CANN swMATH ID: 41756 Software Authors: Linka, Kevin; Hillgärtner, Markus; Abdolazizi, Kian P.; Aydin, Roland C.; Itskov, Mikhail; Cyron, Christian J. Description: Constitutive artificial neural networks: a fast and general approach to predictive data-driven constitutive modeling by deep learning. In this paper we introduce constitutive artificial neural networks (CANNs), a novel machine learning architecture for data-driven modeling of the mechanical constitutive behavior of materials. CANNs are able to incorporate by their very design information from three different sources, namely stress-strain data, theoretical knowledge from materials theory, and diverse additional information (e.g., about microstructure or materials processing). CANNs can easily and efficiently be implemented in standard computational software. They require only a low-to-moderate amount of training data and training time to learn without human guidance the constitutive behavior also of complex nonlinear and anisotropic materials. Moreover, in a simple academic example we demonstrate how the input of microstructural data can endow CANNs with the ability to describe not only the behavior of known materials but to predict also the properties of new materials where no stress-strain data are available yet. This ability may be particularly useful for the future in-silico design of new materials. The developed source code of the CANN architecture and accompanying example data sets are available at url{https://github.com/ConstitutiveANN/CANN}. Homepage: https://www.sciencedirect.com/science/article/pii/S0021999120307841 Source Code: https://github.com/ConstitutiveANN/CANN Keywords: deep learning; data-driven; constitutive modeling; hyperelasticity Related Software: TensorFlow; PySINDy; DiffSharp; Python; laGP; SciPy; DACE; Matlab; PDE-Net; darch; Keras; ABAQUS; SyFi; FEniCS; Gmsh; Adam; NGSolve; MOOSE; F3DAM; redbKIT Cited in: 8 Documents Standard Articles 2 Publications describing the Software, including 2 Publications in zbMATH Year A new family of constitutive artificial neural networks towards automated model discovery. Zbl 07644192Linka, Kevin; Kuhl, Ellen 2023 Constitutive artificial neural networks: a fast and general approach to predictive data-driven constitutive modeling by deep learning. Zbl 07500745Linka, Kevin; Hillgärtner, Markus; Abdolazizi, Kian P.; Aydin, Roland C.; Itskov, Mikhail; Cyron, Christian J. 2021 all top 5 Cited by 27 Authors 3 Linka, Kevin 2 Kuhl, Ellen 1 Abdolazizi, Kian P. 1 Aydin, Roland Can 1 Bazant, Martin Z. 1 Bouklas, Nikolaos 1 Braatz, Richard D. 1 Brummund, Jörg 1 Cyron, Christian Johannes 1 Darwin, Ethan C. 1 Fernández, Mauricio 1 Fuhg, Jan Niklas 1 Gärtner, Til 1 Guo, Theron 1 Hillgärtner, Markus 1 Itskov, Mikhail 1 Kalina, Karl A. 1 Kästner, Markus 1 Levenston, Marc E. 1 Linden, Lennart 1 Metsch, Philipp 1 Rajasekharan, Divya 1 Rokoš, Ondřej 1 St. Pierre, Skyler R. 1 Veroy, Karen 1 Weeger, Oliver 1 Zhao, Hongbo Cited in 3 Serials 4 Computer Methods in Applied Mechanics and Engineering 2 Journal of Computational Physics 2 Computational Mechanics Cited in 5 Fields 5 Mechanics of deformable solids (74-XX) 4 Computer science (68-XX) 3 Biology and other natural sciences (92-XX) 1 Partial differential equations (35-XX) 1 Numerical analysis (65-XX) Citations by Year