TopoMamba: A Load-Support Relation-Guided Multi-Directional State-Space Model for Topology Optimization

2026-09-27

AI Summary

This study addresses the limitations of existing topology optimization methods, which struggle to effectively capture load transfer information and incur high computational costs, thereby constraining model generalization. To overcome these challenges, this work proposes a physics-guided multi-directional state space model (Mamba) that dynamically integrates scanning features by incorporating load-support relationships and a spatial adaptive fusion mechanism. The proposed architecture is coupled with the Solid Isotropic Material with Penalization (SIMP) method to efficiently predict material distributions. Evaluated on two-dimensional benchmarks, the approach significantly improves prediction accuracy, cross-distribution generalization capability, and computational efficiency. Ultimately, this framework achieves a synergistic optimization between deep learning performance and structural mechanics, offering a scalable solution for efficient topology design.

Abstract

Deep learning has emerged as an efficient alternative for predicting high-performance material distributions in topology optimization. Existing methods struggle to accurately capture load-transfer information, limiting out-of-distribution generalization, while their model architectures often incur high computational costs. To address these challenges, this paper proposes TopoMamba, a topology prediction framework incorporating a load-support relation-guided multi-directional state-space model. Coupling physical fields with load-support relations enables more effective modeling of mechanical dependencies. A load-support relation-guided spatially adaptive fusion mechanism dynamically adjusts multi-directional scan features according to spatial conditions. Mamba is coupled with the solid isotropic material with penalty method to enhance structural mechanical performance while maintaining computational efficiency. Results on two-dimensional topology optimization benchmarks demonstrate that TopoMamba achieves superior topology prediction accuracy, out-of-distribution generalization, and computational efficiency over state-of-the-art models. The proposed load-support physics-guided framework enables efficient optimization of more complex structural systems.

Problem

• Topology Optimization
• Load-Transfer Information
• Out-of-Distribution Generalization
• Computational Cost
• Deep Learning

Innovation

• Topology Optimization
• State-Space Model
• Mamba
• Load-Support Relation Guidance
• Physics-Informed Deep Learning