Deep Gaussian Process for the Approximation ...
Type de document :
Compte-rendu et recension critique d'ouvrage
DOI :
Titre :
Deep Gaussian Process for the Approximation of a Quadratic Eigenvalue Problem: Application to Friction-Induced Vibration
Auteur(s) :
Sadet, Jeremy [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201 [LAMIH]
Massa, Franck [Auteur]
INSA Institut National des Sciences Appliquées Hauts-de-France [INSA Hauts-De-France]
Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201 [LAMIH]
Tison, Thierry [Auteur]
Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201 [LAMIH]
Talbi, El-Ghazali [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Turpin, Isabelle [Auteur]
Laboratoire de Matériaux Céramiques et de Mathématiques [CERAMATHS]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201 [LAMIH]
Massa, Franck [Auteur]
INSA Institut National des Sciences Appliquées Hauts-de-France [INSA Hauts-De-France]
Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201 [LAMIH]
Tison, Thierry [Auteur]
Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201 [LAMIH]
Talbi, El-Ghazali [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Turpin, Isabelle [Auteur]
Laboratoire de Matériaux Céramiques et de Mathématiques [CERAMATHS]
Titre de la revue :
Vibration
Pagination :
344-369
Éditeur :
MDPI
Date de publication :
2022
ISSN :
2571-631X
Mot(s)-clé(s) en anglais :
friction-induced vibration
squeal
uncertainty
surrogate modelling
Gaussian process
deep Gaussian process
deep neural network
squeal
uncertainty
surrogate modelling
Gaussian process
deep Gaussian process
deep neural network
Discipline(s) HAL :
Sciences de l'ingénieur [physics]/Mécanique [physics.med-ph]/Vibrations [physics.class-ph]
Mathématiques [math]/Probabilités [math.PR]
Mathématiques [math]/Probabilités [math.PR]
Résumé en anglais : [en]
Despite numerous works over the past two decades, friction-induced vibrations, especially braking noises, are a major issue for transportation manufacturers as well as for the scientific community. To study these fugitive ...
Lire la suite >Despite numerous works over the past two decades, friction-induced vibrations, especially braking noises, are a major issue for transportation manufacturers as well as for the scientific community. To study these fugitive phenomena, the engineers need numerical methods to efficiently predict the mode coupling instabilities in a multiparametric context. The objective of this paper is to approximate the unstable frequencies and the associated damping rates extracted from a complex eigenvalue analysis under variability. To achieve this, a deep Gaussian process is considered to fit the non-linear and non-stationary evolutions of the real and imaginary parts of complex eigenvalues. The current challenge is to build an efficient surrogate modelling, considering a small training set. A discussion about the sample distribution density effect, the training set size and the kernel function choice is proposed. The results are compared to those of a Gaussian process and a deep neural network. A focus is made on several deceptive predictions of surrogate models, although the better settings were well chosen in theory. Finally, the deep Gaussian process is investigated in a multiparametric analysis to identify the best number of hidden layers and neurons, allowing a precise approximation of the behaviours of complex eigensolutions.Lire moins >
Lire la suite >Despite numerous works over the past two decades, friction-induced vibrations, especially braking noises, are a major issue for transportation manufacturers as well as for the scientific community. To study these fugitive phenomena, the engineers need numerical methods to efficiently predict the mode coupling instabilities in a multiparametric context. The objective of this paper is to approximate the unstable frequencies and the associated damping rates extracted from a complex eigenvalue analysis under variability. To achieve this, a deep Gaussian process is considered to fit the non-linear and non-stationary evolutions of the real and imaginary parts of complex eigenvalues. The current challenge is to build an efficient surrogate modelling, considering a small training set. A discussion about the sample distribution density effect, the training set size and the kernel function choice is proposed. The results are compared to those of a Gaussian process and a deep neural network. A focus is made on several deceptive predictions of surrogate models, although the better settings were well chosen in theory. Finally, the deep Gaussian process is investigated in a multiparametric analysis to identify the best number of hidden layers and neurons, allowing a precise approximation of the behaviours of complex eigensolutions.Lire moins >
Langue :
Anglais
Vulgarisation :
Non
Collections :
Source :
Fichiers
- https://hal.archives-ouvertes.fr/hal-03700618/document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-03700618/document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-03700618/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- vibration-05-00020.pdf
- Accès libre
- Accéder au document
- Accès libre
- Accéder au document