Unit Module-Based Convergence Acceleration for Topology Optimization Using the Spatiotemporal Deep Neural Network

IEEE Access

In Gwun Jang¹  Yonggyun Yu²  Younghwan Joo³ 

[1] Korea Advanced Institute of Science and Technology, Yuseong-gu, Daejeon, Republic of Korea;Korea Atomic Energy Research Institute, Yuseong-gu, Daejeon, Republic of Korea;Korea Institute of Energy Research, Yuseong-gu, Daejeon, Republic of Korea;

关键词: Convergence acceleration;    deep learning;    finite element method;    structural topology optimization;   

DOI  :  10.1109/ACCESS.2021.3125014

来源: DOAJ

【 摘 要 】

This study proposes a unit module-based acceleration method for 2-D topology optimization. For the purpose, the first-stage topology optimization is performed until the predefined iteration. After a whole design domain is divided into a set of unit modules, information on the spatiotemporal characteristics of intermediate designs and a filtering radius is used to separately predict a near-optimal design of each unit module through a trained long short-term memory (convLSTM) network. Then, in the second-stage topology optimization, a combined near-optimal design of a whole design domain is used as an initial design to determine the optimized design in a more efficient way. To train a convLSTM network, a history of intermediate designs is obtained under a randomly generated boundary condition of a unit module. The filtering radius is also used as the training data to reflect the geometric features affected by a filtering process. For four examples with different design domains and boundary conditions, the proposed method successfully provides the accelerated convergence up to 6.09 with a negligible loss of accuracy less than 1.12% error. These numerical results also demonstrate that the proposed unit module-based approach achieves a scalable convergence acceleration at a design domain of an arbitrary size (or resolution).

【 授权许可】

Unknown