Theory and implementation of inelastic Constitutive Artificial Neural Networks: Source code and data

This dataset contains the source code of the inelastic Constitutive Artificial Neural Network (iCANN) as well as the data for the examples from the publication:

Holthusen, H., Lamm, L., Brepols, T., Reese, S., & E. Kuhl. Theory and implementation of inelastic Constitutive Artificial Neural Networks.

arXiv: https://doi.org/10.48550/arXiv.2311.06380

Computer Methods in Applied Mechanics and Engineering: https://doi.org/10.1016/j.cma.2024.117063

01_Example01:  Artificially generated data

This example investigates whether the iCANN is able to discover a model for the data generated by a continuum mechanical model.

02_Example02: Discovering a model for the polymer VHB 4910 subjected to cyclic loading

Here, we investigate the ability of iCANN to discover and learn a model for the material response of  VHB 4910 polymer subjected to cyclic loading at different stretch rates.

The experimental data are taken from the literature:

Hossain, M., Vu, D. K., & Steinmann, P. (2012). Experimental study and numerical modelling of VHB 4910 polymer. Computational Materials Science, 59, 65-74.

https://doi.org/10.1016/j.commatsci.2012.02.027

03_Example03: Discovering a model for passive skeletal muscle subjected to relaxation

In this example, we investigate whether the iCANN is able to discover a model for the material behavior of passive skeletal muscles. A total of five independent experiments are carried out in which the maximum applied compression stretch and the stretch rate are varied. In addition, the learning performance of the iCANN is investigated. Training is first carried out in each of the five experiments and then in each of four of the five experiments.

The experimental data are taken from the literature:

Van Loocke, M., Lyons, C. G., & Simms, C. K. (2008). Viscoelastic properties of passive skeletal muscle in compression: stress-relaxation behaviour and constitutive modelling. Journal of biomechanics, 41(7), 1555-1566.

https://doi.org/10.1016/j.jbiomech.2008.02.007

python_requirements.txt: File containing a list of installed Python modules used to implement the iCANN