Data-driven topology design based on principal component analysis for 3D structural design problems
This work addresses a specific bottleneck in structural engineering for topology optimization, offering an incremental but practical solution to enable 3D applications.
The paper tackles the challenge of data-driven topology design (DDTD) for 3D structural problems, where deep generative models struggle with high-dimensional inputs. By using principal component analysis (PCA) to reduce dimensionality before training, the method effectively minimizes maximum stress in 3D structures, demonstrating practical improvements over existing DDTD approaches.
Topology optimization is a structural design methodology widely utilized to address engineering challenges. However, sensitivity-based topology optimization methods struggle to solve optimization problems characterized by strong non-linearity. Leveraging the sensitivity-free nature and high capacity of deep generative models, data-driven topology design (DDTD) methodology is considered an effective solution to this problem. Despite this, the training effectiveness of deep generative models diminishes when input size exceeds a threshold while maintaining high degrees of freedom is crucial for accurately characterizing complex structures. To resolve the conflict between the both, we propose DDTD based on principal component analysis (PCA). Its core idea is to replace the direct training of deep generative models with material distributions by using a principal component score matrix obtained from PCA computation and to obtain the generated material distributions with new features through the restoration process. We apply the proposed PCA-based DDTD to the problem of minimizing the maximum stress in 3D structural mechanics and demonstrate it can effectively address the current challenges faced by DDTD that fail to handle 3D structural design problems. Various experiments are conducted to demonstrate the effectiveness and practicability of the proposed PCA-based DDTD.