Equivariant graph convolutional neural networks for the representation of homogenized anisotropic microstructural mechanical response

arXiv:2404.17584v1 Announce Type: cross
Abstract: Composite materials with different microstructural material symmetries are common in engineering applications where grain structure, alloying and particle/fiber packing are optimized via controlled manufacturing. In fact these microstructural tunings can be done throughout a part to achieve functional gradation and optimization at a structural level. To predict the performance of particular microstructural configuration and thereby overall performance, constitutive models of materials with microstructure are needed.
In this work we provide neural network architectures that provide …

abstract applications arxiv cond-mat.mtrl-sci convolutional convolutional neural networks cs.lg engineering functional graph manufacturing material materials networks neural networks optimization part particle representation type via