A deep material network approach for predicting the thermomechanical response of composites
Not Available
Shin, Dongil (ORCID:0000000336180624)↗
Engineering topics
Alberdi, Ryan
Publications and source records attributed to Alberdi, Ryan.
Structural metamaterials comprising interpenetrating lattices
Multi-body interpenetrating lattices comprise two or more lattices that interlace or interpenetrate through the same volume without any direct physical connection to each other, wherein energy transfer is controlled by surface interactions. As a result, multifunctional or composite-like responses can be achieved by additive manufacturing of the interpenetrating lattices, even with only a single print material, with programmable interface-dominated properties. As a result, the interpenetrating lattices can have unique mechanical properties, including improved toughness, multi-stable/negative stiffness, and electromechanical coupling.
Boyce, Brad↗
Visualization of the Deep Material Network with Recursive Training
Explore the source record for details and available documents.
Lebensohn, Ricardo↗
Predicting the thermo-elasto-plastic response of composites using the Deep Material Network
Explore the source record for details and available documents.
Dingreville, Remi Philippe Michel↗
Deep material network via a quilting strategy: visualization for explainability and recursive training for improved accuracy
Recent developments integrating micromechanics and neural networks offer promising paths for rapid predictions of the response of heterogeneous materials with similar accuracy as direct numerical simulations. The deep material network is one such approaches, featuring a multi-layer network and micromechanics building blocks trained on anisotropic linear elastic properties. Once trained, the network acts as a reduced-order model, which can extrapolate the material’s behavior to more general constitutive laws, including nonlinear behaviors, without the need to be retrained. However, current training methods initialize network parameters randomly, incurring inevitable training and calibration errors. Here, we introduce a way to visualize the network parameters as an analogous unit cell and use this visualization to “quilt” patches of shallower networks to initialize deeper networks for a recursive training strategy. The result is an improvement in the accuracy and calibration performance of the network and an intuitive visual representation of the network for better explainability.
97 MATHEMATICS AND COMPUTING↗