Gaussian Process Surrogate Models for Vibroacoustic Simulations 2024-01-2930
In vehicle NVH development, vibroacoustic simulations with Finite Element (FE) models are a common technique. The computational costs for these calculations are steadily rising due to more detailed modelling and higher frequency ranges. At the same time, the need for multiple evaluations of the same model with different input parameters, e.g., for uncertainty quantification, optimization, or robustness investigations, is also increasing.
Therefore, it is crucial to reduce the computational costs in these cases. A common technique is to use surrogate models that replace the computationally intensive FE model to perform repeated evaluations. Several different methods in this area are well established, but with the continuous advancements in the field of machine learning, interesting new methods like the Gaussian Process (GP) regression arises as a promising approach.
In Gaussian process regression, the model response is expressed as a stochastic process with a user-defined kernel function. The GP is then fit to the reference by finding its optimal hyperparameter values. With a focus on vibroacoustic simulations the influence of the choice of the kernel function is evaluated. For this purpose, different classes of kernels are under investigation. Additionally, a parameter study on the number of training samples is performed.
The research indicates an interesting difference between a simple academic model and a body-in-white model. The underlying effects, such as damping, system complexity, uncertainty and load case are discussed in detail.
Finally, a recommendation using GP as a surrogate model for vibroacoustic simulations is given.
Author(s):
Marinus Luegmair, Rafaella Dantas, Felix Schneider, Gerhard Müller
Affiliated:
BMW AG, Technical Universtity of Munich / BMW AG, TU Munich, Chair of Structural Mechanics
Event:
13th International Styrian Noise, Vibration & Harshness Congress: The European Automotive Noise Conference
ISSN:
0148-7191
e-ISSN:
2688-3627
Related Topics:
Finite element analysis
Machine learning
SAE MOBILUS
Subscribers can view annotate, and download all of SAE's content.
Learn More »