Abstract : In order to reach satisfactory performance, fault diagnosis methods require the tuning of internal parameters, usually called hyperparameters. This is generally achieved by optimizing a performance criterion, typically a trade-off between false-alarm and non-detection rates. Perturbations should also be taken into account, for instance by considering the worst possible case. A new method to achieve such a tuning is described, which is especially interesting when the simulations required are so costly that their number is severely limited. It achieves min-max optimization of the tuning parameters via a relaxation procedure and Kriging-based optimization. This approach is applied to the worst-case optimal tuning of a fault diagnosis method consisting of an observer-based residual generator followed by a statistical test. It readily extends to the tuning of hyperparameters in other contexts.
https://hal-supelec.archives-ouvertes.fr/hal-00615618
Contributeur : Julien Marzat
<>
Soumis le : jeudi 8 septembre 2011 - 09:22:35
Dernière modification le : jeudi 15 novembre 2018 - 08:38:45
Document(s) archivé(s) le : vendredi 9 décembre 2011 - 02:20:29
Julien Marzat, Hélène Piet-Lahanier, Eric Walter. Min-max hyperparameter tuning, with application to fault detection. 18th IFAC World Congress, Aug 2011, Milan, Italy. pp.12904-12909, 2011. 〈hal-00615618〉
