More Like this

1. Data-Driven Multiscale Topology Optimization Using Multi-Response Latent Variable Gaussian Process

   https://doi.org/10.1115/DETC2020-22595  

   Wang, Liwei; Tao, Siyu; Zhu, Ping; Chen, Wei (August 2020, Proceedings of the ASME 2020 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. Volume 11A: 46th Design Automation Conference (DAC)

   null (Ed.)

   Abstract The data-driven approach is emerging as a promising method for the topological design of the multiscale structure with greater efficiency. However, existing data-driven methods mostly focus on a single class of unit cells without considering multiple classes to accommodate spatially varying desired properties. The key challenge is the lack of inherent ordering or “distance” measure between different classes of unit cells in meeting a range of properties. To overcome this hurdle, we extend the newly developed latent-variable Gaussian process (LVGP) to creating multi-response LVGP (MRLVGP) for the unit cell libraries of metamaterials, taking both qualitative unit cell concepts and quantitative unit cell design variables as mixed-variable inputs. The MRLVGP embeds the mixed variables into a continuous design space based on their collective effect on the responses, providing substantial insights into the interplay between different geometrical classes and unit cell materials. With this model, we can easily obtain a continuous and differentiable transition between different unit cell concepts that can render gradient information for multiscale topology optimization. While the proposed approach has a broader impact on the concurrent topological and material design of engineered systems, we demonstrate its benefits through multiscale topology optimization with aperiodic unit cells. Design examples reveal that considering multiple unit cell types can lead to improved performance due to the consistent load-transferred paths for micro- and macrostructures. 

   more » « less
2. Stress-constrained optimization of multiscale structures with parameterized microarchitectures using machine learning

   https://doi.org/10.1007/s00158-024-03821-y  

   Black, Nolan; Najafi, Ahmad (June 2024, Structural and Multidisciplinary Optimization)

   Abstract A multiscale topology optimization framework for stress-constrained design is presented. Spatially varying microstructures are distributed in the macroscale where their material properties are estimated using a neural network surrogate model for homogenized constitutive relations. Meanwhile, the local stress state of each microstructure is evaluated with another neural network trained to emulate second-order homogenization. This combination of two surrogate models — one for effective properties, one for local stress evaluation — is shown to accurately and efficiently predict relevant stress values in structures with spatially varying microstructures. An augmented lagrangian approach to stress-constrained optimization is then implemented to minimize the volume of multiscale structures subjected to stress constraints in each microstructure. Several examples show that the approach can produce designs with varied microarchitectures that respect local stress constraints. As expected, the distributed microstructures cannot surpass density-based topology optimization designs in canonical volume minimization problems. Despite this, the stress-constrained design of hierarchical structures remains an important component in the development of multiphysics and multifunctional design. This work presents an effective approach to multiscale optimization where a machine learning approach to local analysis has increased the information exchange between micro- and macroscales. 

   more » « less
3. Designing Mixed-Category Stochastic Microstructures by Deep Generative Model-based and Curvature Functional-based Methods

   https://doi.org/10.1115/1.4063824  

   Xu, Leidong; Naghavi Khanghah, Kiarash; Xu, Hongyi (October 2023, Journal of Mechanical Design)

   Bridging the gaps among various categories of stochastic microstructures remains a challenge in the design representation of microstructural materials. Each microstructure category requires certain unique mathematical and statistical methods to define the design space (design representation). The design representation methods are usually incompatible between two different categories of stochastic microstructures. The common practice of pre-selecting the microstructure category and the associated design representation method before conducting rigorous computational design restricts the design freedom and hinders the discovery of innovative microstructure designs. To overcome this issue, this paper proposes and compares two novel methods, the deep generative modeling-based method and the curvature functional-based method, to understand their pros and cons in designing mixed-category stochastic microstructures for desired properties. For the deep generative modeling-based method, the Variational Autoencoder is employed to generate an unstructured latent space as the design space. For the curvature functional-based method, the microstructure geometry is represented by curvature functionals, of which the functional parameters are employed as the microstructure design variables. Regressors of the microstructure design variables-property relationship are trained for microstructure design optimization. A comparative study is conducted to understand the relative merits of these two methods in terms of computational cost, continuous transition, design scalability, design diversity, dimensionality of the design space, interpretability of the statistical equivalency, and design performance. 

   more » « less
4. Design of Mixed-Category Stochastic Microstructures: A Comparison of Curvature Functional-Based and Deep Generative Model-Based Methods

   https://doi.org/10.1115/DETC2023-114601  

   Xu, Leidong; Naghavi_Khanghah, Kiarash; Xu, Hongyi (August 2023, American Society of Mechanical Engineers)

   Abstract Bridging the gaps among various categories of stochastic microstructures remains a challenge in the design representation of microstructural materials. Each microstructure category requires certain unique mathematical and statistical methods to define the design space (design representation). The design representation methods are usually incompatible between two different categories of stochastic microstructures. The common practice of pre-selecting the microstructure category and the associated design representation method before conducting rigorous computational design limits the design freedom and reduces the possibility of obtaining innovative microstructure designs. To overcome this issue, this paper proposes and compares two methods, the deep generative modeling-based method and the curvature functional-based method, to understand their pros and cons in designing mixed-category stochastic microstructures for desired properties. For the deep generative modeling-based method, the Variational Autoencoder is employed to generate an unstructured latent space as the design space. For the curvature functional-based method, the microstructure geometry is represented by curvature functionals, of which the functional parameters are employed as the microstructure design variables. Regressors of the microstructure design variables-property relationship are trained for microstructure design optimization. A comparative study is conducted to understand the relative merits of these two methods in terms of computational cost, continuous transition, design scalability, design diversity, dimensionality of the design space, interpretability of the statistical equivalency, and design performance. 

   more » « less
5. Data centric nanocomposites design via mixed-variable Bayesian optimization

   https://doi.org/10.1039/d0me00079e  

   Iyer, Akshay; Zhang, Yichi; Prasad, Aditya; Gupta, Praveen; Tao, Siyu; Wang, Yixing; Prabhune, Prajakta; Schadler, Linda S.; Brinson, L. Catherine; Chen, Wei (January 2020, Molecular Systems Design & Engineering)

   With an unprecedented combination of mechanical and electrical properties, polymer nanocomposites have the potential to be widely used across multiple industries. Tailoring nanocomposites to meet application specific requirements remains a challenging task, owing to the vast, mixed-variable design space that includes composition ( i.e. choice of polymer, nanoparticle, and surface modification) and microstructures ( i.e. dispersion and geometric arrangement of particles) of the nanocomposite material. Modeling properties of the interphase, the region surrounding a nanoparticle, introduces additional complexity to the design process and requires computationally expensive simulations. As a result, previous attempts at designing polymer nanocomposites have focused on finding the optimal microstructure for only a fixed combination of constituents. In this article, we propose a data centric design framework to concurrently identify optimal composition and microstructure using mixed-variable Bayesian optimization. This framework integrates experimental data with state-of-the-art techniques in interphase modeling, microstructure characterization and reconstructions and machine learning. Latent variable Gaussian processes (LVGPs) quantifies the lack-of-data uncertainty over the mixed-variable design space that consists of qualitative and quantitative material design variables. The design of electrically insulating nanocomposites is cast as a multicriteria optimization problem with the goal of maximizing dielectric breakdown strength while minimizing dielectric permittivity and dielectric loss. Within tens of simulations, our method identifies a diverse set of designs on the Pareto frontier indicating the tradeoff between dielectric properties. These findings project data centric design, effectively integrating experimental data with simulations for Bayesian Optimization, as an effective approach for design of engineered material systems. 

   more » « less