AADL Logo Advanced Aircraft Design Lab

Royal Military College of Canada

pyRSM

pyRSM is an object oriented framework to create and use response surface approximations or metamodels. Such approximations are useful in different fields and are particularly useful in design and/or optimization were they can be used in liue of expensive function analyzes.

Design of Experiments (DOE)

Different design of experiments (DOE) are included in the framework to sample a given design space

  • Halton sequences

  • Hammersley sequences

  • Latin Square sampling

  • Monte Carlo sampling

  • Random sampling

  • Taguchi sampling

../../_images/pyrsm_doe.png

DOEs sampling on example 2D design space

Response Surfaces Methods

Different state of art response surface methodologies (RSM) are currently available in the framework.

  • Radial Basis Functions (RBF)

  • Multi Adaptive Regression Splines (MARS)

  • Least-Squares Support Vector Machine (LSSVM)

  • Gaussian Process Regression (GPR or Kriging)

../../_images/pyrsm_rbf.png

Example RBF response prediction of 1D function

../../_images/pyrsm_svm.png

Example LSSVM response prediction of 1D function with noise

This web site is not an official publication of the Royal Military College of Canada nor the Department of National Defence
Ce site web n’est pas une publication officielle du Collége militaire royal du Canada ni du Ministère de la défense nationale