Topology optimization for thin-walled structure based on random forest regression

Abstract

Structural topology optimization for lightweight design faces two major challenges: the high computational cost of iterative finite-element analysis and the limited capacity of conventional surrogate models to solve inverse design problems. To address these issues, this paper introduces a machine learning-assisted inverse parameter prediction framework that couples a Random Forest (RF)-based inverse surrogate model with compliance-minimization topology optimization. The approach inverts the conventional input–output relationship by constructing a direct mapping from deformation response to design parameters. The methodology proceeds in three stages: first, the topology optimization procedure is parameterized to generate a representative sample database; second, an RF model is trained to capture the inverse regression between deformation responses and geometric and optimization parameters; third, engineering-viable solutions are obtained through a compliance-oriented refinement optimization. The proposed inverse surrogate model g1, trained on SIMP-based data, achieves approximately a twofold reduction in computational cost relative to the conventional SIMP approach. By contrast, model g2, trained on level-set-based data, incurs longer computational times, a consequence of the higher cost of level-set sample generation. Load-induced deformation errors are maintained within 5% of the reference value, and prediction accuracy exceeds 95% across repeated trials. These results suggest that the framework may serve as a rapid design initialization tool for lightweight structural applications.