GANTL: Towards Practical and Real-Time Topology Optimization with Conditional GANs and Transfer Learning
This addresses the problem of inefficient and non-generalizable topology optimization for engineers, though it is incremental as it builds on existing GAN and transfer learning techniques.
The paper tackles the high computational cost and poor generalization of existing machine learning methods for topology optimization by proposing a conditional GAN with transfer learning, achieving significant reductions in training dataset size and improved topological connectivity in 2D predictions.
Many machine learning methods have been recently developed to circumvent the high computational cost of the gradient-based topology optimization. These methods typically require extensive and costly datasets for training, have a difficult time generalizing to unseen boundary and loading conditions and to new domains, and do not take into consideration topological constraints of the predictions, which produces predictions with inconsistent topologies. We present a deep learning method based on generative adversarial networks for generative design exploration. The proposed method combines the generative power of conditional GANs with the knowledge transfer capabilities of transfer learning methods to predict optimal topologies for unseen boundary conditions. We also show that the knowledge transfer capabilities embedded in the design of the proposed algorithm significantly reduces the size of the training dataset compared to the traditional deep learning neural or adversarial networks. Moreover, we formulate a topological loss function based on the bottleneck distance obtained from the persistent diagram of the structures and demonstrate a significant improvement in the topological connectivity of the predicted structures. We use numerous examples to explore the efficiency and accuracy of the proposed approach for both seen and unseen boundary conditions in 2D.