Generative Design by Reinforcement Learning: Enhancing the Diversity of Topology Optimization Designs

• Published in: Computer aided design Vol. 146; p. 103225
• Main Authors: Jang, Seowoo, Yoo, Soyoung, Kang, Namwoo
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.05.2022; Elsevier BV
• Subjects: Artificial intelligence; Automotive wheels; Deep learning; Design; Design diversity; Design optimization; Design parameters; Generative design; Machine learning; Neural networks; Optimization; Reinforcement learning; Topology optimization; Deep learning; Design diversity; Topology optimization; Generative design; Reinforcement learning

Generative design refers to computational design methods that can automatically conduct design exploration under constraints defined by designers. Among many approaches, topology optimization-based generative designs aim to explore diverse topology designs, which cannot be represented by conventiona...