Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
Propagation of structural uncertainty to linear aeroelastic stability
Computers and Structures
Bayesian assimilation of multi-fidelity finite element models
Computers and Structures
| Hi-index | 0.00 |
The probabilistic characterisation of a frequency response function can be very valuable for structural design and control. Unfortunately, obtaining a sufficiently large sample for wide ranges of vibration can easily become unaffordable. A variety of modelling assumptions can dramatically add to the computational cost: nonproportional damping, multiscale material properties, and high-resolution finite element analysis are some examples. This paper explores Bayesian emulators as surrogates for expensive finite element models in structural dynamics. We demonstrate the effectiveness of the method by performing uncertainty analysis of the frequency response of a nonproportionally damped plate made of a carbon fibre/epoxy composite material.