Docs | Installation | GitHub | PyPI | Practical sessions
This code intends to facilitate the design and analysis of materials & structures/metamaterials
The Bessa research group at TU Delft is small... At the moment, we have limited availability to help future users/developers adapting the code to new problems, but we will do our best to help!
If you use or edit our work, please cite at least one of the appropriate references:
[1] Bessa, M. A., Bostanabad, R., Liu, Z., Hu, A., Apley, D. W., Brinson, C., Chen, W., & Liu, W. K. (2017). A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality. Computer Methods in Applied Mechanics and Engineering, 320, 633-667.
[2] Bessa, M. A., & Pellegrino, S. (2018). Design of ultra-thin shell structures in the stochastic post-buckling range using Bayesian machine learning and optimization. International Journal of Solids and Structures, 139, 174-188.
[3] Bessa, M. A., Glowacki, P., & Houlder, M. (2019). Bayesian machine learning in metamaterial design: fragile becomes super-compressible. Advanced Materials, 31(48), 1904845.
[4] Mojtaba, M., Bostanabad, R., Chen, W., Ehmann, K., Cao, J., & Bessa, M. A. (2019). Deep learning predicts path-dependent plasticity. Proceedings of the National Academy of Sciences, 116(52), 26414-26420.
https://github.com/bessagroup/F3DASM/blob/f7ff2831f3d8b6d79db30932d437914b7740ff37/src/f3dasm/run_optimization.py#L17
Currently, it is pretty complicated to use hyper-parameters in optimizers. Make this more intuitive
add mirco-structure generator to pr/1.0, (1) circleparticles for 2d rve (2) spherepartices for 3d rve
The Function
and PyBenchFunction
are cluttered and not easy to understand. Redesign this class
Change the documentation of the f3dasm package so that it resembles the functionalities implemented in v1.0
https://bessagroup.github.io/F3DASM/genindex.html This link is broken at the time of checking.
This release is the "development" code developed until 2020 before Martin took over the main responsibilities of the f3dasm project The purpose of this release is to make sure that the original code is not lost, and users may download this legacy code to reproduce their experiments.
This release is the "master branch" code developed until 2020 before Martin took over the main responsibilities of the f3dasm project The purpose of this release is to make sure that the original code is not lost, and users may download this legacy code to reproduce their experiments.
data-driven machine-learning optimization