Algorithmically-Consistent Deep Learning Frameworks for Structural Topology Optimization

TL;DR

This paper introduces a deep learning framework for 3D topology optimization that aligns with traditional algorithms, significantly improving accuracy over existing ML-based methods in both 2D and 3D applications.

Contribution

The authors develop a multi-network deep learning framework that models each step of the topology optimization process, enabling high-resolution 3D optimization with improved accuracy.

Findings

Achieves 5.76x reduction in compliance MSE in 2D

Achieves 2.03x reduction in compliance MSE in 3D

Demonstrates effectiveness on both 2D and 3D geometries

Abstract

Topology optimization has emerged as a popular approach to refine a component's design and increase its performance. However, current state-of-the-art topology optimization frameworks are compute-intensive, mainly due to multiple finite element analysis iterations required to evaluate the component's performance during the optimization process. Recently, machine learning (ML)-based topology optimization methods have been explored by researchers to alleviate this issue. However, previous ML approaches have mainly been demonstrated on simple two-dimensional applications with low-resolution geometry. Further, current methods are based on a single ML model for end-to-end prediction, which requires a large dataset for training. These challenges make it non-trivial to extend current approaches to higher resolutions. In this paper, we develop deep learning-based frameworks consistent with traditional topology optimization algorithms for 3D topology optimization with a reasonably fine (high) resolution. We achieve this by training multiple networks, each learning a different step of the overall topology optimization methodology, making the framework more consistent with the topology optimization algorithm. We demonstrate the application of our framework on both 2D and 3D geometries. The results show that our approach predicts the final optimized design better (5.76x reduction in total compliance MSE in 2D; 2.03x reduction in total compliance MSE in 3D) than current ML-based topology optimization methods.