An official website of the United States government
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
Generative Adversarial Networks for Inverse Design of Two-Dimensional Spinodoid Metamaterials
The geometrical arrangement of metamaterials controls their mechanical properties, such as Young’s modulus and the shear modulus. However, optimizing the geometrical arrangement for user-defined performance criteria leads to an inverse problem that is intractable when considering numerous combinations of properties and underlying geometries. Machine-learning techniques have been proven to be effective and practical to accomplish such nonintuitive design tasks. This paper proposes an inverse design framework using conditional generative adversarial networks (CGANs) to explore and optimize two-dimensional metamaterial designs consisting of spinodal topologies, called spinodoids. CGANs are capable of solving the many-to-many inverse problem, which requires generating a group of geometric patterns of representative volume elements with target combinations of mechanical properties. The performance of the networks was validated by numerical simulations with the finite element method. The proposed inverse design framework vastly improves the efficiency of design exploration and optimization of spinodoid metamaterials.
more »
« less
- PAR ID:
- 10535744
- Publisher / Repository:
- American Institute of Aeronautics and Astronautics
- Date Published:
- Journal Name:
- AIAA Journal
- Volume:
- 62
- Issue:
- 7
- ISSN:
- 0001-1452
- Page Range / eLocation ID:
- 2433 to 2442
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Auxetic materials have a negative Poisson’s ratio and are of significant interest in applications that include impact mitigation, membrane separations and biomedical engineering. While there are numerous examples of structured materials that exhibit auxetic behavior, the examples of engineered auxetic structures is largely limited to periodic lattice structures that are limited to directional or anisotropic auxetic response. Structures that exhibit a three-dimensionally isotropic auxetic response have been, unfortunately, slow to evolve. Here we introduce an inverse design algorithm based on global node optimization to design three-dimensional auxetic metamaterial structures from disordered networks. After specifying the target Poisson’s ratio for a structure, an inverse design algorithm is used to adjust the positions of all nodes in a disordered network structure until the desired mechanical response is achieved. The proposed algorithm allows independent control of shear and bulk moduli, while preserving the density and connectivity of the networks. When the angle bending stiffness in the network is kept low, it is possible to realize optimized structures with a Poisson’s ratios as low as −0.6. During the optimization, the bulk modulus of these networks decreases by almost two orders of magnitude, but the shear modulus remains largely unaltered. The materials designed in this manner are fabricated by dual-material 3D-printing, and are found to exhibit the mechanical responses that were originally encoded in the computational design engine. The approach proposed here provides a materials-by-design platform that could be extended for engineering of optical, acoustic, and electrical properties, beyond the design of auxetic metamaterials.more » « less
-
Arranging semiconducting nanocrystals into ordered superstructures is a promising platform to study fundamental light-matter interactions and develop programmable optical metamaterials. We investigated how the geometrical arrangement of CdS nanocrystals in hierarchical assemblies affects chiroptical properties. To create these structures, we controlled the evaporation of a colloidal CdS nanocrystal solution between two parallel plates. We combined in situ microscopy and computational modeling to establish a formation mechanism involving the shear-induced alignment of nanocrystal fibers and the subsequent mechanical relaxation of the stretched fibers to form Raman noodle–type band textures. The high linear anisotropy in these films shares many similarities with cholesteric liquid crystals. The films deposited on top and bottom surfaces exhibit opposite chirality. The mechanistic insights from this study are consequential to enable future advances in the design and fabrication of programmable optical metamaterials for further development of polarization-based optics toward applications in sensing, hyperspectral imaging, and quantum information technology.more » « less
-
Advances in data-driven design and additive manufacturing have substantially accelerated the development of truss metamaterials—three-dimensional truss networks—offering exceptional mechanical properties at a fraction of the weight of conventional solids. While existing design approaches can generate metamaterials with target linear properties, such as elasticity, they struggle to capture complex nonlinear behaviours and to incorporate geometric and manufacturing constraints—including defects—crucial for engineering applications. Here we present GraphMetaMat, an autoregressive graph-based framework capable of designing three-dimensional truss metamaterials with programmable nonlinear responses, originating from hard-to-capture physics such as buckling, frictional contact and wave propagation, along with arbitrary geometric constraints and defect tolerance. Integrating graph neural networks, physics biases, imitation learning, reinforcement learning and tree search, we show that GraphMetaMat can target stress–strain curves across four orders of magnitude and vibration transmission responses with varying attenuation gaps, unattainable by previous methods. We further demonstrate the use of GraphMetaMat for the inverse design of novel material topologies with tailorable high-energy absorption and vibration damping that outperform existing polymeric foams and phononic crystals, potentially suitable for protective equipment and electric vehicles. This work sets the stage for the automatic design of manufacturable, defect-tolerant materials with on-demand functionalities.more » « less
-
Spinodal metamaterials, with architectures inspired by natural phase-separation processes, have presented a significant alternative to periodic and symmetric morphologies when designing mechanical metamaterials with extreme performance. While their elastic mechanical properties have been systematically determined, their large-deformation, nonlinear responses have been challenging to predict and design, in part due to limited data sets and the need for complex nonlinear simulations. This work presents a novel physics-enhanced machine learning (ML) and optimization framework tailored to address the challenges of designing intricate spinodal metamaterials with customized mechanical properties in large-deformation scenarios where computational modeling is restrictive and experimental data is sparse. By utilizing large-deformation experimental data directly, this approach facilitates the inverse design of spinodal structures with precise finite-strain mechanical responses. The framework sheds light on instability-induced pattern formation in spinodal metamaterialsobserved experimentally and in selected nonlinear simulations—leveraging physics-based inductive biases in the form of nonconvex energetic potentials. Altogether, this combined ML, experimental, and computational effort provides a route for efficient and accurate design of complex spinodal metamaterials for large-deformation scenarios where energy absorption and prediction of nonlinear failure mechanisms is essential.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.2514/1.J063697
