In our latest article, “Uncovering stress fields and defects distributions in graphene using deep neural networks”: https://doi.org/10.1007/s10704-023-00704-z , we showed that conditional generative adversarial networks (cGANs) could transform complex deformation fields into stress fields by eliminating the need to evaluate elasticity distributions and develop complex nonlinear constitutive relations.

Moreover, cGANs demonstrated remarkable generalizability beyond the training samples when predicting defect distributions. The network accurately predicted the existence of a crack in a material sample even though cracked samples had not been used during the training stage.

The MATLAB scripts used to generate LAMMPS data/input files as well as postprocessing the numerical results of the simulations are available here: https://github.com/nuwan-d/deep_generative_neural_net

The trained neural networks and complete data set are available here: https://doi.org/10.5281/zenodo.7834444.

Our new book in structural engineering and mechanics is released!

Georgios Drosopoulos, Georgios Stavroulakis,

Nonlinear Mechanics for Composite Heterogeneous Structures, CRC Press, 2022

https://www.routledge.com/Nonlinear-Mechanics-for-Composite-Heterogeneous-Structures/Drosopoulos-Stavroulakis/p/book/9780367861551

The book provides simple but efficient descriptions for cutting-edge structural engineering concepts, including damage of composite materials and structures as well as methods to simulate damage using the finite element method.

Among others, concepts related to linear and non-linear finite element analysis, large displacement analysis, damage mechanics (appropriate for concrete-masonry), crack propagation using advanced techniques (cohesive zone models, the Extended Finite Element Method), contact mechanics and plasticity, are included in the book.

The book also provides in-depth concepts for multi-scale analysis of composite materials (FE2) and machine learning approaches, including artificial neural networks.

A number of Matlab programmes accompany the book, providing case-studies on the mentioned topics.

The book is suitable for professionals in the field of numerical modelling of structures and materials. It can be useful for engineers working with commercial finite element packages or for those who develop structural analysis programming codes.

It is also suitable for under-graduate studies as final year textbook and post-graduate, MSc and PhD studies in structural, mechanical, aerospace engineering and material science, among others.

Interested in deep learning, scientific computations, solution, and inversion methods for PDE?

Check out the preprint at:

https://www.researchgate.net/publication/341478559_SciANN_A_Keras_wrappe...

Some problems are shared in our GitHub repository on how to use sciann for inversion and forward solution of:

- Linear Elasticity: https://github.com/sciann/sciann-applications/tree/master/SciANN-SolidMe...

- Burgers equation: https://github.com/sciann/sciann-applications/blob/master/SciANN-Burgers...

- Regression: https://github.com/sciann/sciann-applications/tree/master/SciANN-NN-Regr...

- More is coming (Elasto-Plasticity,...)

https://github.com/sciann/sciann-applications