Thomas Kohlsche

Multi-fidelity Gaussian process surrogate models for numerical acoustic design in frequency domain


voorkant	achterkant

ISBN:

978-3-8440-9752-8

Reeks:

Schriftenreihe des Instituts für Modellierung und Berechnung
Uitgever: Prof. Dr.-Ing. Otto von Estorff
Hamburg

Volume:

2025,39

Trefwoorden:

Multi-fidelity; acoustics; surrogate; Gaussian process

Soort publicatie:

Dissertatie

Taal:

Engels

Pagina's:

178 pagina's

Gewicht:

235 g

Formaat:

21 x 14,8 cm

Bindung:

Softcover

Prijs:

58,80 € / 73,60 SFr

Verschijningsdatum:

Januari 2025

Kopen:

Aanbevelen:

Wilt u dit boek aanbevelen?

Recensie-exemplaar

Bestelling van een recensie-exemplaar.

Verlinking

Wilt u een link hebben van uw publicatie met onze online catalogus? Klik hier.

Samenvatting

This thesis investigates Multi-Fidelity (MF) Gaussian Processes (GP) as surrogates in numerical acoustic design. Here, the parameter dependence of the acoustic target quantity is learned based on data of varying fidelity using GP regression. Data of different fidelity levels is generated using finite element models of varying numerical resolution. The fundamental suitability of these data for MF models is examined before discussing the theoretical potential of the method and various practical implementation options. The results of the study demonstrate that while MF models can outperform conventional approaches significantly, their application is considerably more complex and error-prone.