A nonparametric stochastic model for non-Gaussian random fields with SO(n,R)-invariance

Johann Guilleminot (1) , Christian Soize (1)

1 MSME - Laboratoire de Modélisation et Simulation Multi Echelle

In this work, we address the construction of a generalized nonparametric probabilistic model for matrix-valued non-Gaussian random fields exhibiting some invariance properties with respect to given orthogonal transformations. Such an issue naturally arises in linear elasticity, where the so-called material symmetries are defined in terms of some SO(n;R)-invariance.

Mots clés: Random fields; non-Gaussian; SO(n; R)-invariance

Domaines: Mécanique [physics.med-ph]; Matériaux; Probabilités [math.PR]; Statistiques [math.ST]

Johann Guilleminot, Christian Soize. A nonparametric stochastic model for non-Gaussian random fields with SO(n,R)-invariance. Congress on Computational Methods in Applied Sciences and Engineering (ECCOMAS 2012), Vienna University of Technology, Sep 2012, Vienna, Austria. pp.1-2. ⟨hal-00734171⟩