Topology Optimization
Overview
Topology optimization determines where material should be placed or removed to improve goals such as stiffness, vibration control, heat transfer, or actuator motion while respecting constraints. Established approaches include density-based SIMP, level-set methods, and evolutionary methods such as BESO, typically paired with finite-element analysis and sensitivity-based optimization. Newer work uses neural surrogates, graph models, and generative methods to speed up or automate design, and extends optimization to multiple materials, coupled physics, and robotic co-design. A central challenge is achieving speed and generalization without sacrificing physical accuracy, robustness, manufacturability, or fair comparison with well-tuned classical solvers.
Latest papers
37 papers6 papers in the last four weeks, down 14% on the four weeks before. 0.0% of all new papers.
Agent4FreeFem: A Verification-Guided Framework for Autonomous Topology Optimization
SimTO-Robust: Automated Design of Soft Grippers Robust to Grasp Pose and Object Geometry
Scalable Stress-Constrained Topology Optimization: A Simultaneous Approach Based on Machine Learning
Concurrent two-scale topology optimization of printable bone scaffolds via rectified-flow generation and exact latent-space refinement
How the Classical Baseline Shapes Machine-Learning Speed Claims in Topology Optimization
Toward Maximizing Algebraic Connectivity via Density-Dependent Backbone Construction and Reinforcement Learning Completion
TO-mdiSPAs: Topology Optimization of multi-directional Soft Pneumatic Actuators
Neural topology optimization of ship structures under propulsion machinery vibrations
TopoMamba: A Load-Support Relation-Guided Multi-Directional State-Space Model for Topology Optimization
KATOsuper: Surrogate-accelerated neural topology optimization with sensitivity-consistent Fourier neural operators
Bilevel Optimization of Topology and Hyperparameters (BOTH)
magic numbers''---hyperparameters whose tuning significantly affects the outcome. Finding the right values typically requires not only deep problem-specific knowledge but also extensive trial-and-error. While practitioners can use surrogate-assisted hyperparameter optimization as an alternative, this approach requires strictly limiting the number of hyperparameters through careful problem formulation. Here, we propose differentiating TO itself using automatic differentiation. This yields hypergradients'' that allow us to tune these hyperparameters in tandem with the primary optimization. We show that evaluating just one or two steps of TO is sufficiently informative and that the method scales favorably to thousands of hyperparameters at an expense comparable to only a few standard TO runs. We demonstrate this approach on stress-constrained and compliance problems, with the latter utilizing a neural parameterization of the density field.