Ārtap is a framework for robust design optimization in Python. It contains an integrated, multi-physical FEM solver: Agros suite, furthermore it provides simple interfaces for commercial FEM solvers (COMSOL) and meta-heuristic, bayesian or neural network based optimization algorithms surrogate modelling techniques and neural networks.


Artap and its dependencies are available as wheel packages for Windows and Linux* distributions:
We recommend to install Artap under a virtual environment.

pip install --upgrade pip # make sure that pip is reasonably new
pip install artap

*The Windows versions are only partially, the linux packages are fully supported at the current version.


If you use Ārtap in your research, the developers would be grateful if you would cite the relevant publications:

[1] David Pánek, Tamás Orosz, Pavel Karban, Artap: Robust design optimization framework for engineering applications, in: The Third International Conference on Intelligent Computing in Data Sciences ICDS2019, IEEE, 2019, pp. 1–5, [in press]


[2] Karban, P., Pánek, D., & Doležel, I. (2018). Model of induction brazing of nonmagnetic metals using model order reduction approach. COMPEL-The international journal for computation and mathematics in electrical and electronic engineering, 37(4), 1515-1524.

[3] Pánek, D., Orosz, T., Kropík, P., Karban, P., & Doležel, I. (2019, June). Reduced-Order Model Based Temperature Control of Induction Brazing Process. In 2019 Electric Power Quality and Supply Reliability Conference (PQ) & 2019 Symposium on Electrical Engineering and Mechatronics (SEEM) (pp. 1-4). IEEE.

[4] Pánek, D., Karban, P., & Doležel, I. (2019). Calibration of Numerical Model of Magnetic Induction Brazing. IEEE Transactions on Magnetics, 55(6), 1-4.


If you have any questions, do not hesitate to contact us: artap.framework@gmail.com


Ārtap is published under MIT license.