A Deep Adversarial Learning Methodology for Designing Microstructural Material Systems

2018 ◽  
Author(s):  
Xiaolin Li ◽  
Zijiang Yang ◽  
L. Catherine Brinson ◽  
Alok Choudhary ◽  
Ankit Agrawal ◽  
...  
Keyword(s):  
Latent Variables ◽  
Materials Design ◽  
Information Loss ◽  
Bayesian Optimization ◽  
Generative Adversarial Networks ◽  
Microstructural Characteristics ◽  
Significant Information ◽  
Adversarial Learning ◽  
Design Variables ◽  
Microstructural Design

In Computational Materials Design (CMD), it is well recognized that identifying key microstructure characteristics is crucial for determining material design variables. However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for materials design. Some MCR approaches are not applicable for material microstructural design because no parameters are available to serve as design variables, while others introduce significant information loss in either microstructure representation and/or dimensionality reduction. In this work, we present a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques. In the proposed methodology, generative adversarial networks (GAN) are trained to learn the mapping between latent variables and microstructures. Thereafter, the low-dimensional latent variables serve as design variables, and a Bayesian optimization framework is applied to obtain microstructures with desired material property. Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as capturing complex material microstructural characteristics. The validity of the proposed methodology is tested numerically on a synthetic microstructure dataset and its effectiveness for materials design is evaluated through a case study of optimizing optical performance for energy absorption. Additional features, such as scalability and transferability, are also demonstrated in this work. In essence, the proposed methodology provides an end-to-end solution for microstructural design, in which GAN reduces information loss and preserves more microstructural characteristics, and the GP-Hedge optimization improves the efficiency of design exploration.

scholarly journals Microstructural Materials Design Via Deep Adversarial Learning Methodology

2018 ◽  
Vol 140 (11) ◽  
Author(s):  
Zijiang Yang ◽  
Xiaolin Li ◽  
L. Catherine Brinson ◽  
Alok N. Choudhary ◽  
Wei Chen ◽  
...  
Keyword(s):  
Latent Variables ◽  
Network Architecture ◽  
Materials Design ◽  
Information Loss ◽  
Bayesian Optimization ◽  
Generative Adversarial Networks ◽  
Microstructural Characteristics ◽  
Significant Information ◽  
Adversarial Learning ◽  
Design Variables

Identifying the key microstructure representations is crucial for computational materials design (CMD). However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for microstructural materials design. Some MCR approaches are not applicable for microstructural materials design because no parameters are available to serve as design variables, while others introduce significant information loss in either microstructure representation and/or dimensionality reduction. In this work, we present a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques. In the proposed methodology, generative adversarial networks (GAN) are trained to learn the mapping between latent variables and microstructures. Thereafter, the low-dimensional latent variables serve as design variables, and a Bayesian optimization framework is applied to obtain microstructures with desired material property. Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as capturing complex material microstructural characteristics. The validity of the proposed methodology is tested numerically on a synthetic microstructure dataset and its effectiveness for microstructural materials design is evaluated through a case study of optimizing optical performance for energy absorption. Additional features, such as scalability and transferability, are also demonstrated in this work. In essence, the proposed methodology provides an end-to-end solution for microstructural materials design, in which GAN reduces information loss and preserves more microstructural characteristics, and the GP-Hedge optimization improves the efficiency of design exploration.

A Machine Learning-Based Design Representation Method for Designing Heterogeneous Microstructures

2015 ◽  
Vol 137 (5) ◽  
Author(s):  
Hongyi Xu ◽  
Ruoqian Liu ◽  
Alok Choudhary ◽  
Wei Chen
Keyword(s):  
Machine Learning ◽  
Design Space ◽  
Structure Property ◽  
Microstructure Design ◽  
Significant Information ◽  
Design Variables ◽  
Wide Range ◽  
Small Set ◽  
Microstructural Design ◽  
Heterogeneous Microstructures

In designing microstructural materials systems, one of the key research questions is how to represent the microstructural design space quantitatively using a descriptor set that is sufficient yet small enough to be tractable. Existing approaches describe complex microstructures either using a small set of descriptors that lack sufficient level of details, or using generic high order microstructure functions of infinite dimensionality without explicit physical meanings. We propose a new machine learning-based method for identifying the key microstructure descriptors from vast candidates as potential microstructural design variables. With a large number of candidate microstructure descriptors collected from literature covering a wide range of microstructural material systems, a four-step machine learning-based method is developed to eliminate redundant microstructure descriptors via image analyses, to identify key microstructure descriptors based on structure–property data, and to determine the microstructure design variables. The training criteria of the supervised learning process include both microstructure correlation functions and material properties. The proposed methodology effectively reduces the infinite dimension of the microstructure design space to a small set of descriptors without a significant information loss. The benefits are demonstrated by an example of polymer nanocomposites optimization. We compare designs using key microstructure descriptors versus using empirically chosen microstructure descriptors as a demonstration of the proposed method.

A Machine Learning-Based Design Representation Method for Designing Heterogeneous Microstructures

2014 ◽  
Author(s):  
Hongyi Xu ◽  
Ruoqian Liu ◽  
Alok Choudhary ◽  
Wei Chen
Keyword(s):  
Machine Learning ◽  
Design Space ◽  
Structure Property ◽  
Microstructure Design ◽  
Significant Information ◽  
Design Variables ◽  
Wide Range ◽  
Small Set ◽  
Microstructural Design ◽  
Heterogeneous Microstructures

In designing microstructural materials systems, one of the key research questions is how to represent the microstructural design space quantitatively using a descriptor set that is sufficient yet small enough to be tractable. Existing approaches describe complex microstructures either using a small set of descriptors that lack sufficient level of details, or using generic high order microstructure functions of infinite dimensionality without explicit physical meanings. We propose a new machine learning-based method for identifying the key microstructure descriptors from vast candidates as potential microstructural design variables. With a large number of candidate microstructure descriptors collected from literature covering a wide range of microstructural material systems, a 4-step machine learning-based method is developed to eliminate redundant microstructure descriptors via image analyses, to identify key microstructure descriptors based on structure-property data, and to determine the microstructure design variables. The training criteria of the supervised learning process include both microstructure correlation functions and material properties. The proposed methodology effectively reduces the infinite dimension of the microstructure design space to a small set of descriptors without a significant information loss. The benefits are demonstrated by an example of polymer nanocomposites optimization. We compare designs using key microstructure descriptors versus using empirically-chosen microstructure descriptors to validate the proposed method.

Antinoise Learning and Coalitional Game GAN

2021 ◽  
Author(s):  
Hongyou Chen ◽  
Hongjie He ◽  
Fan Chen ◽  
Yiming Zhu
Keyword(s):  
Image Quality ◽  
Real Data ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Coalitional Game ◽  
Generative Adversarial Network ◽  
Adversarial Learning ◽  
Network Convergence ◽  
The Stability ◽  
Zero Sum

Adversarial learning stability has an important influence on the generated image quality and convergence process in generative adversarial networks (GANs). Training dataset (real data) noise and the balance of game players have an impact on adversarial learning stability. In the gradient backpropagation of the discriminator, the noise samples increase the gradient variance. It can increase the uncertainty in the network convergence progress and affect stability. In the two-player zero-sum game, the game ability of the generator and discriminator is unbalanced. Generally, the game ability of the generator is weaker than that of the discriminator, which affects the stability. To improve the stability, an antinoise learning and coalitional game generative adversarial network (ANL-CG GAN) is proposed, which achieves this goal through the following two strategies. (i) In the real data loss function of the discriminator, an effective antinoise learning method is designed, which can improve the gradient variance and network convergence uncertainty. (ii) In the zero-sum game, a generator coalitional game module is designed to enhance its game ability, which can improve the balance between the generator and discriminator via a coalitional game strategy. To verify the performance of this model, the generated results of the designed GAN and other GAN models in CELEBA and CIFAR10 are compared and analyzed. Experimental results show that the novel GAN can improve adversarial learning stability, generate image quality, and reduce the number of training epochs.

Topology Design With Conditional Generative Adversarial Networks

2019 ◽  
Author(s):  
Conner Sharpe ◽  
Carolyn Conner Seepersad
Keyword(s):  
Engineering Design ◽  
Latent Variables ◽  
Computational Design ◽  
Optimization Techniques ◽  
Topology Design ◽  
Generative Adversarial Networks ◽  
Design Parameters ◽  
Full Potential ◽  
Adversarial Networks ◽  
Analytical Sensitivities

Abstract Deep convolutional neural networks have gained significant traction as effective approaches for developing detailed but compact representations of complex structured data. Generative networks in particular have become popular for their ability to mimic data distributions and allow further exploration of them. This attribute can be utilized in engineering design domains, in which the data structures of finite element meshes for analyzing potential designs are well suited to the deep convolutional network approaches that are being developed at a rapid pace in the field of image processing. This paper explores the use of conditional generative adversarial networks (cGANs) as a means of generating a compact latent representation of structures resulting from classical topology optimization techniques. The constraints and contextual factors of a design problem, such as mass fraction, material type, and load location, can then be specified as input conditions to generate potential topologies in a directed fashion. The trained network can be used to aid concept generation, such that engineers can explore a variety of designs relevant to the problem at hand with ease. The latent variables of the generator can also be used as design parameters, and the low dimensionality enables tractable computational design without analytical sensitivities. This paper demonstrates these capabilities and discusses avenues for further developments that would enable the engineering design community to further leverage generative machine learning techniques to their full potential.

Data centric nanocomposites design via mixed-variable Bayesian optimization

2020 ◽  
Vol 5 (8) ◽  
pp. 1376-1390
Author(s):  
Akshay Iyer ◽  
Yichi Zhang ◽  
Aditya Prasad ◽  
Praveen Gupta ◽  
Siyu Tao ◽  
...  
Keyword(s):  
Experimental Data ◽  
Computational Methods ◽  
Bayesian Optimization ◽  
Qualitative Design ◽  
Design Variables ◽  
Mixed Variable

Integrating experimental data with computational methods enables multicriteria design of nanocomposites using quantitative and qualitative design variables.

An anomaly detection method based on double encoder–decoder generative adversarial networks

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Hui Liu ◽  
Tinglong Tang ◽  
Jake Luo ◽  
Meng Zhao ◽  
Baole Zheng ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Latent Variables ◽  
Dimensional Space ◽  
Superior Performance ◽  
Generative Adversarial Networks ◽  
Training Process ◽  
Content Type ◽  
Detection Model ◽  
Adversarial Networks ◽  
Low Dimensional

Purpose This study aims to address the challenge of training a detection model for the robot to detect the abnormal samples in the industrial environment, while abnormal patterns are very rare under this condition. Design/methodology/approach The authors propose a new model with double encoder–decoder (DED) generative adversarial networks to detect anomalies when the model is trained without any abnormal patterns. The DED approach is used to map high-dimensional input images to a low-dimensional space, through which the latent variables are obtained. Minimizing the change in the latent variables during the training process helps the model learn the data distribution. Anomaly detection is achieved by calculating the distance between two low-dimensional vectors obtained from two encoders. Findings The proposed method has better accuracy and F1 score when compared with traditional anomaly detection models. Originality/value A new architecture with a DED pipeline is designed to capture the distribution of images in the training process so that anomalous samples are accurately identified. A new weight function is introduced to control the proportion of losses in the encoding reconstruction and adversarial phases to achieve better results. An anomaly detection model is proposed to achieve superior performance against prior state-of-the-art approaches.

Sign in / Sign up

Export Citation Format

Share Document