A publicly available PyTorch-ABAQUS UMAT deep-learning framework for level-set plasticity

This paper introduces a publicly available PyTorch-ABAQUS deep-learning framework of a family of plasticity models where the yield surface is implicitly represented by a scalar-valued function. In particular, our focus is to introduce a practical framework that can be deployed for engineering analysis that employs a user -defined material subroutine (UMAT/VUMAT) for ABAQUS, which is written in FORTRAN. To accomplish this task while leveraging the back-propagation learning algorithm to speed up the neural-network training, we introduce an interface code where the weights and biases of the trained neural networks obtained via the PyTorch library can be automatically converted into a generic FORTRAN code that can be a part of the UMAT/VUMAT algorithm. To enable third-party validation, we purposely make all the data sets, source code used to train the neural-network-based constitutive models, and the trained models available in a public repository. Furthermore, the practicality of the workflow is then further tested on a dataset for anisotropic yield function to showcase the extensibility of the proposed framework. A number of representative numerical experiments are used to examine the accuracy, robustness and reproducibility of the results generated by the neural network models.

Automated summary

This paper introduces a publicly available PyTorch-ABAQUS deep-learning framework for a family of plasticity models. The framework allows for engineering analysis with a user-defined material subroutine for ABAQUS. An interface code is introduced to convert the trained neural network weights and biases into a generic FORTRAN code. All the data sets, source code, and trained models are made available in a public repository for third-party validation. The practicality of the framework is demonstrated with numerical experiments on anisotropic yield function.