Automated Model Discovery for Tensional Homeostasis: Constitutive Machine Learning in Growth and Remodeling (Source code and data)
Authors/Creators
Description
This dataset contains
- the source code
- the data and examples
- the material subroutine with examples of uniaxial strain and stress
of the inelastic Constitutive Artificial Neural Network (iCANN) enhanced by the concept of homeostatic surfaces to discover tensional homeostasis.
The corresponding publication is:
Holthusen, H., Brepols, T., Linka, K., & Kuhl, E..
Automated Model Discovery for Tensional Homeostasis: Constitutive Machine Learning in Growth and Remodeling.
Standalone_Materialroutine
- 00_Materialroutine: Contains the material subroutine implemented in FORTRAN
- 01_uniaxial_strain: Example of the material subroutine in a uniaxial strain driven manner
- 02_uniaxial_stress: Example of the material subroutine in a uniaxial stress driven manner
TensorFlow
-
iCANN:
-
01_Biax/biax_l1: Keras/TensorFlow implementation of the iCANN. Example of the cross specimen with L1 (Lasso) regularization
-
01_Biax/biax_l2: Keras/TensorFlow implementation of the iCANN. Example of the cross specimen with L2 (ridge) regularization
-
02_Uniax/uniax_l1: Keras/TensorFlow implementation of the iCANN. Example of the stripe specimen with L1 (Lasso) regularization
- 02_Uniax/uniax_l1: Keras/TensorFlow implementation of the iCANN. Example of the stripe specimen with L2 (ridge) regularization
-
-
iCANN_ABS_activation: Same four examples as above, however, with the absolute value activation function
-
installed_packages: File containing a list of installed Python modules used to implement the iCANN
The TensorFlow implementations in all 01_Biax/ and 02_Uniax/ sub-directories are the same.
The implementation in iCANN_ABS_activation is different with respect to the activation functions of the pseudo potential.
The experimental data for the cross and stripe specimen are taken from the literature:
Eichinger, J. F., Paukner, D., Szafron, J. M., Aydin, R. C., Humphrey, J. D., & Cyron, C. J. (2020).
Computer-controlled biaxial bioreactor for investigating cell-mediated homeostasis in tissue equivalents. Journal of biomechanical engineering, 142(7), 071011.
Files
iCANNg_data.zip
Files
(2.0 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:d5f0a18b5e9d6fb44b17cf3e1ae3be4d
|
2.0 MB | Preview Download |
Additional details
Related works
- Is published in
- Preprint: arXiv:2410.13645 (arXiv)
- Journal article: 10.1016/j.compbiomed.2025.109691 (DOI)
Funding
- U.S. National Science Foundation
- Automated Model Discovery for Soft Matter 2320933
- Deutsche Forschungsgemeinschaft
- Eine neue Methode für das effiziente Design von modularen Strukturen aus Carbonbeton (A01) 417002380
- Deutsche Forschungsgemeinschaft
- Kopplung von intrusiven und nichtintrusiven lokal zerlegten Modellreduktionsverfahren für schnelle Simulationen von Straßensystemen 453596084
- Deutsche Forschungsgemeinschaft
- In-Stent-Restenose in koronaren Arterien - In silico-Untersuchungen basierend auf patientenspezifischen Daten und Metamodellierung 465213526
- European Research Council
- DISCOVER 101141626
- Deutsche Forschungsgemeinschaft
- Computational Intelligence für die Mechanik weicher Materialien 533187597