Machine Learning based parameter tuning strategy for MMC based topology optimization. (November 2020)

• Record Type: Journal Article
• Authors: Jiang, Xinchao; Wang, Hu; Li, Yu; Mo, Kangjia
• Is Part Of: Advances in engineering software. Volume 149(2020)
• Publication Date: 2020-11
• Subjects: Topology optimization -- Moving morphable component -- Machine Learning -- Extra-Trees -- Image classification -- Parameter tuning; Computer-aided engineering -- Periodicals; Engineering -- Computer programs -- Periodicals; Engineering -- Software -- Periodicals; Periodicals; 620.0028553
• DOI: 10.1016/j.advengsoft.2020.102841
• Languages: English
• ISSNs: 0965-9978

Abstract

Highlights: An ML-based strategy is proposed to tune parameters automatically; An ET-based image classifier is introduced to determine the feasible solution; The reliability of the ML-based classifier is fully evaluated; The proposed method is validated by two classical cases successfully; The proposed method can be extended for other fields. Abstract: Moving Morphable Component (MMC) based topology optimization approach is an explicit algorithm since the boundary of the entity explicitly described by its functions. Compared with other pixel or node point-based algorithms, it is optimized through the parameter optimization of a Topological Description Function (TDF). However, the optimized results partly depend on the selection of related parameters of Method of Moving Asymptote (MMA), which is the optimizer of MMC based topology optimization. Practically, these parameters are tuned according to the experience and the feasible solution might not be easily obtained, even the solution might be infeasible due to improper parameter setting. In order to address these issues, a Machine Learning (ML) based parameter tuning strategy is proposed in this study. An Extra-Trees (ET) based image classifier is integrated to the optimization framework, and combined with Particle Swarm Optimization (PSO) algorithm to form a closed loop. It makes the optimization process be free from the manual parameter adjustment and the feasible solution in the design domain is obtained. In this study, two classical cases are presented to demonstrate the efficiency of the proposed approach.