Quantum mechanics

Algorithm

Engineering

Network topology

Boundary (topology)

Generative adversarial network

Operating system

Power (physics)

Computer science

Mathematical optimization

Physics

Finite element method

Mathematics

Topology optimization

Domain (mathematical analysis)

Mathematical analysis

Artificial intelligence

Geometry

Combinatorics

Structural engineering

Generator (circuit theory)

Deep learning

Topology (electrical circuits)

Generalization

Reduction (mathematics)

Journal of Mechanical Design

In topology optimization using deep learning, the load and boundary conditions represented as vectors or sparse matrices often miss the opportunity to encode a rich view of the design problem, leading to less than ideal generalization results. We propose a new data-driven topology optimization model called TopologyGAN that takes advantage of various physical fields computed on the original, unoptimized material domain, as inputs to the generator of a conditional generative adversarial network (cGAN). Compared to a baseline cGAN, TopologyGAN achieves a nearly 3 × reduction in the mean squared error and a 2.5 × reduction in the mean absolute error on test problems involving previously unseen boundary conditions. Built on several existing network models, we also introduce a hybrid network called U-SE(Squeeze-and-Excitation)-ResNet for the generator that further increases the overall accuracy. We publicly share our full implementation and trained network.

TopologyGAN: Topology Optimization Using Generative Adversarial Networks Based on Physical Fields Over the Initial Domain