# Data-driven topology design using a deep generative model

@article{Yamasaki2020DatadrivenTD,
title={Data-driven topology design using a deep generative model},
author={Shintaro Yamasaki and Kentaro Yaji and Kikuo Fujita},
journal={arXiv: Computational Physics},
year={2020}
}
• Published 8 June 2020
• Computer Science
• arXiv: Computational Physics
In this paper, we propose a structural design methodology called \textit{data-driven topology design}, which aims to obtain high-performance material distributions for a multi-objective optimization problem from the initially given material distributions in a given design domain. Its basic idea is iterating the following processes: (i) selecting the material distributions from a dataset according to Pareto optimality, (ii) generating new material distributions using a deep generative model with…
5 Citations

### A survey of machine learning techniques in structural and multidisciplinary optimization

• Computer Science
Structural and Multidisciplinary Optimization
• 2022
A survey of this wide but disjointed literature on ML techniques in the structural and multidisciplinary optimization field and how ML can accelerate design synthesis and optimization is presented.

### On the use of Artificial Neural Networks in Topology Optimisation

ArXiv
• 2022
The question of how methods from the field of artificial intelligence can help improve the conventional frameworks for topology optimisation has received increasing attention over the last few years.

### An AI-Assisted Design Method for Topology Optimization without Pre-Optimized Training Data

• Computer Science
Proceedings of the Design Society
• 2022
An AI-assisted design method for topology optimization, which does not require any optimized data, is proposed and generates geometries that are similar to those of conventional topology optimizers, but require only a fraction of the computational effort.

### An Artiﬁcial Intelligence–Assisted Design Method for Topology Optimization without Pre-Optimized Training Data

• Computer Science
• 2021
An AI-assisted design method for topology optimization, which does not require any optimized data and generates geometries that are similar to those of conventional topology optimizers, but require only a fraction of the computational effort.

## References

SHOWING 1-10 OF 58 REFERENCES

### Deep Generative Design: Integration of Topology Optimization and Generative Models

• Computer Science
Journal of Mechanical Design
• 2019
This work proposes an artificial intelligent (AI)-based design automation framework that is capable of generating numerous design options which are not only aesthetic but also optimized for engineering performance.

### An indirect design representation for topology optimization using variational autoencoder and style transfer

• Computer Science
• 2018
The new non-dominated points obtained via the VAE representation were found and compared with the known attainable set, indicating that use of this new design representation can simultaneously improve computational efficiency and solution quality.

### 3D Shape Synthesis for Conceptual Design and Optimization Using Variational Autoencoders

• Computer Science
Volume 2A: 45th Design Automation Conference
• 2019
The results show that when combined with genetic optimization, the proposed approach can generate a rich set of candidate concept designs that achieve prescribed functional goals, even when the original dataset has only a few or no solutions that achieve these goals.

### Deep learning for determining a near-optimal topological design without any iteration

• Computer Science
Structural and Multidisciplinary Optimization
• 2018
The performance evaluation results of the integrated network demonstrate that the proposed method can determine a near-optimal structure in terms of pixel values and compliance with negligible computational time.

### A deep Convolutional Neural Network for topology optimization with strong generalization ability

• Computer Science
ArXiv
• 2019
A deep Convolutional Neural Network (CNN) with strong generalization ability for structural topology optimization and a significant reduction in computation cost was achieved with little sacrifice on the optimality of design solutions.

### A data-driven investigation and estimation of optimal topologies under variable loading configurations

• Computer Science
Comput. methods Biomech. Biomed. Eng. Imaging Vis.
• 2014
The results indicate that when there is an underlying structure in the set of existing solutions, the proposed method can successfully predict the optimal topologies in novel loading configurations and can be used as effective initial conditions for conventional topology optimisation routines, resulting in substantial performance gains.

### Expanding variational autoencoders for learning and exploiting latent representations in search distributions

• Computer Science
GECCO
• 2018
It is shown that VAE can capture dependencies between decision variables and objectives, which is proven to improve the sampling capacity of model based EAs and represents a promising direction for the application of generative models within EDAs.

• Computer Science
NIPS
• 2014
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a

### Topology Optimization Accelerated by Deep Learning

• Computer Science
IEEE Transactions on Magnetics
• 2019
It is numerically shown that the computational cost for the topology optimization can be reduced without the loss of optimization quality.

### Adam: A Method for Stochastic Optimization

• Computer Science
ICLR
• 2015
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.