by optimizing a microstructural architecture to meet different design ***,the machine learning solutions demonstrated equivalent results to the physics-based simulations while significantly improving the computational time *** outcomes of the project show promise to the automation of the design and manufacturing of microstructures to enable their fabrication in large quantities with the utilization of the 3-D printing technology.