Documente Academic
Documente Profesional
Documente Cultură
19
Figure 3: Distance chart (left) and residual chart (right). These charts represent two of the several possibilities offered by modeFRONTIER to validate the meta-models.
Figure 5: Neural Networks (NN) are inspired by the functioning of biological nervous systems. A real neuron (left) and an artificial neuron (right)
Conclusions
Both websites, www.esteco.com as
well as www.network.modefrontier.eu,
the portal of the European
modeFRONTIER Network, provide
several examples of how to use meta-
Figure 5: modeFRONTIER tool for meta-models 3D-exploration modeling techniques to speed-up
optimization.
Considering that several methods for effective surfaces for statistical
interpolation are available, both in analysis, for exploring candidate For any questions on this article or to
modeFRONTIER and in literature, an designs and for the use as surrogates request further examples or
engineer may ask which is the best in optimization. If the training points information, please email the author:
model to be used. There is an obvious are not carefully chosen, the fitted Silvia Poles
notion that more simple functions can model can be really poor and influence ESTECO - Research Labs
be approximated better and more the final results. Inadequate scientific@esteco.com
complex functions are in general more approximations may lead to suboptimal
difficult to approximate regardless of designs or inefficient searches for
the meta-modeling type, design type optimal solutions. References
and design size. A general [1] P. Alfeld. Scattered data
recommendation is to use simple meta- That is why validation is a fundamental interpolation in three or more
models first (such as on low order part of the modeling process. In variables. In T. Lyche and L.
polynomials). Kriging, Gaussian and modeFRONTIER, during the Schumaker, editors, Mathematical
Neural Network should be used for interpolation, a list of messages and Methods in Computer Aided
more complex responses. In general errors generated by the algorithms is Geometric Design, pages 1–34.
and regardless of the meta-model type, shown. The messages provide Academic Press, 1989.
design type, or the complexity of the suggestions for a better tuning of the [2] Martin D. Buhmann, Radial Basis
response, the performance tends to selected models. They generally list the Functions: Theory and
improve with the size of the design, maximum absolute error which is a Implementations Cambridge
especially for Kriging and Artificial measure that provides information University Press, 2003
Neural Networks. about extreme performances of the [3] Armin Iske, Multiresolution
model. The mean absolute error is the Methods in Scattered Data
sum of the absolute errors divided by Modelling, Springer, 2004
Validation of Meta-models the number of data points, and is [4] Georges Matheron. Les Variables
modeFRONTIER has a powerful tool for measured in the same units as the Regionalisees et leur Estimation,
the creation of meta-models, as it original data. The maximum absolute une Application de la Theorie de
gives the possibility to verify the percent error is the maximum absolute Fonctions Aleatoires aux Sciences
accuracy of a particular meta-model numerical difference divided by the de la Nature. Masson et Cie, Paris,
and to decide whether or not to true value. The percentage error is this 1965.
improve its fidelity by adding ratio expressed as a percent. The [5] Holger Wendland, Scattered Data
additional simulation results to the maximum absolute percent error Approximation, Cambridge
database. It is possible to decide on provides a practical account of the University Press, 2004