Real-Time Topology Optimization in 3D via Deep Transfer Learning. (June 2021)

• Record Type: Journal Article
• Authors: Behzadi, Mohammad Mahdi; Ilieş, Horea T.
• Is Part Of: Computer aided design. Volume 135(2021)
• Publication Date: 2021-06
• Subjects: Topology optimization -- Transfer learning -- Real-time predictions -- Design space explorations -- Deep learning; Computer-aided design -- Periodicals; Engineering design -- Data processing -- Periodicals; Computer graphics -- Periodicals; Conception technique -- Informatique -- Périodiques; Infographie -- Périodiques; Computer graphics; Engineering design -- Data processing; Periodicals; Electronic journals; 620.00420285
• DOI: 10.1016/j.cad.2021.103014
• Languages: English
• ISSNs: 0010-4485

Abstract

Abstract: The published literature on topology optimization has exploded over the last two decades to include methods that use shape and topological derivatives or evolutionary algorithms formulated on various geometric representations and parametrizations. One of the key challenges of all these methods is the massive computational cost associated with 3D topology optimization problems. We introduce a transfer learning method based on a convolutional neural network that (1) can handle high-resolution 3D design domains of various shapes and topologies; (2) supports real-time design space explorations as the domain and boundary conditions change; (3) requires a much smaller set of high-resolution examples for the improvement of learning in a new task compared to traditional deep learning networks; (4) is multiple orders of magnitude more efficient than the established gradient-based methods, such as SIMP. We provide numerous 2D and 3D examples to showcase the effectiveness and accuracy of our proposed approach, including for design domains that are unseen to our source network, as well as the generalization capabilities of the transfer learning-based approach. Our experiments achieved an average binary accuracy around 95% at real-time prediction rates. These properties, in turn, suggest that the proposed transfer-learning method may serve as the first practical underlying framework for real-time 3D design exploration based on topology optimization. Highlights: A deep transfer learning approach for topology optimization based on CNNs. A new, real-time 3D TO method based on transfer learning. Strong generalization ability. Much more efficient training than other published deep learning approaches for TO.