An official website of the United States government
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
This content will become publicly available on May 10, 2025
Inverse Design of Plasmonic Phase-Contrast Image Sensors Using Denoising Diffusion Probabilistic Model
We use a generative deep learning method based on denoising diffusion probabilistic model to design plasmonic phase-imaging sensors for broadband operation. This flexible method enables optimized inverse design for a wide range of nanophotonic devices.
more »
« less
- Award ID(s):
- 2139451
- PAR ID:
- 10543576
- Publisher / Repository:
- Optica Publishing Group
- Date Published:
- ISBN:
- 978-1-957171-39-5
- Page Range / eLocation ID:
- FTh1R.4
- Format(s):
- Medium: X
- Location:
- Charlotte, North Carolina
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Integrated third-harmonic generators enable on-chip wavelength conversion translating telecom signals to the visible spectrum. Despite the desirable functionality, the device performance is susceptible to phase distortions. Here, we present a design method of compensating the Kerr-induced distortions in third-harmonic generation. The design method yields a chirped Bragg grating theoretically improving the conversion efficiency by ∼30 dB. We envision the design method will pave the way for demonstrating efficient infrared-to-visible upconversion in silicon nitride chips.more » « less
-
null (Ed.)Abstract Reliability-based design (RBD) identifies design variables that maintain reliability at a required level. For many routine component design jobs, RBD may not be practical as it requires nonlinear optimization and specific reliability methods, especially for those design jobs which are performed manually or with a spreadsheet. This work develops a practical approach to reliability-based component design so that the reliability target can be achieved by conducting traditional component design repeatedly using a deterministic safety factor. The new component design is based on the First Order Reliability Method, which iteratively assigns the safety factor during the design process until the reliability requirement is satisfied. In addition to a number of iterations of deterministic component design, the other additional work is the calculation of the derivatives of the design margin with respect to the random input variables. The proposed method can be used for a wide range of component design applications. For example, if a deterministic component design is performed manually or with a spreadsheet, so it the reliability-based component design. Three examples are used to demonstrate the practicality of the new design method.more » « less
-
Abstract This work harnesses interpretable machine learning methods to address the challenging inverse design problem of origami-inspired systems. We established a work flow based on decision tree-random forest method to fit origami databases, containing both design features and functional performance, and to generate human-understandable decision rules for the inverse design of functional origami. First, the tree method is unique because it can handle complex interactions between categorical features and continuous features, allowing it to compare different origami patterns for a design. Second, this interpretable method can tackle multi-objective problems for designing functional origami with multiple and multi-physical performance targets. Finally, the method can extend existing shape-fitting algorithms for origami to consider non-geometrical performance. The proposed framework enables holistic inverse design of origami, considering both shape and function, to build novel reconfigurable structures for various applications such as metamaterials, deployable structures, soft robots, biomedical devices, and many more.more » « less
-
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
