Integrated DEsign Automation Laboratory

• The optimal design of computer experiments algorithm (OPTDOE) (Jin, et al., JSPI, 2005) has made the just-in-time generation of large computer experiments possible.  The code has been fully integrated into iSIGHT®, a multidisciplinary design optimization software, developed by Dassault Systèmes.
• The Sequential Optimization and Reliability Assessment (SORA) method (Du and Chen 2004) provides an effective strategy for decoupling probabilistic analyses from optimization loops to improve the efficiency of probabilistic optimization.  The method has been integrated into Hyperworks®, an optimization software developed by Altair Engineering.

Our transfer learning approach captures spatial correlations for microstructure reconstruction by leveraging the superior capabilities of deep convolutional networks. As described in the paper, “A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions“, our implementation incorporates an encoder-decoder process and a feature-matching optimization algorithm using the pre-trained VGG19 model. Unlike previous approaches that only apply to specific material systems or require a significant amount of prior knowledge for model selection and hyper-parameter tuning, our method provides an off-the-shelf solution to handle complex microstructures, and has the potential of expediting the discovery of new materials.

The code package may be requested for research purposes by filling out the form below. Someone from IDEAL will contact you with the package after filling out the form.

Using the Material Data Curator System (MDCS) developed at the National Institute of Standards and Technology (NIST), and with the sponsorship of the National Science Foundation (NSF), we have developed a prototype system named “NanoMine” for nanocomposite material data curation, exploration, and analysis. NanoMine currently consists of a growing nanocomposite database; a collection of modular tools for statistical learning, and microstructure characterization and reconstruction (MCR); and simulation software to model bulk nano-polymer composite material response. The underlying principle of NanoMine is to create a living, open-source data resource for nanocomposites that provides data archiving and exchange, statistical analysis, and physics-based modeling for property prediction and materials design.

GO TO NANOMINE

This web-based tool offers the following functionalities:

1. Comparison of Metamaterial Datasets: Visualize the geometries and properties of unit cells in different datasets, facilitating a comprehensive comparison.
2. Interactive Exploration: Explore the geometric and property spaces interactively to identify underlying patterns and inspire new designs.
3. Dataset Management: In addition to the two existing datasets, users can follow the template to upload their datasets for visualized analysis and download selected data.

GO TO VISUALIZATION FOR METAMATERIAL DESIGN

GPM: Gaussian Process Modeling of Multi-Response Datasets

A general and efficient package for modeling (possibly noisy) datasets via Gaussian processes. The modeling method is published in “Leveraging the nugget parameter for efficient Gaussian process modeling” by Ramin Bostanabad, Tucker Kearney, Siyu Tao, Daniel Apley, Wei Chen (2018) International Journal for Numerical Methods in Engineering, 114, no. 5 (2018): 501-516. 

LVGP : Latent Variable Gaussian Process Modeling with Qualitative and Quantitative Input Variables

Fit response surfaces for datasets with latent-variable Gaussian process modeling, predict responses for new inputs, and plot latent variables locations in the latent space (only 1D or 2D). The input variables of the datasets can be quantitative, qualitative/categorical or mixed. The output variable of the datasets is a scalar (quantitative). The optimization of the likelihood function is done using a successive approximation/relaxation algorithm similar to another GP modeling package “GPM”. The modeling method is published in “A Latent Variable Approach to Gaussian Process Modeling with Qualitative and Quantitative Factors” by Yichi Zhang, Siyu Tao, Wei Chen, and Daniel W. Apley (2018) <arXiv:1806.07504>. 

CRAN Pages

GPM PACKAGE        LVGP PACKAGE

• Data info (2D/3D, static/dynamic): 2D-Static
• Author(s):  Northwestern University
• Description: This database contains 248396 orthotropic microstructures represented by 50x50 pixelated matrices as well as the associated independent components of the stiffness tensor calculator by energy-based homogenization, i.e.,C11 ,C12 , C22 and C66. The microstructures are composed of void (air) and solid (Young’s modulus=1(normalized), Poisson’s ratio=0.49). We first performed SIMP-based TO to find a corresponding pixelated microstructure design for each uniformly sampled target stiffness matrix. With 1400 microstructures generated by TO as initial seeds, an iterative stochastic shape perturbation algorithm is employed to perturb microstructure geometries that correspond to extreme and sparse properties. The CMAME version of database (240k) is extended from the SMO version (88k).
• Reference publication:
  • Wang, L., Chan, Y.-C., Ahmed, F., Liu, Z., Zhu, P., & Chen, W. (2020).  Deep generative modeling for mechanistic-based learning and design of metamaterial systems.  Computer Methods in Applied Mechanics and Engineering, 372, 113377.
  • Wang, L., Chan, Y.-C., Liu, Z., Zhu, P., & Chen, W. (2020). Data-driven metamaterial design with Laplace-Beltrami spectrum as “shape-DNA”. Structural and Multidisciplinary Optimization, 1-16.
  • Lee, D., Chan, Y.-C., Chen, W., W., Wang, L., & Chen, W. (2022). “t-METASET: Task-Aware Generation of Metamaterial Datasets by Diversity-Based Active Learning”. ASME International Design Engineering Technical Conferences 48th Design Automation Conference (IDETC-DAC).
  • File format: *.mat files
  • Download link: To request a download, please complete the form below and agree to the terms of use. Someone from IDEAL will contact you with a download link.

  TERMS OF USE: By submitting the form below, you agree to the following terms: 1) The dataset is used for non-profit research and educational purposes only.  2) The creators of the dataset provide no warranties regarding the data and are not liable for any events that may occur as a result of using the data. 3) Please cite the reference publication(s) listed above in any related works using the dataset.

  2D Orthotropic Metamaterial Dataset Download
  Name *
  Affiliation *
  Email *
  Dataset Version Wang et al., CMAME, 2020;Wang et al., SMO, 2020; Lee et al., IDETC, 2022Both
  This form is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
  Request for Download

TERMS OF USE: By submitting the form below, you agree to the following terms: 1) The dataset is used for non-profit research and educational purposes only.  2) The creators of the dataset provide no warranties regarding the data and are not liable for any events that may occur as a result of using the data. 3) Please cite the reference publication(s) listed above in any related works using the dataset.

• Data info (2D/3D, static/dynamic): 2D-Static
• Author(s):  Northwestern University
• Description: This database contains the volume fractions and stiffness tensors of 795 microstructures generated from 10 different lattice models.  Energy-based homogenization is used for the calculation of their effective stiffness tensors (Poisson’s ratio=0.30). The stiffness tensor is normalized with respect to the bulk Young’s modulus.
• Reference publication:
  • Wang, L., van Beek, A., Da, D., Chan, Y.-C., Zhu, P., & Chen, W. (2021). Data-Driven Multiscale Design of Cellular Composites with Multiclass Microstructures for Natural Frequency Maximization. (Submitted).
• File format: *.mat files
• Download link: To download, please complete the form below and agree to the terms of use. Someone from IDEAL will contact you with a download link.

TERMS OF USE: By submitting the form below, you agree to the following terms: 1) The dataset is used for non-profit research and educational purposes only.  2) The creators of the dataset provide no warranties regarding the data and are not liable for any events that may occur as a result of using the data. 3) Please cite the reference publication(s) listed above in any related works using the dataset.