Scalable Microstructure Reconstruction With Multi-Scale Pattern Preservation

Cang, Ruijin; Vipradas, Aditya; Ren, Yi

doi:10.1115/detc2017-68286

Cited by 9 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Better modeling PSP links can in turn create more accurate generative material design pipelines. Many classes of DGMs have been applied to this reconstruction task including GANs [65], VAEs [82] and Convolutional Deep Belief Networks (CDBNs) [132] [106,105,109]. Other studies attempt to bridge the gap between microstructure and properties in generative tasks using trained black-box surrogates, such as Tan et al's work [64].…”

Section: Microstructure Nanostructure and Metamaterialsmentioning

confidence: 99%

Deep Generative Models in Engineering Design: A Review

Regenwetter¹,

Nobari²,

Ahmed³

2021

Preprint

View full text Add to dashboard Cite

Automated design synthesis has the potential to revolutionize the modern human design process and improve access to highly optimized and customized products across countless industries. Successfully adapting generative Machine Learning to design engineering may be the key to such automated design synthesis and is a research subject of great importance. We present a review and analysis of Deep Generative Learning models in engineering design. Deep Generative Models (DGMs) typically leverage deep networks to learn from an input dataset and learn to synthesize new designs. Recently, DGMs such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), feedforward Neural Networks (NNs) and certain Deep Reinforcement Learning (DRL) frameworks have shown promising results in design applications like structural optimization, materials design, and shape synthesis. The prevalence of DGMs in Engineering Design has skyrocketed since 2016. Anticipating continued growth, we conduct a review of recent advances with the hope of benefitting researchers interested in DGMs for design. We structure our review as an exposition of the algorithms, datasets, representation methods, and applications commonly used in the current literature. In particular, we discuss key works that have introduced new techniques and methods in DGMs, successfully applied DGMs to a design-related domain, or directly supported development of DGMs through datasets or auxiliary methods. We further identify key challenges and limitations currently seen in DGMs across design fields, such as design creativity, handling complex constraints and objectives, and modeling both form and functional performance simultaneously. In our discussion we identify possible solution pathways as key areas on which to target future work.

show abstract

Section: Microstructure Nanostructure and Metamaterialsmentioning

confidence: 99%

Deep Generative Models in Engineering Design: A Review

Regenwetter¹,

Nobari²,

Ahmed³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…VAEs and GANs are the two most commonly used models within design. Deep generative models have been used in many applications like de-sign exploration [19,3,4,20], material microstructures design [21,22], and 3D data generation [23]. While the methods we develop in this work are applicable to most deep generative models, we use GANs to demonstrate our results and will describe them next.…”

Section: Design Synthesismentioning

confidence: 99%

PaDGAN: A Generative Adversarial Network for Performance Augmented Diverse Designs

Chen¹,

Ahmed²

2020

Preprint

View full text Add to dashboard Cite

Deep generative models are proven to be a useful tool for automatic design synthesis and design space exploration. When applied in engineering design, existing generative models face two challenges: 1) generated designs lack diversity and do not cover all areas of the design space and 2) it is difficult to explicitly improve the overall performance or quality of generated designs without excluding low-quality designs from the dataset, which may impair the performance of the trained model due to reduced training sample size. In this paper, we simultaneously address these challenges by proposing a new Determinantal Point Processes based loss function for probabilistic modeling of diversity and quality. With this new loss function, we develop a variant of the Generative Adversarial Network, named "Performance Augmented Diverse Generative Adversarial Network" or PaDGAN, which can generate novel high-quality designs with good coverage of the design space. We demonstrate that PaDGAN can generate diverse and high-quality designs on both synthetic and real-world examples and compare PaDGAN against other models such as the vanilla GAN and the BézierGAN. Unlike typical generative models that usually generate new designs by interpolating within the boundary of training data, we show that PaDGAN expands the design space boundary towards high-quality regions. The proposed method is broadly applicable to many tasks including design space exploration, design optimization, and creative solution recommendation.

show abstract

“…The visually more plausible set has worse match to the target with respect to the Euclidean distance in the discretized 2-point correlation space. [35], samples generated by a hybrid model with deep belief network and Markov random field [43], and samples generated by a deep belief network [42]. Better matching in the discretized 2-point correlation space does not indicate better microstructure generations.…”

Section: Data Science Challenges In Computational Materials Sciencementioning

confidence: 99%

“…An example can be found in Fig. 1, where we compare two-point correlation functions of Ti64 alloy samples and three sets of artificial images (see details from [35,42,43]). The visually more plausible set has worse match to the target with respect to the Euclidean distance in the discretized 2-point correlation space.…”

Section: Data Science Challenges In Computational Materials Sciencementioning

confidence: 99%

Improving direct physical properties prediction of heterogeneous materials from imaging data via convolutional neural network and a morphology-aware generative model

Cang

Yao

et al. 2018

Computational Materials Science

Self Cite

162

View full text Add to dashboard Cite

Direct prediction of material properties from microstructures through statistical models has shown to be a potential approach to accelerating computational material design with large design spaces. However, statistical modeling of highly nonlinear mappings defined on highdimensional microstructure spaces is known to be data-demanding. Thus, the added value of such predictive models diminishes in common cases where material samples (in forms of 2D or 3D microstructures) become costly to acquire either experimentally or computationally. To this end, we propose a generative machine learning model that creates an arbitrary amount of artificial material samples with negligible computation cost, when trained on only a limited amount of authentic samples. The key contribution of this work is the introduction of a morphology constraint to the training of the generative model, that enforces the resultant artificial material samples to have the same morphology distribution as the authentic ones. We show empirically that the proposed model creates artificial samples that better match with the authentic ones in material property distributions than those generated from a state-of-the-art Markov Random Field model, and thus is more effective at improving the prediction performance of a predictive structure-property model.

show abstract

Scalable Microstructure Reconstruction With Multi-Scale Pattern Preservation

Cited by 9 publications

References 0 publications

Deep Generative Models in Engineering Design: A Review

Deep Generative Models in Engineering Design: A Review

PaDGAN: A Generative Adversarial Network for Performance Augmented Diverse Designs

Improving direct physical properties prediction of heterogeneous materials from imaging data via convolutional neural network and a morphology-aware generative model

Contact Info

Product

Resources

About