pSeven Core, embedded in pSeven, is a highly-interconnected set of tools with proprietary and state-of-the-art algorithms for Design Space Exploration packed in a scalable and robust Python library.
pSeven Core is available as a standalone product, see licensing for details.
Effectively choose the values of experimental, analytical or simulation model input parameters and study behavior of outputs in the smallest number of iterations as possible with 15 batch, sequential and adaptive techniques.
Quickly find the values of model parameters, which lead to the best performance of analytical or simulation models with 16 efficient algorithms for single-, multi-objective, robust and surrogate-based optimization.
Study the dependencies in the data and find out which input parameters have the most influence on the output and which can be dropped in further model computations.
Build fast and robust approximation models using multiple data sets of variable fidelity, for example, from experiments and simulations, while preserving their degree of importance.
Drastically minimize quantitative description of complex models and geometries defined with multi-dimensional points for easier optimization studies and generating similar objects.