Machine Learning based parameter tuning strategy for MMC based topology optimization

TL;DR

This paper introduces a machine learning-based strategy to automatically tune parameters in MMC-based topology optimization, reducing reliance on manual adjustments and improving solution feasibility.

Contribution

It proposes an integrated ML and PSO framework to optimize MMC parameters, enhancing the robustness and efficiency of topology optimization.

Findings

The ML-based tuning reduces manual effort in parameter selection.

The approach achieves feasible and optimized solutions in classical cases.

It demonstrates improved efficiency over traditional manual tuning methods.

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 reasonable solution in the design domain is obtained. In this study, two classical cases are presented to demonstrate the efficiency of the proposed approach.