Data-driven topology design using a deep generative model

Abstract

In this paper, we propose a sensitivity-free and multi-objective structural design methodology called data-driven topology design. It is schemed to obtain high-performance material distributions from initially given material distributions in a given design domain. Its basic idea is to iterate the following processes: (i) selecting material distributions from a dataset of material distributions according to eliteness, (ii) generating new material distributions using a deep generative model trained with the selected elite material distributions, and (iii) merging the generated material distributions with the dataset. Because of the nature of a deep generative model, the generated material distributions are diverse and inherit features of the training data, that is, the elite material distributions. Therefore, it is expected that some of the generated material distributions are superior to the current elite material distributions, and by merging the generated material distributions with the dataset, the performances of the newly selected elite material distributions are improved. The performances are further improved by iterating the above processes. The usefulness of data-driven topology design is demonstrated through numerical examples.

25 pages, 25 figures

References in corpus (7)

• Conditional Generative Adversarial Nets
• Topology optimization based on moving deformable components: A new computational framework
• Deep Generative Design: Integration of Topology Optimization and Generative Models
• Topology optimization of 2D structures with nonlinearities using deep learning
• A deep Convolutional Neural Network for topology optimization with strong generalization ability
• 3D Topology Optimization using Convolutional Neural Networks
• Topology Optimization and 3D printing of Large Deformation Compliant Mechanisms for Straining Biological Tissues

Cited by in corpus (7)

• On the use of Artificial Neural Networks in Topology Optimisation
• An AI-Assisted Design Method for Topology Optimization Without Pre-Optimized Training Data
• Data-driven multifidelity topology design with multi-channel variational auto-encoder for concurrent optimization of multiple design variable fields
• Data-driven topology design based on principal component analysis for 3D structural design problems
• Data-driven topology design for conductor layout problem of electromagnetic interference filter
• Enhanced Data-driven Topology Design Methodology with Multi-level Mesh and Correlation-based Mutation for Stress-related Multi-objective Optimization
• Evolutionary de-homogenization using a generative model for optimizing solid-porous infill structures considering the stress concentration issue