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

Ulu, Erva; Zhang, Qianbing; Kara, Levent Burak

doi:10.1080/21681163.2015.1030775

Cited by 70 publications

(38 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, new data-driven methods for topology optimization have been proposed to accelerate the process. Deep learning methods have shown promise in efficiently producing near-optimal results with respect to shape similarity as well as compliance with negligible run-time cost [34][35][36][37][38][39][40][41]. Theory-guided machine learning methods use domain-specific theories to establish the mapping between the design variables and the external boundary conditions [42][43][44].…”

Section: Introductionmentioning

confidence: 99%

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

Nie

Lin

Jiang

et al. 2021

Journal of Mechanical Design

Self Cite

122

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Nie

Lin

Jiang

et al. 2021

Journal of Mechanical Design

Self Cite

122

View full text Add to dashboard Cite

show abstract

“…Recently, deep learning has gained significant attention from researchers in various fields, and some studies incorporating it into topology optimization have been proposed. Ulu et al (2016) proposed to predict optimized material distributions of the minimum compliance problem using a neural network. In their study, various optimized material distributions were prepared using topology optimization while changing the load boundary condition.…”

Section: Topology Optimization Based On Deep Learningmentioning

confidence: 99%

“…Optimized material distributions are predicted through two steps in their study. First, an optimized material distribution under a given boundary condition is predicted in a lowresolution mesh, such as that described in the studies of Ulu et al (2016) and Zhang et al (2019b). Next, the predicted material distribution is refined in a high-resolution mesh using cGAN.…”

Section: Topology Optimization Based On Deep Learningmentioning

confidence: 99%

Data-driven topology design using a deep generative model

Yamasaki

Yaji

Fujita

2021

Struct Multidisc Optim

View full text Add to dashboard Cite

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.

show abstract

“…Yumer et al [6] used an autoencoder to enable continuous exploration of the high dimensional procedural modeling spaces within a lower dimensional space representing shape features. Ulu et al [7] trained a neural network to map between the loading configurations and the optimal topologies, and estimate the optimal topologies for novel loading configurations. Ulu et al [8] proposed a biologically inspired growth algorithm to automatically generate support structures based on the input structures.…”

Section: Design Space Exploration and Shape Synthesismentioning

confidence: 99%

How Designs Differ: Non-Linear Embeddings Illuminate Intrinsic Design Complexity

Chen

Chazan

Fuge

2016

Volume 2A: 42nd Design Automation Conference

View full text Add to dashboard Cite

This paper shows how to measure the complexity and reduce the dimensionality of a geometric design space. It assumes that high-dimensional design parameters actually lie in a much lower-dimensional space that represents semantic attributes. Past work has shown how to embed designs using techniques like autoencoders; in contrast, this paper quantifies when and how various embeddings are better than others. It captures the intrinsic dimensionality of a design space, the performance of recreating new designs for an embedding, and the preservation of topology of the original design space. We demonstrate this with both synthetic superformula shapes of varying non-linearity and real glassware designs. We evaluate multiple embeddings by measuring shape reconstruction error, topology preservation, and required semantic space dimensionality. Our work generates fundamental knowledge about the inherent complexity of a design space and how designs differ from one another. This deepens our understanding of design complexity in general.

show abstract

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

Cited by 70 publications

References 28 publications

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

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

Data-driven topology design using a deep generative model

How Designs Differ: Non-Linear Embeddings Illuminate Intrinsic Design Complexity

Contact Info

Product

Resources

About