Welcome to the PML repository for physics-informed neural networks used in corrosion-fatigue prognosis. We will use this repository to disseminate our research in this exciting topic.

In order to run the codes, you will need to install the PINN python package: https://github.com/PML-UCF/pinn.

Please, cite this repository using:

@misc{2019_dourado_viana_python_corrosion_fatigue,
    author    = {A. Dourado and F. A. C. Viana},
    title     = {Python Scripts for Physics-Informed Neural Networks for Corrosion-Fatigue Prognosis},
    month     = Aug,
    year      = 2019,
    doi       = {10.5281/zenodo.3355729},
    version   = {0.0.1},
    publisher = {Zenodo},
    url       = {https://github.com/PML-UCF/pinn_corrosion_fatigue}
    }

The corresponding reference entry should look like:

A. Dourado and F. A. C. Viana, Python Scripts for Physics-Informed Neural Networks for Corrosion-Fatigue Prognosis, v0.0.1, Zenodo, https://github.com/PML-UCF/pinn_corrosion_fatigue, doi:10.5281/zenodo.3355729.

Over time, the following publications out of the PML-UCF research group used/referred to this repository:

• A. Dourado and F. A. C. Viana, "Physics-informed neural networks for missing physics estimation in cumulative damage models: a case study in corrosion fatigue," ASME Journal of Computing and Information Science in Engineering, Online first, 2020. (DOI: 10.1115/1.4047173).

• A. Dourado and F. A. C. Viana, "Physics-informed neural networks for bias compensation in corrosion-fatigue," AIAA SciTech Forum, Orlando, USA, January 6-10, 2020, AIAA 2020-1149 (DOI: 10.2514/6.2020-1149).

• A. Dourado and F. A. C. Viana, "Physics-Informed Neural Networks for Corrosion-Fatigue Prognosis," Proceedings of the Annual Conference of the PHM Society, Scottsdale,USA, September 21-26, 2019.